liu.seSearch for publications in DiVA
Change search
Refine search result
1234567 51 - 100 of 467
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 51.
    Bešenić, Krešimir
    et al.
    Faculty of Electrical Engineering and Computing, University of Zagreb,.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Pandžić, Igor
    Faculty of Electrical Engineering and Computing, University of Zagreb.
    Unsupervised Facial Biometric Data Filtering for Age and Gender Estimation2019In: Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019), SciTePress, 2019, Vol. 5, p. 209-217Conference paper (Refereed)
    Abstract [en]

    Availability of large training datasets was essential for the recent advancement and success of deep learning methods. Due to the difficulties related to biometric data collection, datasets with age and gender annotations are scarce and usually limited in terms of size and sample diversity. Web-scraping approaches for automatic data collection can produce large amounts weakly labeled noisy data. The unsupervised facial biometric data filtering method presented in this paper greatly reduces label noise levels in web-scraped facial biometric data. Experiments on two large state-of-the-art web-scraped facial datasets demonstrate the effectiveness of the proposed method, with respect to training and validation scores, training convergence, and generalization capabilities of trained age and gender estimators.

  • 52.
    Bhat, Goutam
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Danelljan, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Incept Inst Artificial Intelligence, U Arab Emirates.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Combining Local and Global Models for Robust Re-detection2018In: 2018 15TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), IEEE , 2018, p. 25-30Conference paper (Refereed)
    Abstract [en]

    Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual tracking. However, these methods still struggle in occlusion and out-of-view scenarios due to the absence of a re-detection component. While such a component requires global knowledge of the scene to ensure robust re-detection of the target, the standard DCF is only trained on the local target neighborhood. In this paper, we augment the state-of-the-art DCF tracking framework with a re-detection component based on a global appearance model. First, we introduce a tracking confidence measure to detect target loss. Next, we propose a hard negative mining strategy to extract background distractors samples, used for training the global model. Finally, we propose a robust re-detection strategy that combines the global and local appearance model predictions. We perform comprehensive experiments on the challenging UAV123 and LTB35 datasets. Our approach shows consistent improvements over the baseline tracker, setting a new state-of-the-art on both datasets.

  • 53.
    Biedermann, Daniel
    et al.
    Goethe University, Germany.
    Ochs, Matthias
    Goethe University, Germany.
    Mester, Rudolf
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Goethe University, Germany.
    Evaluating visual ADAS components on the COnGRATS dataset2016In: 2016 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), IEEE , 2016, p. 986-991Conference paper (Refereed)
    Abstract [en]

    We present a framework that supports the development and evaluation of vision algorithms in the context of driver assistance applications and traffic surveillance. This framework allows the creation of highly realistic image sequences featuring traffic scenarios. The sequences are created with a realistic state of the art vehicle physics model; different kinds of environments are featured, thus providing a wide range of testing scenarios. Due to the physically-based rendering technique and variable camera models employed for the image rendering process, we can simulate different sensor setups and provide appropriate and fully accurate ground truth data.

  • 54.
    Bock, Alexander
    et al.
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    Pembroke, Asher
    NASA Goddard Space Flight Center, USA.
    Mays, M. Leila
    NASA Goddard Space Flight Center, USA.
    Rastaetter, Lutz
    NASA Goddard Space Flight Center, USA.
    Ynnerman, Anders
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Ropinski, Timo
    Ulm University, Germany.
    Visual Verification of Space Weather Ensemble Simulations2015In: 2015 IEEE Scientific Visualization Conference (SciVis), IEEE, 2015, p. 17-24Conference paper (Refereed)
    Abstract [en]

    We propose a system to analyze and contextualize simulations of coronal mass ejections. As current simulation techniques require manual input, uncertainty is introduced into the simulation pipeline leading to inaccurate predictions that can be mitigated through ensemble simulations. We provide the space weather analyst with a multi-view system providing visualizations to: 1. compare ensemble members against ground truth measurements, 2. inspect time-dependent information derived from optical flow analysis of satellite images, and 3. combine satellite images with a volumetric rendering of the simulations. This three-tier workflow provides experts with tools to discover correlations between errors in predictions and simulation parameters, thus increasing knowledge about the evolution and propagation of coronal mass ejections that pose a danger to Earth and interplanetary travel

  • 55.
    Bock, Alexander
    et al.
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    Pembroke, Asher
    NASA Goddard Space Flight Center, Greenbelt, MD, United States.
    Mays, M. Leila
    Catholic University of America, Washington, DC, United States.
    Ynnerman, Anders
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    OpenSpace: An Open-Source Framework for Data Visualization and Contextualization2015Conference paper (Refereed)
    Abstract [en]

    We present an open-source software development effort called OpenSpace that is tailored for the dissemination of space-related data visualization. In the current stages of the project, we have focussed on the public dissemination of space missions (Rosetta and New Horizons) as well as the support of space weather forecasting. The presented work will focus on the latter of these foci and elaborate on the efforts that have gone into developing a system that allows the user to assess the accuracy and validity of ENLIL ensemble simulations. It becomes possible to compare the results of ENLIL CME simulations with STEREO and SOHO images using an optical flow algorithm. This allows the user to compare velocities in the volumetric rendering of ENLIL data with the movement of CMEs through the field-of-views of various instruments onboard the space craft. By allowing the user access to these comparisons, new information about the time evolution of CMEs through the interplanetary medium is possible. Additionally, contextualizing this information in three-dimensional rendering scene, allows the analyst and the public to disseminate this data. This dissemination is further improved by the ability to connect multiple instances of the software and, thus, reach a broader audience. In a second step, we plan to combine the two foci of the project to enable the visualization of the SWAP instrument onboard New Horizons in context with a far-reaching ENLIL simulation, thus providing additional information about the solar wind dynamics of the outer solar system. The initial work regarding this plan will be presented.

  • 56.
    Borg, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Detecting and Tracking Players in Football Using Stereo Vision2007Independent thesis Advanced level (degree of Master (One Year)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The objective of this thesis is to investigate if it is possible to use stereo vision to find and track the players and the ball during a football game.

    The thesis shows that it is possible to detect all players that isn’t too occluded by another player. Situations when a player is occluded by another player is solved by tracking the players from frame to frame.

    The ball is also detected in most frames by looking for ball-like features. As with the players the ball is tracked from frame to frame so that when the ball is occluded, the positions is estimated by the tracker.

  • 57.
    Borga, Magnus
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, The Institute of Technology.
    Rydell, Joakim
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Signal and Anatomical Constraints in Adaptive Filtering of fMRI Data2007In: Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007: From Nano to Macro, IEEE , 2007, p. 432-435Conference paper (Refereed)
    Abstract [en]

    An adaptive filtering method for fMRI data is presented. The method is related to bilateral filtering, but with a range filter that takes into account local similarities in signal as well as in anatomy. Performance is demonstrated on simulated and real data. It is shown that using both these similarity constraints give better performance than if only one of them is used, and clearly better than standard low-pass filtering.

  • 58.
    Boyer, E
    et al.
    Grenoble, France.
    Bronstein, A.M.
    Tel Aviv University, Israel.
    Bronstein, M.M.
    Università della Svizzera Italiana, Lugano, Switzerland.
    Bustos, B
    University of Chile.
    Darom, T
    Bar-Ilan University, Ramat-Gan, Israel.
    Horaud, R
    Grenoble, France.
    Hotz, Ingrid
    Zuse Institue Berlin.
    Kelle, Y
    Bar-Ilan University, Ramat-Gan, Israel.
    Keustermans, J
    K.U. Leuven, Belgium.
    Kovnatsky, A
    Israel Institute of Technology, Haifa, Israel.
    Litman, R
    Tel Aviv University, Israel.
    Reininghaus, Jan
    Zuse Institue Berlin.
    Sipiran, I
    University of Chile.
    Smeets, D
    K.U. Leuven, Belgium.
    Suetens, P
    K.U. Leuven, Belgium.
    Vandermeulen, D
    K.U. Leuven, Belgium.
    Zaharescu, A
    Waterloo, Canada.
    Zobel, Valentin
    Zuse Institut Berlin, Germany.
    SHREC 2011: Robust Feature Detection and Description Benchmark2011Conference paper (Refereed)
    Abstract [en]

    Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. SHREC’11 robust feature detection and description benchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms. The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations. The benchmark allows evaluating how algorithms cope with certain classes of transformations and strength of the transformations that can be dealt with. The present paper is a report of the SHREC’11 robust feature detection and description benchmark results.

  • 59.
    Bradler, Henry
    et al.
    Goethe University of Frankfurt, Germany.
    Anne Wiegand, Birthe
    Goethe University of Frankfurt, Germany.
    Mester, Rudolf
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Goethe University of Frankfurt, Germany.
    The Statistics of Driving Sequences - and what we can learn from them2015In: 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW), IEEE , 2015, p. 106-114Conference paper (Refereed)
    Abstract [en]

    The motion of a driving car is highly constrained and we claim that powerful predictors can be built that learn the typical egomotion statistics, and support the typical tasks of feature matching, tracking, and egomotion estimation. We analyze the statistics of the ground truth data given in the KITTI odometry benchmark sequences and confirm that a coordinated turn motion model, overlaid by moderate vibrations, is a very realistic model. We develop a predictor that is able to significantly reduce the uncertainty about the relative motion when a new image frame comes in. Such predictors can be used to steer the matching process from frame n to frame n + 1. We show that they can also be employed to detect outliers in the temporal sequence of egomotion parameters.

  • 60.
    Bradler, Henry
    et al.
    Goethe University, Germany.
    Ochs, Matthias
    Goethe University, Germany.
    Fanani, Nolang
    Goethe University, Germany.
    Mester, Rudolf
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Goethe University, Germany.
    Joint Epipolar Tracking (JET): Simultaneous optimization of epipolar geometry and feature correspondences2017In: 2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017), IEEE , 2017, p. 445-453Conference paper (Refereed)
    Abstract [en]

    Traditionally, pose estimation is considered as a two step problem. First, feature correspondences are determined by direct comparison of image patches, or by associating feature descriptors. In a second step, the relative pose and the coordinates of corresponding points are estimated, most often by minimizing the reprojection error (RPE). RPE optimization is based on a loss function that is merely aware of the feature pixel positions but not of the underlying image intensities. In this paper, we propose a sparse direct method which introduces a loss function that allows to simultaneously optimize the unscaled relative pose, as well as the set of feature correspondences directly considering the image intensity values. Furthermore, we show how to integrate statistical prior information on the motion into the optimization process. This constructive inclusion of a Bayesian bias term is particularly efficient in application cases with a strongly predictable (short term) dynamic, e.g. in a driving scenario. In our experiments, we demonstrate that the JET` algorithm we propose outperforms the classical reprojection error optimization on two synthetic datasets and on the KITTI dataset. The JET algorithm runs in real-time on a single CPU thread.

  • 61.
    Brandl, Miriam B
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia .
    Beck, Dominik
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia .
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia .
    Application of Fuzzy c-Means and Joint-Feature-Clustering to Detect Redundancies of Image-Features in Drug Combinations Studies of Breast Cancer2011Conference paper (Refereed)
    Abstract [en]

    The high dimensionality of image‐based dataset can be a drawback for classification accuracy. In this study, we propose the application of fuzzy c‐means clustering, cluster validity indices and the notation of a joint‐feature‐clustering matrix to find redundancies of image‐features. The introduced matrix indicates how frequently features are grouped in a mutual cluster. The resulting information can be used to find data‐derived feature prototypes with a common biological meaning, reduce data storage as well as computation times and improve the classification accuracy

  • 62.
    Brandtberg, Tomas
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Saab Dynam AB, Linköping, Sweden.
    Virtual hexagonal and multi-scale operator for fuzzy rank order texture classification using one-dimensional generalised Fourier analysis2016In: 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), IEEE COMPUTER SOC , 2016, p. 2018-2024Conference paper (Refereed)
    Abstract [en]

    This paper presents a study on a family of local hexagonal and multi-scale operators useful for texture analysis. The hexagonal grid shows an attractive rotation symmetry with uniform neighbour distances. The operator depicts a closed connected curve (1D periodic). It is resized within a scale interval during the conversion from the original square grid to the virtual hexagonal grid. Complementary image features, together with their tangential first-order hexagonal derivatives, are calculated. The magnitude/phase information from the Fourier or Fractional Fourier Transform (FFT, FrFT) are accumulated in thirty different Cartesian (polar for visualisation) and multi-scale domains. Simultaneous phase-correlation of a subset of the data gives an estimate of scaling/rotation relative the references. Similarity metrics are used as template matching. The sample, unseen by the system, is classified into the group with the maximum fuzzy rank order. An instantiation of a 12-point hexagonal operator (radius=2) is first successfully evaluated on a set of thirteen Brodatz images (no scaling/rotation). Then it is evaluated on the more challenging KTH-TIPS2b texture dataset (scaling/rotation, varying pose/illumination). A confusion matrix and cumulative fuzzy rank order summaries show, for example, that the correct class is top-ranked 44 - 50% and top-three ranked 68 - 76% of all sample images. A similar evaluation, using a box-like 12-point mask of square grids, gives overall lower accuracies. Finally, the FrFT parameter is an additional tuning parameter influencing the accuracies significantly.

  • 63.
    Brattberg, Oskar
    et al.
    Dept. of IR Systems, Div. of Sensor Tecnology, Swedish Defence Research Agency (FOI), Linköping, Sweden.
    Ahlberg, Jörgen
    Dept. of IR Systems, Div. of Sensor Tecnology, Swedish Defence Research Agency (FOI), Linköping, Sweden.
    Analysis of Multispectral Reconnaissance Imagery for Target Detection and Operator Support2006Conference paper (Other academic)
    Abstract [en]

    This paper describes a method to estimate motion in an image sequence acquired using a multispectral airborne sensor. The purpose of the motion estimation is to align the sequentually acquired spectral bands and fuse them into multispectral images. These multispectral images are then analysed and presented in order to support an operator in an air-to-ground reconnaissance scenario.

  • 64.
    Bremer, Peer-Timo
    et al.
    California, Usa.
    Hotz, IngridBerlin, Germany.Pascucci, ValerioUtah, Usa.Peikert, RonaldZurich, Switzerland.
    Topological Methods in Data Analysis and Visualization III: Theory, Algorithms, and Applications2014Collection (editor) (Refereed)
  • 65.
    Brolund, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Förbättring av fluoroskopibilder2006Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In X-ray technology, fluoroscopy stands for continuous irradiation. For the sake of both patients and doctors the dose has to be kept low, which leads to noisy images and the question of possible enhancement by digital image processing. Since such enhancement has to be done in real-time, most conventional and available methods are unsuitable.

    The purpose of this thesis is to examine how derivative operators can be used to improve fluoroscopy images in terms of noise reduction and edge enhancement. Since the derivative operators are designed as highly separable convolution kernels the image derivatives can be computed very efficiently with a scheme that is readily embedded in a scale-space pyramid. In this pyramid, structures and details of different sizes can be processed separately with optimal parameter settings. In the final solution we also discriminate between structure and noise in order to avoid amplification, even suppress contributions from frequency bands where a certain pixel position is dominated by noise.

    Experimental results show that noise can indeed be suppressed while edges and lines are enhanced. Oriented filtering may induce false structures in areas where only noise is present, something that can be avoided by correcting the parameters in the noise/structure discriminator. The relation between oriented and non-oriented filtering is likewise controllable with a parameter that can be optimized for application dependent needs and desires.

  • 66.
    Brolund, Per
    Linköping University, Department of Electrical Engineering.
    Forensisk längdmätning i bilder2006Independent thesis Basic level (professional degree), 20 points / 30 hpStudent thesis
    Abstract [sv]

    Detta examensarbete undersöker forensisk längdmätning i bild, t ex längduppskattning av människor i bilder rörande brottsmål. Problemen identifieras och några av dagens befintliga längdmätningsmetoder diskuteras.

    Den metod som bäst uppfyller de i arbetet ställda kraven, d v s snabb handläggning, minimal systeminformation, minimalt arbete på plats och exakthet, har valts ut, anpassats och utvärderats. Metoden bygger på att hitta s k gränspunkter och grundplanets gränslinje i bilden och utifrån en i världen känd referenslängd beräkna den sökta längden. Den bakomliggande teorin presenteras och metoden beskrivs i detalj. Funktioner, algoritmer och ett användargränssnitt har implementerats i beräkningsprogrammet MatLab. Tester har utförts för att validera metodens noggrannhet och parameterberoende. Metoden visar sig ge mycket bra resultat då rätt förutsättningar ges, men har konstaterats vara känslig för variation på gränslinjen. En rad förbättringsförslag presenteras för att utveckla metoden och stabilisera resultatet.

    Examensarbetet omfattar 20 högskolepoäng och utgör ett obligatoriskt moment i utbildningsprogrammet civilingenjör i datateknik som ges av Linköpings universitet. Arbetet är utfört vid och på uppdrag av Statens kriminaltekniska laboratorium (SKL) i Linköping.

  • 67.
    Brun, Anders
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV). Centre for Image Analysis, SLU, Uppsala, Sweden.
    Martin-Fernandez, Marcos
    Universidad de Valladolid Laboratorio de Procesado de Imagen (LPI), Dept. Teoría de la Señal y Comunicaciones e Ingeniería Telemática Spain.
    Acar, Burac
    Boğaziçi University 5 Electrical & Electronics Engineering Department Istanbul Turkey.
    Munoz-Moreno, Emma
    Universidad de Valladolid Laboratorio de Procesado de Imagen (LPI), Dept. Teoría de la Señal y Comunicaciones e Ingeniería Telemática Spain.
    Cammoun, Leila
    Signal Processing Institute (ITS), Ecole Polytechnique Fédérale Lausanne (EPFL) Lausanne Switzerland.
    Sigfridsson, Andreas
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV). Center for Technology in Medicine, Dept. Señales y Comunicaciones, University of Las Palmas de Gran Canaria, Spain.
    Sosa-Cabrera, Dario
    Center for Technology in Medicine, Dept. Señales y Comunicaciones, University of Las Palmas de Gran Canaria, Spain.
    Svensson, Björn
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Herberthson, Magnus
    Linköping University, Department of Mathematics, Applied Mathematics. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Similar Tensor Arrays - A Framework for Storage of Tensor Array Data2009In: Tensors in Image Processing and Computer Vision / [ed] Santiago Aja-Fern´andez, Rodrigo de Luis Garc´ıa, Dacheng Tao, Xuelong Li, Springer Science+Business Media B.V., 2009, 1, p. 407-428Chapter in book (Refereed)
    Abstract [en]

    This chapter describes a framework for storage of tensor array data, useful to describe regularly sampled tensor fields. The main component of the framework, called Similar Tensor Array Core (STAC), is the result of a collaboration between research groups within the SIMILAR network of excellence. It aims to capture the essence of regularly sampled tensor fields using a minimal set of attributes and can therefore be used as a “greatest common divisor” and interface between tensor array processing algorithms. This is potentially useful in applied fields like medical image analysis, in particular in Diffusion Tensor MRI, where misinterpretation of tensor array data is a common source of errors. By promoting a strictly geometric perspective on tensor arrays, with a close resemblance to the terminology used in differential geometry, (STAC) removes ambiguities and guides the user to define all necessary information. In contrast to existing tensor array file formats, it is minimalistic and based on an intrinsic and geometric interpretation of the array itself, without references to other coordinate systems.

  • 68.
    Bujack, Roxana
    et al.
    Leipzig University, Leipzig, Germany.
    Hotz, Ingrid
    German Aerospace Center, Braunschweig, Germany..
    Scheuermann, Gerik
    Leipzig University, Leipzig, Germany.
    Hitzer, E.
    Christian University, Tokyo, Japan.
    Moment Invariants for 2D Flow Fields via Normalization in Detail2014Conference paper (Refereed)
    Abstract [en]

    The analysis of 2D flow data is often guided by the search for characteristic structures with semantic meaning. One way to approach this question is to identify structures of interest by a human observer, with the goal of finding similar structures in the same or other datasets. The major challenges related to this task are to specify the notion of similarity and define respective pattern descriptors. While the descriptors should be invariant to certain transformations, such as rotation and scaling, they should provide a similarity measure with respect to other transformations, such as deformations. In this paper, we propose to use moment invariants as pattern descriptors for flow fields. Moment invariants are one of the most popular techniques for the description of objects in the field of image recognition. They have recently also been applied to identify 2D vector patterns limited to the directional properties of flow fields. Moreover, we discuss which transformations should be considered for the application to flow analysis. In contrast to previous work, we follow the intuitive approach of moment normalization, which results in a complete and independent set of translation, rotation, and scaling invariant flow field descriptors. They also allow to distinguish flow features with different velocity profiles. We apply the moment invariants in a pattern recognition algorithm to a real world dataset and show that the theoretical results can be extended to discrete functions in a robust way.

  • 69.
    Burdakov, Oleg
    et al.
    Linköping University, Department of Mathematics, Optimization . Linköping University, The Institute of Technology.
    Doherty, Patrick
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Kvarnström, Jonas
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Local Search for Hop-constrained Directed Steiner Tree Problem with Application to UAV-based Multi-target Surveillance2014Report (Other academic)
    Abstract [en]

    We consider the directed Steiner tree problem (DSTP) with a constraint on the total number of arcs (hops) in the tree. This problem is known to be NP-hard, and therefore, only heuristics can be applied in the case of its large-scale instances.   For the hop-constrained DSTP, we propose local search strategies aimed at improving any heuristically produced initial Steiner tree. They are based on solving a sequence of hop-constrained shortest path problems for which we have recently developed ecient label correcting algorithms.   The presented approach is applied to nding suitable 3D locations where unmanned aerial vehicles (UAVs) can be placed to relay information gathered in multi-target monitoring and surveillance. The eciency of our algorithms is illustrated by results of numerical experiments involving problem instances with up to 40 000 nodes and up to 20 million arcs.

  • 70.
    Burdakov, Oleg
    et al.
    Linköping University, Department of Mathematics, Optimization . Linköping University, The Institute of Technology.
    Doherty, Patrick
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Kvarnström, Jonas
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Optimal Scheduling for Replacing Perimeter Guarding Unmanned Aerial Vehicles2014Report (Other academic)
    Abstract [en]

    Guarding the perimeter of an area in order to detect potential intruders is an important task in a variety of security-related applications. This task can in many circumstances be performed by a set of camera-equipped unmanned aerial vehicles (UAVs). Such UAVs will occasionally require refueling or recharging, in which case they must temporarily be replaced by other UAVs in order to maintain complete surveillance of the perimeter. In this paper we consider the problem of scheduling such replacements. We present optimal replacement strategies and justify their optimality.

  • 71.
    Bäck, David
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Neural Network Gaze Tracking using Web Camera2006Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Gaze tracking means to detect and follow the direction in which a person looks. This can be used in for instance human-computer interaction. Most existing systems illuminate the eye with IR-light, possibly damaging the eye. The motivation of this thesis is to develop a truly non-intrusive gaze tracking system, using only a digital camera, e.g. a web camera.

    The approach is to detect and track different facial features, using varying image analysis techniques. These features will serve as inputs to a neural net, which will be trained with a set of predetermined gaze tracking series. The output is coordinates on the screen.

    The evaluation is done with a measure of accuracy and the result is an average angular deviation of two to four degrees, depending on the quality of the image sequence. To get better and more robust results, a higher image quality from the digital camera is needed.

  • 72.
    Carlsson, Mattias
    Linköping University, Department of Electrical Engineering, Computer Vision.
    Neural Networks for Semantic Segmentation in the Food Packaging Industry2018Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Industrial applications of computer vision often utilize traditional image processing techniques whereas state-of-the-art methods in most image processing challenges are almost exclusively based on convolutional neural networks (CNNs). Thus there is a large potential for improving the performance of many machine vision applications by incorporating CNNs.

    One such application is the classification of juice boxes with straws, where the baseline solution uses classical image processing techniques on depth images to reject or accept juice boxes. This thesis aim to investigate how CNNs perform on the task of semantic segmentation (pixel-wise classification) of said images and if the result can be used to increase classification performance.

    A drawback of CNNs is that they usually require large amounts of labelled data for training to be able to generalize and learn anything useful. As labelled data is hard to come by, two ways to get cheap data are investigated, one being synthetic data generation and the other being automatic labelling using the baseline solution.

    The implemented network performs well on semantic segmentation, even when trained on synthetic data only, though the performance increases with the ratio of real (automatically labelled) to synthetic images. The classification task is very sensitive to small errors in semantic segmentation and the results are therefore not as good as the baseline solution. It is suspected that the drop in performance between validation and test data is due to a domain shift between the data sets, e.g. variations in data collection and straw and box type, and fine-tuning to the target domain could definitely increase performance.

    When trained on synthetic data the domain shift is even larger and the performance on classification is next to useless. It is likely that the results could be improved by using more advanced data generation, e.g. a generative adversarial network (GAN), or more rigorous modelling of the data.

  • 73.
    Ceco, Ema
    Linköping University, Department of Electrical Engineering, Computer Vision.
    Image Analysis in the Field of Oil Contamination Monitoring2011Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Monitoring wear particles in lubricating oils allows specialists to evaluate thehealth and functionality of a mechanical system. The main analysis techniquesavailable today are manual particle analysis and automatic optical analysis. Man-ual particle analysis is effective and reliable since the analyst continuously seeswhat is being counted . The drawback is that the technique is quite time demand-ing and dependent of the skills of the analyst. Automatic optical particle countingconstitutes of a closed system not allowing for the objects counted to be observedin real-time. This has resulted in a number of sources of error for the instrument.In this thesis a new method for counting particles based on light microscopywith image analysis is proposed. It has proven to be a fast and effective methodthat eliminates the sources of error of the previously described methods. Thenew method correlates very well with manual analysis which is used as a refer-ence method throughout this study. Size estimation of particles and detectionof metallic particles has also shown to be possible with the current image analy-sis setup. With more advanced software and analysis instrumentation, the imageanalysis method could be further developed to a decision based machine allowingfor declarations about which wear mode is occurring in a mechanical system.

  • 74.
    Clarke, Emily L.
    et al.
    Univ Leeds, England; Leeds Teaching Hosp NHS Trust, England.
    Revie, Craig
    FFEI Ltd, England.
    Brettle, David
    Leeds Teaching Hosp NHS Trust, England.
    Shires, Michael
    Univ Leeds, England.
    Jackson, Peter
    Leeds Teaching Hosp NHS Trust, England.
    Cochrane, Ravinder
    FFEI Ltd, England.
    Wilson, Robert
    FFEI Ltd, England.
    Mello-Thoms, Claudia
    Univ Sydney, Australia.
    Treanor, Darren
    Linköping University, Department of Clinical and Experimental Medicine, Division of Neuro and Inflammation Science. Linköping University, Faculty of Medicine and Health Sciences. Linköping University, Center for Medical Image Science and Visualization (CMIV). Region Östergötland, Center for Diagnostics, Clinical pathology. Univ Leeds, England; Leeds Teaching Hosp NHS Trust, England.
    Development of a novel tissue-mimicking color calibration slide for digital microscopy2018In: Color Research and Application, ISSN 0361-2317, E-ISSN 1520-6378, Vol. 43, no 2, p. 184-197Article in journal (Refereed)
    Abstract [en]

    Digital microscopy produces high resolution digital images of pathology slides. Because no acceptable and effective control of color reproduction exists in this domain, there is significant variability in color reproduction of whole slide images. Guidance from international bodies and regulators highlights the need for color standardization. To address this issue, we systematically measured and analyzed the spectra of histopathological stains. This information was used to design a unique color calibration slide utilizing real stains and a tissue-like substrate, which can be stained to produce the same spectral response as tissue. By closely mimicking the colors in stained tissue, our target can provide more accurate color representation than film-based targets, whilst avoiding the known limitations of using actual tissue. The application of the color calibration slide in the clinical setting was assessed by conducting a pilot user-evaluation experiment with promising results. With the imminent integration of digital pathology into the routine work of the diagnostic pathologist, it is hoped that this color calibration slide will help provide a universal color standard for digital microscopy thereby ensuring better and safer healthcare delivery.

  • 75.
    Conrad, Christian
    et al.
    Goethe University, Germany.
    Mester, Rudolf
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Goethe University, Germany.
    LEARNING RANK REDUCED MAPPINGS USING CANONICAL CORRELATION ANALYSIS2016In: 2016 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), IEEE , 2016Conference paper (Refereed)
    Abstract [en]

    Correspondence relations between different views of the same scene can be learnt in an unsupervised manner. We address autonomous learning of arbitrary fixed spatial (point-to-point) mappings. Since any such transformation can be represented by a permutation matrix, the signal model is a linear one, whereas the proposed analysis method, mainly based on Canonical Correlation Analysis (CCA) is based on a generalized eigensystem problem, i.e., a nonlinear operation. The learnt transformation is represented implicitly in terms of pairs of learned basis vectors and does neither use nor require an analytic/parametric expression for the latent mapping. We show how the rank of the signal that is shared among views may be determined from canonical correlations and how the overlapping (=shared) dimensions among the views may be inferred.

  • 76.
    Conrad, Christian
    et al.
    Goethe University, Germany.
    Mester, Rudolf
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Goethe University, Germany.
    Learning Relative Photometric Differences of Pairs of Cameras2015In: 2015 12TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), IEEE , 2015Conference paper (Refereed)
    Abstract [en]

    We present an approach to learn relative photometric differences between pairs of cameras, which have partially overlapping fields of views. This is an important problem, especially in appearance based methods to correspondence estimation or object identification in multi-camera systems where grey values observed by different cameras are processed. We model intensity differences among pairs of cameras by means of a low order polynomial (Gray Value Transfer Function - GVTF) which represents the characteristic curve of the mapping of grey values, s(i) produced by camera C-i to the corresponding grey values s(j) acquired with camera C-j. While the estimation of the GVTF parameters is straightforward once a set of truly corresponding pairs of grey values is available, the non trivial task in the GVTF estimation process solved in this paper is the extraction of corresponding grey value pairs in the presence of geometric and photometric errors. We also present a temporal GVTF update scheme to adapt to gradual global illumination changes, e.g., due to the change of daylight.

  • 77.
    Danelljan, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Learning Convolution Operators for Visual Tracking2018Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    Visual tracking is one of the fundamental problems in computer vision. Its numerous applications include robotics, autonomous driving, augmented reality and 3D reconstruction. In essence, visual tracking can be described as the problem of estimating the trajectory of a target in a sequence of images. The target can be any image region or object of interest. While humans excel at this task, requiring little effort to perform accurate and robust visual tracking, it has proven difficult to automate. It has therefore remained one of the most active research topics in computer vision.

    In its most general form, no prior knowledge about the object of interest or environment is given, except for the initial target location. This general form of tracking is known as generic visual tracking. The unconstrained nature of this problem makes it particularly difficult, yet applicable to a wider range of scenarios. As no prior knowledge is given, the tracker must learn an appearance model of the target on-the-fly. Cast as a machine learning problem, it imposes several major challenges which are addressed in this thesis.

    The main purpose of this thesis is the study and advancement of the, so called, Discriminative Correlation Filter (DCF) framework, as it has shown to be particularly suitable for the tracking application. By utilizing properties of the Fourier transform, a correlation filter is discriminatively learned by efficiently minimizing a least-squares objective. The resulting filter is then applied to a new image in order to estimate the target location.

    This thesis contributes to the advancement of the DCF methodology in several aspects. The main contribution regards the learning of the appearance model: First, the problem of updating the appearance model with new training samples is covered. Efficient update rules and numerical solvers are investigated for this task. Second, the periodic assumption induced by the circular convolution in DCF is countered by proposing a spatial regularization component. Third, an adaptive model of the training set is proposed to alleviate the impact of corrupted or mislabeled training samples. Fourth, a continuous-space formulation of the DCF is introduced, enabling the fusion of multiresolution features and sub-pixel accurate predictions. Finally, the problems of computational complexity and overfitting are addressed by investigating dimensionality reduction techniques.

    As a second contribution, different feature representations for tracking are investigated. A particular focus is put on the analysis of color features, which had been largely overlooked in prior tracking research. This thesis also studies the use of deep features in DCF-based tracking. While many vision problems have greatly benefited from the advent of deep learning, it has proven difficult to harvest the power of such representations for tracking. In this thesis it is shown that both shallow and deep layers contribute positively. Furthermore, the problem of fusing their complementary properties is investigated.

    The final major contribution of this thesis regards the prediction of the target scale. In many applications, it is essential to track the scale, or size, of the target since it is strongly related to the relative distance. A thorough analysis of how to integrate scale estimation into the DCF framework is performed. A one-dimensional scale filter is proposed, enabling efficient and accurate scale estimation.

    List of papers
    1. Adaptive Color Attributes for Real-Time Visual Tracking
    Open this publication in new window or tab >>Adaptive Color Attributes for Real-Time Visual Tracking
    2014 (English)In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014, IEEE Computer Society, 2014, p. 1090-1097Conference paper, Published paper (Refereed)
    Abstract [en]

    Visual tracking is a challenging problem in computer vision. Most state-of-the-art visual trackers either rely on luminance information or use simple color representations for image description. Contrary to visual tracking, for object recognition and detection, sophisticated color features when combined with luminance have shown to provide excellent performance. Due to the complexity of the tracking problem, the desired color feature should be computationally efficient, and possess a certain amount of photometric invariance while maintaining high discriminative power.

    This paper investigates the contribution of color in a tracking-by-detection framework. Our results suggest that color attributes provides superior performance for visual tracking. We further propose an adaptive low-dimensional variant of color attributes. Both quantitative and attributebased evaluations are performed on 41 challenging benchmark color sequences. The proposed approach improves the baseline intensity-based tracker by 24% in median distance precision. Furthermore, we show that our approach outperforms state-of-the-art tracking methods while running at more than 100 frames per second.

    Place, publisher, year, edition, pages
    IEEE Computer Society, 2014
    Series
    IEEE Conference on Computer Vision and Pattern Recognition. Proceedings, ISSN 1063-6919
    National Category
    Computer Engineering
    Identifiers
    urn:nbn:se:liu:diva-105857 (URN)10.1109/CVPR.2014.143 (DOI)2-s2.0-84911362613 (Scopus ID)978-147995117-8 (ISBN)
    Conference
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, June 24-27, 2014
    Note

    Publication status: Accepted

    Available from: 2014-04-10 Created: 2014-04-10 Last updated: 2018-04-25Bibliographically approved
    2. Coloring Channel Representations for Visual Tracking
    Open this publication in new window or tab >>Coloring Channel Representations for Visual Tracking
    2015 (English)In: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings / [ed] Rasmus R. Paulsen, Kim S. Pedersen, Springer, 2015, Vol. 9127, p. 117-129Conference paper, Published paper (Refereed)
    Abstract [en]

    Visual object tracking is a classical, but still open research problem in computer vision, with many real world applications. The problem is challenging due to several factors, such as illumination variation, occlusions, camera motion and appearance changes. Such problems can be alleviated by constructing robust, discriminative and computationally efficient visual features. Recently, biologically-inspired channel representations \cite{felsberg06PAMI} have shown to provide promising results in many applications ranging from autonomous driving to visual tracking.

    This paper investigates the problem of coloring channel representations for visual tracking. We evaluate two strategies, channel concatenation and channel product, to construct channel coded color representations. The proposed channel coded color representations are generic and can be used beyond tracking.

    Experiments are performed on 41 challenging benchmark videos. Our experiments clearly suggest that a careful selection of color feature together with an optimal fusion strategy, significantly outperforms the standard luminance based channel representation. Finally, we show promising results compared to state-of-the-art tracking methods in the literature.

    Place, publisher, year, edition, pages
    Springer, 2015
    Series
    Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 9127
    Keywords
    Visual tracking, channel coding, color names
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-121003 (URN)10.1007/978-3-319-19665-7_10 (DOI)978-3-319-19664-0 (ISBN)978-3-319-19665-7 (ISBN)
    Conference
    Scandinavian Conference on Image Analysis
    Available from: 2015-09-02 Created: 2015-09-02 Last updated: 2018-04-25Bibliographically approved
    3. Discriminative Scale Space Tracking
    Open this publication in new window or tab >>Discriminative Scale Space Tracking
    2017 (English)In: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 39, no 8, p. 1561-1575Article in journal (Refereed) Published
    Abstract [en]

    Accurate scale estimation of a target is a challenging research problem in visual object tracking. Most state-of-the-art methods employ an exhaustive scale search to estimate the target size. The exhaustive search strategy is computationally expensive and struggles when encountered with large scale variations. This paper investigates the problem of accurate and robust scale estimation in a tracking-by-detection framework. We propose a novel scale adaptive tracking approach by learning separate discriminative correlation filters for translation and scale estimation. The explicit scale filter is learned online using the target appearance sampled at a set of different scales. Contrary to standard approaches, our method directly learns the appearance change induced by variations in the target scale. Additionally, we investigate strategies to reduce the computational cost of our approach. Extensive experiments are performed on the OTB and the VOT2014 datasets. Compared to the standard exhaustive scale search, our approach achieves a gain of 2.5 percent in average overlap precision on the OTB dataset. Additionally, our method is computationally efficient, operating at a 50 percent higher frame rate compared to the exhaustive scale search. Our method obtains the top rank in performance by outperforming 19 state-of-the-art trackers on OTB and 37 state-of-the-art trackers on VOT2014.

    Place, publisher, year, edition, pages
    IEEE COMPUTER SOC, 2017
    Keywords
    Visual tracking; scale estimation; correlation filters
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-139382 (URN)10.1109/TPAMI.2016.2609928 (DOI)000404606300006 ()27654137 (PubMedID)
    Note

    Funding Agencies|Swedish Foundation for Strategic Research; Swedish Research Council; Strategic Vehicle Research and Innovation (FFI); Wallenberg Autonomous Systems Program; National Supercomputer Centre; Nvidia

    Available from: 2017-08-07 Created: 2017-08-07 Last updated: 2018-10-17
    4. Learning Spatially Regularized Correlation Filters for Visual Tracking
    Open this publication in new window or tab >>Learning Spatially Regularized Correlation Filters for Visual Tracking
    2015 (English)In: Proceedings of the International Conference in Computer Vision (ICCV), 2015, IEEE Computer Society, 2015, p. 4310-4318Conference paper, Published paper (Refereed)
    Abstract [en]

    Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively learned correlation filters (DCF) have been successfully applied to address this problem for tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood. However, the periodic assumption also introduces unwanted boundary effects, which severely degrade the quality of the tracking model.

    We propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. A spatial regularization component is introduced in the learning to penalize correlation filter coefficients depending on their spatial location. Our SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples. We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014. Our approach achieves state-of-the-art results on all four datasets. On OTB-2013 and OTB-2015, we obtain an absolute gain of 8.0% and 8.2% respectively, in mean overlap precision, compared to the best existing trackers.

    Place, publisher, year, edition, pages
    IEEE Computer Society, 2015
    Series
    IEEE International Conference on Computer Vision. Proceedings, ISSN 1550-5499
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-121609 (URN)10.1109/ICCV.2015.490 (DOI)000380414100482 ()978-1-4673-8390-5 (ISBN)
    Conference
    International Conference in Computer Vision (ICCV), Santiago, Chile, December 13-16, 2015
    Available from: 2015-09-28 Created: 2015-09-28 Last updated: 2018-04-25
    5. Convolutional Features for Correlation Filter Based Visual Tracking
    Open this publication in new window or tab >>Convolutional Features for Correlation Filter Based Visual Tracking
    2015 (English)In: 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), IEEE conference proceedings, 2015, p. 621-629Conference paper, Published paper (Refereed)
    Abstract [en]

    Visual object tracking is a challenging computer vision problem with numerous real-world applications. This paper investigates the impact of convolutional features for the visual tracking problem. We propose to use activations from the convolutional layer of a CNN in discriminative correlation filter based tracking frameworks. These activations have several advantages compared to the standard deep features (fully connected layers). Firstly, they mitigate the need of task specific fine-tuning. Secondly, they contain structural information crucial for the tracking problem. Lastly, these activations have low dimensionality. We perform comprehensive experiments on three benchmark datasets: OTB, ALOV300++ and the recently introduced VOT2015. Surprisingly, different to image classification, our results suggest that activations from the first layer provide superior tracking performance compared to the deeper layers. Our results further show that the convolutional features provide improved results compared to standard handcrafted features. Finally, results comparable to state-of-theart trackers are obtained on all three benchmark datasets.

    Place, publisher, year, edition, pages
    IEEE conference proceedings, 2015
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-128869 (URN)10.1109/ICCVW.2015.84 (DOI)000380434700075 ()9781467397117 (ISBN)9781467397100 (ISBN)
    Conference
    15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015, 7-13 December 2015, Santiago, Chile
    Available from: 2016-06-02 Created: 2016-06-02 Last updated: 2019-06-26Bibliographically approved
    6. Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
    Open this publication in new window or tab >>Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
    2016 (English)In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), 2016, p. 1430-1438Conference paper, Published paper (Refereed)
    Abstract [en]

    Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data, additional samples need to be extracted and labeled by the tracker itself. This often leads to the inclusion of corrupted training samples, due to occlusions, misalignments and other perturbations. Existing tracking-by-detection methods either ignore this problem, or employ a separate component for managing the training set. We propose a novel generic approach for alleviating the problem of corrupted training samples in tracking-by-detection frameworks. Our approach dynamically manages the training set by estimating the quality of the samples. Contrary to existing approaches, we propose a unified formulation by minimizing a single loss over both the target appearance model and the sample quality weights. The joint formulation enables corrupted samples to be down-weighted while increasing the impact of correct ones. Experiments are performed on three benchmarks: OTB-2015 with 100 videos, VOT-2015 with 60 videos, and Temple-Color with 128 videos. On the OTB-2015, our unified formulation significantly improves the baseline, with a gain of 3.8% in mean overlap precision. Finally, our method achieves state-of-the-art results on all three datasets.

    Place, publisher, year, edition, pages
    Institute of Electrical and Electronics Engineers (IEEE), 2016
    Series
    IEEE Conference on Computer Vision and Pattern Recognition, E-ISSN 1063-6919 ; 2016
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-137882 (URN)10.1109/CVPR.2016.159 (DOI)000400012301051 ()9781467388511 (ISBN)9781467388528 (ISBN)
    Conference
    29th IEEE Conference on Computer Vision and Pattern Recognition, 27-30 June 2016, Las Vegas, NV, USA
    Note

    Funding Agencies|SSF (CUAS); VR (EMC2); VR (ELLIIT); Wallenberg Autonomous Systems Program; NSC; Nvidia

    Available from: 2017-06-01 Created: 2017-06-01 Last updated: 2019-06-27Bibliographically approved
    7. Deep motion and appearance cues for visual tracking
    Open this publication in new window or tab >>Deep motion and appearance cues for visual tracking
    Show others...
    2019 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 124, p. 74-81Article in journal (Refereed) Published
    Abstract [en]

    Generic visual tracking is a challenging computer vision problem, with numerous applications. Most existing approaches rely on appearance information by employing either hand-crafted features or deep RGB features extracted from convolutional neural networks. Despite their success, these approaches struggle in case of ambiguous appearance information, leading to tracking failure. In such cases, we argue that motion cue provides discriminative and complementary information that can improve tracking performance. Contrary to visual tracking, deep motion features have been successfully applied for action recognition and video classification tasks. Typically, the motion features are learned by training a CNN on optical flow images extracted from large amounts of labeled videos. In this paper, we investigate the impact of deep motion features in a tracking-by-detection framework. We also evaluate the fusion of hand-crafted, deep RGB, and deep motion features and show that they contain complementary information. To the best of our knowledge, we are the first to propose fusing appearance information with deep motion features for visual tracking. Comprehensive experiments clearly demonstrate that our fusion approach with deep motion features outperforms standard methods relying on appearance information alone.

    Place, publisher, year, edition, pages
    Elsevier, 2019
    Keywords
    Visual tracking, Deep learning, Optical flow, Discriminative correlation filters
    National Category
    Computer and Information Sciences
    Identifiers
    urn:nbn:se:liu:diva-148015 (URN)10.1016/j.patrec.2018.03.009 (DOI)000469427700008 ()2-s2.0-85044328745 (Scopus ID)
    Note

    Funding agencies: Swedish Foundation for Strategic Research; Swedish Research Council [2016-05543]; Wallenberg Autonomous Systems Program; Swedish National Infrastructure for Computing (SNIC); Nvidia

    Available from: 2018-05-24 Created: 2018-05-24 Last updated: 2019-06-24Bibliographically approved
    8. Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
    Open this publication in new window or tab >>Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
    2016 (English)In: Computer Vision - ECCV 2016, Pt V, Springer, 2016, Vol. 9909, p. 472-488Conference paper, Published paper (Refereed)
    Abstract [en]

    Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a training sample. However, the underlying DCF formulation is restricted to single-resolution feature maps, significantly limiting its potential. In this paper, we go beyond the conventional DCF framework and introduce a novel formulation for training continuous convolution filters. We employ an implicit interpolation model to pose the learning problem in the continuous spatial domain. Our proposed formulation enables efficient integration of multi-resolution deep feature maps, leading to superior results on three object tracking benchmarks: OTB-2015 (+5.1% in mean OP), Temple-Color (+4.6% in mean OP), and VOT2015 (20% relative reduction in failure rate). Additionally, our approach is capable of sub-pixel localization, crucial for the task of accurate feature point tracking. We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments.

    Place, publisher, year, edition, pages
    Springer, 2016
    Series
    Lecture Notes in Computer Science, ISSN 0302-9743
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-133550 (URN)10.1007/978-3-319-46454-1_29 (DOI)000389385400029 ()978-3-319-46453-4 (ISBN)
    Conference
    14th European Conference on Computer Vision (ECCV)
    Available from: 2016-12-30 Created: 2016-12-29 Last updated: 2019-06-26Bibliographically approved
    9. ECO: Efficient Convolution Operators for Tracking
    Open this publication in new window or tab >>ECO: Efficient Convolution Operators for Tracking
    2017 (English)In: Proceedings 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 6931-6939Conference paper, Published paper (Refereed)
    Abstract [en]

    In recent years, Discriminative Correlation Filter (DCF) based methods have significantly advanced the state-of-the-art in tracking. However, in the pursuit of ever increasing tracking performance, their characteristic speed and real-time capability have gradually faded. Further, the increasingly complex models, with massive number of trainable parameters, have introduced the risk of severe over-fitting. In this work, we tackle the key causes behind the problems of computational complexity and over-fitting, with the aim of simultaneously improving both speed and performance. We revisit the core DCF formulation and introduce: (i) a factorized convolution operator, which drastically reduces the number of parameters in the model; (ii) a compact generative model of the training sample distribution, that significantly reduces memory and time complexity, while providing better diversity of samples; (iii) a conservative model update strategy with improved robustness and reduced complexity. We perform comprehensive experiments on four benchmarks: VOT2016, UAV123, OTB-2015, and Temple-Color. When using expensive deep features, our tracker provides a 20-fold speedup and achieves a 13.0% relative gain in Expected Average Overlap compared to the top ranked method [12] in the VOT2016 challenge. Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65.0% AUC on OTB-2015.

    Place, publisher, year, edition, pages
    Institute of Electrical and Electronics Engineers (IEEE), 2017
    Series
    IEEE Conference on Computer Vision and Pattern Recognition, ISSN 1063-6919 ; 2017
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-144284 (URN)10.1109/CVPR.2017.733 (DOI)000418371407004 ()9781538604571 (ISBN)9781538604588 (ISBN)
    Conference
    30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 21-26 July 2017, Honolulu, HI, USA
    Note

    Funding Agencies|SSF (SymbiCloud); VR (EMC2) [2016-05543]; SNIC; WASP; Visual Sweden; Nvidia

    Available from: 2018-01-12 Created: 2018-01-12 Last updated: 2019-06-26Bibliographically approved
  • 78.
    Danelljan, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Visual Tracking2013Independent thesis Advanced level (degree of Master (Two Years)), 300 HE creditsStudent thesis
    Abstract [en]

    Visual tracking is a classical computer vision problem with many important applications in areas such as robotics, surveillance and driver assistance. The task is to follow a target in an image sequence. The target can be any object of interest, for example a human, a car or a football. Humans perform accurate visual tracking with little effort, while it remains a difficult computer vision problem. It imposes major challenges, such as appearance changes, occlusions and background clutter. Visual tracking is thus an open research topic, but significant progress has been made in the last few years.

    The first part of this thesis explores generic tracking, where nothing is known about the target except for its initial location in the sequence. A specific family of generic trackers that exploit the FFT for faster tracking-by-detection is studied. Among these, the CSK tracker have recently shown obtain competitive performance at extraordinary low computational costs. Three contributions are made to this type of trackers. Firstly, a new method for learning the target appearance is proposed and shown to outperform the original method. Secondly, different color descriptors are investigated for the tracking purpose. Evaluations show that the best descriptor greatly improves the tracking performance. Thirdly, an adaptive dimensionality reduction technique is proposed, which adaptively chooses the most important feature combinations to use. This technique significantly reduces the computational cost of the tracking task. Extensive evaluations show that the proposed tracker outperform state-of-the-art methods in literature, while operating at several times higher frame rate.

    In the second part of this thesis, the proposed generic tracking method is applied to human tracking in surveillance applications. A causal framework is constructed, that automatically detects and tracks humans in the scene. The system fuses information from generic tracking and state-of-the-art object detection in a Bayesian filtering framework. In addition, the system incorporates the identification and tracking of specific human parts to achieve better robustness and performance. Tracking results are demonstrated on a real-world benchmark sequence.

  • 79.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Bhat, Goutam
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    ECO: Efficient Convolution Operators for Tracking2017In: Proceedings 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 6931-6939Conference paper (Refereed)
    Abstract [en]

    In recent years, Discriminative Correlation Filter (DCF) based methods have significantly advanced the state-of-the-art in tracking. However, in the pursuit of ever increasing tracking performance, their characteristic speed and real-time capability have gradually faded. Further, the increasingly complex models, with massive number of trainable parameters, have introduced the risk of severe over-fitting. In this work, we tackle the key causes behind the problems of computational complexity and over-fitting, with the aim of simultaneously improving both speed and performance. We revisit the core DCF formulation and introduce: (i) a factorized convolution operator, which drastically reduces the number of parameters in the model; (ii) a compact generative model of the training sample distribution, that significantly reduces memory and time complexity, while providing better diversity of samples; (iii) a conservative model update strategy with improved robustness and reduced complexity. We perform comprehensive experiments on four benchmarks: VOT2016, UAV123, OTB-2015, and Temple-Color. When using expensive deep features, our tracker provides a 20-fold speedup and achieves a 13.0% relative gain in Expected Average Overlap compared to the top ranked method [12] in the VOT2016 challenge. Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65.0% AUC on OTB-2015.

  • 80.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Häger, Gustav
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Discriminative Scale Space Tracking2017In: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 39, no 8, p. 1561-1575Article in journal (Refereed)
    Abstract [en]

    Accurate scale estimation of a target is a challenging research problem in visual object tracking. Most state-of-the-art methods employ an exhaustive scale search to estimate the target size. The exhaustive search strategy is computationally expensive and struggles when encountered with large scale variations. This paper investigates the problem of accurate and robust scale estimation in a tracking-by-detection framework. We propose a novel scale adaptive tracking approach by learning separate discriminative correlation filters for translation and scale estimation. The explicit scale filter is learned online using the target appearance sampled at a set of different scales. Contrary to standard approaches, our method directly learns the appearance change induced by variations in the target scale. Additionally, we investigate strategies to reduce the computational cost of our approach. Extensive experiments are performed on the OTB and the VOT2014 datasets. Compared to the standard exhaustive scale search, our approach achieves a gain of 2.5 percent in average overlap precision on the OTB dataset. Additionally, our method is computationally efficient, operating at a 50 percent higher frame rate compared to the exhaustive scale search. Our method obtains the top rank in performance by outperforming 19 state-of-the-art trackers on OTB and 37 state-of-the-art trackers on VOT2014.

  • 81.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Häger, Gustav
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking2016In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), 2016, p. 1430-1438Conference paper (Refereed)
    Abstract [en]

    Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data, additional samples need to be extracted and labeled by the tracker itself. This often leads to the inclusion of corrupted training samples, due to occlusions, misalignments and other perturbations. Existing tracking-by-detection methods either ignore this problem, or employ a separate component for managing the training set. We propose a novel generic approach for alleviating the problem of corrupted training samples in tracking-by-detection frameworks. Our approach dynamically manages the training set by estimating the quality of the samples. Contrary to existing approaches, we propose a unified formulation by minimizing a single loss over both the target appearance model and the sample quality weights. The joint formulation enables corrupted samples to be down-weighted while increasing the impact of correct ones. Experiments are performed on three benchmarks: OTB-2015 with 100 videos, VOT-2015 with 60 videos, and Temple-Color with 128 videos. On the OTB-2015, our unified formulation significantly improves the baseline, with a gain of 3.8% in mean overlap precision. Finally, our method achieves state-of-the-art results on all three datasets.

  • 82.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Häger, Gustav
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Coloring Channel Representations for Visual Tracking2015In: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings / [ed] Rasmus R. Paulsen, Kim S. Pedersen, Springer, 2015, Vol. 9127, p. 117-129Conference paper (Refereed)
    Abstract [en]

    Visual object tracking is a classical, but still open research problem in computer vision, with many real world applications. The problem is challenging due to several factors, such as illumination variation, occlusions, camera motion and appearance changes. Such problems can be alleviated by constructing robust, discriminative and computationally efficient visual features. Recently, biologically-inspired channel representations \cite{felsberg06PAMI} have shown to provide promising results in many applications ranging from autonomous driving to visual tracking.

    This paper investigates the problem of coloring channel representations for visual tracking. We evaluate two strategies, channel concatenation and channel product, to construct channel coded color representations. The proposed channel coded color representations are generic and can be used beyond tracking.

    Experiments are performed on 41 challenging benchmark videos. Our experiments clearly suggest that a careful selection of color feature together with an optimal fusion strategy, significantly outperforms the standard luminance based channel representation. Finally, we show promising results compared to state-of-the-art tracking methods in the literature.

  • 83.
    Danelljan, Martin
    et al.
    Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.
    Häger, Gustav
    Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.
    Khan, Fahad Shahbaz
    Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.
    Felsberg, Michael
    Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.
    Convolutional Features for Correlation Filter Based Visual Tracking2015In: 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), IEEE conference proceedings, 2015, p. 621-629Conference paper (Refereed)
    Abstract [en]

    Visual object tracking is a challenging computer vision problem with numerous real-world applications. This paper investigates the impact of convolutional features for the visual tracking problem. We propose to use activations from the convolutional layer of a CNN in discriminative correlation filter based tracking frameworks. These activations have several advantages compared to the standard deep features (fully connected layers). Firstly, they mitigate the need of task specific fine-tuning. Secondly, they contain structural information crucial for the tracking problem. Lastly, these activations have low dimensionality. We perform comprehensive experiments on three benchmark datasets: OTB, ALOV300++ and the recently introduced VOT2015. Surprisingly, different to image classification, our results suggest that activations from the first layer provide superior tracking performance compared to the deeper layers. Our results further show that the convolutional features provide improved results compared to standard handcrafted features. Finally, results comparable to state-of-theart trackers are obtained on all three benchmark datasets.

  • 84.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Häger, Gustav
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Learning Spatially Regularized Correlation Filters for Visual Tracking2015In: Proceedings of the International Conference in Computer Vision (ICCV), 2015, IEEE Computer Society, 2015, p. 4310-4318Conference paper (Refereed)
    Abstract [en]

    Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively learned correlation filters (DCF) have been successfully applied to address this problem for tracking. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood. However, the periodic assumption also introduces unwanted boundary effects, which severely degrade the quality of the tracking model.

    We propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. A spatial regularization component is introduced in the learning to penalize correlation filter coefficients depending on their spatial location. Our SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples. We further propose an optimization strategy, based on the iterative Gauss-Seidel method, for efficient online learning of our SRDCF. Experiments are performed on four benchmark datasets: OTB-2013, ALOV++, OTB-2015, and VOT2014. Our approach achieves state-of-the-art results on all four datasets. On OTB-2013 and OTB-2015, we obtain an absolute gain of 8.0% and 8.2% respectively, in mean overlap precision, compared to the best existing trackers.

  • 85.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Granström, Karl
    Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
    Heintz, Fredrik
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Rudol, Piotr
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Wzorek, Mariusz
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Kvarnström, Jonas
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    Doherty, Patrick
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, The Institute of Technology.
    A Low-Level Active Vision Framework for Collaborative Unmanned Aircraft Systems2015In: COMPUTER VISION - ECCV 2014 WORKSHOPS, PT I / [ed] Lourdes Agapito, Michael M. Bronstein and Carsten Rother, Springer Publishing Company, 2015, Vol. 8925, p. 223-237Conference paper (Refereed)
    Abstract [en]

    Micro unmanned aerial vehicles are becoming increasingly interesting for aiding and collaborating with human agents in myriads of applications, but in particular they are useful for monitoring inaccessible or dangerous areas. In order to interact with and monitor humans, these systems need robust and real-time computer vision subsystems that allow to detect and follow persons.

    In this work, we propose a low-level active vision framework to accomplish these challenging tasks. Based on the LinkQuad platform, we present a system study that implements the detection and tracking of people under fully autonomous flight conditions, keeping the vehicle within a certain distance of a person. The framework integrates state-of-the-art methods from visual detection and tracking, Bayesian filtering, and AI-based control. The results from our experiments clearly suggest that the proposed framework performs real-time detection and tracking of persons in complex scenarios

  • 86.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Meneghetti, Giulia
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    A Probabilistic Framework for Color-Based Point Set Registration2016In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), 2016, p. 1818-1826Conference paper (Refereed)
    Abstract [en]

    In recent years, sensors capable of measuring both color and depth information have become increasingly popular. Despite the abundance of colored point set data, state-of-the-art probabilistic registration techniques ignore the available color information. In this paper, we propose a probabilistic point set registration framework that exploits available color information associated with the points. Our method is based on a model of the joint distribution of 3D-point observations and their color information. The proposed model captures discriminative color information, while being computationally efficient. We derive an EM algorithm for jointly estimating the model parameters and the relative transformations. Comprehensive experiments are performed on the Stanford Lounge dataset, captured by an RGB-D camera, and two point sets captured by a Lidar sensor. Our results demonstrate a significant gain in robustness and accuracy when incorporating color information. On the Stanford Lounge dataset, our approach achieves a relative reduction of the failure rate by 78% compared to the baseline. Furthermore, our proposed model outperforms standard strategies for combining color and 3D-point information, leading to state-of-the-art results.

  • 87.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Meneghetti, Giulia
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Aligning the Dissimilar: A Probabilistic Feature-Based Point Set Registration Approach2016In: Proceedings of the 23rd International Conference on Pattern Recognition (ICPR) 2016, IEEE, 2016, p. 247-252Conference paper (Refereed)
    Abstract [en]

    3D-point set registration is an active area of research in computer vision. In recent years, probabilistic registration approaches have demonstrated superior performance for many challenging applications. Generally, these probabilistic approaches rely on the spatial distribution of the 3D-points, and only recently color information has been integrated into such a framework, significantly improving registration accuracy. Other than local color information, high-dimensional 3D shape features have been successfully employed in many applications such as action recognition and 3D object recognition. In this paper, we propose a probabilistic framework to integrate high-dimensional 3D shape features with color information for point set registration. The 3D shape features are distinctive and provide complementary information beneficial for robust registration. We validate our proposed framework by performing comprehensive experiments on the challenging Stanford Lounge dataset, acquired by a RGB-D sensor, and an outdoor dataset captured by a Lidar sensor. The results clearly demonstrate that our approach provides superior results both in terms of robustness and accuracy compared to state-of-the-art probabilistic methods.

  • 88.
    Danelljan, Martin
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Robinson, Andreas
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking2016In: Computer Vision - ECCV 2016, Pt V, Springer, 2016, Vol. 9909, p. 472-488Conference paper (Refereed)
    Abstract [en]

    Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a training sample. However, the underlying DCF formulation is restricted to single-resolution feature maps, significantly limiting its potential. In this paper, we go beyond the conventional DCF framework and introduce a novel formulation for training continuous convolution filters. We employ an implicit interpolation model to pose the learning problem in the continuous spatial domain. Our proposed formulation enables efficient integration of multi-resolution deep feature maps, leading to superior results on three object tracking benchmarks: OTB-2015 (+5.1% in mean OP), Temple-Color (+4.6% in mean OP), and VOT2015 (20% relative reduction in failure rate). Additionally, our approach is capable of sub-pixel localization, crucial for the task of accurate feature point tracking. We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments.

  • 89.
    Dehlin, Jonas
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Löf, Joakim
    Linköping University, Department of Electrical Engineering.
    Dynamic Infrared Simulation: A Feasibility Study of a Physically Based Infrared Simulation Model2006Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The increased usage of infrared sensors by pilots has created a growing demand for simulated environments based on infrared radiation. This has led to an increased need for Saab to refine their existing model for simulating real-time infrared imagery, resulting in the carrying through of this thesis. Saab develops the Gripen aircraft, and they provide training simulators where pilots can train in a realistic environment. The new model is required to be based on the real-world behavior of infrared radiation, and furthermore, unlike Saab's existing model, have dynamically changeable attributes.

    This thesis seeks to develop a simulation model compliant with the requirements presented by Saab, and to develop the implementation of a test environment demonstrating the features and capabilities of the proposed model. All through the development of the model, the pilot training value has been kept in mind.

    The first part of the thesis consists of a literature study to build a theoretical base for the rest of the work. This is followed by the development of the simulation model itself and a subsequent implementation thereof. The simulation model and the test implementation are evaluated as the final step conducted within the framework of this thesis.

    The main conclusions of this thesis first of all includes that the proposed simulation model does in fact have its foundation in physics. It is further concluded that certain attributes of the model, such as time of day, are dynamically changeable as requested. Furthermore, the test implementation is considered to have been feasibly integrated with the current simulation environment.

    A plan concluding how to proceed has also been developed. The plan suggests future work with the proposed simulation model, since the evaluation shows that it performs well in comparison to the existing model as well as other products on the market.

  • 90.
    Dornaika, Fadi
    et al.
    Linköping University, Department of Electrical Engineering, Image Coding. Linköping University, The Institute of Technology.
    Ahlberg, Jörgen
    Swedish Defence Research Agency (FOI), Linköping, Sweden.
    Face Model Adaptation for Tracking and Active Appearance Model Training2003In: Proceedings of the British Machine Vision Conference / [ed] Richard Harvey and Andrew Bangham, 2003, p. 57.1-57.10Conference paper (Other academic)
    Abstract [en]

    In this paper, we consider the potentialities of adapting a 3D deformable face model to video sequences. Two adaptation methods are proposed. The first method computes the adaptation using a locally exhaustive and directed search in the parameter space. The second method decouples the estimation of head and facial feature motion. It computes the 3D head pose by combining: (i) a robust feature-based pose estimator, and (ii) a global featureless criterion. The facial animation parameters are then estimated with a combined exhaustive and directed search. Tracking experiments and performance evaluation demonstrate the feasibility and usefulness of the developed methods. These experiments also show that the proposed methods can outperform the adaptation based on a directed continuous search.

  • 91.
    Dornaika, Fadi
    et al.
    Laboratoire Heudiasyc, Université de Technologie de Compiègne, France.
    Ahlberg, Jörgen
    Swedish Defence Research Agency (FOI), Linköping, Sweden.
    Fast and Reliable Active Appearance Model Search for 3D Face Tracking2004In: IEEE transactions on systems, man and cybernetics. Part B. Cybernetics, ISSN 1083-4419, E-ISSN 1941-0492, Vol. 34, no 4, p. 1838-1853Article in journal (Refereed)
    Abstract [en]

    This paper addresses the three-dimensional (3-D) tracking of pose and animation of the human face in monocular image sequences using active appearance models. The major problem of the classical appearance-based adaptation is the high computationaltimeresultingfrom theinclusionofasynthesisstep in the iterative optimization. Whenever the dimension of the face space is large, a real-time performance cannot be achieved. In this paper, we aim at designing a fast and stable active appearance model search for 3-D face tracking. The main contribution is a search algorithm whose CPU-time is not dependent on the dimension of the face space. Using this algorithm, we show that both the CPU-time and the likelihood of a nonaccurate tracking are reduced. Experiments evaluating the effectiveness of the proposed algorithm are reported, as well as method comparison and tracking synthetic and real image sequences.

  • 92.
    Dornaika, Fadi
    et al.
    Computer Vision Centre, Autonomous University of Barcelona, Edifici O, Campus UAB, Bellaterra, Barcelona, Spain.
    Ahlberg, Jörgen
    Swedish Defence Research Agency (FOI), Linköping, Sweden.
    Fitting 3D Face Models for Tracking and Active Appearance Model Training2006In: Image and Vision Computing, ISSN 0262-8856, E-ISSN 1872-8138, Vol. 24, no 9, p. 1010-1024Article in journal (Refereed)
    Abstract [en]

    In this paper, we consider fitting a 3D deformable face model to continuous video sequences for the tasks of tracking and training. We propose two appearance-based methods that only require a simple statistical facial texture model and do not require any information about an empirical or analytical gradient matrix, since the best search directions are estimated on the fly. The first method computes the fitting using a locally exhaustive and directed search where the 3D head pose and the facial actions are simultaneously estimated. The second method decouples the estimation of these parameters. It computes the 3D head pose using a robust feature-based pose estimator incorporating a facial texture consistency measure. Then, it estimates the facial actions with an exhaustive and directed search. Fitting and tracking experiments demonstrate the feasibility and usefulness of the developed methods. A performance evaluation also shows that the proposed methods can outperform the fitting based on an active appearance model search adopting a pre-computed gradient matrix. Although the proposed schemes are not as fast as the schemes adopting a directed continuous search, they can tackle many disadvantages associated with such approaches.

  • 93. Eidenvall, Lars
    et al.
    Sjöberg, Birgitta Janero
    Linköping University, Department of Medical and Health Sciences, Clinical Physiology. Linköping University, Faculty of Health Sciences. Linköping University, Center for Medical Image Science and Visualization (CMIV). Östergötlands Läns Landsting, Heart and Medicine Center, Department of Clinical Physiology in Linköping.
    Ask, Per
    Linköping University, Department of Biomedical Engineering, Physiological Measurements. Linköping University, The Institute of Technology.
    Loyd, Dan
    Linköping University, Department of Management and Engineering, Applied Thermodynamics and Fluid Mechanics. Linköping University, The Institute of Technology.
    Wranne, Bengt
    Linköping University, Department of Medicine and Care, Clinical Physiology. Linköping University, Faculty of Health Sciences. Östergötlands Läns Landsting, Heart and Medicine Center, Department of Clinical Physiology in Linköping.
    Two-dimensional color Doppler flow velocity profiles can be time corrected with an external ECG-delay device.1992In: Journal of the American Society of Echocardiography, ISSN 0894-7317, E-ISSN 1097-6795, Vol. 5, no 4, p. 405-413Article in journal (Refereed)
    Abstract [en]

    Although two-dimensional ultrasound color flow imaging is often considered to be a real-time technique, the acquisition time for two-dimensional color images may be up to 200 msec. Time correction is therefore necessary to obtain correct flow velocity profiles. We have developed a time-correction method in which a specially designed unit detects the QRS complex from the patient and creates a trig pulse that is delayed incrementally in relation to the QRS complex. This trig pulse controls the acquisition of the ultrasound images. A number of consecutively delayed images, with known incremental delay between the sweeps, can thus be stored in the memory of the echocardiograph and transferred digitally to a computer. The time-corrected flow velocity profile is obtained by interpolation of data from the time-delayed profiles. The system was evaluated in a Doppler string phantom test. With this technique it is possible to study time-corrected flow velocity profiles without the need to alter existing ultrasound Doppler equipment.

  • 94.
    Eilertsen, Gabriel
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    The high dynamic range imaging pipeline: Tone-mapping, distribution, and single-exposure reconstruction2018Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    Techniques for high dynamic range (HDR) imaging make it possible to capture and store an increased range of luminances and colors as compared to what can be achieved with a conventional camera. This high amount of image information can be used in a wide range of applications, such as HDR displays, image-based lighting, tone-mapping, computer vision, and post-processing operations. HDR imaging has been an important concept in research and development for many years. Within the last couple of years it has also reached the consumer market, e.g. with TV displays that are capable of reproducing an increased dynamic range and peak luminance.

    This thesis presents a set of technical contributions within the field of HDR imaging. First, the area of HDR video tone-mapping is thoroughly reviewed, evaluated and developed upon. A subjective comparison experiment of existing methods is performed, followed by the development of novel techniques that overcome many of the problems evidenced by the evaluation. Second, a largescale objective comparison is presented, which evaluates existing techniques that are involved in HDR video distribution. From the results, a first open-source HDR video codec solution, Luma HDRv, is built using the best performing techniques. Third, a machine learning method is proposed for the purpose of reconstructing an HDR image from one single-exposure low dynamic range (LDR) image. The method is trained on a large set of HDR images, using recent advances in deep learning, and the results increase the quality and performance significantly as compared to existing algorithms.

    The areas for which contributions are presented can be closely inter-linked in the HDR imaging pipeline. Here, the thesis work helps in promoting efficient and high-quality HDR video distribution and display, as well as robust HDR image reconstruction from a single conventional LDR image.

    List of papers
    1. A comparative review of tone-mapping algorithms for high dynamic range video
    Open this publication in new window or tab >>A comparative review of tone-mapping algorithms for high dynamic range video
    2017 (English)In: Computer graphics forum (Print), ISSN 0167-7055, E-ISSN 1467-8659, Vol. 36, no 2, p. 565-592Article in journal (Refereed) Published
    Abstract [en]

    Tone-mapping constitutes a key component within the field of high dynamic range (HDR) imaging. Its importance is manifested in the vast amount of tone-mapping methods that can be found in the literature, which are the result of an active development in the area for more than two decades. Although these can accommodate most requirements for display of HDR images, new challenges arose with the advent of HDR video, calling for additional considerations in the design of tone-mapping operators (TMOs). Today, a range of TMOs exist that do support video material. We are now reaching a point where most camera captured HDR videos can be prepared in high quality without visible artifacts, for the constraints of a standard display device. In this report, we set out to summarize and categorize the research in tone-mapping as of today, distilling the most important trends and characteristics of the tone reproduction pipeline. While this gives a wide overview over the area, we then specifically focus on tone-mapping of HDR video and the problems this medium entails. First, we formulate the major challenges a video TMO needs to address. Then, we provide a description and categorization of each of the existing video TMOs. Finally, by constructing a set of quantitative measures, we evaluate the performance of a number of the operators, in order to give a hint on which can be expected to render the least amount of artifacts. This serves as a comprehensive reference, categorization and comparative assessment of the state-of-the-art in tone-mapping for HDR video.

    Place, publisher, year, edition, pages
    WILEY, 2017
    National Category
    Computer Sciences
    Identifiers
    urn:nbn:se:liu:diva-139637 (URN)10.1111/cgf.13148 (DOI)000404474000048 ()
    Conference
    38th Annual Conference of the European-Association-for-Computer-Graphics (EUROGRAPHICS)
    Note

    Funding Agencies|Swedish Foundation for Strategic Research (SSF) [IIS11-0081]; Linkoping University Center for Industrial Information Technology (CENIIT); Swedish Research Council through the Linnaeus Environment CADICS

    Available from: 2017-08-16 Created: 2017-08-16 Last updated: 2018-05-15
    2. Evaluation of Tone Mapping Operators for HDR-Video
    Open this publication in new window or tab >>Evaluation of Tone Mapping Operators for HDR-Video
    2013 (English)In: Computer graphics forum (Print), ISSN 0167-7055, E-ISSN 1467-8659, Vol. 32, no 7, p. 275-284Article in journal (Refereed) Published
    Abstract [en]

    Eleven tone-mapping operators intended for video processing are analyzed and evaluated with camera-captured and computer-generated high-dynamic-range content. After optimizing the parameters of the operators in a formal experiment, we inspect and rate the artifacts (flickering, ghosting, temporal color consistency) and color rendition problems (brightness, contrast and color saturation) they produce. This allows us to identify major problems and challenges that video tone-mapping needs to address. Then, we compare the tone-mapping results in a pair-wise comparison experiment to identify the operators that, on average, can be expected to perform better than the others and to assess the magnitude of differences between the best performing operators.

    Place, publisher, year, edition, pages
    Wiley, 2013
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-104135 (URN)10.1111/cgf.12235 (DOI)000327310800029 ()
    Projects
    VPS
    Available from: 2014-02-07 Created: 2014-02-07 Last updated: 2018-05-15Bibliographically approved
    3. Real-time noise-aware tone mapping
    Open this publication in new window or tab >>Real-time noise-aware tone mapping
    2015 (English)In: ACM Transactions on Graphics, ISSN 0730-0301, E-ISSN 1557-7368, ISSN 0730-0301, Vol. 34, no 6, p. 198:1-198:15, article id 198Article in journal (Refereed) Published
    Abstract [en]

    Real-time high quality video tone mapping is needed for manyapplications, such as digital viewfinders in cameras, displayalgorithms which adapt to ambient light, in-camera processing,rendering engines for video games and video post-processing. We propose a viable solution for these applications by designing a videotone-mapping operator that controls the visibility of the noise,adapts to display and viewing environment, minimizes contrastdistortions, preserves or enhances image details, and can be run inreal-time on an incoming sequence without any preprocessing. To ourknowledge, no existing solution offers all these features. Our novelcontributions are: a fast procedure for computing local display-adaptivetone-curves which minimize contrast distortions, a fast method for detailenhancement free from ringing artifacts, and an integrated videotone-mapping solution combining all the above features.

    Place, publisher, year, edition, pages
    New York, NY, USA: Association for Computing Machinery (ACM), 2015
    Keywords
    Tone mapping, high dynamic range video, display algorithms
    National Category
    Computer Sciences Media Engineering
    Identifiers
    urn:nbn:se:liu:diva-122681 (URN)10.1145/2816795.2818092 (DOI)000363671200035 ()
    Conference
    SIGGRAPH Aisa 2015
    Projects
    VPS
    Funder
    Swedish Foundation for Strategic Research
    Available from: 2015-11-14 Created: 2015-11-14 Last updated: 2018-05-15
    4. A HIGH DYNAMIC RANGE VIDEO CODEC OPTIMIZED BY LARGE-SCALE TESTING
    Open this publication in new window or tab >>A HIGH DYNAMIC RANGE VIDEO CODEC OPTIMIZED BY LARGE-SCALE TESTING
    2016 (English)In: 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), IEEE , 2016, p. 1379-1383Conference paper, Published paper (Refereed)
    Abstract [en]

    While a number of existing high-bit depth video compression methods can potentially encode high dynamic range (HDR) video, few of them provide this capability. In this paper, we investigate techniques for adapting HDR video for this purpose. In a large-scale test on 33 HDR video sequences, we compare 2 video codecs, 4 luminance encoding techniques (transfer functions) and 3 color encoding methods, measuring quality in terms of two objective metrics, PU-MSSIM and HDR-VDP-2. From the results we design an open source HDR video encoder, optimized for the best compression performance given the techniques examined.

    Place, publisher, year, edition, pages
    IEEE, 2016
    Series
    IEEE International Conference on Image Processing ICIP, ISSN 1522-4880
    Keywords
    High dynamic range (HDR) video; HDR video coding; perceptual image metrics
    National Category
    Signal Processing
    Identifiers
    urn:nbn:se:liu:diva-134106 (URN)10.1109/ICIP.2016.7532584 (DOI)000390782001093 ()978-1-4673-9961-6 (ISBN)
    Conference
    23rd IEEE International Conference on Image Processing (ICIP)
    Available from: 2017-01-22 Created: 2017-01-22 Last updated: 2018-05-15
    5. HDR image reconstruction from a single exposure using deep CNNs
    Open this publication in new window or tab >>HDR image reconstruction from a single exposure using deep CNNs
    Show others...
    2017 (English)In: ACM Transactions on Graphics, ISSN 0730-0301, E-ISSN 1557-7368, Vol. 36, no 6, article id 178Article in journal (Refereed) Published
    Abstract [en]

    Camera sensors can only capture a limited range of luminance simultaneously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting information that have been lost in saturated image areas, in order to enable HDR reconstruction from a single exposure. We show that this problem is well-suited for deep learning algorithms, and propose a deep convolutional neural network (CNN) that is specifically designed taking into account the challenges in predicting HDR values. To train the CNN we gather a large dataset of HDR images, which we augment by simulating sensor saturation for a range of cameras. To further boost robustness, we pre-train the CNN on a simulated HDR dataset created from a subset of the MIT Places database. We demonstrate that our approach can reconstruct high-resolution visually convincing HDR results in a wide range of situations, and that it generalizes well to reconstruction of images captured with arbitrary and low-end cameras that use unknown camera response functions and post-processing. Furthermore, we compare to existing methods for HDR expansion, and show high quality results also for image based lighting. Finally, we evaluate the results in a subjective experiment performed on an HDR display. This shows that the reconstructed HDR images are visually convincing, with large improvements as compared to existing methods.

    Place, publisher, year, edition, pages
    ASSOC COMPUTING MACHINERY, 2017
    Keywords
    HDR reconstruction; inverse tone-mapping; deep learning; convolutional network
    National Category
    Media Engineering
    Identifiers
    urn:nbn:se:liu:diva-143943 (URN)10.1145/3130800.3130816 (DOI)000417448700008 ()
    Conference
    10th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia
    Note

    Funding Agencies|Linkoping University Center for Industrial Information Technology (CENIIT); Swedish Science Council [2015-05180]; Wallenberg Autonomous Systems Program (WASP)

    Available from: 2017-12-29 Created: 2017-12-29 Last updated: 2018-05-15
  • 95.
    Eilertsen, Gabriel
    et al.
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Unger, Jonas
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    BriefMatch: Dense binary feature matching for real-time optical flow estimation2017In: Proceedings of the Scandinavian Conference on Image Analysis (SCIA17) / [ed] Puneet Sharma, Filippo Maria Bianchi, Springer, 2017, Vol. 10269, p. 221-233Conference paper (Refereed)
    Abstract [en]

    Research in optical flow estimation has to a large extent focused on achieving the best possible quality with no regards to running time. Nevertheless, in a number of important applications the speed is crucial. To address this problem we present BriefMatch, a real-time optical flow method that is suitable for live applications. The method combines binary features with the search strategy from PatchMatch in order to efficiently find a dense correspondence field between images. We show that the BRIEF descriptor provides better candidates (less outlier-prone) in shorter time, when compared to direct pixel comparisons and the Census transform. This allows us to achieve high quality results from a simple filtering of the initially matched candidates. Currently, BriefMatch has the fastest running time on the Middlebury benchmark, while placing highest of all the methods that run in shorter than 0.5 seconds.

  • 96.
    Eilertsen, Gabriel
    et al.
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. IRYSTEC, Canada.
    Mantiuk, Rafal K.
    University of Cambridge, England; IRYSTEC, Canada.
    Unger, Jonas
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. IRYSTEC, Canada.
    REAL-TIME NOISE-AWARE TONE-MAPPING AND ITS USE IN LUMINANCE RETARGETING2016In: 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), IEEE , 2016, p. 894-898Conference paper (Refereed)
    Abstract [en]

    With the aid of tone-mapping operators, high dynamic range images can be mapped for reproduction on standard displays. However, for large restrictions in terms of display dynamic range and peak luminance, limitations of the human visual system have significant impact on the visual appearance. In this paper, we use components from the real-time noise-aware tone-mapping to complement an existing method for perceptual matching of image appearance under different luminance levels. The refined luminance retargeting method improves subjective quality on a display with large limitations in dynamic range, as suggested by our subjective evaluation.

  • 97.
    Eklund, Anders
    Linköping University, Department of Electrical Engineering.
    Image coding with H.264 I-frames2007Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In this thesis work a part of the video coding standard H.264 has been implemented. The part of the video coder that is used to code the I-frames has been implemented to see how well suited it is for regular image coding. The big difference versus other image coding standards, such as JPEG and JPEG2000, is that this video coder uses both a predictor and a transform to compress the I-frames, while JPEG and JPEG2000 only use a transform. Since the prediction error is sent instead of the actual pixel values, a lot of the values are zero or close to zero before the transformation and quantization. The method is much like a video encoder but the difference is that blocks of an image are predicted instead of frames in a video sequence.

  • 98.
    Eldesokey, Abdelrahman
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Ellipse Detection for Visual Cyclists Analysis “In the Wild”2017In: Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I / [ed] Michael Felsberg, Anders Heyden and Norbert Krüger, Springer, 2017, Vol. 10424, p. 319-331Conference paper (Refereed)
    Abstract [en]

    Autonomous driving safety is becoming a paramount issue due to the emergence of many autonomous vehicle prototypes. The safety measures ensure that autonomous vehicles are safe to operate among pedestrians, cyclists and conventional vehicles. While safety measures for pedestrians have been widely studied in literature, little attention has been paid to safety measures for cyclists. Visual cyclists analysis is a challenging problem due to the complex structure and dynamic nature of the cyclists. The dynamic model used for cyclists analysis heavily relies on the wheels. In this paper, we investigate the problem of ellipse detection for visual cyclists analysis in the wild. Our first contribution is the introduction of a new challenging annotated dataset for bicycle wheels, collected in real-world urban environment. Our second contribution is a method that combines reliable arcs selection and grouping strategies for ellipse detection. The reliable selection and grouping mechanism leads to robust ellipse detections when combined with the standard least square ellipse fitting approach. Our experiments clearly demonstrate that our method provides improved results, both in terms of accuracy and robustness in challenging urban environment settings.

  • 99.
    Eldesokey, Abdelrahman
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Inception Institute of Artificial Intelligence Abu Dhabi, UAE.
    Propagating Confidences through CNNs for Sparse Data Regression2018Conference paper (Refereed)
    Abstract [en]

    In most computer vision applications, convolutional neural networks (CNNs) operate on dense image data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open problem with numerous applications in autonomous driving, robotics, and surveillance. To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. Furthermore, we propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. Comprehensive experiments are performed on the KITTI depth benchmark and the results clearly demonstrate that the proposed approach achieves superior performance while requiring three times fewer parameters than the state-of-the-art methods. Moreover, our approach produces a continuous pixel-wise confidence map enabling information fusion, state inference, and decision support.

  • 100.
    Ellner, Henrik
    Linköping University, Department of Electrical Engineering.
    Facial animation parameter extraction using high-dimensional manifolds2006Independent thesis Basic level (professional degree), 20 points / 30 hpStudent thesis
    Abstract [en]

    This thesis presents and examines a method that can potentially be used for extracting parameters from a manifold in a space. In the thesis the method is presented, and a potential application is described. The application is determining FAP-values. FAP-values

    are used for parameterizing faces, which can e.g. be used to compress data when sending video sequences over limited bandwidth.

1234567 51 - 100 of 467
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf