liu.seSearch for publications in DiVA
Change search
Refine search result
1234567 1 - 50 of 595
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the 'Create feeds' function.
  • 1.
    Ahlberg, Jörgen
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Active Contours in Three Dimensions1996Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    To find a shape in an image, a technique called snakes or active contours can be used. An active contour is a curve that moves towards the sought-for shape in a way controlled by internal forces - such as rigidity and elasticity - and an image force. The image force should attract the contour to certain features, such as edges, in the image. This is done by creating an attractor image, which defines how strongly each point in the image should attract the contour.

    In this thesis the extension to contours (surfaces) in three dimensional images is studied. Methods of representation of the contour and computation of the internal forces are treated.

    Also, a new way of creating the attractor image, using the orientation tensor to detect planar structure in 3D images, is studied. The new method is not generally superior to those already existing, but still has its uses in specific applications.

    During the project, it turned out that the main problem of active contours in 3D images was instability due to strong internal forces overriding the influence of the attractor image. The problem was solved satisfactory by projecting the elasticity force on the contour’s tangent plane, which was approximated efficiently using sphere-fitting.

  • 2.
    Aksoy, Selim
    et al.
    Intelligent Systems Laboratory, University of Washington, Seattle, USA.
    Ming, Ye
    Intelligent Systems Laboratory, University of Washington, Seattle, USA.
    Schauf, Michael L.
    Intelligent Systems Laboratory, University of Washington, Seattle, USA.
    Song, Mingzhou
    Intelligent Systems Laboratory, University of Washington, Seattle, USA.
    Wang, Yalin
    n/a.
    Haralick, Robert M.
    Intelligent Systems Laboratory, University of Washington, Seattle, USA.
    Parker, Jim R.
    University of Calgary, Dept. of Computer Science, Calgary, Canada.
    Pivovarov, Juraj
    University of Calgary, Dept. of Computer Science, Calgary, Canada.
    Royko, Dominik
    University of Calgary, Dept. of Computer Science, Calgary, Canada.
    Sun, Changming
    CSIRO Mathematical and Information Sciences, Australia.
    Farnebäck, Gunnar
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Algorithm Performance Contest2000In: Proceedings. 15th International Conference on Pattern Recognition, 2000: Barcelona, Spain, IEEE , 2000, Vol. 4, p. 870-876Conference paper (Refereed)
    Abstract [en]

    This contest involved the running and evaluation of computer vision and pattern recognition techniques on different data sets with known groundwidth. The contest included three areas; binary shape recognition, symbol recognition and image flow estimation. A package was made available for each area. Each package contained either real images with manual groundtruth or programs to generate data sets of ideal as well as noisy images with known groundtruth. They also contained programs to evaluate the results of an algorithm according to the given groundtruth. These evaluation criteria included the generation of confusion matrices, computation of the misdetection and false alarm rates and other performance measures suitable for the problems. The paper summarizes the data generation for each area and experimental results for a total of six participating algorithms

  • 3.
    Albregtsen, Fritz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Enhancing Satellite Images of the Antarctic Snow and Ice Cover by Context Dependent Anisotropic Nonstationary Filtering.1987Report (Other academic)
  • 4.
    Andersson, Adam
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Range Gated Viewing with Underwater Camera2005Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The purpose of this master thesis, performed at FOI, was to evaluate a range gated underwater camera, for the application identification of bottom objects. The master thesis was supported by FMV within the framework of “arbetsorder Systemstöd minjakt (Jan Andersson, KC Vapen)”. The central part has been field trials, which have been performed in both turbid and clear water. Conclusions about the performance of the camera system have been done, based on resolution and contrast measurements during the field trials. Laboratory testing has also been done to measure system specific parameters, such as the effective gate profile and camera gate distances.

    The field trials shows that images can be acquired at significantly longer distances with the tested gated camera, compared to a conventional video camera. The distance where the target can be detected is increased by a factor of 2. For images suitable for mine identification, the increase is about 1.3. However, studies of the performance of other range gated systems shows that the increase in range for mine identification can be about 1.6. Gated viewing has also been compared to other technical solutions for underwater imaging.

  • 5.
    Andersson, Mathias
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Image processing algorithms for compensation of spatially variant blur2005Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    This report adresses the problem of software correction of spatially variant blur in digital images. The problem arises when the camera optics contains flaws, when the scene contains multiple moving objects with different relative motion or the camera itself is i.e. rotated. Compensation through deconvolving is impossible due to the shift-variance in the PSF hence alternative methods are required. There are a number of suggested methods published. This report evaluates two methods

  • 6.
    Andersson, Mats
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Image Feature Representation for Analogue VLSI Representation1989Licentiate thesis, monograph (Other academic)
  • 7.
    Andersson, Mats
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    A Hybrid Image Processing Architecture1988Report (Other academic)
  • 8.
    Andersson, Mats
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Controllable 3-D Filters1993In: Proceedings of the SSAB Symposium on Image Analysis: Gothenburg, 1993Conference paper (Refereed)
  • 9.
    Andersson, Mats
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Orientation Estimation in Ambiguous Neighbourhoods1992In: Theory & Applications of Image Analysis: eds P. Johansen and S. Olsen / [ed] P. Johansen and S. Olsen, Singapore: World Scientific Publishing Co , 1992, p. 189-210Chapter in book (Refereed)
  • 10.
    Andersson, Mats
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Implementation of Image Processing Operations from Analogue Convolver Responses1989In: Proceedings of the SSAB Conference on Image Analysis: Gothenburg, Sweden, 1989, p. 67-74Conference paper (Refereed)
  • 11.
    Andersson, Mats T.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Controllable Multi-dimensional Filters and Models in Low-Level Computer Vision1992Doctoral thesis, monograph (Other academic)
    Abstract [en]

    This thesis concerns robust estimation of low-level features for use in computer vision systems. The presentation consists of two parts.

    The first part deals with controllable filters and models. A basis filter set is introduced which supports a computationally efficient synthesis of filters in arbitrary orientations. In contrast to many earlier methods, this approach allows the use of more complex models at an early stage of the processing. A new algorithm for robust estimation of orientation is presented. The algorithm is based on synthesized quadrature responses and supports the simultaneous representation and individual averaging of multiple events. These models are then extended to include estimation and representation of more complex image primitives such as as line ends, T-junctions, crossing lines and curvature. The proposed models are based on symmetry properties in the Fourier domain as well as in the spatial plane and the feature extraction is performed by applying the original basis filters directly on the grey-level image. The basis filters and interpolation scheme are finally generalized to allow synthesis of 3-D filters. The performance of the proposed models and algorithms is demonstrated using test images of both synthetic and real world data.

    The second part of the thesis concerns an image feature representation adapted for a robust analogue implementation. A possible use for this approach is in analogue VLSI or corresponding analogue hardware adapted for neural networks. The methods are based on projections of quadrature filter responses and mutual inhibition of magnitude signals.

  • 12.
    Andersson, Mats T.
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Controllable 3-D Filters for Low Level Computer Vision1993Report (Other academic)
    Abstract [en]

    Three-dimensional data processing is becoming more and more common. Typical operations are for example estimation of optical flow in video sequences and orientation estimation in 3-D MR images. This paper proposes an efficient approach to robust low level feature extraction for 3-D image analysis. In contrast to many earlier algorithms the methods proposed in this paper support the use of relatively complex models at the initial processing steps. The aim of this approach is to provide the means to handle complex events at the initial processing steps and to enable reliable estimates in the presence of noise. A limited basis filter set is proposed which forms a basis on the unit sphere and is related to spherical harmonics. From these basis filters, different types of orientation selective filters are synthesized. An interpolation scheme that provides a rotation as well as a translation of the synthesized filter is presented. The purpose is to obtain a robust and invariant feature extraction at a manageable computational cost.

  • 13.
    Andersson, Mats
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Wiklund, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Filter Networks1999In: Proceedings of Signal and Image Processing (SIP'99), Nassau, Bahamas: IASTED , 1999, p. 213-217Conference paper (Refereed)
    Abstract [en]

    This paper presents a new and efficient approach for optimization and implementation of filter banks e.g. velocity channels, orientation channels and scale spaces. The multi layered structure of a filter network enable a powerful decomposition of complex filters into simple filter components and the intermediary results may contribute to several output nodes. Compared to a direct implementation a filter network uses only a fraction of the coefficients to provide the same result. The optimization procedure is recursive and all filters on each level are optimized simultaneously. The individual filters of the network, in general, contain very few non-zero coefficients, but there are are no restrictions on the spatial position of the coefficients, they may e.g. be concentrated on a line or be sparsely scattered. An efficient implementation of a quadrature filter hierarchy for generic purposes using sparse filter components is presented.

  • 14.
    Andersson, Mats
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Wiklund, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Sequential Filter Trees for Efficient 2D 3D and 4D Orientation Estimation1998Report (Other academic)
    Abstract [en]

    A recursive method to condense general multidimensional FIR-filters into a sequence of simple kernels with mainly one dimensional extent has been worked out. Convolver networks adopted for 2, 3 and 4D signals is presented and the performance is illustrated for spherically separable quadrature filters. The resulting filter responses are mapped to a non biased tensor representation where the local tensor constitutes a robust estimate of both the shape and the orientation (velocity) of the neighbourhood. A qualitative evaluation of this General Sequential Filter concept results in no detectable loss in accuracy when compared to conventional FIR (Finite Impulse Response) filters but the computational complexity is reduced several orders in magnitude. For the examples presented in this paper the attained speed-up is 5, 25 and 300 times for 2D, 3D and 4D data respectively The magnitude of the attained speed-up implies that complex spatio-temporal analysis can be performed using standard hardware, such as a powerful workstation, in close to real time. Due to the soft implementation of the convolver and the tree structure of the sequential filtering approach the processing is simple to reconfigure for the outer as well as the inner (vector length) dimensionality of the signal. The implementation was made in AVS (Application Visualization System) using modules written in C.

  • 15.
    Andersson, Per
    et al.
    n/a.
    Kuchcinski, Krzysztof
    n/a.
    Nordberg, Klas
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Doherty, Patrick
    Linköping University, Department of Computer and Information Science, KPLAB - Knowledge Processing Lab. Linköping University, The Institute of Technology.
    Integrating a computational model and a run time system for image processing on a UAV2002In: Euromicro Symposium on Digital System Design (DSD), 2002, p. 102-109Conference paper (Refereed)
    Abstract [en]

    Recently substantial research has been devoted to Unmanned Aerial Vehicles (UAVs). One of a UAV's most demanding subsystem is vision. The vision subsystem must dynamically combine different algorithms as the UAVs goal and surrounding change. To fully utilize the available hardware, a run time system must be able to vary the quality and the size of regions the algorithms are applied to, as the number of image processing tasks changes. To allow this the run time system and the underlying computational model must be integrated. In this paper we present a computational model suitable for integration with a run time system. The computational model is called Image Processing Data Flow Graph (IP-DFG). IP-DFG has been developed for modeling of complex image processing algorithms. IP-DFG is based on data flow graphs, but has been extended with hierarchy and new rules for token consumption, which makes the computational model more flexible and more suitable for human interaction. In this paper we also show that IP-DFGs are suitable for modelling expressions, including data dependent decisions and iterations, which are common in complex image processing algorithms.

  • 16.
    Andersson, Thord
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Learning in a Reactive Robotic Architecture2000Licentiate thesis, monograph (Other academic)
    Abstract [en]

    In this licenciate thesis, we discuss how to generate actions from percepts within an autonomous robotic system. In particular, we discuss and propose an original reactive architecture suitable for response generation, learning and self-organization.

    The architecture uses incremental learning and supports self organization through distributed dynamic model generation and self-contained components. Signals to and from the architecture are represented using the channel representation, which is presented in that context.

    The components of the architecture use a novel and flexible implementation of an artificial neural network. The learning rules for this implementation are derived.

    A simulator is presented. It has been designed and implemented in order to test and evaluate the proposed architecture.

    Results of a series of experiments on the reactive architecture are discussed and accounted for. The experiments have been performed within three different scenarios, using the developed simulator.

    The problem of information representation in robotic architectures is illustrated by a problem of anchoring symbols to visual data. This is presented in the context of the WITAS project.

  • 17.
    Andersson, Thord
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Coradeschi, Silvia
    n/a.
    Saffiotti, Alessandro
    n/a.
    Fuzzy matching of visual cues in an unmanned airborne vehicle1999Report (Other academic)
    Abstract [en]

    Computer vision systems used in autonomous mobile vehicles are typically linked to higher-level deliberation processes. One important aspect of this link is how to connect, or anchor, the symbols used at the higher level to the objects in the vision system that these symbols refer to. Anchoring is complicated by the fact that the vision data are inherently affected by uncertainty. We propose an anchoring technique that uses fuzzy sets to represent the uncertainty in the perceptual data. We show examples where this technique allows a deliberative system to reason about the objects (cars) detected by a vision system embarked in an unmanned helicopter, in the framework of the Witas project.

  • 18.
    Andersson, Thord
    et al.
    n/a.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Farnebäck, Gunnar
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Nordberg, Klas
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Wiklund, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    WITAS Project at Computer Vision Laboratory; A status report (Jan 1998)1998In: Proceedings of the SSAB symposium on image analysis: Uppsala, Sweden, 1998, p. 113-116Conference paper (Refereed)
    Abstract [en]

    WITAS will be engaged in goal-directed basic research in the area of intelligent autonomous vehicles and other autonomous systems. In this paper an overview of the project is given together with a presentation of our research interests in the project. The current status of our part in the project is also given.

  • 19.
    Andersson, Thord
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Karlsson, Mikael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Neuronnätsbaserad identifiering av processparametrar vid tillverkning av pappersmassa1997Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Artificiella neurala nätverk (ANN) är en teknik som under de senaste tio åren har mognat och som numera återfinns i allt fler tillämpningar så som avläsning av skriven text, linjär programmering, reglerteknik, expertsystem, taligenkänning och många olika sorters klassificeringsproblem [Zurada, 1992]. Vi ville i vårt examensarbete försöka använda ANN i en industriell process där standardmetoder ej fungerat tillfredsställande eller varit svåra att tillämpa. En sådan process fann vi i tillverkningen av pappersmassa.

    För att tillverka pappersmassa från ved krävs en lång och komplicerad process uppdelad i flera olika steg. Ett av dessa steg är den så kallade kokningen där man med hjälp av högt tryck och varm lut bryter ned träflis till fibrer. Kokningsprocessen är komplex, pågår under lång tid (ca. 8 timmar) samt påverkas av en stor mängd parametrar och därför krävs det stor erfarenhet och kunskap för att kunna styra den. På Kværner Pulping Technologies i Karlstad, som konstruerar bl.a. kokare, har man tagit fram en simulator för kokningsprocessen för att man skall få en bättre insikt i hur processen fungerar och följaktligen kunna styra kokningen på ett bättre sätt. Simulatorns beteende är beroende av ett antal s.k. dolda parametrar som är en delmängd av de parametrar som antas påverka kokningsprocessen. Dessa dolda parametrar är svåra/omöjliga att mäta och därför sätts dessa i simuleringen till estimerade värden. De, i den riktiga processen, motsvarande dolda parametrarna varierar dock på ett okänt sätt. De påverkas dels av interna processer i kokaren, dels av externa orsaker, t.ex. kan träflis av en annan kvalitet matas in i kokaren. Detta leder till simulatorn ger bra simuleringar under ganska kort tid då de dolda parametrarna är approximativt konstanta.

    Om man på något sätt skulle kunna detektera förändringarna i de dolda parametrarna i processen och föra över dessa till simulatorn, skulle den kunna gå "parallellt" med kokprocessen. Simulatorn skulle i detta fall utgöra ett utmärkt kompletterande verktyg för den person som styr kokprocessen, eftersom han/hon skulle få en bättre uppfattning om vad som händer/hände i processen och därmed få ett större beslutsunderlag för styrning. Detta förutsätter att simulatorn är så pass bra att den under stationära förhållanden i parametrarna lyckas fånga den globala utvecklingen i kokaren med tillräcklig precision.

    Som ett första steg för att nå detta mål avser vi i denna rapport att undersöka om detektering av förändringar i de dolda parametrarna i simulatorn är möjlig med hjälp av framåtkopplade ANN och inlärningsalgoritmen resilient propagation.

    Rapporten är uppdelad i 7 kapitel där vi i kapitel 2 kommer behandla problemet mer i detalj. Kapitel 3 och 4 är av allmänt slag där vi beskriver tillverkningsprocessen för papper och vad artificiella neurala nätverk egentligen är. I kapitel 5 beskriver vi de olika lösningsförslag som behandlats och de resultat vi har uppnått. Slutsatser och resultat sammanfattas i kapitel 6 . Det finns mycket mer vi skulle vilja pröva på och undersöka, dessa fortsatta arbeten beskriver vi kapitel 7. Sist i rapporten kommer bilagorna 1 och 2 med detaljer som vi finner relevanta, men som är för skrymmande att ta med i huvuddelen av rapporten. I bilaga 3 har vi bifogat den programkod vi producerat under arbetets gång.

  • 20.
    Arvidsson, Lars
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Stereoseende i realtid2007Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In this thesis, two real-time stereo methods have been implemented and evaluated. The first one is based on blockmatching and the second one is based on local phase. The goal was to be able to run the algorithms at real-time and examine which one is best. The blockmatching method performed better than the phase based method, both in speed and accuracy. SIMD operations (Single Instruction Multiple Data) have been used in the processor giving a speed boost by a factor of two.

  • 21.
    Benderius, Björn
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Laser Triangulation Using Spacetime Analysis2007Independent thesis Advanced level (degree of Master (One Year)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In this thesis spacetime analysis is applied to laser triangulation in an attempt to eliminate certain artifacts caused mainly by reflectance variations of the surface being measured. It is shown that spacetime analysis do eliminate these artifacts almost completely, it is also shown that the shape of the laser beam used no longer is critical thanks to the spacetime analysis, and that in some cases the laser probably even could be exchanged for a non-coherent light source. Furthermore experiments of running the derived algorithm on a GPU (Graphics Processing Unit) are conducted with very promising results.

    The thesis starts by deriving the theory needed for doing spacetime analysis in a laser triangulation setup taking perspective distortions into account, then several experiments evaluating the method is conducted.

  • 22.
    Berg, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Pose Recognition for Tracker Initialization Using 3D Models2008Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In this thesis it is examined whether the pose of an object can be determined by a system trained with a synthetic 3D model of said object. A number of variations of methods using P-channel representation are examined. Reference images are rendered from the 3D model, features, such as gradient orientation and color information are extracted and encoded into P-channels. The P-channel representation is then used to estimate an overlapping channel representation, using B1-spline functions, to estimate a density function for the feature set. Experiments were conducted with this representation as well as the raw P-channel representation in conjunction with a number of distance measures and estimation methods.

    It is shown that, with correct preprocessing and choice of parameters, the pose can be detected with some accuracy and, if not in real-time, fast enough to be useful in a tracker initialization scenario. It is also concluded that the success rate of the estimation depends heavily on the nature of the object.

  • 23.
    Bergquist, Urban
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Colour Vision and Hue for Autonomous Vehicle Guidance1999Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    We explore the use of colour for interpretation of unstructured off-road scenes. The aim is to extract driveable areas for use in an autonomous off-road vehicle in real-time. The terrain is an unstructured tropical jungle area with vegetation, water and red mud roads.

    We show that hue is both robust to changing lighting conditions and an important feature for correctly interpreting this type of scene. We believe that our method also can be deployed in other types of terrain, with minor changes, as long as the terrain is coloured and well saturated.

    Only 2D information is processed at the moment, but we aim at extending the method to also treat 3D information, by the use of stereo vision or motion.

  • 24.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Circular Symmetry Models in Image Processing1986Licentiate thesis, monograph (Other academic)
    Abstract [en]

    New methods for feature extraction based on the spectral properties of local neighbourhoods is presented. The spectral behaviour of the neighbourhoods is investigated in the spatial domain using the Parseval relation applied to partial derivative pictures. Two types of such properties are considered for circular symmetric and linear symmetric neighbourhoods. These two properties are the existence of point concentration and line concentration in the spectra. For the circular symmetry investigation a new basis function set is introduced. To obtain a spectrum in the terms of these basis function sets, a scalar product is introduced for circular neighbourhoods. The same is carried out for linear symmetry spectra using the well-known basis set and the scalar product consisting of cosines and 𝓛2(Ω) scalar product. Confidence parameters are introduced to measure the significance of the extracted features. These are basically different types of variance measures and they are shown to be specific for the desired information: The existence of point concentration or line concentration in the spectra of the local neighbourhoods.

  • 25.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Detection of Linear Symmetry in Multiple Dimensions for Description of Local Orientation and Optical Flow1988Report (Other academic)
    Abstract [en]

    The symmetries in a neighbourhood of a gray value image are modelled by conjugate harmonic function pairs. A harmonic function pair is utilized to represent a coordinate transformation defining a symmetry type. Inthis coordinate representation the image parts, which are symmetric with respect to the chosen function pair, have iso-gray value curves which are simple lines or parallel line patterns. The detection is modelled in thespecial Fourier domain corresponding to the new variables by minimizing an error function. It is shown that the minimiza.tion process ar detection of these patterns can be carried out for the whole image entirely in the spatial domain by convolutions. The convolution kernel is complex valued, as is the the result. The magnitudes of the result are shown to correspond to a well defi.ned certainty measure, while the orientation is the lea.st square estimate of an orientation in the Fourier transform corresponding to the harmonic coordinates. Applica tions to four symmetries a.re given. These are circular, linear, hyperbolic and parabolic symmetries. Experimental results a.re presented.

  • 26.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Impressions from Picture Processing in USA and Japan1988Report (Other academic)
  • 27.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Optimal Orientation Detection of Circular Symmetry.1987Report (Other academic)
  • 28.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Optimal Orientation Detection of Linear Symmetry1987Report (Other academic)
    Abstract [en]

    The problem of optimal detection of orientation in arbitrary neighborhoods is solved in the least squares sense. It is shown that this corresponds to fitting an axis in the Fourier domain of the n-dimensional neighborhood, the solution of which is a well known solution of a matrix eigenvalue problem. The eigenvalues are the variance or inertia with respect to the axes given by their respective eigen vectors. The orientation is taken as the axis given by the least eigenvalue. Moreover it is shown that the necessary computations can be pursued in the spatial domain without doing a Fourier transformation. An implementation for 2-D is presented. Two certainty measures are given corresponding to the orientation estimate. These are the relative or the absolute distances between the two eigenvalues, revealing whether the fitted axis is much better than an axis orthogonal to it. The result of the implementation is verified by experiments which confirm an accurate orientation estimation and reliable certainty measure in the presence of additive noise at high level as well as low levels.

  • 29.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Pattern Recognition by detection of local symmetries1988In: Pattern Recognition and Artificial Intelligence / [ed] E. S. Gelsema and L. N. Kanal, 1988, p. 75-90Conference paper (Refereed)
    Abstract [en]

    The symmetries in a neighbourhood of a gray value image are modelled by conjugate harmonic function pairs. These are shown to be a suitable curve linear coordinate pair, in which the model represents a neighbourhood. In this representation the image parts, which are symmetric with respect to the chosen function pair, have iso-gray value curves which are simple lines or parallel line patterns. The detection is modelled in the special Fourier domain corresponding to the new variables by minimizing an error function. It is shown that the  minimization process or detection of these patterns can be carried out for the whole image entirely in the spatial domain by convolutions. What will be defined as the partial derivative image is the image which takes part in the convolution. The convolution kernel is complex valued, as are the partial derivative image and the result. The magnitudes of the result are shown to correspond to a well defined certainty measure, while the orientation is the least square estimate of an orientation in the Fourier transform corresponding to the harmonic coordinates. Applications to four symmetries are given. These are circular, linear, hyperbolic and parabolic symmetries. Experimental results are presented.

  • 30.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Recognition of Local Symmetries in Gray Value Images by Harmonic Functions1988In: Proceedings of the 9th International Conference on Pattern Recognition, Vol. 1, 1988, p. 345-347Conference paper (Refereed)
    Abstract [en]

    A method for modeling symmetries of the neighborhoods in gray-value images is derived. It is based on the form of the iso-gray-value curves. For every neighborhood a complex number is obtained through a convolution of a complex-valued image with a complex-valued filter. The magnitude of the complex number is the degree of symmetry with respect to the a priori chosen harmonic function pair. The degree of symmetry has a clear definition which is based on the error in the Fourier domain. The argument of the complex number is the angle representing the relative dominance of one of the pair of harmonic functions compared to the other.

  • 31.
    Bigun, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Some Mathematical Tools of Computers for Vision Purposes1987In: Proceedings of the 7th Nordic Conference on Teaching of Matematics at Technical Universities: Aalborg University, Denmark, 1987Conference paper (Refereed)
  • 32.
    Bigun, Josef
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Central Symmetry Modelling1986Report (Other academic)
    Abstract [en]

    A definition of central symmetry for local neighborhoods of 2-D images is given. A complete ON-set of centrally symmetric basis functions is proposed. The local neighborhoods are expanded in this basis. The behavior of coefficient spectrum obtained by this expansion is proposed to be the foundation of central symmetry parameters of the neighbqrhoods. Specifically examination of two such behaviors are proposed: Point concentration and line concentration of the energy spectrum. Moreover, the study of these types of behaviors of the spectrum are shown to be possible to do in the spatial domain.

  • 33.
    Bigun, Josef
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Central Symmetry Modelling1986In: Proceedings of EUSIPCO-86, Third European Signal Processing Conference / [ed] Ian T. Young, 1986, p. 883-886Conference paper (Refereed)
    Abstract [en]

    A definition of central symmetry for local neighborhoods of 2-D images is given. A complete ON-set of centrally symmetric basis functions is proposed. The local neighborhoods are expanded in this basis. The behavior of coefficient spectrum obtained by this expansion is proposed to be the foundation of central symmetry parameters of the neighbqrhoods. Specifically examination of two such behaviors are proposed: Point concentration and line concentration of the energy spectrum. Moreover, the study of these types of behaviors of the spectrum are shown to be possible to do in the spatial domain.

  • 34.
    Bigun, Josef
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Optical Flow Based on the Inertia Matrix of the Frequency Domain1988In: Proceedings from SSAB Symposium on Picture Processing: Lund University, Sweden, 1988, p. 132-135Conference paper (Refereed)
  • 35.
    Bigun, Josef
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Optimal Orientation Detection of Linear Symmetry1987In: Proceedings of the IEEE First International Conference on Computer Vision, 1987, p. 433-438Conference paper (Refereed)
    Abstract [en]

    The problem of optimal detection of orientation in arbitrary neighborhoods is solved in the least squares sense. It is shown that this corresponds to fitting an axis in the Fourier domain of the n-dimensional neighborhood, the solution of which is a well known solution of a matrix eigenvalue problem. The eigenvalues are the variance or inertia with respect to the axes given by their respective eigen vectors. The orientation is taken as the axis given by the least eigenvalue. Moreover it is shown that the necessary computations can be pursued in the spatial domain without doing a Fourier transformation. An implementation for 2-D is presented. Two certainty measures are given corresponding to the orientation estimate. These are the relative or the absolute distances between the two eigenvalues, revealing whether the fitted axis is much better than an axis orthogonal to it. The result of the implementation is verified by experiments which confirm an accurate orientation estimation and reliable certainty measure in the presence of additive noise at high level as well as low levels.

  • 36.
    Bigun, Josef
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision . Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision . Linköping University, The Institute of Technology.
    Wiklund, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision . Linköping University, The Institute of Technology.
    Multidimensional orientation estimation with applications to texture analysis and optical flow1991In: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 13, no 8, p. 775-790Article in journal (Refereed)
    Abstract [en]

    The problem of detection of orientation in finite dimensional Euclidean spaces is solved in the least squares sense. In particular, the theory is developed for the case when such orientation computations are necessary at all local neighborhoods of the n-dimensional Euclidean space. Detection of orientation is shown to correspond to fitting an axis or a plane to the Fourier transform of an n-dimensional structure. The solution of this problem is related to the solution of a well-known matrix eigenvalue problem. Moreover, it is shown that the necessary computations can be performed in the spatial domain without actually doing a Fourier transformation. Along with the orientation estimate, a certainty measure, based on the error of the fit, is proposed. Two applications in image analysis are considered: texture segmentation and optical flow. An implementation for 2-D (texture features) as well as 3-D (optical flow) is presented. In the case of 2-D, the method exploits the properties of the complex number field to by-pass the eigenvalue analysis, improving the speed and the numerical stability of the method. The theory is verified by experiments which confirm accurate orientation estimates and reliable certainty measures in the presence of noise. The comparative results indicate that the proposed theory produces algorithms computing robust texture features as well as optical flow. The computations are highly parallelizable and can be used in realtime image analysis since they utilize only elementary functions in a closed form (up to dimension 4) and Cartesian separable convolutions.

  • 37.
    Bigun, Josef
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Wiklund, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Multidimensional orientation: texture analysis and optical flow1991In: Proceedings of the SSAB Symposium on Image Analysis: Stockholm, 1991, p. 110-113Conference paper (Refereed)
  • 38.
    Bigün, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision . Linköping University, The Institute of Technology.
    A Structure Feature for Some Image Processing Applications Based on Spiral Functions1990In: Computer Vision, Graphics and Image Processing, ISSN 0734-189X, Vol. 51, no 2, p. 166-194Article in journal (Refereed)
    Abstract [en]

    A new low-level vision primitive based on logarithmic spirals is presented for various image processing tasks. The detection of such primitives is equivalent to detection of lines and edges in another coordinate system which has been used to model the mapping of the visual field to the striate cortex. Algorithms detecting the proposed primitives and pointing out a matched subclass are presented along with necessary theory. As a result, if the local structure is describable by the proposed primitives then a certainty parameter based on a well-defined mismatch (error) function will indicate this. Moreover, the best fit of a subclass of the proposed primitives in the least squares sense will be computed. The resulting images are unthresholded. They are computed by means of simple convolutions and pixelwise arithmetic operations which make the algorithms suitable for real time image processing applications. Since the resulting images contain information about the local structure, they can be used as feature images in applications like remote sensing, texture analysis, and object recognition. Experimental results on the latter including synthetic as well as natural images are presented along with noise sensitivity tests. The results exhibit good detection properties for the subclasses of the modeled primitives along with uniform and reliable behavior of the corresponding certainty measures.

  • 39.
    Bigün, Josef
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Local symmetry features in image processing1988Doctoral thesis, monograph (Other academic)
    Abstract [en]

    The extraction of features is necessary for all aspects of image processing and analysis such as classification, segmentation, enhancement and coding. In the course of developing models to describe images, a need arises for description of more complex structures than lines. This need does not reject the importance of line structures but indicates the need to complement and utilize them in a more systematic way.

    In this thesis, some new methods for extraction of local symmetry features as well as experimental results and applications are presented. The local images are expanded in terms of orthogonal functions with iso-value curves being harmonic functions. Circular, linear, hyperbolic and parabolic structures are studied in particular and some two-step algorithms involving only convolutions are given for detection purposes. Confidence measures with a reliability verified by both theoretical and experimental studies, are proposed. The method is extended to symmetric patterns fulfilling certain general conditions. It is shown that in the general case the resulting algorithms are implementable through the same computing schemes used for detection of linear structures except for a use of different filters.

    Multidimensional linear symmetry is studied and an application problem in 3-D or in particular, optical flow, and the solution proposed by this general framework is presented. The solution results in a closed form algorithm consisting of two steps, in which spatio-temporal gradient and Gaussian filtering are performed. The result consists of an optical flow estimate minimizing the linear symmetry criterion and a confidence measure based on the minimum error. The frequency band sensitivity of the obtained results is found to be possible to control. Experimental results are presented.

  • 40.
    Bjurström, Håkan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Svensson, Jon
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Assessment of Grapevine Vigour Using Image Processing2002Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This Master’s thesis studies the possibility of using image processing as a tool to facilitate vine management, in particular shoot counting and assessment of the grapevine canopy. Both are areas where manual inspection is done today. The thesis presents methods of capturing images and segmenting different parts of a vine. It also presents and evaluates different approaches on how shoot counting can be done. Within canopy assessment, the emphasis is on methods to estimate canopy density. Other possible assessment areas are also discussed, such as canopy colour and measurement of canopy gaps and fruit exposure. An example of a vine assessment system is given.

  • 41.
    Björk, Mårten
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Max, Sofia
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    ARTSY: A Reproduction Transaction System2003Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    A Transaction Reproduction System (ARTSY) is a distributed system that enables secure transactions and reproductions of digital content over an insecure network. A field of application is reproductions of visual arts: A print workshop could for example use ARTSY to print a digital image that is located at a remote museum. The purpose of this master thesis project was to propose a specification for ARTSY and to show that it is technically feasible to implement it.

    An analysis of the security threats in the ARTSY context was performed and a security model was developed. The security model was approved by a leading computer security expert. The security mechanisms that were chosen for the model were: Asymmetric cryptology, digital signatures, symmetric cryptology and a public key registry. A Software Requirements Specification was developed. It contains extra directives for image reproduction systems but it is possible to use it for an arbitrary type of reproduction system. A prototype of ARTSY was implemented using the Java programming language. The prototype uses XML to manage information and Java RMI to enable remote communication between its components. It was built as a platform independent system and it has been tested and proven to be operational on the Sun Solaris platform as well as the Win32 platform.

  • 42.
    Björling, Robin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Denoising of Infrared Images Using Independent Component Analysis2005Independent thesis Basic level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The purpose of this thesis is to evaluate the applicability of the method Independent Component Analysis (ICA) for noise reduction of infrared images. The focus lies on reducing the additive uncorrelated noise and the sensor specific additive Fixed Pattern Noise (FPN). The well known method sparse code shrinkage, in combination with ICA, is applied to reduce the uncorrelated noise degrading infrared images. The result is compared to an adaptive Wiener filter. A novel method, also based on ICA, for reducing FPN is developed. An independent component analysis is made on images from an infrared sensor and typical fixed pattern noise components are manually identified. The identified components are used to fast and effectively reduce the FPN in images taken by the specific sensor. It is shown that both the FPN reduction algorithm and the sparse code shrinkage method work well for infrared images. The algorithms are tested on synthetic as well as on real images and the performance is measured.

  • 43.
    Borg, Johan
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Detecting and Tracking Players in Football Using Stereo Vision2007Independent thesis Advanced level (degree of Master (One Year)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

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

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

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

  • 44.
    Borga, Magnus
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Hierarchical Reinforcement Learning1993In: ICANN'93 eds S. Gielen and B. Kappen: Amsterdam, 1993Conference paper (Refereed)
    Abstract [en]

    A hierarchical representation of the input-output transition function in a learning system is suggested. The choice of either representing the knowledge in a learning system as a discrete set of input-output pairs or as a continuous input-output transition function is discussed. The conclusion that both representations could be efficient, but at different levels of abstraction is made. The difference between strategies and actions is defined. An algorithm for using adaptive critic methods in a two-level reinforcement learning system is presented. Simulations of a one dimensional hierarchical reinforcement learning system is presented.

  • 45.
    Borga, Magnus
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Learning Multidimensional Signal Processing1998Doctoral thesis, monograph (Other academic)
    Abstract [en]

    The subject of this dissertation is to show how learning can be used for multidimensional signal processing, in particular computer vision. Learning is a wide concept, but it can generally be defined as a system’s change of behaviour in order to improve its performance in some sense.

    Learning systems can be divided into three classes: supervised learning, reinforcement learning and unsupervised learning. Supervised learning requires a set of training data with correct answers and can be seen as a kind of function approximation. A reinforcement learning system does not require a set of answers. It learns by maximizing a scalar feedback signal indicating the system’s performance. Unsupervised learning can be seen as a way of finding a good representation of the input signals according to a given criterion.

    In learning and signal processing, the choice of signal representation is a central issue. For high-dimensional signals, dimensionality reduction is often necessary. It is then important not to discard useful information. For this reason, learning methods based on maximizing mutual information are particularly interesting.

    A properly chosen data representation allows local linear models to be used in learning systems. Such models have the advantage of having a small number of parameters and can for this reason be estimated by using relatively few samples. An interesting method that can be used to estimate local linear models is canonical correlation analysis (CCA). CCA is strongly related to mutual information. The relation between CCA and three other linear methods is discussed. These methods are principal component analysis (PCA), partial least squares (PLS) and multivariate linear regression (MLR). An iterative method for CCA, PCA, PLS and MLR, in particular low-rank versions of these methods, is presented.

    A novel method for learning filters for multidimensional signal processing using CCA is presented. By showing the system signals in pairs, the filters can be adapted to detect certain features and to be invariant to others. A new method for local orientation estimation has been developed using this principle. This method is significantly less sensitive to noise than previously used methods.

    Finally, a novel stereo algorithm is presented. This algorithm uses CCA and phase analysis to detect the disparity in stereo images. The algorithm adapts filters in each local neighbourhood of the image in a way which maximizes the correlation between the filtered images. The adapted filters are then analysed to find the disparity. This is done by a simple phase analysis of the scalar product of the filters. The algorithm can even handle cases where the images have different scales. The algorithm can also handle depth discontinuities and give multiple depth estimates for semi-transparent images.

  • 46.
    Borga, Magnus
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Reinforcement Learning Using Local Adaptive Models1995Licentiate thesis, monograph (Other academic)
    Abstract [en]

    In this thesis, the theory of reinforcement learning is described and its relation to learning in biological systems is discussed. Some basic issues in reinforcement learning, the credit assignment problem and perceptual aliasing, are considered. The methods of temporal difference are described. Three important design issues are discussed: information representation and system architecture, rules for improving the behaviour and rules for the reward mechanisms. The use of local adaptive models in reinforcement learning is suggested and exemplified by some experiments. This idea is behind all the work presented in this thesis. A method for learning to predict the reward called the prediction matrix memory is presented. This structure is similar to the correlation matrix memory but differs in that it is not only able to generate responses to given stimuli but also to predict the rewards in reinforcement learning. The prediction matrix memory uses the channel representation, which is also described. A dynamic binary tree structure that uses the prediction matrix memories as local adaptive models is presented. The theory of canonical correlation is described and its relation to the generalized eigenproblem is discussed. It is argued that the directions of canonical correlations can be used as linear models in the input and output spaces respectively in order to represent input and output signals that are maximally correlated. It is also argued that this is a better representation in a response generating system than, for example, principal component analysis since the energy of the signals has nothing to do with their importance for the response generation. An iterative method for finding the canonical correlations is presented. Finally, the possibility of using the canonical correlation for response generation in a reinforcement learning system is indicated.

  • 47.
    Borga, Magnus
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Carlsson, Tomas
    n/a.
    A Survey of Current Techniques for Reinforcement Learning1992Report (Other academic)
    Abstract [en]

    This survey considers response generating systems that improve their behaviour using reinforcement learning. The difference between unsupervised learning, supervised learning, and reinforcement learning is described. Two general problems concerning learning systems are presented; the credit assignment problem and the problem of perceptual aliasing. Notations and some general issues concerning reinforcement learning systems are presented. Reinforcement learning systems are further divided into two main classes; memory mapping and projective mapping systems. Each of these classes is described and some examples are presented. Some other approaches are mentioned that do not fit into the two main classes. Finally some issues not covered by the surveyed articles are discussed, and some comments on the subject are made.

  • 48.
    Borga, Magnus
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    A Binary Competition Tree for Reinforcement Learning1994Report (Other academic)
    Abstract [en]

    A robust, general and computationally simple reinforcement learning system is presented. It uses a channel representation which is robust and continuous. The accumulated knowledge is represented as a reward prediction function in the outer product space of the input- and output channel vectors. Each computational unit generates an output simply by a vector-matrix multiplication and the response can therefore be calculated fast. The response and a prediction of the reward are calculated simultaneously by the same system, which makes TD-methods easy to implement if needed. Several units can cooperate to solve more complicated problems. A dynamic tree structure of linear units is grown in order to divide the knowledge space into a sufficiently number of regions in which the reward function can be properly described. The tree continuously tests split- and prune criteria in order to adapt its size to the complexity of the problem.

  • 49.
    Borga, Magnus
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    An Adaptive Stereo Algorithm Based on Canonical Correlation Analysis1998In: Proceedings of the Second IEEE International Conference on Intelligent Processing Systems: Gold Coast, Austalia, 1998, p. 177-182Conference paper (Refereed)
    Abstract [en]

    This paper presents a novel algorithm that uses CCA and phase analysis to detect the disparity in stereo images. The algorithm adapts filters in each local neighbourhood of the image in a way which maximizes the correlation between the filtered images. The adapted filters are then analyzed to find the disparity. This is done by a simple phase analysis of the scalar product of the filters. The algorithm can even handle cases where the images have different scales. The algorithm can also handle depth discontinuities and give multiple depth estimates for semi-transparent images.

  • 50.
    Borga, Magnus
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Knutsson, Hans
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    An Adaptive Stereo Algorithm Based on Canonical Correlation Analysis1998Report (Other academic)
1234567 1 - 50 of 595
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf