liu.seSök publikationer i DiVA
Ändra sökning
Avgränsa sökresultatet
5678910 351 - 400 av 481
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 351.
    Schötz, Susanne
    et al.
    Lund University.
    van de Weijer, Joost
    Lund University.
    Eklund, Robert
    Linköpings universitet, Institutionen för kultur och kommunikation, Avdelningen för språk och litteratur. Linköpings universitet, Filosofiska fakulteten.
    Phonetic Characteristics of Domestic Cat Vocalisations2017Ingår i: Proceedings of the 1st International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots, VIHAR 2017 / [ed] Angela Dassow, Ricard Marxer & Roger K. Moore, 2017, s. 5-6Konferensbidrag (Refereegranskat)
    Abstract [en]

    The cat (Felis catus, Linneaus 1758) has lived around or with humans for at least 10,000 years, and is now one of the most popular pets of the world with more than 600 millionindividuals. Domestic cats have developed a more extensive, variable and complex vocal repertoire than most other members of the Carnivora, which may be explained by their social organisation, their nocturnal activity and the long period of association between mother and young. Still, we know surprisingly little about the phonetic characteristics of these sounds, and about the interaction between cats and humans.

    Members of the research project Melody in human–cat communication (Meowsic) investigate the prosodic characteristics of cat vocalisations as well as the communication between human and cat. The first step includes a categorisation of cat vocalisations. In the next step it will be investigated how humans perceive the vocal signals of domestic cats. This paper presents an outline of the project which has only recently started.

  • 352.
    Selin, Magnus
    et al.
    Linköpings universitet, Institutionen för datavetenskap, Artificiell intelligens och integrerade datorsystem. Linköpings universitet, Tekniska fakulteten. Royal Institute of Technology, Stockholm Sweden.
    Tiger, Mattias
    Linköpings universitet, Institutionen för datavetenskap, Artificiell intelligens och integrerade datorsystem. Linköpings universitet, Tekniska fakulteten.
    Duberg, Daniel
    Royal Institute of Technology, Stockholm Sweden.
    Heintz, Fredrik
    Linköpings universitet, Institutionen för datavetenskap, Artificiell intelligens och integrerade datorsystem. Linköpings universitet, Tekniska fakulteten.
    Jensfelt, Patric
    Royal Institute of Technology, Stockholm Sweden.
    Efficient Autonomous Exploration Planning of Large Scale 3D-Environments2019Ingår i: IEEE Robotics and Automation Letters, ISSN 2377-3766, E-ISSN 1949-3045Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Exploration is an important aspect of robotics, whether it is for mapping, rescue missions or path planning in an unknown environment. Frontier Exploration planning (FEP) and Receding Horizon Next-Best-View planning (RH-NBVP) are two different approaches with different strengths and weaknesses. FEP explores a large environment consisting of separate regions with ease, but is slow at reaching full exploration due to moving back and forth between regions. RH-NBVP shows great potential and efficiently explores individual regions, but has the disadvantage that it can get stuck in large environments not exploring all regions. In this work we present a method that combines both approaches, with FEP as a global exploration planner and RH-NBVP for local exploration. We also present techniques to estimate potential information gain faster, to cache previously estimated gains and to exploit these to efficiently estimate new queries.

  • 353.
    Shimoni, Michal
    et al.
    Signal and Image Centre, Dept. of Electrical Engineering (SIC-RMA), Brussels, Belgium.
    Tolt, Gustav
    FOI Swedish Defence Research Agency, Linköping, Sweden.
    Perneel, Christiaan
    Dept. of Mathematics, Royal Military Academy, Brussels, Belgium.
    Ahlberg, Jörgen
    FOI Swedish Defence Research Agency, Linköping, Sweden.
    Detection of vehicles in shadow areas2011Ingår i: 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), IEEE , 2011, s. 1-4Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper presents a new method to automatically detect occluded vehicle in semi or deep shadow areas using combined very high resolution (VHR) 3D LIDAR and hyperspectral data. The proposed shape/spectral integration (SSI) decision fusion algorithm was shown to outperform the spectral based anomaly algorithm mainly in deep shadow areas. The fusion of LIDAR DSM data with spectral data is useful in the detection of vehicles in semi and deep shadow areas. The utility of shape information was shown to be a way to enhance spectral target detection in complex urban scene.

  • 354.
    Shimoni, Michal
    et al.
    Signal and Image Centre, Dept. of Electrical Engineering (SIC-RMA), Brussels, Belgium.
    Tolt, Gustav
    FOI Swedish Defence Research Agency, Linköping, Sweden.
    Perneel, Christiaan
    Dept. of Mathematics, Royal Military Academy, Brussels, Belgium.
    Ahlberg, Jörgen
    FOI Swedish Defence Research Agency, Linköping, Sweden.
    Detection of vehicles in shadow areas using combined hyperspectral and LIDAR data2011Ingår i: 2011 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE , 2011, s. 4427-4430Konferensbidrag (Refereegranskat)
    Abstract [en]

    In an effort to overcome the limitations of small target detection in complex urban scene, complementary data sets are combined to provide additional insight about a particular scene. This paper presents a method based on shape/spectral integration (SSI) decision level fusion algorithm to improve the detection of vehicles in semi and deep shadow areas. A four steps process combines high resolution LIDAR and hyperspectral data to classify shadow areas, segment vehicles in LIDAR data, detect spectral anomalies and improves vehicle detection. The SSI decision level fusion algorithm was shown to outperform detection using a single data set and the utility of shape information was shown to be a way to enhance spectral target detection in complex urban scenes.  

  • 355.
    Sigfridsson, Andreas
    Linköpings universitet, Institutionen för medicinsk teknik. Linköpings universitet, Tekniska högskolan.
    Multidimensional MRI of Cardiac Motion: Acquisition, Reconstruction and Visualization2006Licentiatavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    Methods for measuring deformation and motion of the human heart in-vivo are crucial in the assessment of cardiac function. Applications ranging from basic physiological research, through early detection of disease to follow-up studies, all benefit from improved methods of measuring the dynamics of the heart. This thesis presents new methods for acquisition, reconstruction and visualization of cardiac motion and deformation, based on magnetic resonance imaging.

    Local heart wall deformation can be quantified in a strain rate tensor field. This tensor field describes the local deformation excluding rigid body translation and rotation. The drawback of studying this tensor-valued quantity, as opposed to a velocity vector field, is the high dimensionality of the tensor. The problem of visualizing the tensor field is approached by combining a local visualization that displays all degrees of freedom for a single tensor with an overview visualization using a scalar field representation of the complete tensor field. The scalar field is obtained by iterated adaptive filtering of a noise field.

    Several methods for synchronizing the magnetic resonance imaging acquisition to the heart beat have previously been used to resolve individual heart phases from multiple cardiac cycles. In the present work, one of these techniques is extended to resolve two temporal dimensions simultaneously, the cardiac cycle and the respiratory cycle. This is combined with volumetric imaging to produce a five-dimensional data set. Furthermore, the acquisition order is optimized in order to reduce eddy current artifacts.

    The five-dimensional acquisition either requires very long scan times or can only provide low spatiotemporal resolution. A method that exploits the variation in temporal bandwidth over the imaging volume, k-t BLAST, is described and extended to two simultaneous temporal dimensions. The new method, k-t2 BLAST, allows simultaneous reduction of scan time and improvement of spatial resolution.

    Delarbeten
    1. Tensor Field Visualisation using Adaptive Filtering of Noise Fields combined with Glyph Rendering
    Öppna denna publikation i ny flik eller fönster >>Tensor Field Visualisation using Adaptive Filtering of Noise Fields combined with Glyph Rendering
    2002 (Engelska)Ingår i: IEEE Visualization 2002 Conference, IEEE , 2002, s. 371-378Konferensbidrag, Publicerat paper (Refereegranskat)
    Abstract [en]

    While many methods exist for visualising scalar and vector data, visualisation of tensor data is still troublesome. We present a method for visualising second order tensors in three dimensions using a hybrid between direct volume rendering and glyph rendering.

    An overview scalar field is created by using three-dimensional adaptive filtering of a scalar field containing noise. The filtering process is controlled by the tensor field to be visualised, creating patterns that characterise the tensor field. By combining direct volume rendering of the scalar field with standard glyph rendering methods for detailed tensor visualisation, a hybrid solution is created.

    A combined volume and glyph renderer was implemented and tested with both synthetic tensors and strain-rate tensors from the human heart muscle, calculated from phase contrast magnetic resonance image data. A comprehensible result could be obtained, giving both an overview of the tensor field as well as detailed information on individual tensors.

    Ort, förlag, år, upplaga, sidor
    IEEE, 2002
    Nyckelord
    Tensor, Visualisation, Volume rendering, Glyph rendering, Hybrid rendering, Strain-rate
    Nationell ämneskategori
    Medicin och hälsovetenskap Medicinsk laboratorie- och mätteknik
    Identifikatorer
    urn:nbn:se:liu:diva-14011 (URN)
    Tillgänglig från: 2006-10-04 Skapad: 2006-10-04 Senast uppdaterad: 2013-09-03Bibliografiskt granskad
    2. Five-dimensional MRI Incorporating Simultaneous Resolution of Cardiac and Respiratory Phases for Volumetric Imaging
    Öppna denna publikation i ny flik eller fönster >>Five-dimensional MRI Incorporating Simultaneous Resolution of Cardiac and Respiratory Phases for Volumetric Imaging
    2006 (Engelska)Ingår i: Journal of Magnetic Resonance Imaging, ISSN 1053-1807, E-ISSN 1522-2586, Vol. 25, nr 1, s. 113-121Artikel i tidskrift (Refereegranskat) Published
    Abstract [en]

    Purpose

    To develop a new volumetric imaging method resolved over both the cardiac and respiratory cycles, to enable future physiological and pathophysiological studies of respiratory-related cardiac motion.

    Materials and Methods

    An acquisition scheme is proposed whereby the k-space acquisition order is controlled in real-time by the current cardiac and respiratory phases. To reduce eddy-current effects induced by sudden jumps in k-space, the acquisition order is further optimized by the use of a Hilbert curve trajectory in the ky-kz plane. A complete three-dimensional (3D) k-space is acquired for all combinations of cardiac and respiratory phases, yielding a five-dimensional (5D) data set after retrospective reconstruction.

    Results

    Left (LV) and right ventricular (RV) wall excursion was measured in a healthy volunteer. Diastolic LV diameter was shown to increase during expiration and decrease during inspiration, as expected from previous echocardiography studies. The LV volume was estimated for all cardiac and respiratory phases with the use of a fully 3D segmentation tool. The results confirmed that the diastolic LV volume increased during expiration and decreased during inspiration.

    Conclusion

    With its ability to measure motion anywhere in the heart, the described technique provides a promising approach for in-depth description of interventricular coupling, including 3D ventricular volumes, during both the cardiac and respiratory cycles.

    Nyckelord
    respiration, septal motion, interventricular coupling, volumetric MRI, cine imaging
    Nationell ämneskategori
    Medicin och hälsovetenskap Medicinsk laboratorie- och mätteknik
    Identifikatorer
    urn:nbn:se:liu:diva-14012 (URN)10.1002/jmri.20820 (DOI)000243250800014 ()
    Tillgänglig från: 2006-10-04 Skapad: 2006-10-04 Senast uppdaterad: 2017-12-13Bibliografiskt granskad
    3. k-t2 BLAST: Exploiting spatiotemporal structure in simultaneously cardiac and respiratory time-resolved volumetric imaging
    Öppna denna publikation i ny flik eller fönster >>k-t2 BLAST: Exploiting spatiotemporal structure in simultaneously cardiac and respiratory time-resolved volumetric imaging
    2007 (Engelska)Ingår i: Magnetic Resonance in Medicine, ISSN 0740-3194, E-ISSN 1522-2594, Vol. 58, nr 5, s. 922-930Artikel i tidskrift (Refereegranskat) Published
    Abstract [en]

    Multidimensional imaging resolving both the cardiac and respiratory cycles simultaneously has the potential to describe important physiological interdependences between the heart and pulmonary processes. A fully five-dimensional acquisition with three spatial and two temporal dimensions is hampered, however, by the long acquisition time and low spatial resolution. A technique is proposed to reduce the scan time substantially by extending the k-t BLAST framework to two temporal dimensions. By sampling the k-t space sparsely in a lattice grid, the signal in the transform domain, x-f space, can be densely packed, exploiting the fact that large regions in the field of view have low temporal bandwidth. A volumetric online prospective triggering approach with full cardiac and respiratory cycle coverage was implemented. Retrospective temporal interpolation was used to refine the timing estimates for the center of k-space, which is sampled for all cardiac and respiratory time frames. This resulted in reduced reconstruction error compared with conventional k-t BLAST reconstruction. The k-t2 BLAST technique was evaluated by decimating a fully sampled five-dimensional data set, and feasibility was further demonstrated by performing sparsely sampled acquisitions. Compared to the fully sampled data, a fourfold improvement in spatial resolution was accomplished in approximately half the scan time.

    Nyckelord
    Cine imaging, k-t BLAST, Respiration, Volumetric MRI
    Nationell ämneskategori
    Teknik och teknologier Medicinsk laboratorie- och mätteknik
    Identifikatorer
    urn:nbn:se:liu:diva-47833 (URN)10.1002/mrm.21295 (DOI)000250560000009 ()
    Tillgänglig från: 2009-10-11 Skapad: 2009-10-11 Senast uppdaterad: 2017-12-13Bibliografiskt granskad
  • 356.
    Simberg, Gustav
    et al.
    Linköpings universitet, Institutionen för systemteknik.
    Viggeborn, Björn
    Linköpings universitet, Institutionen för systemteknik.
    Utveckling av mobiltelefonapplikation för kommunikation i ad-hoc nätverk med Bluetoothteknik2005Självständigt arbete på avancerad nivå (magisterexamen), 20 poäng / 30 hpStudentuppsats
    Abstract [en]

    The purpose of this thesis is to develop an application for mobile phones that simplifies communication. The company Doberman wanted to look at possibilities to develop such an application that uses Bluetooth™ technol-ogy to communicate in ad-hoc networks. The aim has been an application to run on mobile phones in which you can send messages and files to other devices and also add a user profile with personal information to share with others. The communication will take place in temporary networks created when Bluetooth enabled devices is in range of each other.

    The market for mobile phones has grown rapidly over the past years and is still growing. There are many differ-ent phone models and it is difficult to find a developer platform that covers many phone models. In the beginning of this thesis an inquiry of different developer platforms has been made. The Java™ platform is supported by most phones but has limitations in accessing functions on the device. The best alternative was Symbian C++ for devices with Symbian OS. This alternative does not have the same limitations as Java and is still supported by relatively many devices. The application was then developed in Symbian C++. There are a number of different versions of Symbian OS and different GUI-platforms that runs on Symbian OS which leads to other issues in the development. We have limited the development of the application to the Series 60 platform for Symbian OS v7.0s. During design and implementation portability to other GUI-platforms has been considered.

    We have tested the application on emulator compatible with Symbian OS v7.0s and Symbian OS v8.0a and found some compatibility problems between the two versions. We have also tested the application on mobile phones and between emulator and the phone with corresponding OS-version no new problems occurred

  • 357.
    Sjanic, Zoran
    et al.
    Linköpings universitet, Institutionen för systemteknik, Reglerteknik. Linköpings universitet, Tekniska högskolan.
    Gustafsson, Fredrik
    Linköpings universitet, Institutionen för systemteknik, Reglerteknik. Linköpings universitet, Tekniska fakulteten.
    Simultaneous Navigation and Synthetic Aperture Radar Focusing2015Ingår i: IEEE Transactions on Aerospace and Electronic Systems, ISSN 0018-9251, E-ISSN 1557-9603, Vol. 51, nr 2, s. 1253-1266Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Synthetic aperture radar (SAR) equipment is a radar imaging system that can be used to create high-resolution images of a scene by utilizing the movement of a flying platform. Knowledge of the platforms trajectory is essential to get good and focused images. An emerging application field is real-time SAR imaging using small and cheap platforms where estimation errors in navigation systems imply unfocused images. This contribution investigates a joint estimation of the trajectory and SAR image. Starting with a nominal trajectory, we successively improve the image by optimizing a focus measure and updating the trajectory accordingly. The method is illustrated using simulations using typical navigation performance of an unmanned aerial vehicle. One real data set is used to show feasibility, where the result indicates that, in particular, the azimuth position error is decreased as the image focus is iteratively improved.

  • 358.
    Sjöholm, Alexander
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Closing the Loop: Mobile Visual Location Recognition2014Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Visual simultaneous localization and mapping (SLAM) as field has been researched for ten years, but with recent advances in mobile performance visual SLAM is entering the consumer market in a completely new way. A visual SLAM system will however be sensitive to non cautious use that may result in severe motion, occlusion or poor surroundings in terms of visual features that will cause the system to temporarily fail. The procedure of recovering from such a fail is called relocalization. Together with two similar problems localization, to find your position in an existing SLAM session, and loop closing, the online reparation and perfection of the map in an active SLAM session, these can be grouped as visual location recognition (VLR).

    This thesis presents novel results by combining the scalability of FabMap and the precision of 13th Lab's tracking yielding high-precision VLR, +/- 10 cm, while maintaining above 99 % precision and 60 % recall for sessions containing thousands of images. Everything functional purely on a normal mobile phone.

    The applications of VLR are many. Indoors, where GPS is not functioning, VLR can still provide positional information and navigate you through big complexes like airports and museums. Outdoors, VLR can improve the precision of GPS tenfold yielding a new level of navigational experience. Virtual and augmented reality applications are other areas that benefit from improved positioning and localization.

  • 359.
    Skoglund, Johan
    Linköpings universitet, Institutionen för systemteknik, Bildbehandling. Linköpings universitet, Tekniska högskolan.
    Robust Real-Time Estimation of Region Displacements in Video Sequences2007Licentiatavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    The possibility to use real-time computer vision in video sequences gives many opportunities for a system to interact with the environment. Possible ways for interaction are e.g. augmented reality like in the MATRIS project where the purpose is to add new objects into the video sequence, or surveillance where the purpose is to find abnormal events.

    The increase of the speed of computers the last years has simplified this process and it is now possible to use at least some of the more advanced computer vision algorithms that are available. The computational speed of computers is however still a problem, for an efficient real-time system efficient code and methods are necessary. This thesis deals with both problems, one part is about efficient implementations using single instruction multiple data (SIMD) instructions and one part is about robust tracking.

    An efficient real-time system requires efficient implementations of the used computer vision methods. Efficient implementations requires knowledge about the CPU and the possibilities given. In this thesis, one method called SIMD is explained. SIMD is useful when the same operation is applied to multiple data which usually is the case in computer vision, the same operation is executed on each pixel.

    Following the position of a feature or object in a video sequence is called tracking. Tracking can be used for a number of applications. The application in this thesis is to use tracking for pose estimation. One way to do tracking is to cut out a small region around the feature, creating a patch and find the position on this patch in the other frames. To find the position, a measure of the difference between the patch and the image in a given position is used. This thesis thoroughly investigates the sum of absolute difference (SAD) error measure. The investigation involves different ways to improve the robustness and to decrease the average error. One method to estimate the average error, the covariance of the position error is proposed. An estimate of the average error is needed when different measurements are combined.

    Finally, a system for camera pose estimation is presented. The computer vision part of this system is based on the result in this thesis. This presentation contains also a discussion about the result of this system.

  • 360.
    Solli, Martin
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier. Linköpings universitet, Tekniska högskolan.
    Color Image Retrieval with Bags-of-Emotions2009Ingår i: Proceedings of SSBA 2009, Symposium on image analysis, 2009 / [ed] Josef Bigun, Antanas Verikas, Halmstad, Sweden: Halmstad University , 2009, s. 37-40Konferensbidrag (Övrigt vetenskapligt)
  • 361.
    Solli, Martin
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Topics in Content Based Image Retrieval: Fonts and Color Emotions2009Licentiatavhandling, monografi (Övrigt vetenskapligt)
    Abstract [en]

    Two novel contributions to Content Based Image Retrieval are presented and discussed. The first is a search engine for font recognition. The intended usage is the search in very large font databases. The input to the search engine is an image of a text line, and the output is the name of the font used when printing the text. After pre-processing and segmentation of the input image, a local approach is used, where features are calculated for individual characters. The method is based on eigenimages calculated from edge filtered character images, which enables compact feature vectors that can be computed rapidly. A system for visualizing the entire font database is also proposed. Applying geometry preserving linear- and non-linear manifold learning methods, the structure of the high-dimensional feature space is mapped to a two-dimensional representation, which can be reorganized into a grid-based display. The performance of the search engine and the visualization tool is illustrated with a large database containing more than 2700 fonts.

    The second contribution is the inclusion of color-based emotion-related properties in image retrieval. The color emotion metric used is derived from psychophysical experiments and uses three scales: activity, weight and heat. It was originally designed for single-color combinations and later extended to include pairs of colors. A modified approach for statistical analysis of color emotions in images, involving transformations of ordinary RGB-histograms, is used for image classification and retrieval. The methods are very fast in feature extraction, and descriptor vectors are very short. This is essential in our application where the intended use is the search in huge image databases containing millions or billions of images. The proposed method is evaluated in psychophysical experiments, using both category scaling and interval scaling. The results show that people in general perceive color emotions for multi-colored images in similar ways, and that observer judgments correlate with derived values.

    Both the font search engine and the emotion based retrieval system are implemented in publicly available search engines. User statistics gathered during a period of 20 respectively 14 months are presented and discussed.

  • 362.
    Solli, Martin
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Color Based Bags-of-Emotions2009Ingår i: CAIP, Computer Analysis of Images and Patterns / [ed] Xiaoyi Jiang, Nicolai Petkov, Berlin / Heidelberg: Springer , 2009, s. 573-580Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper we describe how to include high level semantic information, such as aesthetics and emotions, into Content Based Image Retrieval. We present a color-based emotion-related image descriptor that can be used for describing the emotional content of images. The color emotion metric used is derived from psychophysical experiments and based on three variables: activity, weight and heat. It was originally designed for single-colors, but recent research has shown that the same emotion estimates can be applied in the retrieval of multi-colored images. Here we describe a new approach, based on the assumption that perceived color emotions in images are mainly affected by homogenous regions, defined by the emotion metric, and transitions between regions. RGB coordinates are converted to emotion coordinates, and for each emotion channel, statistical measurements of gradient magnitudes within a stack of low-pass filtered images are used for finding interest points corresponding to homogeneous regions and transitions between regions. Emotion characteristics are derived for patches surrounding each interest point, and saved in a bag-of-emotions, that, for instance, can be used for retrieving images based on emotional content.

  • 363.
    Solli, Martin
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Lenz, Reiner
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Color Emotions for Image Classification and Retrieval2008Ingår i: Proc. IS&Ts 4th European Conference on Colour in Graphics, Imaging, and Vision, CGIV 2008, 7003 Kilworth Lane, Springfield, VA 22151 USA: Society for Imaging Science and Technology , 2008, , s. 367-371Konferensbidrag (Refereegranskat)
    Abstract [en]

    Many content-based image retrieval systems are not takinginto account high level semantic information. In this paperwe describe our attempts to include color-based emotion-relatedproperties of images in the search. We show that using coloremotion metrics in content-based image retrieval leads to interestingmethods for image retrieval and classification based onsemantic concepts. The color emotion metric used is derivedfrom psychophysical experiments and uses three scales: activity,weight and heat. It was originally designed for single-colorcombinations and later extended to include pairs of colors. Weshow that a modified approach for statistical analysis of coloremotions in images, involving transformations of ordinary RGBhistograms,provides a useful tool for image classification andretrieval. The methods used are both very fast in feature extraction,and descriptor vectors are very short. This is essential inour application where we intend to use it for searching huge imagedatabases containing millions or billions of images.

  • 364.
    Solli, Martin
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan.
    Color emotions for multi-colored images2011Ingår i: Color Research and Application, ISSN 0361-2317, E-ISSN 1520-6378, Vol. 36, nr 3, s. 210-221Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We investigate the emotional response to colors in ordinary multicolored images. In psychophysical experiments, using both category scaling and interval scaling, observers are asked to judge images using three emotion factors: activity, weight, and heat. The color emotion metric was originally developed for single colors, and later extended to include pairs of colors. The same metric was recently used in image retrieval. The results show that people in general perceive color emotions for multi-colored images in similar ways, and that observer judgments correlate with the recently proposed method used in image retrieval. The intended usage is in retrieval systems publicly available on the Internet, where both the user and the viewing environment is unknown, which requires novel ways of conducting the psychophysical experiments.

  • 365.
    Solli, Martin
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier. Linköpings universitet, Tekniska högskolan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier. Linköpings universitet, Tekniska högskolan.
    Color Harmony for Image Indexing2009Ingår i: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, IEEE , 2009, s. 1885-1892Konferensbidrag (Refereegranskat)
    Abstract [en]

    A predictive model for estimating the perceived harmony of ordinary multi-colored images is proposed and evaluated. The model is based on earlier research concerning two-color harmonies. Color regions of images are extracted using mean shift segmentation. Global and local harmony scores are derived for two-color combinations included in different subsets of all segmented regions. Statistical measurements of the obtained harmony scores are used for predicting the perceived overall harmony. The model is validated in a psychophysical experiment, where human observers are judging images on a harmony scale. The findings show that humans do perceive harmony in multi-colored images in similar ways, and that the proposed model results in useful predictions of harmony. The model can be applied in automatic labeling or classification of images.

  • 366.
    Solli, Martin
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier. Linköpings universitet, Tekniska högskolan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier. Linköpings universitet, Tekniska högskolan.
    Color Semantics for Image Indexing2010Ingår i: CGIV 2010/MCS'10 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science / [ed] Jussi Parkkinen, Timo Jääskeläinen, Theo Gevers, Alain Trémeau, Springfield, USA: The Society for Imaging Science and Technology, 2010, s. 353-358Konferensbidrag (Refereegranskat)
    Abstract [en]

    We propose a color-based image descriptor that can be used for image indexing based on high-level semantic concepts. The descriptor is based on Kobayashi's Color Image Scale, which is a system that includes 130 basic colors combined in 1170 three-color combinations. Each combination is labeled with one of 180 high-level semantic concepts, like "elegant", "romantic", "provocative", etc. Moreover, words are located in a two-dimensional semantic space, and arranged into groups based on perceived similarity. From a modified approach for statistical analysis of images, involving transformations of ordinary RGB-histograms, a semantic image descriptor is derived, containing semantic information about both color combinations and single colors in the image. We show how the descriptor can be translated into different levels of semantic information, and used in indexing of multi-colored images. Intended applications are, for instance, image labeling and retrieval.

  • 367.
    Solli, Martin
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan.
    Content Based Detection of Popular Images in Large Image Databases2011Ingår i: 17th Scandinavian Conference on Image Analysis, SCIA 2011 / [ed] A. Heyden, F. Kahl, Berlin Heidelberg: Springer-Verlag , 2011, s. 218-227Konferensbidrag (Refereegranskat)
    Abstract [en]

    We investigate the use of standard image descriptors and a supervised learning algorithm for estimating the popularity of images. The intended application is in large scale image search engines, where the proposed approach can enhance the user experience by improving the sorting of images in a retrieval result. Classification methods are trained and evaluated on real-world user statistics recorded by a major image search engine. The conclusion is that for many image categories, the combination of supervised learning algorithms and standard image descriptors results in useful popularity predictions.

  • 368.
    Solli, Martin
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan.
    Emotion Related Structures in Large Image Databases2010Ingår i: CIVR 2010: 2010 ACM International Conference on Image and Video Retrieval / [ed] Chunna Tian, New York, USA: The Association for Computing Machinery , 2010, s. 398-405Konferensbidrag (Refereegranskat)
    Abstract [en]

    We introduce two large databases consisting of 750 000 and 1.2 million thumbnail-sized images, labeled with emotion-related keywords. The smaller database consists of images from Matton Images, an image provider. The larger database consists of web images that were indexed by the crawler of the image search engine Picsearch. The images in the Picsearch database belong to one of 98 emotion related categories and contain meta-data in the form of secondary keywords, the originating website and some view statistics. We use two psycho-physics related feature vectors based on the emotional impact of color combinations, the standard RGB-histogram and two SIFT-related descriptors to characterize the visual properties of the images. These features are then used in two-class classification experiments to explore the discrimination properties of emotion-related categories. The clustering software and the classifiers are available in the public domain, and the same standard configurations are used in all experiments. Our findings show that for emotional categories, descriptors based on global image statistics (global histograms) perform better than local image descriptors (bag-of-words models). This indicates that content-based indexing and retrieval using emotion-based approaches are fundamentally different from the dominant object- recognition based approaches for which SIFT-related features are the standard descriptors.

  • 369.
    Solli, Martin
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Lenz, Reiner
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Emotional Satisfaction in Color Image Retrieval2008Ingår i: SSBA 2008, Symposium on Image Analysis, 2008, Lund, Sweden: Lund University , 2008, s. 7-10Konferensbidrag (Övrigt vetenskapligt)
  • 370.
    Solli, Martin
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Lenz, Reiner
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    FyFont: Find-your-Font in Large Font Databases2007Ingår i: Scandinavian Conference on Image Analysis, SCIA 2007 / [ed] Bjarne Kjær Ersbøll, Kim Steenstrup Pedersen, Berlin: Springer , 2007, , s. 432-441s. 432-441Konferensbidrag (Refereegranskat)
    Abstract [en]

    A search engine for font recognition in very large font data-bases is presented and evaluated. The search engine analyzes an image of a text line, and responds with the name of the font used when writing the text. After segmenting the input image into single characters, the recognition is mainly based on eigenimages calculated from edge filtered character images. We evaluate the system with printed and scanned text lines and character images. The database used contains 2763 different fonts from the English alphabet. Our evaluation shows that for 99.8 % of the queries, the correct font name is one of the five best matches. Apart from finding fonts in large databases, the search engine can also be used as a pre-processor for Optical Character Recognition.

  • 371.
    Solli, Martin
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    Lenz, Reiner
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier.
    How to find the font name for this title2007Ingår i: SSBA 2007, Symposium on Image Analysis, 2007 / [ed] Magnus Borga, Anders Brun, Michael Felsberg, Linköping, Sweden: Linköping University , 2007, s. 37-40Konferensbidrag (Övrigt vetenskapligt)
  • 372.
    Solli, Martin
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier. Linköpings universitet, Tekniska högskolan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Digitala Medier. Linköpings universitet, Tekniska högskolan.
    Visualization of large font databases2009Ingår i: Advances in Printing and Media Technology Vol. XXXVI: Proceedings of the 36th International Research Conference of iarigai / [ed] Nils Enlund, Mladen Lovrecek, Darmstadt, Germany: iarigai , 2009, s. 67-74Konferensbidrag (Refereegranskat)
    Abstract [en]

    We describe a novel system for interaction with large font databases. The system is an efficient tool for browsing in large font databases and as such it can be used by people in the Graphic Arts industry. The proposed approach is based on shape descriptors developed for visual characterization of character images rendered from different fonts. Here the descriptors are used in a visualization of a large font database containing more than 2700 fonts. By applying geometry preserving linear- and non-linear manifold learning methods, in combination with a refinement process, character images of different fonts are organized on a two-dimensional grid, where fonts are positioned based on visual similarity.

  • 373.
    Spiecker, E.
    et al.
    University of Kiel, Germany.
    Garbrecht, Magnus
    Linköpings universitet, Institutionen för fysik, kemi och biologi, Tunnfilmsfysik. Linköpings universitet, Tekniska fakulteten.
    Jaeger, W.
    University of Kiel, Germany.
    Tillmann, K.
    Forschungszentrum Julich, Germany; Forschungszentrum Julich, Germany.
    Advantages of aberration correction for HRTEM investigation of complex layer compounds2010Ingår i: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, Vol. 237, nr 3, s. 341-346Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Aberration-corrected high-resolution transmission electron microscopy (HRTEM) has been applied to resolve the atomic structure of a complex layered crystal, (PbS)(1.14)NbS(2), which comprises a high density of incommensurate interfaces. The strong suppression of image delocalization and the favourable contrast transfer under negative C(s) imaging (NCSI) conditions have been exploited for obtaining HRTEM images which directly reveal the projected crystal structure and allow to study lattice imperfections, like stacking disorder and layer undulations, with atomic scale resolution. The advantages of aberration-corrected HRTEM over conventional HRTEM are demonstrated by direct comparison of experimental images and computer simulations.

  • 374.
    Sreevalsan-Nair, Jaya
    et al.
    Institute of Information Technology Bangalore, India (IIIT).
    Auer, Cornelia
    Zuse Institute Berlin.
    Hamann, Bernd
    University of California, Davis, USA.
    Hotz, Ingrid
    Zuse Institue Berlin.
    Eigenvector-based Interpolation and Segmentation of 2D Tensor Fields2011Ingår i: Topological Methods in Data Analysis and Visualization. Theory, Algorithms, and Applications / [ed] Peer-Timo Bremer, Ingrid Hotz, Valerio Pascucci, Ronald Peikert, Springer, 2011, s. 139-150Kapitel i bok, del av antologi (Refereegranskat)
    Abstract [en]

    We propose a topology-based segmentation of 2D symmetric tensor fields, which results in cells bounded by tensorlines. We are particularly interested in the influence of the interpolation scheme on the topology, considering eigenvector-based and component-wise linear interpolation. When using eigenvector-based interpolation the most significant modification to the standard topology extraction algorithm is the insertion of additional vertices at degenerate points. A subsequent Delaunay re-triangulation leads to connections between close degenerate points. These new connections create degenerate edges and tri angles.When comparing the resulting topology per triangle with the one obtained by component-wise linear interpolation the results are qualitatively similar, but our approach leads to a less “cluttered” segmentation

  • 375.
    Stein, Madeleine
    et al.
    Linköpings universitet, Institutionen för systemteknik, Reglerteknik. Linköpings universitet, Tekniska fakulteten.
    Bargoti, Suchet
    University of Sydney, Australia.
    Underwood, James
    University of Sydney, Australia.
    Image Based Mango Fruit Detection, Localisation and Yield Estimation Using Multiple View Geometry2016Ingår i: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 16, nr 11, artikel-id 1915Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper presents a novel multi-sensor framework to efficiently identify, track, localise and map every piece of fruit in a commercial mango orchard. A multiple viewpoint approach is used to solve the problem of occlusion, thus avoiding the need for labour-intensive field calibration to estimate actual yield. Fruit are detected in images using a state-of-the-art faster R-CNN detector, and pair-wise correspondences are established between images using trajectory data provided by a navigation system. A novel LiDAR component automatically generates image masks for each canopy, allowing each fruit to be associated with the corresponding tree. The tracked fruit are triangulated to locate them in 3D, enabling a number of spatial statistics per tree, row or orchard block. A total of 522 trees and 71,609 mangoes were scanned on a Calypso mango orchard near Bundaberg, Queensland, Australia, with 16 trees counted by hand for validation, both on the tree and after harvest. The results show that single, dual and multi-view methods can all provide precise yield estimates, but only the proposed multi-view approach can do so without calibration, with an error rate of only 1.36% for individual trees.

  • 376.
    Steinbauer, Gerald
    et al.
    Graz University of Technology, Austria.
    Kleiner, Alexander
    Linköpings universitet, Institutionen för datavetenskap, Artificiell intelligens och integrerad datorsystem. Linköpings universitet, Tekniska högskolan.
    Towards CSP-based mission dispatching in C2/C4I systems2012Ingår i: Proc. of the IEEE Int. Workshop on Safety, Security and Rescue Robotics (SSRR), IEEE , 2012, s. 1-6Konferensbidrag (Refereegranskat)
    Abstract [en]

    One challenging problem in disaster response is to efficiently assign resources such as fire fighters and trucks to local incidents that are spatially distributed on a map. Existing systems for command and control (C2/C4I) are coming with powerful interfaces enabling the manual assignment of resources to the incident commander. However, with increasing number of local incidents over time the performance of manual methods departs arbitrarily from an optimal solution. In this paper we introduce preliminary results of building an interface between existing professional C2/C4I systems and Constraint Satisfaction Problem (CSP)-solvers. We show by using an example the feasibility of scheduling and assigning missions having deadlines and resource constraints.

  • 377.
    Stenhagen, Petter
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Improving Realism in Synthetic Barcode Images using Generative Adversarial Networks2018Självständigt arbete på avancerad nivå (masterexamen), 300 hpStudentuppsats (Examensarbete)
    Abstract [en]

    This master thesis explores the possibility of using generative Adversarial Networks (GANs) to refine labeled synthetic code images to resemble real code images while preserving label information. The GAN used in this thesis consists of a refiner and a discriminator. The discriminator tries to distinguish between real images and refined synthetic images. The refiner tries to fool the discriminator by producing refined synthetic images such that the discriminator classify them as real. By updating these two networks iteratively, the idea is that they will push each other to get better, resulting in refined synthetic images with real image characteristics.

    The aspiration, if the exploration of GANs turns out successful, is to be able to use refined synthetic images as training data in Semantic Segmentation (SS) tasks and thereby eliminate the laborious task of gathering and labeling real data. Starting off from a foundational GAN-model, different network architectures, hyperparameters and other design choices are explored to find the best performing GAN-model.

    As is widely acknowledged in the relevant literature, GANs can be difficult to train and the results in this thesis are varying and sometimes ambiguous. Based on the results from this study, the best performing models do however perform better in SS tasks than the unrefined synthetic set they are based on and benchmarked against, with regards to Intersection over Union.

  • 378.
    Stigson, Magnus
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Object Tracking Using Tracking-Learning-Detection inThermal Infrared Video2013Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Automatic tracking of an object of interest in a video sequence is a task that has been much researched. Difficulties include varying scale of the object, rotation and object appearance changing over time, thus leading to tracking failures. Different tracking methods, such as short-term tracking often fail if the object steps out of the camera’s field of view, or changes shape rapidly. Also, small inaccuracies in the tracking method can accumulate over time, which can lead to tracking drift. Long-term tracking is also problematic, partly due to updating and degradation of the object model, leading to incorrectly classified and tracked objects.

    This master’s thesis implements a long-term tracking framework called Tracking-Learning-Detection which can learn and adapt, using so called P/N-learning, to changing object appearance over time, thus making it more robust to tracking failures. The framework consists of three parts; a tracking module which follows the object from frame to frame, a learning module that learns new appearances of the object, and a detection module which can detect learned appearances of the object and correct the tracking module if necessary.

    This tracking framework is evaluated on thermal infrared videos and the results are compared to the results obtained from videos captured within the visible spectrum. Several important differences between visual and thermal infrared tracking are presented, and the effect these have on the tracking performance is evaluated.

    In conclusion, the results are analyzed to evaluate which differences matter the most and how they affect tracking, and a number of different ways to improve the tracking are proposed.

  • 379.
    Strand, Mattias
    Linköpings universitet, Institutionen för systemteknik.
    A Software Framework for Facial Modelling and Tracking2010Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    The WinCandide application, a platform for face tracking and model based coding, had become out of date and needed to be upgraded. This report is based on the work of investigating possible open source GUIs and computer vision tool kits that could replace the old ones that are unsupported. Multi platform GUIs are of special interest.

  • 380.
    Strömgren, Oliver
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Deep Learning for Autonomous Collision Avoidance2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Deep learning has been rapidly growing in recent years obtaining excellent results for many computer vision applications, such as image classification and object detection. One aspect for the increased popularity of deep learning is that it mitigates the need for hand-crafted features. This thesis work investigates deep learning as a methodology to solve the problem of autonomous collision avoidance for a small robotic car. To accomplish this, transfer learning is used with the VGG16 deep network pre-trained on ImageNet dataset. A dataset has been collected and then used to fine-tune and validate the network offline. The deep network has been used with the robotic car in a real-time manner. The robotic car sends images to an external computer, which is used for running the network. The predictions from the network is sent back to the robotic car which takes actions based on those predictions. The results show that deep learning has great potential in solving the collision avoidance problem.

  • 381.
    Stynsberg, John
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Incorporating Scene Depth in Discriminative Correlation Filters for Visual Tracking2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Visual tracking is a computer vision problem where the task is to follow a targetthrough a video sequence. Tracking has many important real-world applications in several fields such as autonomous vehicles and robot-vision. Since visual tracking does not assume any prior knowledge about the target, it faces different challenges such occlusion, appearance change, background clutter and scale change. In this thesis we try to improve the capabilities of tracking frameworks using discriminative correlation filters by incorporating scene depth information. We utilize scene depth information on three main levels. First, we use raw depth information to segment the target from its surroundings enabling occlusion detection and scale estimation. Second, we investigate different visual features calculated from depth data to decide which features are good at encoding geometric information available solely in depth data. Third, we investigate handling missing data in the depth maps using a modified version of the normalized convolution framework. Finally, we introduce a novel approach for parameter search using genetic algorithms to find the best hyperparameters for our tracking framework. Experiments show that depth data can be used to estimate scale changes and handle occlusions. In addition, visual features calculated from depth are more representative if they were combined with color features. It is also shown that utilizing normalized convolution improves the overall performance in some cases. Lastly, the usage of genetic algorithms for hyperparameter search leads to accuracy gains as well as some insights on the performance of different components within the framework.

  • 382.
    Su, R.
    et al.
    Tianjin University, Peoples R China.
    Zhang, C.
    CSIRO Data61, Australia; University of New South Wales, Australia.
    Pham, Tuan
    Linköpings universitet, Institutionen för medicinsk teknik. Linköpings universitet, Tekniska fakulteten.
    Davey, R.
    CSIRO Food and Nutr, Australia.
    Bischof, L.
    CSIRO Data61, Australia.
    Vallotton, P.
    CSIRO Data61, Australia; ETH, Switzerland.
    Lovell, D.
    CSIRO Data61, Australia; Queensland University of Technology, Australia.
    Hope, S.
    CSIRO Food and Nutr, Australia.
    Schmoelzl, S.
    CSIRO Food and Nutr, Australia.
    Sun, C.
    CSIRO Data61, Australia.
    Detection of tubule boundaries based on circular shortest path and polar-transformation of arbitrary shapes2016Ingår i: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, Vol. 264, nr 2, s. 127-142Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In studies of germ cell transplantation, counting cells and measuring tubule diameters from different populations using labelled antibodies are important measurement processes. However, it is slow and sanity grinding to do these tasks manually. This paper proposes a way to accelerate these processes using a new image analysis framework based on several novel algorithms: centre points detection of tubules, tubule shape classification, skeleton-based polar-transformation, boundary weighting of polar-transformed image, and circular shortest path smoothing. The framework has been tested on a dataset consisting of 27 images which contain a total of 989 tubules. Experiments show that the detection results of our algorithm are very close to the results obtained manually and the novel approach can achieve a better performance than two existing methods. Lay description In studies of germ cell transplantation, counting cells and measuring tubule diameters from different populations using labelled antibodies are important measurement processes. However, it is slow and sanity grinding to do these tasks manually. This paper proposes a way to accelerate these processes using a new image analysis framework based on several novel algorithms: center points detection of tubules, tubule shape classification, skeleton based polar-transformation, boundary weighting of polar-transformed image, and circular shortest path smoothing. The framework has been tested on a dataset consisting of 27 images which contain a total of 989 tubules. Experiments show that the detection results of our algorithm are very close to the results obtained manually and the novel approach can achieve a better performance than two existing methods.

  • 383.
    Su, Ran
    et al.
    The University of New South Wales, Canberra, ACT 2600, Australia/ North Ryde, NSW 1670, Australia.
    Sun, Changming
    Informatics and Statistics, North Ryde, NSW 1670, Australia.
    Pham, Tuan D
    The University of Aizu, Aizu-Wakamatsu, Fukushima 965-8580, Japan.
    Junction detection for linear structures based on Hessian, correlation and shape information2012Ingår i: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 45, nr 10, s. 3695-3706Artikel i tidskrift (Refereegranskat)
    Abstract [be]

    Junctions have been demonstrated to be important features in many visual tasks such as image registration, matching, and segmentation, as they can provide reliable local information. This paper presents a method for detecting junctions in 2D images with linear structures as well as providing the number of branches and branch orientations. The candidate junction points are selected through a new measurement which combines Hessian information and correlation matrix. Then the locations of the junction centers are refined and the branches of the junctions are found using the intensity information of a stick-shaped window at a number of orientations and the correlation value between the intensity of a local region and a Gaussian-shaped multi-scale stick template. The multi-scale template is used here to detect the structures with various widths. We present the results of our algorithm on images of different types and compare our algorithm with three other methods. The results have shown that the proposed approach can detect junctions more accurately.

  • 384.
    Sumiya, Runa
    et al.
    Chuo Univ, Japan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Chao, Jinhui
    Chuo Univ, Japan.
    Measurement of JND Thresholds and Riemannian Geometry in Facial Expression Space2018Ingår i: HUMAN-COMPUTER INTERACTION: THEORIES, METHODS, AND HUMAN ISSUES, HCI INTERNATIONAL 2018, PT I, SPRINGER INTERNATIONAL PUBLISHING AG , 2018, Vol. 10901, s. 453-464Konferensbidrag (Refereegranskat)
    Abstract [en]

    Currently the most popular approach to facial expression analysis uses categorical representations of expressions based on labels like sad, happy and angry. Subtle expression variations require however a quantitative and continuous representation. Besides, todays subjective expression spaces, built by semantic differential level scores and reduced to low dimensional continuous spaces using MDS or PCA have no direct correspondence with the physical stimuli or the expression images. On the other hand, the spaces used in engineering are based on purely physical stimuli or images which can hardly be called expression spaces. Even in models incorporating spacial structure, the geometry of the expression space received little attention and is usually assumed to be Euclidean. The aim of this paper is to build an expression space which is directly connected with the physical stimuli or the expression images. At the same time, it has to incorporate the subjective characteristics of expression perception. We use methods from psychophysics to build an expression space based on the physical stimuli or expression image space equipped with JND or discrimination threshold data. The construction follows the approach used in color science where the MacAdam ellipsoids provide for every color a metric tensor in a Riemannian space. We show that the discrimination thresholds indicate that the space is not Non- Euclidean. We will also illustrate the intrinsic geometrical structure of the expression spaces for several observers obtained from two large image databases of face expressions.

  • 385.
    Svensk, Joakim
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Evaluation of Aerial Image Stereo Matching Methods for Forest Variable Estimation2017Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    This work investigates the landscape of aerial image stereo matching (AISM) methods suitable for large scale forest variable estimation. AISM methods are an important source of remotely collected information used in modern forestry to keep track of a growing forest's condition.

    A total of 17 AISM methods are investigated, out of which 4 are evaluated by processing a test data set consisting of three aerial images. The test area is located in southern Sweden, consisting of mainly Norway Spruce and Scots Pine. From the resulting point clouds and height raster images, a total of 30 different metrics of both height and density types are derived. Linear regression is used to fit functions from metrics derived from AISM data to a set of forest variables including tree height (HBW), tree diameter (DBW), basal area, volume. As ground truth, data collected by dense airborne laser scanning is used. Results are presented as RMSE and standard deviation concluded from the linear regression.

    For tree height, tree diameter, basal area, volume the RMSE ranged from 7.442% to 10.11%, 11.58% to 13.96%, 32.01% to 35.10% and 34.01% to 38.26% respectively. The results concluded that all four tested methods achieved comparable estimation quality although showing small differences among them. Keystone and SURE performed somewhat better while MicMac placed third and Photoscan achieved the less accurate result.

  • 386.
    Svensson, Fredrik
    Linköpings universitet, Institutionen för systemteknik, Bildbehandling.
    Structure from Forward Motion2010Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    I detta examensarbete undersöks svårigheterna kring att skapa en djupbild från att endast använda en lågupplöst gråskalekamera monterad framtill i en bil. Målet är att producera en djupbild i realtid som kan nyttjas i andra delar av bilens säkerhetssystem. Detta har visat sig vara svårt att lösa med den undersökta kombinationen av kameraplacering och val av algoritmer.

    Det huvudsakliga problemet är att räkna ut ett noggrant optiskt flöde. Andra problem härrör från objekt som rör på sig. Slutsatsen är att implementationerna, mestadels triangulering av korresponderande punktpar som följts med hjälp av en Lucas Kanade-följare, ger resultat av för dålig kvalitet för att vara till nytta för bilens säkerhetssystem.

  • 387.
    Svensson, Martin
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Accelerated Volumetric Next-Best-View Planning in 3D Mapping2014Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    The Next-Best-View (NBV) problem plays an important part in automatic 3D object reconstruction and exploration applications. This thesis presents a novel approach of ray-casting in Occupancy Grid Maps (OGM) in the context of solving the NBV problem in a 3D-exploration setting. The proposed approach utilizes the structure of an octree-based OGM to perform calculations of potential information gain. The computations are significantly faster than current methods, without decreasing mapping quality. Performance, both in terms of mapping quality, coverage and computational complexity, is experimentally verified through a comparison with existing state-of-the-art methods using high-resolution point cloud data generated using time-of-flight laser range scanners.

    Current methods for viewpoint ranking focus either heavily on mapping performance or computation speed. The results presented in this thesis indicate that the proposed method is able to achieve a mapping performance similar to the performance-oriented approaches while maintaining the same low computation speed as more approximative methods.

  • 388.
    Sällqvist, Jessica
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Real-time 3D Semantic Segmentation of Timber Loads with Convolutional Neural Networks2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Volume measurements of timber loads is done in conjunction with timber trade. When dealing with goods of major economic values such as these, it is important to achieve an impartial and fair assessment when determining price-based volumes.

    With the help of Saab’s missile targeting technology, CIND AB develops products for digital volume measurement of timber loads. Currently there is a system in operation that automatically reconstructs timber trucks in motion to create measurable images of them. Future iterations of the system is expected to fully automate the scaling by generating a volumetric representation of the timber and calculate its external gross volume. The first challenge towards this development is to separate the timber load from the truck.

    This thesis aims to evaluate and implement appropriate method for semantic pixel-wise segmentation of timber loads in real time. Image segmentation is a classic but difficult problem in computer vision. To achieve greater robustness, it is therefore important to carefully study and make use of the conditions given by the existing system. Variations in timber type, truck type and packing together create unique combinations that the system must be able to handle. The system must work around the clock in different weather conditions while maintaining high precision and performance.

  • 389.
    Söderroos, Anna
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Fisheye Camera Calibration and Image Stitching for Automotive Applications2015Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Integrated camera systems for increasing safety and maneuverability are becoming increasingly common for heavy vehicles. One problem with heavy vehicles today is that there are blind spots where the driver has no or very little view. There is a great demand on increasing the safety and helping the driver to get a better view of his surroundings. This can be achieved by a sophisticated camera system, using cameras with wide field of view, that could cover dangerous blind spots.

    This master thesis aims to investigate and develop a prototype solution for a camera system consisting of two fisheye cameras. The solution covers both hardware choices and software development including camera calibration and image stitching. Two different fisheye camera calibration toolboxes are compared and their results discussed, with the aim to find the most suitable for this application. The result from the two toolboxes differ in performance, and the result from only one of the toolboxes is sufficient for image stitching. 

  • 390.
    Söderström, Rikard
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    An early fire detection system through registration and analysis of waste station IR-images2011Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    I denna uppsats görs en undersökning av sätt att urskilja mellan bränder och fordon vid avfallsbunkrar, i hopp om att ta bortfordon som felkälla under tidig branddetektion. Dagens system använder sig av en värmekamera som roterar i 48 vinklar(även kallade zoner) från en fix position och larmar då det blir för varmt i någon zon.Roteringen av kameran medför en icke önskvärd förskjutning mellan två efterföljande bilder inom samma zon. Processenbildregistrering används för att eliminera denna förskjutning. Efter registreringen utförs en segmentering där kalla objekt tasbort som felkälla. När detta är utfört görs en analys av de varma objekten med en mängd mätningar.I slutet bevisas att registreringen har fungerat mycket väl, likaså att det går till viss del att eliminera fordon som felkällaunder tidig brandetektion.

  • 391.
    Sörsäter, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Active Learning for Road Segmentation using Convolutional Neural Networks2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    In recent years, development of Convolutional Neural Networks has enabled high performing semantic segmentation models. Generally, these deep learning based segmentation methods require a large amount of annotated data. Acquiring such annotated data for semantic segmentation is a tedious and expensive task.

    Within machine learning, active learning involves in the selection of new data in order to limit the usage of annotated data. In active learning, the model is trained for several iterations and additional samples are selected that the model is uncertain of. The model is then retrained on additional samples and the process is repeated again. In this thesis, an active learning framework has been applied to road segmentation which is semantic segmentation of objects related to road scenes.

    The uncertainty in the samples is estimated with Monte Carlo dropout. In Monte Carlo dropout, several dropout masks are applied to the model and the variance is captured, working as an estimate of the model’s uncertainty. Other metrics to rank the uncertainty evaluated in this work are: a baseline method that selects samples randomly, the entropy in the default predictions and three additional variations/extensions of Monte Carlo dropout.

    Both the active learning framework and uncertainty estimation are implemented in the thesis. Monte Carlo dropout performs slightly better than the baseline in 3 out of 4 metrics. Entropy outperforms all other implemented methods in all metrics. The three additional methods do not perform better than Monte Carlo dropout.

    An analysis of what kind of uncertainty Monte Carlo dropout capture is performed together with a comparison of the samples selected by baseline and Monte Carlo dropout. Future development and possible improvements are also discussed.

  • 392.
    Tan Nguyen, Khoa
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Ynnerman, Anders
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Ropinski, Timo
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska högskolan.
    Analyzing and Reducing DTI Tracking Uncertainty by Combining Deterministic and Stochastic Approaches2013Ingår i: Advances in Visual Computing: 9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part I / [ed] Bebis, G.; Boyle, R.; Parvin, B.; Koracin, D.; Li, B.; Porikli, F.; Zordan, V.; Klosowski, J.; Coquillart, S.; Luo, X.; Chen, M.; Gotz, D., Springer Berlin/Heidelberg, 2013, s. 266-279Konferensbidrag (Refereegranskat)
    Abstract [en]

    Diffusion Tensor Imaging (DTI) in combination with fiber tracking algorithms enables visualization and characterization of white matter structures in the brain. However, the low spatial resolution associated with the inherently low signal-to-noise ratio of DTI has raised concerns regarding the reliability of the obtained fiber bundles. Therefore, recent advancements in fiber tracking algorithms address the accuracy of the reconstructed fibers. In this paper, we propose a novel approach for analyzing and reducing the uncertainty of densely sampled 3D DTI fibers in biological specimens. To achieve this goal, we derive the uncertainty in the reconstructed fiber tracts using different deterministic and stochastic fiber tracking algorithms. Through a unified representation of the derived uncertainty, we generate a new set of reconstructed fiber tracts that has a lower level of uncertainty. We will discuss our approach in detail and present the results we could achieve when applying it to several use cases.

  • 393.
    Tan, Xiao
    et al.
    Department of Computer Science, University of Hong Kong, Hong Kong.
    Sun, Changming
    CSIRO Digital Productivity, Sydney, NSW, Australia.
    Pham, Tuan
    Linköpings universitet, Institutionen för medicinsk teknik. Linköpings universitet, Tekniska fakulteten.
    Edge-aware filtering with local polynomial approximation and rectangle based weighting2016Ingår i: IEEE Transactions on Cybernetics, ISSN 2168-2267, E-ISSN 2168-2275, Vol. 46, nr 12, s. 2693-2705Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper presents a novel method for performing guided image filtering using local polynomial approximation (LPA) with range guidance. In our method, the LPA is introduced into a multipoint framework for reliable model regression and better preservation on image spatial variation which usually contains the essential information in the input image. In addition, we develop a weighting scheme which has the spatial flexibility during the filtering process. All components in our method are efficiently implemented and a constant computation complexity is achieved. Compared with conventional filtering methods, our method provides clearer boundaries and performs especially better in recovering spatial variation from noisy images. We conduct a number of experiments for different applications: depth image upsampling, joint image denoising, details enhancement, and image abstraction. Both quantitative and qualitative comparisons demonstrate that our method outperforms state-of-the-art methods.

  • 394.
    Tan, Xiao
    et al.
    The University of New South Wales, Canberra, ACT 2600, Australia; CSIRO Computational Informatics, Locked Bag 17, North Ryde, NSW 1670, Australia.
    Sun, Changming
    CSIRO Computational Informatics, Locked Bag 17, North Ryde, NSW 1670, Australia.
    Sirault, Xavier
    CSIRO Agriculture Flagship, Clunies Ross Street, Canberra, ACT 2601, Australia.
    Furbank, Robert
    CSIRO Agriculture Flagship, Clunies Ross Street, Canberra, ACT 2601, Australia.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, The University of Aizu, Fukushima 965-8580, Japan.
    Feature matching in stereo images encouraging uniform spatial distribution2015Ingår i: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 48, nr 8, s. 2530-2542Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Finding feature correspondences between a pair of stereo images is a key step in computer vision for 3D reconstruction and object recognition. In practice, a larger number of correct correspondences and a higher percentage of correct matches are beneficial. Previous researches show that the spatial distribution of correspondences are also very important especially for fundamental matrix estimation. So far, no existing feature matching method considers the spatial distribution of correspondences. In our research, we develop a new algorithm to find good correspondences in all the three aspects mentioned, i.e., larger number of correspondences, higher percentage of correct correspondences, and better spatial distribution of correspondences. Our method consists of two processes: an adaptive disparity smoothing filter to remove false correspondences based on the disparities of neighboring correspondences and a matching exploration algorithm to find more correspondences according to the spatial distribution of correspondences so that the correspondences are as uniformly distributed as possible in the images. To find correspondences correctly and efficiently, we incorporate the cheirality constraint under an epipole polar transformation together with the epipolar constraint to predict the potential location of matching point. Experiments demonstrate that our method performs very well on both the number of correct correspondences and the percentage of correct correspondences; and the obtained correspondences are also well distributed over the image space.

  • 395.
    Tan, Xiao
    et al.
    The University of Hong Kong, Pokfulam, Hong Kong.
    Sun, Changming
    CSIRO Computational Informatics, North Ryde, NSW, Australia.
    Wong, Kwan-YeeK.
    The University of Hong Kong, Pokfulam, Hong Kong.
    Pham, Tuan
    Aizu Research Cluster for Medical Engineering and Informatics, The University of Aizu, Fukushima, Japan.
    Guided image completion by confidence propagation2016Ingår i: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 50, s. 210-222Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper presents a new guided image completion method which fills any missing values by considering information from a guidance image. We develop a confidence propagation scheme that allows the filling process to be carried out simultaneously without the need of deciding the filling order. We conduct experiments in several applications where the problem can be formulated into a guided image completion problem, such as interactive segmentation and colorization. The experimental results show that our method provides good results and succeeds in situations where conventional methods fail. In addition, as all building blocks are parallel processes, our method is much suitable for hardware acceleration.

  • 396.
    Tasaki, Hajime
    et al.
    Chuo University, Japan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten.
    Chao, Jinhui
    Chuo University, Japan.
    Simplex-Based Dimension Estimation of Topological Manifolds2016Ingår i: 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), IEEE COMPUTER SOC , 2016, s. 3609-3614Konferensbidrag (Refereegranskat)
    Abstract [en]

    Dimension reduction is one of the most important issues in machine learning and computational intelligence. Typical data sets are point clouds in a high dimensional space with a hidden structure to be found in low dimensional submanifolds. Finding this intrinsic manifold structure is very important in the understanding of the data and for reducing computational complexity. In this paper, we propose a novel approach for dimension estimation of topological manifolds based on measures of simplices. We also investigate the effects of resolution changes for dimension estimation in the framework of Morse theory. The result is a method that can be used for data located in simplical complexes of varying dimensions and with no continuous or differentiable structure. The proposed method is applied to images of handwritten digits with known deforming dimensions, data with a nontrivial topology and noisy data. We compare the estimates with results obtain by local PCA.

  • 397.
    Thomasson, Viola
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Liver Tumor Segmentation Using Level Sets and Region Growing2011Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Medical imaging is an important tool for diagnosis and treatment planning today. However as the demand for efficiency increases at the same time as the data volumes grow immensely, the need for computer assisted analysis, such as image segmentation, to help and guide the practitioner increases.

    Medical image segmentation could be used for various different tasks, the localization and delineation of pathologies such as cancer tumors is just one example. Numerous problems with noise and image artifacts in the generated images make the segmentation a difficult task, and the developer is forced to choose between speed and performance. In clinical practise, however, this is impossible as both speed and performance are crucial. One solution to this problem might be to involve the user more in the segmentation, using interactivite algorithms where the user might influence the segmentation for an improved result.

    This thesis has concentrated on finding a fast and interactive segmentation method for liver tumor segmentation. Various different methods were explored, and a few were chosen for implementation and further development. Two methods appeared to be the most promising, Bayesian Region Growing (BRG) and Level Set.

    An interactive Level Set algorithm emerged as the best alternative for the interactivity of the algorithm, and could be used in combination with both BRG and Level Set. A new data term based on a probability model instead of image edges was also explored for the Level Set-method, and proved to be more promising than the original one. The probability based Level Set and the BRG method both provided good quality results, but the fastest of the two was the BRG-method, which could segment a tumor present in 25 CT image slices in less than 10 seconds when implemented in Matlab and mex-C++ code on an ACPI x64-based PC with two 2.4 GHz Intel(R) Core(TM) 2CPU and 8 GB RAM memory. The interactive Level Set could be succesfully used as an interactive addition to the automatic method, but its usefulness was somewhat reduced by its slow processing time ( 1.5 s/slice) and the relative complexity of the needed user interactions.

  • 398.
    Thulin, Oskar
    Linköpings universitet, Institutionen för systemteknik.
    Intermediate View Interpolation of Stereoscopic Images for 3D-Display2006Självständigt arbete på grundnivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats
    Abstract [en]

    This thesis investigates how disparity estimation may be used to visualize an object on a 3D-screen. The first part looks into different methods of disparity estimation, and the second part examines different ways to visualize an object from one or several stereo pairs and a disparity map. Input to the system is one or several stereo pairs, and output is a sequence of images of the input scene but from more angles. This sequence of images can be shown on Setred AB's 3D-screen. The system has high real time demands and the goal is to do the disparity estimation and visualization in real time.

    In the first part of the thesis, three different ways to calculate disparity maps are implemented and compared. The three methods are correlation-based, local structure-based and phase-based techniques. The correlation-based methods cannot satisfy the real-time demands due to the large number of 2D-convolutions required per pixel. The local structure-based methods have too much noise and cannot satisfy the quality requirements. Therefore, the best method by far is the phase-based method. This method has been implemented in Matlab and C and comparisons between the different implementations are presented.

    The quality of the disparity maps is satisfying, but the real-time demands cannot yet be fulfilled. The future work is therefore to optimize the C code and move some functions to a GPU, because a GPU can perform calculations in parallel with the CPU. Another reason is that many of the calculations are related to resizing and warping, which are well-suited to implementation on a GPU.

  • 399.
    Thulin, Peter
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Anomaly Detection for Product Inspection and Surveillance Applications2015Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Anomaly detection is a general theory of detecting unusual patterns or events in data. This master thesis investigates the subject of anomaly detection in two different applications. The first application is product inspection using a camera and the second application is surveillance using a 2D laser scanner.

    The first part of the thesis presents a system for automatic visual defect inspection. The system is based on aligning the images of the product to a common template and doing pixel-wise comparisons. The system is trained using only images of products that are defined as normal, i.e. non-defective products. The visual properties of the inspected products are modelled using three different methods. The performance of the system and the different methods have been evaluated on four different datasets.

    The second part of the thesis presents a surveillance system based on a single laser range scanner. The system is able to detect certain anomalous events based on the time, position and velocities of individual objects in the scene. The practical usefulness of the system is made plausible by a qualitative evaluation using unlabelled data.

  • 400.
    Tiger, Mattias
    et al.
    Linköpings universitet, Institutionen för datavetenskap, Artificiell intelligens och integrerade datorsystem. Linköpings universitet, Tekniska fakulteten.
    Heintz, Fredrik
    Linköpings universitet, Institutionen för datavetenskap, Artificiell intelligens och integrerade datorsystem. Linköpings universitet, Tekniska fakulteten.
    Gaussian Process Based Motion Pattern Recognition with Sequential Local Models2018Ingår i: 2018 IEEE Intelligent Vehicles Symposium (IV), 2018Konferensbidrag (Refereegranskat)
    Abstract [en]

    Conventional trajectory-based vehicular traffic analysis approaches work well in simple environments such as a single crossing but they do not scale to more structurally complex environments such as networks of interconnected crossings (e.g. urban road networks). Local trajectory models are necessary to cope with the multi-modality of such structures, which in turn introduces new challenges. These larger and more complex environments increase the occurrences of non-consistent lack of motion and self-overlaps in observed trajectories which impose further challenges. In this paper we consider the problem of motion pattern recognition in the setting of sequential local motion pattern models. That is, classifying sub-trajectories from observed trajectories in accordance with which motion pattern that best explains it. We introduce a Gaussian process (GP) based modeling approach which outperforms the state-of-the-art GP based motion pattern approaches at this task. We investigate the impact of varying local model overlap and the length of the observed trajectory trace on the classification quality. We further show that introducing a pre-processing step filtering out stops from the training data significantly improves the classification performance. The approach is evaluated using real GPS position data from city buses driving in urban areas for extended periods of time.

5678910 351 - 400 av 481
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf