liu.seSearch for publications in DiVA
Change search
Refine search result
1 - 17 of 17
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • 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.
    Bjuremark, Anna
    et al.
    Linköping University, Department of Behavioural Sciences and Learning. Linköping University, Faculty of Arts and Sciences.
    Hedborg, Johan
    Linköping University, Department of Electrical Engineering. Linköping University, The Institute of Technology.
    Musk, Nigel John
    Linköping University, Department of Culture and Communication. Linköping University, Faculty of Arts and Sciences.
    Tjernström, Eva
    Linköping University, Faculty of Arts and Sciences.
    Hemtenta, salstenta, muntlig tenta, inlämningsuppgifter, portfolio: Variation på temat examination2008Report (Other academic)
    Abstract [sv]

    Enligt de dokumentatörer som deltog i samtalen hade de allra flesta egna erfarenheter av hemtentor. En hemtentamen definierades som att studenten utförde sin examination i hemmet med tillgång till olika typer av källmateri-al, som kurs- och annan litteratur samt med hjälp av tidskrifter och journaler via internet. Ett vanligt förhållande tycktes vara att en tentamen var begrän-sad till 1-2 veckor, vilket skiljde sig från lärarprogrammets terminsvisa tentor. I de allra flesta fall offentliggjordes hemtentan ett visst klockslag via nätet, ofta med hjälp av lärplattformar som It’s Learning. Oavsett den tid som stu-denterna hade till förfogande betonades vikten av att sätta tydliga tidsramar och att man som lärare följde efterlevnaden av dessa ramar.

  • 2.
    Ellis, Liam
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Pugeault, Nicolas
    CVSSP, University of Surrey, Guildford, UK.
    Öfjäll, Kristoffer
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Hedborg, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Bowden, Richard
    CVSSP, University of Surrey, Guildford, UK.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Autonomous Navigation and Sign Detector Learning2013In: IEEE Workshop on Robot Vision(WORV) 2013, IEEE , 2013, p. 144-151Conference paper (Refereed)
    Abstract [en]

    This paper presents an autonomous robotic system that incorporates novel Computer Vision, Machine Learning and Data Mining algorithms in order to learn to navigate and discover important visual entities. This is achieved within a Learning from Demonstration (LfD) framework, where policies are derived from example state-to-action mappings. For autonomous navigation, a mapping is learnt from holistic image features (GIST) onto control parameters using Random Forest regression. Additionally, visual entities (road signs e.g. STOP sign) that are strongly associated to autonomously discovered modes of action (e.g. stopping behaviour) are discovered through a novel Percept-Action Mining methodology. The resulting sign detector is learnt without any supervision (no image labeling or bounding box annotations are used). The complete system is demonstrated on a fully autonomous robotic platform, featuring a single camera mounted on a standard remote control car. The robot carries a PC laptop, that performs all the processing on board and in real-time.

  • 3.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Hedborg, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Real-Time View-Based Pose Recognition and Interpolation for Tracking Initialization2007In: Journal of Real-Time Image Processing, ISSN 1861-8200, E-ISSN 1861-8219, Journal of real-time image processing, ISSN 1861-8200, Vol. 2, no 2-3, p. 103-115Article in journal (Refereed)
    Abstract [en]

    In this paper we propose a new approach to real-time view-based pose recognition and interpolation. Pose recognition is particularly useful for identifying camera views in databases, video sequences, video streams, and live recordings. All of these applications require a fast pose recognition process, in many cases video real-time. It should further be possible to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions such as clutter and occlusion. The recognition algorithm consists of three steps: (1) low-level image features for color and local orientation are extracted in each point of the image; (2) these features are encoded into P-channels by combining similar features within local image regions; (3) the query P-channels are compared to a set of prototype P-channels in a database using a least-squares approach. The algorithm is applied in two scene registration experiments with fisheye camera data, one for pose interpolation from synthetic images and one for finding the nearest view in a set of real images. The method compares favorable to SIFT-based methods, in particular concerning interpolation. The method can be used for initializing pose-tracking systems, either when starting the tracking or when the tracking has failed and the system needs to re-initialize. Due to its real-time performance, the method can also be embedded directly into the tracking system, allowing a sensor fusion unit choosing dynamically between the frame-by-frame tracking and the pose recognition.

  • 4.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Hedborg, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Real-Time Visual Recognition of Objects and Scenes Using P-Channel Matching2007In: Proceedings 15th Scandinavian Conference on Image Analysis / [ed] Bjarne K. Ersboll and Kim S. Pedersen, Berlin, Heidelberg: Springer, 2007, Vol. 4522, p. 908-917Conference paper (Refereed)
    Abstract [en]

    In this paper we propose a new approach to real-time view-based object recognition and scene registration. Object recognition is an important sub-task in many applications, as e.g., robotics, retrieval, and surveillance. Scene registration is particularly useful for identifying camera views in databases or video sequences. All of these applications require a fast recognition process and the possibility to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions as clutter and occlusion. The recognition algorithm extracts a number of basic, intensity invariant image features, encodes them into P-channels, and compares the query P-channels to a set of prototype P-channels in a database. The algorithm is applied in a cross-validation experiment on the COIL database, resulting in nearly ideal ROC curves. Furthermore, results from scene registration with a fish-eye camera are presented.

  • 5.
    Hedborg, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Motion and Structure Estimation From Video2012Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    Digital camera equipped cell phones were introduced in Japan in 2001, they quickly became popular and by 2003 outsold the entire stand-alone digital camera market. In 2010 sales passed one billion units and the market is still growing. Another trend is the rising popularity of smartphones which has led to a rapid development of the processing power on a phone, and many units sold today bear close resemblance to a personal computer. The combination of a powerful processor and a camera which is easily carried in your pocket, opens up a large eld of interesting computer vision applications.

    The core contribution of this thesis is the development of methods that allow an imaging device such as the cell phone camera to estimates its own motion and to capture the observed scene structure. One of the main focuses of this thesis is real-time performance, where a real-time constraint does not only result in shorter processing times, but also allows for user interaction.

    In computer vision, structure from motion refers to the process of estimating camera motion and 3D structure by exploring the motion in the image plane caused by the moving camera. This thesis presents several methods for estimating camera motion. Given the assumption that a set of images has known camera poses associated to them, we train a system to solve the camera pose very fast for a new image. For the cases where no a priory information is available a fast minimal case solver is developed. The solver uses ve points in two camera views to estimate the cameras relative position and orientation. This type of minimal case solver is usually used within a RANSAC framework. In order to increase accuracy and performance a renement to the random sampling strategy of RANSAC is proposed. It is shown that the new scheme doubles the performance for the ve point solver used on video data. For larger systems of cameras a new Bundle Adjustment method is developed which are able to handle video from cell phones.

    Demands for reduction in size, power consumption and price has led to a redesign of the image sensor. As a consequence the sensors have changed from a global shutter to a rolling shutter, where a rolling shutter image is acquired row by row. Classical structure from motion methods are modeled on the assumption of a global shutter and a rolling shutter can severely degrade their performance. One of the main contributions of this thesis is a new Bundle Adjustment method for cameras with a rolling shutter. The method accurately models the camera motion during image exposure with an interpolation scheme for both position and orientation.

    The developed methods are not restricted to cellphones only, but is rather applicable to any type of mobile platform that is equipped with cameras, such as a autonomous car or a robot. The domestic robot comes in many  avors, everything from vacuum cleaners to service and pet robots. A robot equipped with a camera that is capable of estimating its own motion while sensing its environment, like the human eye, can provide an eective means of navigation for the robot. Many of the presented methods are well suited of robots, where low latency and real-time constraints are crucial in order to allow them to interact with their environment.

    List of papers
    1. Real-Time View-Based Pose Recognition and Interpolation for Tracking Initialization
    Open this publication in new window or tab >>Real-Time View-Based Pose Recognition and Interpolation for Tracking Initialization
    2007 (English)In: Journal of Real-Time Image Processing, ISSN 1861-8200, E-ISSN 1861-8219, Journal of real-time image processing, ISSN 1861-8200, Vol. 2, no 2-3, p. 103-115Article in journal (Refereed) Published
    Abstract [en]

    In this paper we propose a new approach to real-time view-based pose recognition and interpolation. Pose recognition is particularly useful for identifying camera views in databases, video sequences, video streams, and live recordings. All of these applications require a fast pose recognition process, in many cases video real-time. It should further be possible to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions such as clutter and occlusion. The recognition algorithm consists of three steps: (1) low-level image features for color and local orientation are extracted in each point of the image; (2) these features are encoded into P-channels by combining similar features within local image regions; (3) the query P-channels are compared to a set of prototype P-channels in a database using a least-squares approach. The algorithm is applied in two scene registration experiments with fisheye camera data, one for pose interpolation from synthetic images and one for finding the nearest view in a set of real images. The method compares favorable to SIFT-based methods, in particular concerning interpolation. The method can be used for initializing pose-tracking systems, either when starting the tracking or when the tracking has failed and the system needs to re-initialize. Due to its real-time performance, the method can also be embedded directly into the tracking system, allowing a sensor fusion unit choosing dynamically between the frame-by-frame tracking and the pose recognition.

    Keywords
    computer vision
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-39505 (URN)10.1007/s11554-007-0044-y (DOI)49062 (Local ID)49062 (Archive number)49062 (OAI)
    Note
    Original Publication: Michael Felsberg and Johan Hedborg, Real-Time View-Based Pose Recognition and Interpolation for Tracking Initialization, 2007, Journal of real-time image processing, (2), 2-3, 103-115. http://dx.doi.org/10.1007/s11554-007-0044-y Copyright: Springer Science Business MediaAvailable from: 2009-10-10 Created: 2009-10-10 Last updated: 2017-12-13Bibliographically approved
    2. KLT Tracking Implementation on the GPU
    Open this publication in new window or tab >>KLT Tracking Implementation on the GPU
    2007 (English)In: Proceedings SSBA 2007 / [ed] Magnus Borga, Anders Brun and Michael Felsberg;, 2007Conference paper, Oral presentation only (Other academic)
    Abstract [en]

    The GPU is the main processing unit on a graphics card. A modern GPU typically provides more than ten times the computational power of an ordinary PC processor. This is a result of the high demands for speed and image quality in computer games. This paper investigates the possibility of exploiting this computational power for tracking points in image sequences. Tracking points is used in many computer vision tasks, such as tracking moving objects, structure from motion, face tracking etc. The algorithm was successfully implemented on the GPU and a large speed up was achieved.

    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-21602 (URN)
    Conference
    SSBA, Swedish Symposium in Image Analysis 2007, 14-15 March, Linköping, Sweden
    Available from: 2009-10-05 Created: 2009-10-05 Last updated: 2016-05-04
    3. Fast and Accurate Structure and Motion Estimation
    Open this publication in new window or tab >>Fast and Accurate Structure and Motion Estimation
    2009 (English)In: International Symposium on Visual Computing / [ed] George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin, Yoshinori Kuno, Junxian Wang, Jun-Xuan Wang, Junxian Wang, Renato Pajarola and Peter Lindstrom et al., Berlin Heidelberg: Springer-Verlag , 2009, p. 211-222Conference paper, Oral presentation only (Refereed)
    Abstract [en]

    This paper describes a system for structure-and-motion estimation for real-time navigation and obstacle avoidance. We demonstrate it technique to increase the efficiency of the 5-point solution to the relative pose problem. This is achieved by a novel sampling scheme, where We add a distance constraint on the sampled points inside the RANSAC loop. before calculating the 5-point solution. Our setup uses the KLT tracker to establish point correspondences across tone in live video We also demonstrate how an early outlier rejection in the tracker improves performance in scenes with plenty of occlusions. This outlier rejection scheme is well Slated to implementation on graphics hardware. We evaluate the proposed algorithms using real camera sequences with fine-tuned bundle adjusted data as ground truth. To strenghten oar results we also evaluate using sequences generated by a state-of-the-art rendering software. On average we are able to reduce the number of RANSAC iterations by half and thereby double the speed.

    Place, publisher, year, edition, pages
    Berlin Heidelberg: Springer-Verlag, 2009
    Series
    Lecture Notes in Computer Science, ISSN 0302-9743 ; Volume 5875
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-50624 (URN)10.1007/978-3-642-10331-5_20 (DOI)000278937300020 ()
    Conference
    5th International Symposium, ISVC 2009, November 30 - December 2, Las Vegas, NV, USA
    Projects
    DIPLECS
    Available from: 2009-10-13 Created: 2009-10-13 Last updated: 2016-05-04Bibliographically approved
    4. Fast Iterative Five point Relative Pose Estimation
    Open this publication in new window or tab >>Fast Iterative Five point Relative Pose Estimation
    (English)Manuscript (preprint) (Other academic)
    Abstract [en]

    Robust estimation of the relative pose between two cameras is a fundamental part of Structure and Motion methods. For calibrated cameras, the five point method together with a robust estimator such as RANSAC gives the best result in most cases. The current state-of-the-art method for solving the relative pose problem from five points is due to Nist´er [1], because it is faster than other methods and in the RANSAC scheme one can improve precision by increasing the number of iterations.

    In this paper, we propose a new iterative method, which is based on Powell’s Dog Leg algorithm. The new method has the same precision and is approximately twice as fast as Nist´er’s algorithm. The proposed algorithm is systematically evaluated on two types of datasets with known ground truth.

    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-76902 (URN)
    Available from: 2012-04-24 Created: 2012-04-24 Last updated: 2016-05-04Bibliographically approved
    5. Structure and Motion Estimation from Rolling Shutter Video
    Open this publication in new window or tab >>Structure and Motion Estimation from Rolling Shutter Video
    2011 (English)In: IEEE International Conference onComputer Vision Workshops (ICCV Workshops), 2011, IEEE Xplore , 2011, p. 17-23Conference paper, Published paper (Refereed)
    Abstract [en]

    The majority of consumer quality cameras sold today have CMOS sensors with rolling shutters. In a rolling shutter camera, images are read out row by row, and thus each row is exposed during a different time interval. A rolling-shutter exposure causes geometric image distortions when either the camera or the scene is moving, and this causes state-of-the-art structure and motion algorithms to fail. We demonstrate a novel method for solving the structure and motion problem for rolling-shutter video. The method relies on exploiting the continuity of the camera motion, both between frames, and across a frame. We demonstrate the effectiveness of our method by controlled experiments on real video sequences. We show, both visually and quantitatively, that our method outperforms standard structure and motion, and is more accurate and efficient than a two-step approach, doing image rectification and structure and motion.

    Place, publisher, year, edition, pages
    IEEE Xplore, 2011
    Keywords
    Structure and Motion, Rolling Shutter, Bundel Adjustment
    National Category
    Computer Vision and Robotics (Autonomous Systems)
    Identifiers
    urn:nbn:se:liu:diva-75258 (URN)10.1109/ICCVW.2011.6130217 (DOI)978-1-4673-0062-9 (ISBN)
    Conference
    2nd IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2011,6-13 November,Barcelona, Spain
    Available from: 2012-03-01 Created: 2012-02-23 Last updated: 2018-01-12Bibliographically approved
    6. Rolling Shutter Bundle Adjustment
    Open this publication in new window or tab >>Rolling Shutter Bundle Adjustment
    2012 (English)Conference paper, Published paper (Refereed)
    Abstract [en]

    This paper introduces a bundle adjustment (BA) method that obtains accurate structure and motion from rolling shutter (RS) video sequences: RSBA. When a classical BA algorithm processes a rolling shutter video, the resultant camera trajectory is brittle, and complete failures are not uncommon. We exploit the temporal continuity of the camera motion to define residuals of image point trajectories with respect to the camera trajectory. We compare the camera trajectories from RSBA to those from classical BA, and from classical BA on rectified videos. The comparisons are done on real video sequences from an iPhone 4, with ground truth obtained from a global shutter camera, rigidly mounted to the iPhone 4. Compared to classical BA, the rolling shutter model requires just six extra parameters. It also degrades the sparsity of the system Jacobian slightly, but as we demonstrate, the increase in computation time is moderate. Decisive advantages are that RSBA succeeds in cases where competing methods diverge, and consistently produces more accurate results.

    Place, publisher, year, edition, pages
    IEEE Computer Society; 1999, 2012
    Series
    Computer Vision and Pattern Recognition, ISSN 1063-6919
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-76903 (URN)10.1109/CVPR.2012.6247831 (DOI)000309166201074 ()978-1-4673-1227-1 (ISBN)
    Conference
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012
    Projects
    VPS
    Available from: 2012-04-24 Created: 2012-04-24 Last updated: 2017-06-01Bibliographically approved
  • 6.
    Hedborg, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Pose Estimation and Structure Analysisof Image Sequences2009Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    Autonomous navigation for ground vehicles has many challenges. Autonomous systems must be able to self-localise, avoid obstacles and determine navigable surfaces. This thesis studies several aspects of autonomous navigation with a particular emphasis on vision, motivated by it being a primary component for navigation in many high-level biological organisms.  The key problem of self-localisation or pose estimation can be solved through analysis of the changes in appearance of rigid objects observed from different view points. We therefore describe a system for structure and motion estimation for real-time navigation and obstacle avoidance. With the explicit assumption of a calibrated camera, we have studied several schemes for increasing accuracy and speed of the estimation.The basis of most structure and motion pose estimation algorithms is a good point tracker. However point tracking is computationally expensive and can occupy a large portion of the CPU resources. In thisthesis we show how a point tracker can be implemented efficiently on the graphics processor, which results in faster tracking of points and the CPU being available to carry out additional processing tasks.In addition we propose a novel view interpolation approach, that can be used effectively for pose estimation given previously seen views. In this way, a vehicle will be able to estimate its location by interpolating previously seen data.Navigation and obstacle avoidance may be carried out efficiently using structure and motion, but only whitin a limited range from the camera. In order to increase this effective range, additional information needs to be incorporated, more specifically the location of objects in the image. For this, we propose a real-time object recognition method, which uses P-channel matching, which may be used for improving navigation accuracy at distances where structure estimation is unreliable.

    List of papers
    1. Real-Time View-Based Pose Recognition and Interpolation for Tracking Initialization
    Open this publication in new window or tab >>Real-Time View-Based Pose Recognition and Interpolation for Tracking Initialization
    2007 (English)In: Journal of Real-Time Image Processing, ISSN 1861-8200, E-ISSN 1861-8219, Journal of real-time image processing, ISSN 1861-8200, Vol. 2, no 2-3, p. 103-115Article in journal (Refereed) Published
    Abstract [en]

    In this paper we propose a new approach to real-time view-based pose recognition and interpolation. Pose recognition is particularly useful for identifying camera views in databases, video sequences, video streams, and live recordings. All of these applications require a fast pose recognition process, in many cases video real-time. It should further be possible to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions such as clutter and occlusion. The recognition algorithm consists of three steps: (1) low-level image features for color and local orientation are extracted in each point of the image; (2) these features are encoded into P-channels by combining similar features within local image regions; (3) the query P-channels are compared to a set of prototype P-channels in a database using a least-squares approach. The algorithm is applied in two scene registration experiments with fisheye camera data, one for pose interpolation from synthetic images and one for finding the nearest view in a set of real images. The method compares favorable to SIFT-based methods, in particular concerning interpolation. The method can be used for initializing pose-tracking systems, either when starting the tracking or when the tracking has failed and the system needs to re-initialize. Due to its real-time performance, the method can also be embedded directly into the tracking system, allowing a sensor fusion unit choosing dynamically between the frame-by-frame tracking and the pose recognition.

    Keywords
    computer vision
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-39505 (URN)10.1007/s11554-007-0044-y (DOI)49062 (Local ID)49062 (Archive number)49062 (OAI)
    Note
    Original Publication: Michael Felsberg and Johan Hedborg, Real-Time View-Based Pose Recognition and Interpolation for Tracking Initialization, 2007, Journal of real-time image processing, (2), 2-3, 103-115. http://dx.doi.org/10.1007/s11554-007-0044-y Copyright: Springer Science Business MediaAvailable from: 2009-10-10 Created: 2009-10-10 Last updated: 2017-12-13Bibliographically approved
    2. Real-Time Visual Recognition of Objects and Scenes Using P-Channel Matching
    Open this publication in new window or tab >>Real-Time Visual Recognition of Objects and Scenes Using P-Channel Matching
    2007 (English)In: Proceedings 15th Scandinavian Conference on Image Analysis / [ed] Bjarne K. Ersboll and Kim S. Pedersen, Berlin, Heidelberg: Springer, 2007, Vol. 4522, p. 908-917Conference paper, Published paper (Refereed)
    Abstract [en]

    In this paper we propose a new approach to real-time view-based object recognition and scene registration. Object recognition is an important sub-task in many applications, as e.g., robotics, retrieval, and surveillance. Scene registration is particularly useful for identifying camera views in databases or video sequences. All of these applications require a fast recognition process and the possibility to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions as clutter and occlusion. The recognition algorithm extracts a number of basic, intensity invariant image features, encodes them into P-channels, and compares the query P-channels to a set of prototype P-channels in a database. The algorithm is applied in a cross-validation experiment on the COIL database, resulting in nearly ideal ROC curves. Furthermore, results from scene registration with a fish-eye camera are presented.

    Place, publisher, year, edition, pages
    Berlin, Heidelberg: Springer, 2007
    Series
    Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 4522
    Keywords
    Object recognition - scene registration - P-channels - real-time processing - view-based computer vision
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-21618 (URN)10.1007/978-3-540-73040-8 (DOI)978-3-540-73039-2 (ISBN)
    Conference
    15th Scandinavian Conference, SCIA 2007, June 10-24, Aalborg, Denmark
    Note

    Original Publication: Michael Felsberg and Johan Hedborg, Real-Time Visual Recognition of Objects and Scenes Using P-Channel Matching, 2007, Proc. 15th Scandinavian Conference on Image Analysis, 908-917. http://dx.doi.org/10.1007/978-3-540-73040-8 Copyright: Springer

    Available from: 2009-10-05 Created: 2009-10-05 Last updated: 2017-03-23Bibliographically approved
    3. Fast and Accurate Structure and Motion Estimation
    Open this publication in new window or tab >>Fast and Accurate Structure and Motion Estimation
    2009 (English)In: International Symposium on Visual Computing / [ed] George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin, Yoshinori Kuno, Junxian Wang, Jun-Xuan Wang, Junxian Wang, Renato Pajarola and Peter Lindstrom et al., Berlin Heidelberg: Springer-Verlag , 2009, p. 211-222Conference paper, Oral presentation only (Refereed)
    Abstract [en]

    This paper describes a system for structure-and-motion estimation for real-time navigation and obstacle avoidance. We demonstrate it technique to increase the efficiency of the 5-point solution to the relative pose problem. This is achieved by a novel sampling scheme, where We add a distance constraint on the sampled points inside the RANSAC loop. before calculating the 5-point solution. Our setup uses the KLT tracker to establish point correspondences across tone in live video We also demonstrate how an early outlier rejection in the tracker improves performance in scenes with plenty of occlusions. This outlier rejection scheme is well Slated to implementation on graphics hardware. We evaluate the proposed algorithms using real camera sequences with fine-tuned bundle adjusted data as ground truth. To strenghten oar results we also evaluate using sequences generated by a state-of-the-art rendering software. On average we are able to reduce the number of RANSAC iterations by half and thereby double the speed.

    Place, publisher, year, edition, pages
    Berlin Heidelberg: Springer-Verlag, 2009
    Series
    Lecture Notes in Computer Science, ISSN 0302-9743 ; Volume 5875
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-50624 (URN)10.1007/978-3-642-10331-5_20 (DOI)000278937300020 ()
    Conference
    5th International Symposium, ISVC 2009, November 30 - December 2, Las Vegas, NV, USA
    Projects
    DIPLECS
    Available from: 2009-10-13 Created: 2009-10-13 Last updated: 2016-05-04Bibliographically approved
    4. Real time camera ego-motion compensation and lens undistortion on GPU
    Open this publication in new window or tab >>Real time camera ego-motion compensation and lens undistortion on GPU
    2007 (English)Manuscript (preprint) (Other academic)
    Abstract [en]

    This paper describes a GPU implementation for simultaneous camera ego-motion compensation and lens undistortion. The main idea is to transform the image under an ego-motion constraint so that trackedpoints in the image, that are assumed to come from the ego-motion, maps as close as possible to their averageposition in time. The lens undistortion is computed si-multaneously. We compare the performance with and without compensation using two measures; mean timedifference and mean statistical background subtraction.

    Publisher
    p. 8
    Keywords
    GPU, camera ego-motion compensation, lens undistortion
    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-58547 (URN)
    Available from: 2010-08-18 Created: 2010-08-13 Last updated: 2011-01-25Bibliographically approved
    5. KLT Tracking Implementation on the GPU
    Open this publication in new window or tab >>KLT Tracking Implementation on the GPU
    2007 (English)In: Proceedings SSBA 2007 / [ed] Magnus Borga, Anders Brun and Michael Felsberg;, 2007Conference paper, Oral presentation only (Other academic)
    Abstract [en]

    The GPU is the main processing unit on a graphics card. A modern GPU typically provides more than ten times the computational power of an ordinary PC processor. This is a result of the high demands for speed and image quality in computer games. This paper investigates the possibility of exploiting this computational power for tracking points in image sequences. Tracking points is used in many computer vision tasks, such as tracking moving objects, structure from motion, face tracking etc. The algorithm was successfully implemented on the GPU and a large speed up was achieved.

    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-21602 (URN)
    Conference
    SSBA, Swedish Symposium in Image Analysis 2007, 14-15 March, Linköping, Sweden
    Available from: 2009-10-05 Created: 2009-10-05 Last updated: 2016-05-04
    6. Synthetic Ground Truth for Feature Trackers
    Open this publication in new window or tab >>Synthetic Ground Truth for Feature Trackers
    2008 (English)In: Swedish Symposium on Image Analysis 2008, 2008Conference paper, Published paper (Other academic)
    Abstract [en]

    Good data sets for evaluation of computer visionalgorithms are important for the continuedprogress of the field. There exist good evaluationsets for many applications, but there are othersfor which good evaluation sets are harder to comeby. One such example is feature tracking, wherethere is an obvious difficulty in the collection ofdata. Good evaluation data is important both forcomparisons of different algorithms, and to detectweaknesses in a specific method.All image data is a result of light interactingwith its environment. These interactions are sowell modelled in rendering software that sometimesnot even the sharpest human eye can tell the differencebetween reality and simulation. In this paperwe thus propose to use a high quality renderingsystem to create evaluation data for sparse pointcorrespondence trackers.

    National Category
    Engineering and Technology
    Identifiers
    urn:nbn:se:liu:diva-58548 (URN)
    Conference
    Swedish Symposium on Image Analysis 2008, 13-14 Marsh, Lund, Sweden
    Available from: 2010-08-18 Created: 2010-08-13 Last updated: 2015-12-10Bibliographically approved
  • 7.
    Hedborg, Johan
    et al.
    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.
    Fast and Robust Relative Pose Estimation for Forward and Sideways Motions2010In: SSBA, 2010Conference paper (Other academic)
  • 8.
    Hedborg, Johan
    et al.
    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.
    Fast Iterative Five point Relative Pose Estimation2013Conference paper (Refereed)
    Abstract [en]

    Robust estimation of the relative pose between two cameras is a fundamental part of Structure and Motion methods. For calibrated cameras, the five point method together with a robust estimator such as RANSAC gives the best result in most cases. The current state-of-the-art method for solving the relative pose problem from five points is due to Nistér [9], because it is faster than other methods and in the RANSAC scheme one can improve precision by increasing the number of iterations. In this paper, we propose a new iterative method, which is based on Powell's Dog Leg algorithm. The new method has the same precision and is approximately twice as fast as Nister's algorithm. The proposed method is easily extended to more than five points while retaining a efficient error metrics. This makes it also very suitable as an refinement step. The proposed algorithm is systematically evaluated on three types of datasets with known ground truth.

  • 9.
    Hedborg, Johan
    et al.
    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.
    Fast Iterative Five point Relative Pose EstimationManuscript (preprint) (Other academic)
    Abstract [en]

    Robust estimation of the relative pose between two cameras is a fundamental part of Structure and Motion methods. For calibrated cameras, the five point method together with a robust estimator such as RANSAC gives the best result in most cases. The current state-of-the-art method for solving the relative pose problem from five points is due to Nist´er [1], because it is faster than other methods and in the RANSAC scheme one can improve precision by increasing the number of iterations.

    In this paper, we propose a new iterative method, which is based on Powell’s Dog Leg algorithm. The new method has the same precision and is approximately twice as fast as Nist´er’s algorithm. The proposed algorithm is systematically evaluated on two types of datasets with known ground truth.

  • 10.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Fast and Accurate Ego-Motion Estimation2009Conference paper (Refereed)
    Abstract [en]

    This paper describes a system that efficiently uses the KLT tracker together with a calibrated 5-point solver for structure-from-motion (SfM). Our system uses a GPU to perform tracking, and the CPU for SfM.

    In this setup, it is advantageous to run the tracker both forwards and backwards in time, to detect incorrectly tracked points. We introduce a modification to the point selection inside the RANSAC step of the 5-point solver, and demonstrate how this speeds up the algorithm. Our evaluations are done using both real camera sequences, and data from a state-of-the art rendering engine with associated ground-truth.

  • 11.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Synthetic Ground Truth for Feature Trackers2008In: Swedish Symposium on Image Analysis 2008, 2008Conference paper (Other academic)
    Abstract [en]

    Good data sets for evaluation of computer visionalgorithms are important for the continuedprogress of the field. There exist good evaluationsets for many applications, but there are othersfor which good evaluation sets are harder to comeby. One such example is feature tracking, wherethere is an obvious difficulty in the collection ofdata. Good evaluation data is important both forcomparisons of different algorithms, and to detectweaknesses in a specific method.All image data is a result of light interactingwith its environment. These interactions are sowell modelled in rendering software that sometimesnot even the sharpest human eye can tell the differencebetween reality and simulation. In this paperwe thus propose to use a high quality renderingsystem to create evaluation data for sparse pointcorrespondence trackers.

  • 12.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-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.
    Fast and Accurate Structure and Motion Estimation2009In: International Symposium on Visual Computing / [ed] George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin, Yoshinori Kuno, Junxian Wang, Jun-Xuan Wang, Junxian Wang, Renato Pajarola and Peter Lindstrom et al., Berlin Heidelberg: Springer-Verlag , 2009, p. 211-222Conference paper (Refereed)
    Abstract [en]

    This paper describes a system for structure-and-motion estimation for real-time navigation and obstacle avoidance. We demonstrate it technique to increase the efficiency of the 5-point solution to the relative pose problem. This is achieved by a novel sampling scheme, where We add a distance constraint on the sampled points inside the RANSAC loop. before calculating the 5-point solution. Our setup uses the KLT tracker to establish point correspondences across tone in live video We also demonstrate how an early outlier rejection in the tracker improves performance in scenes with plenty of occlusions. This outlier rejection scheme is well Slated to implementation on graphics hardware. We evaluate the proposed algorithms using real camera sequences with fine-tuned bundle adjusted data as ground truth. To strenghten oar results we also evaluate using sequences generated by a state-of-the-art rendering software. On average we are able to reduce the number of RANSAC iterations by half and thereby double the speed.

  • 13.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-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.
    Ringaby, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Rolling Shutter Bundle Adjustment2012Conference paper (Refereed)
    Abstract [en]

    This paper introduces a bundle adjustment (BA) method that obtains accurate structure and motion from rolling shutter (RS) video sequences: RSBA. When a classical BA algorithm processes a rolling shutter video, the resultant camera trajectory is brittle, and complete failures are not uncommon. We exploit the temporal continuity of the camera motion to define residuals of image point trajectories with respect to the camera trajectory. We compare the camera trajectories from RSBA to those from classical BA, and from classical BA on rectified videos. The comparisons are done on real video sequences from an iPhone 4, with ground truth obtained from a global shutter camera, rigidly mounted to the iPhone 4. Compared to classical BA, the rolling shutter model requires just six extra parameters. It also degrades the sparsity of the system Jacobian slightly, but as we demonstrate, the increase in computation time is moderate. Decisive advantages are that RSBA succeeds in cases where competing methods diverge, and consistently produces more accurate results.

  • 14.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Johansson, Björn
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Real time camera ego-motion compensation and lens undistortion on GPU2007Manuscript (preprint) (Other academic)
    Abstract [en]

    This paper describes a GPU implementation for simultaneous camera ego-motion compensation and lens undistortion. The main idea is to transform the image under an ego-motion constraint so that trackedpoints in the image, that are assumed to come from the ego-motion, maps as close as possible to their averageposition in time. The lens undistortion is computed si-multaneously. We compare the performance with and without compensation using two measures; mean timedifference and mean statistical background subtraction.

  • 15.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Ringaby, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-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.
    Structure and Motion Estimation from Rolling Shutter Video2011In: IEEE International Conference onComputer Vision Workshops (ICCV Workshops), 2011, IEEE Xplore , 2011, p. 17-23Conference paper (Refereed)
    Abstract [en]

    The majority of consumer quality cameras sold today have CMOS sensors with rolling shutters. In a rolling shutter camera, images are read out row by row, and thus each row is exposed during a different time interval. A rolling-shutter exposure causes geometric image distortions when either the camera or the scene is moving, and this causes state-of-the-art structure and motion algorithms to fail. We demonstrate a novel method for solving the structure and motion problem for rolling-shutter video. The method relies on exploiting the continuity of the camera motion, both between frames, and across a frame. We demonstrate the effectiveness of our method by controlled experiments on real video sequences. We show, both visually and quantitatively, that our method outperforms standard structure and motion, and is more accurate and efficient than a two-step approach, doing image rectification and structure and motion.

  • 16.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Robinson, Andreas
    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.
    Robust Three-View Triangulation Done Fast2014In: Proceedings: 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014, IEEE , 2014, p. 152-157Conference paper (Refereed)
    Abstract [en]

    Estimating the position of a 3-dimensional world point given its 2-dimensional projections in a set of images is a key component in numerous computer vision systems. There are several methods dealing with this problem, ranging from sub-optimal, linear least square triangulation in two views, to finding the world point that minimized the L2-reprojection error in three views. This leads to the statistically optimal estimate under the assumption of Gaussian noise. In this paper we present a solution to the optimal triangulation in three views. The standard approach for solving the three-view triangulation problem is to find a closed-form solution. In contrast to this, we propose a new method based on an iterative scheme. The method is rigorously tested on both synthetic and real image data with corresponding ground truth, on a midrange desktop PC and a Raspberry Pi, a low-end mobile platform. We are able to improve the precision achieved by the closed-form solvers and reach a speed-up of two orders of magnitude compared to the current state-of-the-art solver. In numbers, this amounts to around 300K triangulations per second on the PC and 30K triangulations per second on Raspberry Pi.

  • 17.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Skoglund, Johan
    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.
    KLT Tracking Implementation on the GPU2007In: Proceedings SSBA 2007 / [ed] Magnus Borga, Anders Brun and Michael Felsberg;, 2007Conference paper (Other academic)
    Abstract [en]

    The GPU is the main processing unit on a graphics card. A modern GPU typically provides more than ten times the computational power of an ordinary PC processor. This is a result of the high demands for speed and image quality in computer games. This paper investigates the possibility of exploiting this computational power for tracking points in image sequences. Tracking points is used in many computer vision tasks, such as tracking moving objects, structure from motion, face tracking etc. The algorithm was successfully implemented on the GPU and a large speed up was achieved.

1 - 17 of 17
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • 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