liu.seSearch for publications in DiVA
Change search
Refine search result
1234 1 - 50 of 185
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.
  • 1.
    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.
    Gladh, Susanna
    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.
    Deep motion and appearance cues for visual tracking2019In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 124, p. 74-81Article in journal (Refereed)
    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.

  • 2.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Termisk Systemteknik AB, Linköping, Sweden.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision.
    Visual Spectrum Image Generation fromThermal Infrared2019Conference paper (Other academic)
    Abstract [en]

    We address short-term, single-object tracking, a topic that is currently seeing fast progress for visual video, for the case of thermal infrared (TIR) imagery. Tracking methods designed for TIR are often subject to a number of constraints, e.g., warm objects, low spatial resolution, and static camera. As TIR cameras become less noisy and get higher resolution these constraints are less relevant, and for emerging civilian applications, e.g., surveillance and automotive safety, new tracking methods are needed. Due to the special characteristics of TIR imagery, we argue that template-based trackers based on distribution fields should have an advantage over trackers based on spatial structure features. In this paper, we propose a templatebased tracking method (ABCD) designed specifically for TIR and not being restricted by any of the constraints above. The proposed tracker is evaluated on the VOT-TIR2015 and VOT2015 datasets using the VOT evaluation toolkit and a comparison of relative ranking of all common participating trackers in the challenges is provided. Experimental results show that the ABCD tracker performs particularly well on thermal infrared sequences.

  • 3.
    Öfjäll, Kristoffer
    et al.
    Visionists AB, Gothenburg, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Approximative Coding Methods for Channel Representations2018In: Journal of Mathematical Imaging and Vision, ISSN 0924-9907, E-ISSN 1573-7683, Vol. 60, no 6, p. 929-940Article in journal (Refereed)
    Abstract [en]

    Most methods that address computer vision prob-lems require powerful visual features. Many successfulapproaches apply techniques motivated from nonparametricstatistics. The channel representation provides a frameworkfornonparametricdistributionrepresentation.Althoughearlywork has focused on a signal processing view of the rep-resentation, the channel representation can be interpretedin probabilistic terms, e.g., representing the distribution oflocal image orientation. In this paper, a variety of approxi-mative channel-based algorithms for probabilistic problemsare presented: a novel efficient algorithm for density recon-struction, a novel and efficient scheme for nonlinear griddingof densities, and finally a novel method for estimating Copuladensities. The experimental results provide evidence that byrelaxing the requirements for exact solutions, efficient algo-rithms are obtained

  • 4.
    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.

  • 5.
    Holmquist, Karl
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Senel, Oeniz
    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.
    Computing a Collision-Free Path using the monogenic scale space2018In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2018, p. 8097-8102Conference paper (Refereed)
    Abstract [en]

    Mobile robots have been used for various purposes with different functionalities which require them to freely move in environments containing both static and dynamic obstacles to accomplish given tasks. One of the most relevant capabilities in terms of navigating a mobile robot in such an environment is to find a safe path to a goal position. This paper shows that there exists an accurate solution to the Laplace equation which allows finding a collision-free path and that it can be efficiently calculated for a rectangular bounded domain such as a map which is represented as an image. This is accomplished by the use of the monogenic scale space resulting in a vector field which describes the attracting and repelling forces from the obstacles and the goal. The method is shown to work in reasonably convex domains and by the use of tessellation of the environment map for non-convex environments.

  • 6.
    Häger, Gustav
    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.
    Countering bias in tracking evaluations2018In: Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications / [ed] Francisco Imai, Alain Tremeau and Jose Braz, Science and Technology Publications, Lda , 2018, Vol. 5, p. 581-587Conference paper (Refereed)
    Abstract [en]

    Recent years have witnessed a significant leap in visual object tracking performance mainly due to powerfulfeatures, sophisticated learning methods and the introduction of benchmark datasets. Despite this significantimprovement, the evaluation of state-of-the-art object trackers still relies on the classical intersection overunion (IoU) score. In this work, we argue that the object tracking evaluations based on classical IoU score aresub-optimal. As our first contribution, we theoretically prove that the IoU score is biased in the case of largetarget objects and favors over-estimated target prediction sizes. As our second contribution, we propose a newscore that is unbiased with respect to target prediction size. We systematically evaluate our proposed approachon benchmark tracking data with variations in relative target size. Our empirical results clearly suggest thatthe proposed score is unbiased in general.

  • 7.
    Järemo Lawin, Felix
    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 Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Forssén, Per-Erik
    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.
    Density Adaptive Point Set Registration2018In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018, p. 3829-3837Conference paper (Refereed)
    Abstract [en]

    Probabilistic methods for point set registration have demonstrated competitive results in recent years. These techniques estimate a probability distribution model of the point clouds. While such a representation has shown promise, it is highly sensitive to variations in the density of 3D points. This fundamental problem is primarily caused by changes in the sensor location across point sets.    We revisit the foundations of the probabilistic registration paradigm. Contrary to previous works, we model the underlying structure of the scene as a latent probability distribution, and thereby induce invariance to point set density changes. Both the probabilistic model of the scene and the registration parameters are inferred by minimizing the Kullback-Leibler divergence in an Expectation Maximization based framework. Our density-adaptive registration successfully handles severe density variations commonly encountered in terrestrial Lidar applications. We perform extensive experiments on several challenging real-world Lidar datasets. The results demonstrate that our approach outperforms state-of-the-art probabilistic methods for multi-view registration, without the need of re-sampling.

  • 8.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Generating Visible Spectrum Images from Thermal Infrared2018In: Proceedings 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops CVPRW 2018, Institute of Electrical and Electronics Engineers (IEEE), 2018, p. 1224-1233Conference paper (Refereed)
    Abstract [en]

    Transformation of thermal infrared (TIR) images into visual, i.e. perceptually realistic color (RGB) images, is a challenging problem. TIR cameras have the ability to see in scenarios where vision is severely impaired, for example in total darkness or fog, and they are commonly used, e.g., for surveillance and automotive applications. However, interpretation of TIR images is difficult, especially for untrained operators. Enhancing the TIR image display by transforming it into a plausible, visual, perceptually realistic RGB image presumably facilitates interpretation. Existing grayscale to RGB, so called, colorization methods cannot be applied to TIR images directly since those methods only estimate the chrominance and not the luminance. In the absence of conventional colorization methods, we propose two fully automatic TIR to visual color image transformation methods, a two-step and an integrated approach, based on Convolutional Neural Networks. The methods require neither pre- nor postprocessing, do not require any user input, and are robust to image pair misalignments. We show that the methods do indeed produce perceptually realistic results on publicly available data, which is assessed both qualitatively and quantitatively.

  • 9.
    Grelsson, Bertil
    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.
    Improved Learning in Convolutional Neural Networks with Shifted Exponential Linear Units (ShELUs)2018In: 2018 24th International Conference on Pattern Recognition (ICPR), IEEE, 2018, p. 517-522Conference paper (Refereed)
    Abstract [en]

    The Exponential Linear Unit (ELU) has been proven to speed up learning and improve the classification performance over activation functions such as ReLU and Leaky ReLU for convolutional neural networks. The reasons behind the improved behavior are that ELU reduces the bias shift, it saturates for large negative inputs and it is continuously differentiable. However, it remains open whether ELU has the optimal shape and we address the quest for a superior activation function.We use a new formulation to tune a piecewise linear activation function during training, to investigate the above question, and learn the shape of the locally optimal activation function. With this tuned activation function, the classification performance is improved and the resulting, learned activation function shows to be ELU-shaped irrespective if it is initialized as a RELU, LReLU or ELU. Interestingly, the learned activation function does not exactly pass through the origin indicating that a shifted ELU-shaped activation function is preferable. This observation leads us to introduce the Shifted Exponential Linear Unit (ShELU) as a new activation function.Experiments on Cifar-100 show that the classification performance is further improved when using the ShELU activation function in comparison with ELU. The improvement is achieved when learning an individual bias shift for each neuron.

  • 10.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Probabilistic and biologically inspired feature representations2018Book (Refereed)
    Abstract [en]

    Under the title "Probabilistic and Biologically Inspired Feature Representations," this text collects a substantial amount of work on the topic of channel representations. Channel representations are a biologically motivated, wavelet-like approach to visual feature descriptors: they are local and compact, they form a computational framework, and the represented information can be reconstructed. The first property is shared with many histogram- and signature-based descriptors, the latter property with the related concept of population codes. In their unique combination of properties, channel representations become a visual Swiss army knife—they can be used for image enhancement, visual object tracking, as 2D and 3D descriptors, and for pose estimation. In the chapters of this text, the framework of channel representations will be introduced and its attributes will be elaborated, as well as further insight into its probabilistic modeling and algorithmic implementation will be given. Channel representations are a useful toolbox to represent visual information for machine learning, as they establish a generic way to compute popular descriptors such as HOG, SIFT, and SHOT. Even in an age of deep learning, they provide a good compromise between hand-designed descriptors and a-priori structureless feature spaces as seen in the layers of deep networks.

  • 11.
    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.

  • 12.
    Khan, Fahad
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    van de Weijer, Joost
    University of Autonoma Barcelona, Spain.
    Muhammad Anwer, Rao
    Aalto University, Finland.
    Bagdanov, Andrew D.
    University of Florence, Italy.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Laaksonen, Jorma
    Aalto University, Finland.
    Scale coding bag of deep features for human attribute and action recognition2018In: Machine Vision and Applications, ISSN 0932-8092, E-ISSN 1432-1769, Vol. 29, no 1, p. 55-71Article in journal (Refereed)
    Abstract [en]

    Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art.

  • 13.
    Grelsson, Bertil
    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.
    Felsberg, Michael
    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.
    Signal Reconstruction Performance under Quantized Noisy Compressed Sensing2018In: 2019 DATA COMPRESSION CONFERENCE (DCC), IEEE , 2018, p. 149-155Conference paper (Refereed)
    Abstract [en]

    n/a

  • 14.
    Johnander, Joakim
    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 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.
    DCCO: Towards Deformable Continuous Convolution Operators for Visual Tracking2017In: 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. 55-67Conference paper (Refereed)
    Abstract [en]

    Discriminative Correlation Filter (DCF) based methods have shown competitive performance on tracking benchmarks in recent years. Generally, DCF based trackers learn a rigid appearance model of the target. However, this reliance on a single rigid appearance model is insufficient in situations where the target undergoes non-rigid transformations. In this paper, we propose a unified formulation for learning a deformable convolution filter. In our framework, the deformable filter is represented as a linear combination of sub-filters. Both the sub-filter coefficients and their relative locations are inferred jointly in our formulation. Experiments are performed on three challenging tracking benchmarks: OTB-2015, TempleColor and VOT2016. Our approach improves the baseline method, leading to performance comparable to state-of-the-art.

  • 15.
    Järemo-Lawin, Felix
    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.
    Tosteberg, Patrik
    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.
    Deep Projective 3D Semantic Segmentation2017In: 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, p. 95-107Conference paper (Refereed)
    Abstract [en]

    Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmentation, its impact on point cloud data has been limited so far. Recent attempts, based on 3D deep learning approaches (3D-CNNs), have achieved below-expected results. Such methods require voxelizations of the underlying point cloud data, leading to decreased spatial resolution and increased memory consumption. Additionally, 3D-CNNs greatly suffer from the limited availability of annotated datasets.

  • 16.
    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.

  • 17.
    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.

  • 18.
    Nawaz, Tahir
    et al.
    Computational Vision Group, Department of Computer Science, University of Reading.
    Berg, Amanda
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Ferryman, James
    Computational Vision Group, Department of Computer Science, University of Reading.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Effective evaluation of privacy protection techniques in visible and thermal imagery2017In: Journal of Electronic Imaging (JEI), ISSN 1017-9909, E-ISSN 1560-229X, Vol. 26, no 5, article id 051408Article in journal (Refereed)
    Abstract [en]

    Privacy protection may be defined as replacing the original content in an image region with a new (less intrusive) content having modified target appearance information to make it less recognizable by applying a privacy protection technique. Indeed the development of privacy protection techniques needs also to be complemented with an established objective evaluation method to facilitate their assessment and comparison. Generally, existing evaluation methods rely on the use of subjective judgements or assume a specific target type in image data and use target detection and recognition accuracies to assess privacy protection. This work proposes a new annotation-free evaluation method that is neither subjective nor assumes a specific target type. It assesses two key aspects of privacy protection: protection and utility. Protection is quantified as an appearance similarity and utility is measured as a structural similarity between original and privacy-protected image regions. We performed an extensive experimentation using six challenging datasets (having 12 video sequences) including a new dataset (having six sequences) that contains visible and thermal imagery. The new dataset, called TST-Priv, is made available online below for community. We demonstrate effectiveness of the proposed method by evaluating six image-based privacy protection techniques, and also show comparisons of the proposed method over existing methods.

  • 19.
    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.

  • 20.
    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).
    Five years after the Deep Learning revolution of computer vision: State of the art methods for online image and video analysis2017Report (Other academic)
    Abstract [en]

    The purpose of this document is to reect on novel and upcoming methods for computer vision that might have relevance for application in robot vision and video analytics. The document covers many dierent sub-elds of computer vision, most of which have been addressed by our research activity at the computer vision laboratory. The report has been written based on a request of, and supported by, FOI.

  • 21.
    Åström, Freddie
    et al.
    Heidelberg University, Germany.
    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).
    Baravdish, George
    Linköping University, Department of Science and Technology, Communications and Transport Systems. Linköping University, Faculty of Science & Engineering.
    Mapping-Based Image Diffusion2017In: Journal of Mathematical Imaging and Vision, ISSN 0924-9907, E-ISSN 1573-7683, Vol. 57, no 3, p. 293-323Article in journal (Refereed)
    Abstract [en]

    In this work, we introduce a novel tensor-based functional for targeted image enhancement and denoising. Via explicit regularization, our formulation incorporates application-dependent and contextual information using first principles. Few works in literature treat variational models that describe both application-dependent information and contextual knowledge of the denoising problem. We prove the existence of a minimizer and present results on tensor symmetry constraints, convexity, and geometric interpretation of the proposed functional. We show that our framework excels in applications where nonlinear functions are present such as in gamma correction and targeted value range filtering. We also study general denoising performance where we show comparable results to dedicated PDE-based state-of-the-art methods.

  • 22.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Object Tracking in Thermal Infrared Imagery based on Channel Coded Distribution Fields2017Conference paper (Other academic)
    Abstract [en]

    We address short-term, single-object tracking, a topic that is currently seeing fast progress for visual video, for the case of thermal infrared (TIR) imagery. Tracking methods designed for TIR are often subject to a number of constraints, e.g., warm objects, low spatial resolution, and static camera. As TIR cameras become less noisy and get higher resolution these constraints are less relevant, and for emerging civilian applications, e.g., surveillance and automotive safety, new tracking methods are needed. Due to the special characteristics of TIR imagery, we argue that template-based trackers based on distribution fields should have an advantage over trackers based on spatial structure features. In this paper, we propose a templatebased tracking method (ABCD) designed specifically for TIR and not being restricted by any of the constraints above. The proposed tracker is evaluated on the VOT-TIR2015 and VOT2015 datasets using the VOT evaluation toolkit and a comparison of relative ranking of all common participating trackers in the challenges is provided. Experimental results show that the ABCD tracker performs particularly well on thermal infrared sequences.

  • 23.
    Grelsson, Bertil
    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.
    Performance boost in Convolutional Neural Networks by tuning shifted activation functions2017Report (Other academic)
    Abstract [en]

    The Exponential Linear Unit (ELU) has been proven to speed up learning and improve the classification performance over activation functions such as ReLU and Leaky ReLU for convolutional neural networks. The reasons behind the improved behavior are that ELU reduces the bias shift, it saturates for large negative inputs and it is continuously differentiable. However, it remains open whether ELU has the optimal shape and we address the quest for a superior activation function.

    We use a new formulation to tune a piecewise linear activation function during training, to investigate the above question, and learn the shape of the locally optimal activation function. With this tuned activation function, the classification performance is improved and the resulting, learned activation function shows to be ELU-shaped irrespective if it is initialized as a RELU, LReLU or ELU. Interestingly, the learned activation function does not exactly pass through the origin indicating that a shifted ELU-shaped activation function is preferable. This observation leads us to introduce the Shifted Exponential Linear Unit (ShELU) as a new activation function.

    Experiments on Cifar-100 show that the classification performance is further improved when using the ShELU activation function in comparison with ELU. The improvement is achieved when learning an individual bias shift for each neuron.

  • 24.
    Robinson, Andreas
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Persson, Mikael
    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.
    Robust Accurate Extrinsic Calibration of Static Non-overlapping Cameras2017In: Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part II / [ed] Michael Felsberg, Anders Heyden and Norbert Krüger, Springer, 2017, Vol. 10425, p. 342-353Conference paper (Refereed)
    Abstract [en]

    An increasing number of robots and autonomous vehicles are equipped with multiple cameras to achieve surround-view sensing. The estimation of their relative poses, also known as extrinsic parameter calibration, is a challenging problem, particularly in the non-overlapping case. We present a simple and novel extrinsic calibration method based on standard components that performs favorably to existing approaches. We further propose a framework for predicting the performance of different calibration configurations and intuitive error metrics. This makes selecting a good camera configuration straightforward. We evaluate on rendered synthetic images and show good results as measured by angular and absolute pose differences, as well as the reprojection error distributions.

  • 25.
    Kristan, Matej
    et al.
    Univ Ljubljana, Slovenia.
    Leonardis, Ales
    Univ Birmingham, England.
    Matas, Jiri
    Czech Tech Univ, Czech Republic.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Pflugfelder, Roman
    Austrian Inst Technol, Austria.
    Zajc, Luka Cehovin
    Univ Ljubljana, Slovenia.
    Vojir, Tomas
    Czech Tech Univ, Czech Republic.
    Häger, Gustav
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Lukezic, Alan
    Univ Ljubljana, Slovenia.
    Eldesokey, Abdelrahman
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Fernandez, Gustavo
    Austrian Inst Technol, Austria.
    Garcia-Martin, Alvaro
    Univ Autonoma Madrid, Spain.
    Muhic, A.
    Univ Ljubljana, Slovenia.
    Petrosino, Alfredo
    Univ Parthenope Naples, Italy.
    Memarmoghadam, Alireza
    Univ Isfahan, Iran.
    Vedaldi, Andrea
    Univ Oxford, England.
    Manzanera, Antoine
    Univ Paris Saclay, France.
    Tran, Antoine
    Univ Paris Saclay, France.
    Alatan, Aydin
    Middle East Tech Univ, Turkey.
    Mocanu, Bogdan
    Univ Politehn Bucuresti, Romania.
    Chen, Boyu
    Dalian Univ Technol, Peoples R China.
    Huang, Chang
    Horizon Robot Inc, Peoples R China.
    Xu, Changsheng
    Chinese Acad Sci, Peoples R China.
    Sun, Chong
    Dalian Univ Technol, Peoples R China.
    Du, Dalong
    Horizon Robot Inc, Peoples R China; Univ Chinese Acad Sci, Peoples R China.
    Zhang, David
    Hong Kong Polytech Univ, Peoples R China.
    Du, Dawei
    Horizon Robot Inc, Peoples R China; Univ Chinese Acad Sci, Peoples R China.
    Mishra, Deepak
    Indian Inst Space Sci and Technol Trivandrum, India.
    Gundogdu, Erhan
    Aselsan Res Ctr, Turkey; Middle East Tech Univ, Turkey.
    Velasco-Salido, Erik
    Univ Autonoma Madrid, Spain.
    Khan, Fahad
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Battistone, Francesco
    Univ Parthenope Naples, Italy.
    Subrahmanyam, Gorthi R. K. Sai
    Indian Inst Space Sci and Technol Trivandrum, India.
    Bhat, Goutam
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Huang, Guan
    Horizon Robot Inc, Peoples R China.
    Bastos, Guilherme
    Univ Fed Itajuba, Brazil.
    Seetharaman, Guna
    Naval Res Lab, DC 20375 USA.
    Zhang, Hongliang
    Natl Univ Def Technol, Peoples R China.
    Li, Houqiang
    Univ Sci and Technol China, Peoples R China.
    Lu, Huchuan
    Dalian Univ Technol, Peoples R China.
    Drummond, Isabela
    Univ Fed Itajuba, Brazil.
    Valmadre, Jack
    Univ Oxford, England.
    Jeong, Jae-Chan
    ETRI, South Korea.
    Cho, Jae-Il
    ETRI, South Korea.
    Lee, Jae-Yeong
    ETRI, South Korea.
    Noskova, Jana
    Czech Tech Univ, Czech Republic.
    Zhu, Jianke
    Zhejiang Univ, Peoples R China.
    Gao, Jin
    Chinese Acad Sci, Peoples R China.
    Liu, Jingyu
    Chinese Acad Sci, Peoples R China.
    Kim, Ji-Wan
    ETRI, South Korea.
    Henriques, Joao F.
    Univ Oxford, England.
    Martinez, Jose M.
    Univ Autonoma Madrid, Spain.
    Zhuang, Junfei
    Beijing Univ Posts and Telecommun, Peoples R China.
    Xing, Junliang
    Chinese Acad Sci, Peoples R China.
    Gao, Junyu
    Chinese Acad Sci, Peoples R China.
    Chen, Kai
    Huazhong Univ Sci and Technol, Peoples R China.
    Palaniappan, Kannappan
    Univ Missouri Columbia, MO USA.
    Lebeda, Karel
    The Foundry, England.
    Gao, Ke
    Univ Missouri Columbia, MO USA.
    Kitani, Kris M.
    Carnegie Mellon Univ, PA 15213 USA.
    Zhang, Lei
    Hong Kong Polytech Univ, Peoples R China.
    Wang, Lijun
    Dalian Univ Technol, Peoples R China.
    Yang, Lingxiao
    Hong Kong Polytech Univ, Peoples R China.
    Wen, Longyin
    GE Global Res, NY USA.
    Bertinetto, Luca
    Univ Oxford, England.
    Poostchi, Mahdieh
    Univ Missouri Columbia, MO USA.
    Danelljan, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Mueller, Matthias
    KAUST, Saudi Arabia.
    Zhang, Mengdan
    Chinese Acad Sci, Peoples R China.
    Yang, Ming-Hsuan
    Univ Calif Merced, CA USA.
    Xie, Nianhao
    Natl Univ Def Technol, Peoples R China.
    Wang, Ning
    Univ Sci and Technol China, Peoples R China.
    Miksik, Ondrej
    Univ Oxford, England.
    Moallem, P.
    Univ Isfahan, Iran.
    Venugopal, Pallavi M.
    Indian Inst Space Sci and Technol Trivandrum, India.
    Senna, Pedro
    Univ Fed Itajuba, Brazil.
    Torr, Philip H. S.
    Univ Oxford, England.
    Wang, Qiang
    Chinese Acad Sci, Peoples R China.
    Yu, Qifeng
    Natl Univ Def Technol, Peoples R China.
    Huang, Qingming
    Univ Chinese Acad Sci, Peoples R China.
    Martin-Nieto, Rafael
    Univ Autonoma Madrid, Spain.
    Bowden, Richard
    Univ Surrey, England.
    Liu, Risheng
    Dalian Univ Technol, Peoples R China.
    Tapu, Ruxandra
    Univ Politehn Bucuresti, Romania.
    Hadfield, Simon
    Univ Surrey, England.
    Lyu, Siwei
    SUNY Albany, NY 12222 USA.
    Golodetz, Stuart
    Univ Oxford, England.
    Choi, Sunglok
    ETRI, South Korea.
    Zhang, Tianzhu
    Chinese Acad Sci, Peoples R China.
    Zaharia, Titus
    Inst. Mines-Telecom/ TelecomSudParis, France.
    Santopietro, Vincenzo
    Univ Parthenope Naples, Italy.
    Zou, Wei
    Chinese Acad Sci, Peoples R China.
    Hu, Weiming
    Chinese Acad Sci, Peoples R China.
    Tao, Wenbing
    Huazhong Univ Sci and Technol, Peoples R China.
    Li, Wenbo
    SUNY Albany, NY 12222 USA.
    Zhou, Wengang
    Univ Sci and Technol China, Peoples R China.
    Yu, Xianguo
    Natl Univ Def Technol, Peoples R China.
    Bian, Xiao
    GE Global Res, NY USA.
    Li, Yang
    Zhejiang Univ, Peoples R China.
    Xing, Yifan
    Carnegie Mellon Univ, PA 15213 USA.
    Fan, Yingruo
    Beijing Univ Posts and Telecommun, Peoples R China.
    Zhu, Zheng
    Chinese Acad Sci, Peoples R China; Univ Chinese Acad Sci, Peoples R China.
    Zhang, Zhipeng
    Chinese Acad Sci, Peoples R China.
    He, Zhiqun
    Beijing Univ Posts and Telecommun, Peoples R China.
    The Visual Object Tracking VOT2017 challenge results2017In: 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), IEEE , 2017, p. 1949-1972Conference paper (Refereed)
    Abstract [en]

    The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art published at major computer vision conferences or journals in recent years. The evaluation included the standard VOT and other popular methodologies and a new "real-time" experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The VOT2017 goes beyond its predecessors by (i) improving the VOT public dataset and introducing a separate VOT2017 sequestered dataset, (ii) introducing a realtime tracking experiment and (iii) releasing a redesigned toolkit that supports complex experiments. The dataset, the evaluation kit and the results are publicly available at the challenge website(1).

  • 26.
    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.

  • 27.
    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.

  • 28.
    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.

  • 29.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    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.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    An Overview of the Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge2016Conference paper (Other academic)
    Abstract [en]

    The Thermal Infrared Visual Object Tracking (VOT-TIR2015) Challenge was organized in conjunction with ICCV2015. It was the first benchmark on short-term,single-target tracking in thermal infrared (TIR) sequences. The challenge aimed at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. It was based on the VOT2013 Challenge, but introduced the following novelties: (i) the utilization of the LTIR (Linköping TIR) dataset, (ii) adaption of the VOT2013 attributes to thermal data, (iii) a similar evaluation to that of VOT2015. This paper provides an overview of the VOT-TIR2015 Challenge as well as the results of the 24 participating trackers.

  • 30.
    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.

  • 31.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, Faculty of Science & Engineering.
    Channel Coded Distribution Field Tracking for Thermal Infrared Imagery2016In: PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016), IEEE , 2016, p. 1248-1256Conference paper (Refereed)
    Abstract [en]

    We address short-term, single-object tracking, a topic that is currently seeing fast progress for visual video, for the case of thermal infrared (TIR) imagery. The fast progress has been possible thanks to the development of new template-based tracking methods with online template updates, methods which have not been explored for TIR tracking. Instead, tracking methods used for TIR are often subject to a number of constraints, e.g., warm objects, low spatial resolution, and static camera. As TIR cameras become less noisy and get higher resolution these constraints are less relevant, and for emerging civilian applications, e.g., surveillance and automotive safety, new tracking methods are needed. Due to the special characteristics of TIR imagery, we argue that template-based trackers based on distribution fields should have an advantage over trackers based on spatial structure features. In this paper, we propose a template-based tracking method (ABCD) designed specifically for TIR and not being restricted by any of the constraints above. In order to avoid background contamination of the object template, we propose to exploit background information for the online template update and to adaptively select the object region used for tracking. Moreover, we propose a novel method for estimating object scale change. The proposed tracker is evaluated on the VOT-TIR2015 and VOT2015 datasets using the VOT evaluation toolkit and a comparison of relative ranking of all common participating trackers in the challenges is provided. Further, the proposed tracker, ABCD, and the VOT-TIR2015 winner SRDCFir are evaluated on maritime data. Experimental results show that the ABCD tracker performs particularly well on thermal infrared sequences.

  • 32.
    Häger, Gustav
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Bhat, Goutam
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Danelljan, Martin
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Khan, Fahad Shahbaz
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Felsberg, Michael
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Rudol, Piotr
    Linköping University, The Institute of Technology.
    Doherty, Patrick
    Linköping University, The Institute of Technology.
    Combining Visual Tracking and Person Detection for Long Term Tracking on a UAV2016In: Proceedings of the 12th International Symposium on Advances in Visual Computing, 2016Conference paper (Refereed)
    Abstract [en]

    Visual object tracking performance has improved significantly in recent years. Most trackers are based on either of two paradigms: online learning of an appearance model or the use of a pre-trained object detector. Methods based on online learning provide high accuracy, but are prone to model drift. The model drift occurs when the tracker fails to correctly estimate the tracked object’s position. Methods based on a detector on the other hand typically have good long-term robustness, but reduced accuracy compared to online methods.

    Despite the complementarity of the aforementioned approaches, the problem of fusing them into a single framework is largely unexplored. In this paper, we propose a novel fusion between an online tracker and a pre-trained detector for tracking humans from a UAV. The system operates at real-time on a UAV platform. In addition we present a novel dataset for long-term tracking in a UAV setting, that includes scenarios that are typically not well represented in standard visual tracking datasets.

  • 33.
    Gladh, Susanna
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Danelljan, Martin
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Khan, Fahad Shahbaz
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Felsberg, Michael
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Deep motion features for visual tracking2016In: Proceedings of the 23rd International Conference on, Pattern Recognition (ICPR), 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, p. 1243-1248Conference paper (Refereed)
    Abstract [en]

    Robust visual tracking is a challenging computer vision problem, with many real-world applications. Most existing approaches employ hand-crafted appearance features, such as HOG or Color Names. Recently, deep RGB features extracted from convolutional neural networks have been successfully applied for tracking. Despite their success, these features only capture appearance information. On the other hand, motion cues provide 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. This paper presents an investigation of the impact of deep motion features in a tracking-by-detection framework. We further show that hand-crafted, deep RGB, and deep motion features 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 suggest that our fusion approach with deep motion features outperforms standard methods relying on appearance information alone.

  • 34.
    Bianco, Giuseppe
    et al.
    Lund University, Sweden.
    Ilieva, Mihaela
    Lund University, Sweden; Bulgarian Academic Science, Bulgaria.
    Veibäck, Clas
    Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Faculty of Science & Engineering.
    Öfjäll, Kristoffer
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Gadomska, Alicja
    Lund University, Sweden.
    Hendeby, Gustaf
    Linköping University, Department of Electrical Engineering, Automatic Control. 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).
    Gustafsson, Fredrik
    Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Faculty of Science & Engineering.
    Åkesson, Susanne
    Lund University, Sweden.
    Emlen funnel experiments revisited: methods update for studying compass orientation in songbirds2016In: Ecology and Evolution, ISSN 2045-7758, E-ISSN 2045-7758, Vol. 6, no 19, p. 6930-6942Article in journal (Refereed)
    Abstract [en]

    1 Migratory songbirds carry an inherited capacity to migrate several thousand kilometers each year crossing continental landmasses and barriers between distant breeding sites and wintering areas. How individual songbirds manage with extreme precision to find their way is still largely unknown. The functional characteristics of biological compasses used by songbird migrants has mainly been investigated by recording the birds directed migratory activity in circular cages, so-called Emlen funnels. This method is 50 years old and has not received major updates over the past decades. The aim of this work was to compare the results from newly developed digital methods with the established manual methods to evaluate songbird migratory activity and orientation in circular cages. 2 We performed orientation experiments using the European robin (Erithacus rubecula) using modified Emlen funnels equipped with thermal paper and simultaneously recorded the songbird movements from above. We evaluated and compared the results obtained with five different methods. Two methods have been commonly used in songbirds orientation experiments; the other three methods were developed for this study and were based either on evaluation of the thermal paper using automated image analysis, or on the analysis of videos recorded during the experiment. 3 The methods used to evaluate scratches produced by the claws of birds on the thermal papers presented some differences compared with the video analyses. These differences were caused mainly by differences in scatter, as any movement of the bird along the sloping walls of the funnel was recorded on the thermal paper, whereas video evaluations allowed us to detect single takeoff attempts by the birds and to consider only this behavior in the orientation analyses. Using computer vision, we were also able to identify and separately evaluate different behaviors that were impossible to record by the thermal paper. 4 The traditional Emlen funnel is still the most used method to investigate compass orientation in songbirds under controlled conditions. However, new numerical image analysis techniques provide a much higher level of detail of songbirds migratory behavior and will provide an increasing number of possibilities to evaluate and quantify specific behaviors as new algorithms will be developed.

  • 35.
    Berg, Amanda
    et al.
    Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision. Termisk Syst Tekn AB, Diskettgatan 11 B, SE-58335 Linkoping, Sweden.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Syst Tekn AB, Diskettgatan 11 B, SE-58335 Linkoping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Enhanced analysis of thermographic images for monitoring of district heat pipe networks2016In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 83, no 2, p. 215-223Article in journal (Refereed)
    Abstract [en]

    We address two problems related to large-scale aerial monitoring of district heating networks. First, we propose a classification scheme to reduce the number of false alarms among automatically detected leakages in district heating networks. The leakages are detected in images captured by an airborne thermal camera, and each detection corresponds to an image region with abnormally high temperature. This approach yields a significant number of false positives, and we propose to reduce this number in two steps; by (a) using a building segmentation scheme in order to remove detections on buildings, and (b) to use a machine learning approach to classify the remaining detections as true or false leakages. We provide extensive experimental analysis on real-world data, showing that this post-processing step significantly improves the usefulness of the system. Second, we propose a method for characterization of leakages over time, i.e., repeating the image acquisition one or a few years later and indicate areas that suffer from an increased energy loss. We address the problem of finding trends in the degradation of pipe networks in order to plan for long-term maintenance, and propose a visualization scheme exploiting the consecutive data collections.

  • 36.
    Grelsson, Bertil
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology. Saab Dynamics, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Isaksson, Folke
    Vricon Systems, Saab, Linköping, Sweden.
    Highly Accurate Attitude Estimation via Horizon Detection2016In: Journal of Field Robotics, ISSN 1556-4959, E-ISSN 1556-4967, Vol. 33, no 7, p. 967-993Article in journal (Refereed)
    Abstract [en]

    Attitude (pitch and roll angle) estimation from visual information is necessary for GPS-free navigation of airborne vehicles. We propose a highly accurate method to estimate the attitude by horizon detection in fisheye images. A Canny edge detector and a probabilistic Hough voting scheme are used to compute an approximate attitude and the corresponding horizon line in the image. Horizon edge pixels are extracted in a band close to the approximate horizon line. The attitude estimates are refined through registration of the extracted edge pixels with the geometrical horizon from a digital elevation map (DEM), in our case the SRTM3 database, extracted at a given approximate position. The proposed method has been evaluated using 1629 images from a flight trial with flight altitudes up to 600 m in an area with ground elevations ranging from sea level up to 500 m. Compared with the ground truth from a filtered inertial measurement unit (IMU)/GPS solution, the standard deviation for the pitch and roll angle errors obtained with 30 Mpixel images are 0.04° and 0.05°, respectively, with mean errors smaller than 0.02°. To achieve the high-accuracy attitude estimates, the ray refraction in the earth's atmosphere has been taken into account. The attitude errors obtained on real images are less or equal to those achieved on synthetic images for previous methods with DEM refinement, and the errors are about one order of magnitude smaller than for any previous vision-based method without DEM refinement.

  • 37.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Kristan, Matej
    University of Ljubljana, Slovenia.
    Matas, Jiri
    Czech Technical University, Czech Republic.
    Leonardis, Ales
    University of Birmingham, England.
    Pflugfelder, Roman
    Austrian Institute Technology, Austria.
    Häger, Gustav
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Berg, Amanda
    Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision. Termisk Syst Tekn AB, Linkoping, Sweden.
    Eldesokey, Abdelrahman
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Syst Tekn AB, Linkoping, Sweden.
    Cehovin, Luka
    University of Ljubljana, Slovenia.
    Vojir, Tomas
    Czech Technical University, Czech Republic.
    Lukezic, Alan
    University of Ljubljana, Slovenia.
    Fernandez, Gustavo
    Austrian Institute Technology, Austria.
    Petrosino, Alfredo
    Parthenope University of Naples, Italy.
    Garcia-Martin, Alvaro
    University of Autonoma Madrid, Spain.
    Solis Montero, Andres
    University of Ottawa, Canada.
    Varfolomieiev, Anton
    Kyiv Polytech Institute, Ukraine.
    Erdem, Aykut
    Hacettepe University, Turkey.
    Han, Bohyung
    POSTECH, South Korea.
    Chang, Chang-Ming
    University of Albany, GA USA.
    Du, Dawei
    Australian National University, Australia; Chinese Academic Science, Peoples R China.
    Erdem, Erkut
    Hacettepe University, Turkey.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Porikli, Fatih
    ARC Centre Excellence Robot Vis, Australia; CSIRO, Australia.
    Zhao, Fei
    Australian National University, Australia; Chinese Academic Science, Peoples R China.
    Bunyak, Filiz
    University of Missouri, MO 65211 USA.
    Battistone, Francesco
    Parthenope University of Naples, Italy.
    Zhu, Gao
    University of Missouri, Columbia, USA.
    Seetharaman, Guna
    US Navy, DC 20375 USA.
    Li, Hongdong
    ARC Centre Excellence Robot Vis, Australia.
    Qi, Honggang
    Australian National University, Australia; Chinese Academic Science, Peoples R China.
    Bischof, Horst
    Graz University of Technology, Austria.
    Possegger, Horst
    Graz University of Technology, Austria.
    Nam, Hyeonseob
    NAVER Corp, South Korea.
    Valmadre, Jack
    University of Oxford, England.
    Zhu, Jianke
    Zhejiang University, Peoples R China.
    Feng, Jiayi
    Australian National University, Australia; Chinese Academic Science, Peoples R China.
    Lang, Jochen
    University of Ottawa, Canada.
    Martinez, Jose M.
    University of Autonoma Madrid, Spain.
    Palaniappan, Kannappan
    University of Missouri, MO 65211 USA.
    Lebeda, Karel
    University of Surrey, England.
    Gao, Ke
    University of Missouri, MO 65211 USA.
    Mikolajczyk, Krystian
    Imperial Coll London, England.
    Wen, Longyin
    University of Albany, GA USA.
    Bertinetto, Luca
    University of Oxford, England.
    Poostchi, Mahdieh
    University of Missouri, MO 65211 USA.
    Maresca, Mario
    Parthenope University of Naples, Italy.
    Danelljan, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Arens, Michael
    Fraunhofer IOSB, Germany.
    Tang, Ming
    Australian National University, Australia; Chinese Academic Science, Peoples R China.
    Baek, Mooyeol
    POSTECH, South Korea.
    Fan, Nana
    Harbin Institute Technology, Peoples R China.
    Al-Shakarji, Noor
    University of Missouri, MO 65211 USA.
    Miksik, Ondrej
    University of Oxford, England.
    Akin, Osman
    Hacettepe University, Turkey.
    Torr, Philip H. S.
    University of Oxford, England.
    Huang, Qingming
    Australian National University, Australia; Chinese Academic Science, Peoples R China.
    Martin-Nieto, Rafael
    University of Autonoma Madrid, Spain.
    Pelapur, Rengarajan
    University of Missouri, MO 65211 USA.
    Bowden, Richard
    University of Surrey, England.
    Laganiere, Robert
    University of Ottawa, Canada.
    Krah, Sebastian B.
    Fraunhofer IOSB, Germany.
    Li, Shengkun
    University of Albany, GA USA.
    Yao, Shizeng
    University of Missouri, MO 65211 USA.
    Hadfield, Simon
    University of Surrey, England.
    Lyu, Siwei
    University of Albany, GA USA.
    Becker, Stefan
    Fraunhofer IOSB, Germany.
    Golodetz, Stuart
    University of Oxford, England.
    Hu, Tao
    Australian National University, Australia; Chinese Academic Science, Peoples R China.
    Mauthner, Thomas
    Graz University of Technology, Austria.
    Santopietro, Vincenzo
    Parthenope University of Naples, Italy.
    Li, Wenbo
    Lehigh University, PA 18015 USA.
    Huebner, Wolfgang
    Fraunhofer IOSB, Germany.
    Li, Xin
    Harbin Institute Technology, Peoples R China.
    Li, Yang
    Zhejiang University, Peoples R China.
    Xu, Zhan
    Zhejiang University, Peoples R China.
    He, Zhenyu
    Harbin Institute Technology, Peoples R China.
    The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results2016In: Computer Vision – ECCV 2016 Workshops. ECCV 2016. / [ed] Hua G., Jégou H., SPRINGER INT PUBLISHING AG , 2016, p. 824-849Conference paper (Refereed)
    Abstract [en]

    The Thermal Infrared Visual Object Tracking challenge 2016, VOT-TIR2016, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2016 is the second benchmark on short-term tracking in TIR sequences. Results of 24 trackers are presented. For each participating tracker, a short description is provided in the appendix. The VOT-TIR2016 challenge is similar to the 2015 challenge, the main difference is the introduction of new, more difficult sequences into the dataset. Furthermore, VOT-TIR2016 evaluation adopted the improvements regarding overlap calculation in VOT2016. Compared to VOT-TIR2015, a significant general improvement of results has been observed, which partly compensate for the more difficult sequences. The dataset, the evaluation kit, as well as the results are publicly available at the challenge website.

  • 38.
    Kristan, Matej
    et al.
    University of Ljubljana, Slovenia.
    Leonardis, Ales
    University of Birmingham, England.
    Matas, Jiri
    Czech Technical University, Czech Republic.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Pflugfelder, Roman
    Austrian Institute Technology, Austria.
    Cehovin, Luka
    University of Ljubljana, Slovenia.
    Vojir, Tomas
    Czech Technical University, Czech Republic.
    Häger, Gustav
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Lukezic, Alan
    University of Ljubljana, Slovenia.
    Fernandez, Gustavo
    Austrian Institute Technology, Austria.
    Gupta, Abhinav
    Carnegie Mellon University, PA 15213 USA.
    Petrosino, Alfredo
    Parthenope University of Naples, Italy.
    Memarmoghadam, Alireza
    University of Isfahan, Iran.
    Garcia-Martin, Alvaro
    University of Autonoma Madrid, Spain.
    Solis Montero, Andres
    University of Ottawa, Canada.
    Vedaldi, Andrea
    University of Oxford, England.
    Robinson, Andreas
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Ma, Andy J.
    Hong Kong Baptist University, Peoples R China.
    Varfolomieiev, Anton
    Kyiv Polytech Institute, Ukraine.
    Alatan, Aydin
    Middle East Technical University, Çankaya, Turkey.
    Erdem, Aykut
    Hacettepe University, Turkey.
    Ghanem, Bernard
    KAUST, Saudi Arabia.
    Liu, Bin
    Moshanghua Technology Co, Peoples R China.
    Han, Bohyung
    POSTECH, South Korea.
    Martinez, Brais
    University of Nottingham, England.
    Chang, Chang-Ming
    University of Albany, GA USA.
    Xu, Changsheng
    Chinese Academic Science, Peoples R China.
    Sun, Chong
    Dalian University of Technology, Peoples R China.
    Kim, Daijin
    POSTECH, South Korea.
    Chen, Dapeng
    Xi An Jiao Tong University, Peoples R China.
    Du, Dawei
    University of Chinese Academic Science, Peoples R China.
    Mishra, Deepak
    Indian Institute Space Science and Technology, India.
    Yeung, Dit-Yan
    Hong Kong University of Science and Technology, Peoples R China.
    Gundogdu, Erhan
    Aselsan Research Centre, Turkey.
    Erdem, Erkut
    Hacettepe University, Turkey.
    Khan, Fahad
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Porikli, Fatih
    ARC Centre Excellence Robot Vis, Australia; Australian National University, Australia; CSIRO, Australia.
    Zhao, Fei
    Chinese Academic Science, Peoples R China.
    Bunyak, Filiz
    University of Missouri, MO 65211 USA.
    Battistone, Francesco
    Parthenope University of Naples, Italy.
    Zhu, Gao
    Australian National University, Australia.
    Roffo, Giorgio
    University of Verona, Italy.
    Sai Subrahmanyam, Gorthi R. K.
    Indian Institute Space Science and Technology, India.
    Bastos, Guilherme
    University of Federal Itajuba, Brazil.
    Seetharaman, Guna
    US Navy, DC 20375 USA.
    Medeiros, Henry
    Marquette University, WI 53233 USA.
    Li, Hongdong
    ARC Centre Excellence Robot Vis, Australia; Australian National University, Australia.
    Qi, Honggang
    University of Chinese Academic Science, Peoples R China.
    Bischof, Horst
    Graz University of Technology, Austria.
    Possegger, Horst
    Graz University of Technology, Austria.
    Lu, Huchuan
    Dalian University of Technology, Peoples R China.
    Lee, Hyemin
    POSTECH, South Korea.
    Nam, Hyeonseob
    NAVER Corp, South Korea.
    Jin Chang, Hyung
    Imperial Coll London, England.
    Drummond, Isabela
    University of Federal Itajuba, Brazil.
    Valmadre, Jack
    University of Oxford, England.
    Jeong, Jae-chan
    ASRI, South Korea; Elect and Telecommun Research Institute, South Korea.
    Cho, Jae-il
    Elect and Telecommun Research Institute, South Korea.
    Lee, Jae-Yeong
    Elect and Telecommun Research Institute, South Korea.
    Zhu, Jianke
    Zhejiang University, Peoples R China.
    Feng, Jiayi
    Chinese Academic Science, Peoples R China.
    Gao, Jin
    Chinese Academic Science, Peoples R China.
    Young Choi, Jin
    ASRI, South Korea.
    Xiao, Jingjing
    University of Birmingham, England.
    Kim, Ji-Wan
    Elect and Telecommun Research Institute, South Korea.
    Jeong, Jiyeoup
    ASRI, South Korea; Elect and Telecommun Research Institute, South Korea.
    Henriques, Joao F.
    University of Oxford, England.
    Lang, Jochen
    University of Ottawa, Canada.
    Choi, Jongwon
    ASRI, South Korea.
    Martinez, Jose M.
    University of Autonoma Madrid, Spain.
    Xing, Junliang
    Chinese Academic Science, Peoples R China.
    Gao, Junyu
    Chinese Academic Science, Peoples R China.
    Palaniappan, Kannappan
    University of Missouri, MO 65211 USA.
    Lebeda, Karel
    University of Surrey, England.
    Gao, Ke
    University of Missouri, MO 65211 USA.
    Mikolajczyk, Krystian
    Imperial Coll London, England.
    Qin, Lei
    Chinese Academic Science, Peoples R China.
    Wang, Lijun
    Dalian University of Technology, Peoples R China.
    Wen, Longyin
    University of Albany, GA USA.
    Bertinetto, Luca
    University of Oxford, England.
    Kumar Rapuru, Madan
    Indian Institute Space Science and Technology, India.
    Poostchi, Mahdieh
    University of Missouri, MO 65211 USA.
    Maresca, Mario
    Parthenope University of Naples, Italy.
    Danelljan, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Mueller, Matthias
    KAUST, Saudi Arabia.
    Zhang, Mengdan
    Chinese Academic Science, Peoples R China.
    Arens, Michael
    Fraunhofer IOSB, Germany.
    Valstar, Michel
    University of Nottingham, England.
    Tang, Ming
    Chinese Academic Science, Peoples R China.
    Baek, Mooyeol
    POSTECH, South Korea.
    Haris Khan, Muhammad
    University of Nottingham, England.
    Wang, Naiyan
    Hong Kong University of Science and Technology, Peoples R China.
    Fan, Nana
    Harbin Institute Technology, Peoples R China.
    Al-Shakarji, Noor
    University of Missouri, MO 65211 USA.
    Miksik, Ondrej
    University of Oxford, England.
    Akin, Osman
    Hacettepe University, Turkey.
    Moallem, Payman
    University of Isfahan, Iran.
    Senna, Pedro
    University of Federal Itajuba, Brazil.
    Torr, Philip H. S.
    University of Oxford, England.
    Yuen, Pong C.
    Hong Kong Baptist University, Peoples R China.
    Huang, Qingming
    Harbin Institute Technology, Peoples R China; University of Chinese Academic Science, Peoples R China.
    Martin-Nieto, Rafael
    University of Autonoma Madrid, Spain.
    Pelapur, Rengarajan
    University of Missouri, MO 65211 USA.
    Bowden, Richard
    University of Surrey, England.
    Laganiere, Robert
    University of Ottawa, Canada.
    Stolkin, Rustam
    University of Birmingham, England.
    Walsh, Ryan
    Marquette University, WI 53233 USA.
    Krah, Sebastian B.
    Fraunhofer IOSB, Germany.
    Li, Shengkun
    Hong Kong University of Science and Technology, Peoples R China; University of Albany, GA USA.
    Zhang, Shengping
    Harbin Institute Technology, Peoples R China.
    Yao, Shizeng
    University of Missouri, MO 65211 USA.
    Hadfield, Simon
    University of Surrey, England.
    Melzi, Simone
    University of Verona, Italy.
    Lyu, Siwei
    University of Albany, GA USA.
    Li, Siyi
    Hong Kong University of Science and Technology, Peoples R China; University of Albany, GA USA.
    Becker, Stefan
    Fraunhofer IOSB, Germany.
    Golodetz, Stuart
    University of Oxford, England.
    Kakanuru, Sumithra
    Indian Institute Space Science and Technology, India.
    Choi, Sunglok
    Elect and Telecommun Research Institute, South Korea.
    Hu, Tao
    University of Chinese Academic Science, Peoples R China.
    Mauthner, Thomas
    Graz University of Technology, Austria.
    Zhang, Tianzhu
    Chinese Academic Science, Peoples R China.
    Pridmore, Tony
    University of Nottingham, England.
    Santopietro, Vincenzo
    Parthenope University of Naples, Italy.
    Hu, Weiming
    Chinese Academic Science, Peoples R China.
    Li, Wenbo
    Lehigh University, PA 18015 USA.
    Huebner, Wolfgang
    Fraunhofer IOSB, Germany.
    Lan, Xiangyuan
    Hong Kong Baptist University, Peoples R China.
    Wang, Xiaomeng
    University of Nottingham, England.
    Li, Xin
    Harbin Institute Technology, Peoples R China.
    Li, Yang
    Zhejiang University, Peoples R China.
    Demiris, Yiannis
    Imperial Coll London, England.
    Wang, Yifan
    Dalian University of Technology, Peoples R China.
    Qi, Yuankai
    Harbin Institute Technology, Peoples R China.
    Yuan, Zejian
    Xi An Jiao Tong University, Peoples R China.
    Cai, Zexiong
    Hong Kong Baptist University, Peoples R China.
    Xu, Zhan
    Zhejiang University, Peoples R China.
    He, Zhenyu
    Harbin Institute Technology, Peoples R China.
    Chi, Zhizhen
    Dalian University of Technology, Peoples R China.
    The Visual Object Tracking VOT2016 Challenge Results2016In: COMPUTER VISION - ECCV 2016 WORKSHOPS, PT II, SPRINGER INT PUBLISHING AG , 2016, Vol. 9914, p. 777-823Conference paper (Refereed)
    Abstract [en]

    The Visual Object Tracking challenge VOT2016 aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 70 trackers are presented, with a large number of trackers being published at major computer vision conferences and journals in the recent years. The number of tested state-of-the-art trackers makes the VOT 2016 the largest and most challenging benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the Appendix. The VOT2016 goes beyond its predecessors by (i) introducing a new semi-automatic ground truth bounding box annotation methodology and (ii) extending the evaluation system with the no-reset experiment.

  • 39.
    Öfjäll, Kristoffer
    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. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Robinson, Andreas
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Visual Autonomous Road Following by Symbiotic Online Learning2016In: Intelligent Vehicles Symposium (IV), 2016 IEEE, 2016, p. 136-143Conference paper (Refereed)
    Abstract [en]

    Recent years have shown great progress in driving assistance systems, approaching autonomous driving step by step. Many approaches rely on lane markers however, which limits the system to larger paved roads and poses problems during winter. In this work we explore an alternative approach to visual road following based on online learning. The system learns the current visual appearance of the road while the vehicle is operated by a human. When driving onto a new type of road, the human driver will drive for a minute while the system learns. After training, the human driver can let go of the controls. The present work proposes a novel approach to online perception-action learning for the specific problem of road following, which makes interchangeably use of supervised learning (by demonstration), instantaneous reinforcement learning, and unsupervised learning (self-reinforcement learning). The proposed method, symbiotic online learning of associations and regression (SOLAR), extends previous work on qHebb-learning in three ways: priors are introduced to enforce mode selection and to drive learning towards particular goals, the qHebb-learning methods is complemented with a reinforcement variant, and a self-assessment method based on predictive coding is proposed. The SOLAR algorithm is compared to qHebb-learning and deep learning for the task of road following, implemented on a model RC-car. The system demonstrates an ability to learn to follow paved and gravel roads outdoors. Further, the system is evaluated in a controlled indoor environment which provides quantifiable results. The experiments show that the SOLAR algorithm results in autonomous capabilities that go beyond those of existing methods with respect to speed, accuracy, and functionality. 

  • 40.
    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

  • 41.
    Åström, Freddie
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Baravdish, George
    Linköping University, Department of Science and Technology, Communications and Transport Systems. Linköping University, The Institute of Technology.
    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).
    A Tensor Variational Formulation of Gradient Energy Total Variation2015In: ENERGY MINIMIZATION METHODS IN COMPUTER VISION AND PATTERN RECOGNITION, EMMCVPR 2015, Springer Berlin/Heidelberg, 2015, Vol. 8932, p. 307-320Conference paper (Refereed)
    Abstract [en]

    We present a novel variational approach to a tensor-based total variation formulation which is called gradient energy total variation, GETV. We introduce the gradient energy tensor into the GETV and show that the corresponding Euler-Lagrange (E-L) equation is a tensor-based partial differential equation of total variation type. Furthermore, we give a proof which shows that GETV is a convex functional. This approach, in contrast to the commonly used structure tensor, enables a formal derivation of the corresponding E-L equation. Experimental results suggest that GETV compares favourably to other state of the art variational denoising methods such as extended anisotropic diffusion (EAD) and total variation (TV) for gray-scale and colour images.

  • 42.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    A thermal infrared dataset for evaluation of short-term tracking methods2015Conference paper (Other academic)
    Abstract [en]

    During recent years, thermal cameras have decreased in both size and cost while improving image quality. The area of use for such cameras has expanded with many exciting applications, many of which require tracking of objects. While being subject to extensive research in the visual domain, tracking in thermal imagery has historically been of interest mainly for military purposes. The available thermal infrared datasets for evaluating methods addressing these problems are few and the ones that do are not challenging enough for today’s tracking algorithms. Therefore, we hereby propose a thermal infrared dataset for evaluation of short-term tracking methods. The dataset consists of 20 sequences which have been collected from multiple sources and the data format used is in accordance with the Visual Object Tracking (VOT) Challenge.

  • 43.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    A Thermal Object Tracking Benchmark2015Conference paper (Refereed)
    Abstract [en]

    Short-term single-object (STSO) tracking in thermal images is a challenging problem relevant in a growing number of applications. In order to evaluate STSO tracking algorithms on visual imagery, there are de facto standard benchmarks. However, we argue that tracking in thermal imagery is different than in visual imagery, and that a separate benchmark is needed. The available thermal infrared datasets are few and the existing ones are not challenging for modern tracking algorithms. Therefore, we hereby propose a thermal infrared benchmark according to the Visual Object Tracking (VOT) protocol for evaluation of STSO tracking methods. The benchmark includes the new LTIR dataset containing 20 thermal image sequences which have been collected from multiple sources and annotated in the format used in the VOT Challenge. In addition, we show that the ranking of different tracking principles differ between the visual and thermal benchmarks, confirming the need for the new benchmark.

  • 44.
    Åström, Freddie
    et al.
    Heidelberg Collaboratory for Image Processing Heidelberg University Heidelberg, Germany.
    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).
    Scharr, Hanno
    BG-2: Plant Sciences Forschungszentrum Jülich 52425, Jülich, Germany.
    Adaptive sharpening of multimodal distributions2015In: Colour and Visual Computing Symposium (CVCS), 2015 / [ed] Marius Pedersen and Jean-Baptiste Thomas, IEEE , 2015Conference paper (Refereed)
    Abstract [en]

    In this work we derive a novel framework rendering measured distributions into approximated distributions of their mean. This is achieved by exploiting constraints imposed by the Gauss-Markov theorem from estimation theory, being valid for mono-modal Gaussian distributions. It formulates the relation between the variance of measured samples and the so-called standard error, being the standard deviation of their mean. However, multi-modal distributions are present in numerous image processing scenarios, e.g. local gray value or color distributions at object edges, or orientation or displacement distributions at occlusion boundaries in motion estimation or stereo. Our method not only aims at estimating the modes of these distributions together with their standard error, but at describing the whole multi-modal distribution. We utilize the method of channel representation, a kind of soft histogram also known as population codes, to represent distributions in a non-parametric, generic fashion. Here we apply the proposed scheme to general mono- and multimodal Gaussian distributions to illustrate its effectiveness and compliance with the Gauss-Markov theorem.

  • 45.
    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.

  • 46.
    Khan, Fahad Shahbaz
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Muhammad Anwer, Rao
    Department of Information and Computer Science, Aalto University School of Science, Finland.
    van de Weijer, Joost
    Computer Vision Center, CS Dept. Universitat Autonoma de Barcelona, Spain.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, The Institute of Technology.
    Laaksonen, Jorma
    Department of Information and Computer Science, Aalto University School of Science, Finland.
    Compact color–texture description for texture classification2015In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 51, p. 16-22Article in journal (Refereed)
    Abstract [en]

    Describing textures is a challenging problem in computer vision and pattern recognition. The classification problem involves assigning a category label to the texture class it belongs to. Several factors such as variations in scale, illumination and viewpoint make the problem of texture description extremely challenging. A variety of histogram based texture representations exists in literature. However, combining multiple texture descriptors and assessing their complementarity is still an open research problem. In this paper, we first show that combining multiple local texture descriptors significantly improves the recognition performance compared to using a single best method alone. This gain in performance is achieved at the cost of high-dimensional final image representation. To counter this problem, we propose to use an information-theoretic compression technique to obtain a compact texture description without any significant loss in accuracy. In addition, we perform a comprehensive evaluation of pure color descriptors, popular in object recognition, for the problem of texture classification. Experiments are performed on four challenging texture datasets namely, KTH-TIPS-2a, KTH-TIPS-2b, FMD and Texture-10. The experiments clearly demonstrate that our proposed compact multi-texture approach outperforms the single best texture method alone. In all cases, discriminative color names outperforms other color features for texture classification. Finally, we show that combining discriminative color names with compact texture representation outperforms state-of-the-art methods by 7.8%,4.3%7.8%,4.3% and 5.0%5.0% on KTH-TIPS-2a, KTH-TIPS-2b and Texture-10 datasets respectively.

  • 47.
    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.

  • 48.
    Khan, Fahad Shahbaz
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Rao, Muhammad Anwer
    Department of Information and Computer Science, Aalto University School of Science, Aalto, Finland.
    van de Weijer, Joost
    Computer Vision Center, CS Department, Universitet Autonoma de Barcelona, Barcelona, Spain.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Laaksonen, Jorma
    Department of Information and Computer Science, Aalto University School of Science, Aalto, Finland.
    Deep Semantic Pyramids for Human Attributes and Action Recognition2015In: Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings / [ed] Paulsen, Rasmus R., Pedersen, Kim S., Springer, 2015, Vol. 9127, p. 341-353Conference paper (Refereed)
    Abstract [en]

    Describing persons and their actions is a challenging problem due to variations in pose, scale and viewpoint in real-world images. Recently, semantic pyramids approach [1] for pose normalization has shown to provide excellent results for gender and action recognition. The performance of semantic pyramids approach relies on robust image description and is therefore limited due to the use of shallow local features. In the context of object recognition [2] and object detection [3], convolutional neural networks (CNNs) or deep features have shown to improve the performance over the conventional shallow features.

    We propose deep semantic pyramids for human attributes and action recognition. The method works by constructing spatial pyramids based on CNNs of different part locations. These pyramids are then combined to obtain a single semantic representation. We validate our approach on the Berkeley and 27 Human Attributes datasets for attributes classification. For action recognition, we perform experiments on two challenging datasets: Willow and PASCAL VOC 2010. The proposed deep semantic pyramids provide a significant gain of 17.2%, 13.9%, 24.3% and 22.6% compared to the standard shallow semantic pyramids on Berkeley, 27 Human Attributes, Willow and PASCAL VOC 2010 datasets respectively. Our results also show that deep semantic pyramids outperform conventional CNNs based on the full bounding box of the person. Finally, we compare our approach with state-of-the-art methods and show a gain in performance compared to best methods in literature.

  • 49.
    Berg, Amanda
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Öfjäll, Kristoffer
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Termisk Systemteknik AB, Linköping, Sweden.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Detecting Rails and Obstacles Using a Train-Mounted Thermal Camera2015In: Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings / [ed] Rasmus R. Paulsen; Kim S. Pedersen, Springer, 2015, p. 492-503Conference paper (Refereed)
    Abstract [en]

    We propose a method for detecting obstacles on the railway in front of a moving train using a monocular thermal camera. The problem is motivated by the large number of collisions between trains and various obstacles, resulting in reduced safety and high costs. The proposed method includes a novel way of detecting the rails in the imagery, as well as a way to detect anomalies on the railway. While the problem at a first glance looks similar to road and lane detection, which in the past has been a popular research topic, a closer look reveals that the problem at hand is previously unaddressed. As a consequence, relevant datasets are missing as well, and thus our contribution is two-fold: We propose an approach to the novel problem of obstacle detection on railways and we describe the acquisition of a novel data set.

  • 50.
    Zografos, Vasileios
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Lenz, Reiner
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Ringaby, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Nordberg, Klas
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Fast segmentation of sparse 3D point trajectories using group theoretical invariants2015In: COMPUTER VISION - ACCV 2014, PT IV / [ed] D. Cremers, I. Reid, H. Saito, M.-H. Yang, Springer, 2015, Vol. 9006, p. 675-691Conference paper (Refereed)
    Abstract [en]

    We present a novel approach for segmenting different motions from 3D trajectories. Our approach uses the theory of transformation groups to derive a set of invariants of 3D points located on the same rigid object. These invariants are inexpensive to calculate, involving primarily QR factorizations of small matrices. The invariants are easily converted into a set of robust motion affinities and with the use of a local sampling scheme and spectral clustering, they can be incorporated into a highly efficient motion segmentation algorithm. We have also captured a new multi-object 3D motion dataset, on which we have evaluated our approach, and compared against state-of-the-art competing methods from literature. Our results show that our approach outperforms all methods while being robust to perspective distortions and degenerate configurations.

1234 1 - 50 of 185
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