liu.seSearch for publications in DiVA
Change search
Refine search result
1234567 151 - 200 of 595
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.
  • 151.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Larsson, Fredrik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Wang, Han
    National University Singapore.
    Ynnerman, Anders
    Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, The Institute of Technology.
    Schön, Thomas
    Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
    Torchlight Navigation2010In: Proceedings of the 20th International Conferenceon Pattern Recognition, 2010, p. 302-306Conference paper (Refereed)
    Abstract [en]

    A common computer vision task is navigation and mapping. Many indoor navigation tasks require depth knowledge of flat, unstructured surfaces (walls, floor, ceiling). With passive illumination only, this is an ill-posed problem. Inspired by small children using a torchlight, we use a spotlight for active illumination. Using our torchlight approach, depth and orientation estimation of unstructured, flat surfaces boils down to estimation of ellipse parameters. The extraction of ellipses is very robust and requires little computational effort.

  • 152.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Larsson, Fredrik
    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.
    Wadströmer, Niclas
    FOI.
    Ahlberg, Jörgen
    Termisk Systemteknik AB.
    Online Learning of Correspondences between Images2013In: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 35, no 1, p. 118-129Article in journal (Refereed)
    Abstract [en]

    We propose a novel method for iterative learning of point correspondences between image sequences. Points moving on surfaces in 3D space are projected into two images. Given a point in either view, the considered problem is to determine the corresponding location in the other view. The geometry and distortions of the projections are unknown as is the shape of the surface. Given several pairs of point-sets but no access to the 3D scene, correspondence mappings can be found by excessive global optimization or by the fundamental matrix if a perspective projective model is assumed. However, an iterative solution on sequences of point-set pairs with general imaging geometry is preferable. We derive such a method that optimizes the mapping based on Neyman's chi-square divergence between the densities representing the uncertainties of the estimated and the actual locations. The densities are represented as channel vectors computed with a basis function approach. The mapping between these vectors is updated with each new pair of images such that fast convergence and high accuracy are achieved. The resulting algorithm runs in real-time and is superior to state-of-the-art methods in terms of convergence and accuracy in a number of experiments.

  • 153.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Scharr, Hanno
    n/a.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    The B-Spline Channel Representation: Channel Algebra and Channel Based Diffusion Filtering2002Report (Other academic)
    Abstract [en]

    In this paper we consider the channel representation based upon quadratic B-splines from a statistical point of view. Interpreting the channel representation as a kernel method for estimating probability density functions, we establish a channel algebra which allows to perform basic algebraic operations on measurements directly in the channel representation. Furthermore, as a central point, we identify the smoothing of channel values with a robust estimator, or equivalently, a diffusion process.

  • 154.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Shaukat, Affan
    University of Surrey, Guildford, UK..
    Windridge, David
    University of Surrey, Guildford, UK..
    Online Learning in Perception-Action Systems2010In: ECCV 2010 Workshop on Vision for Cognitive Tasks, 2010Conference paper (Refereed)
    Abstract [en]

    In this position paper, we seek to extend the layered perception-action paradigm for on-line learning such that it includes an explicit symbolic processing capability. By incorporating symbolic processing at the apex of the perception action hierarchy in this way, we ensure that abstract symbol manipulation is fully grounded, without the necessity of specifying an explicit representational framework. In order to carry out this novel interfacing between symbolic and sub-symbolic processing, it is necessary to embed fuzzy rst-order logic theorem proving within a variational framework. The online learning resulting from the corresponding Euler-Lagrange equations establishes an extended adaptability compared to the standard subsumption architecture. We discuss an application of this approach within the eld of advanced driver assistance systems, demonstrating that a closed-form solution to the Euler Lagrange optimization problem is obtainable for simple cases.

     

  • 155.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Sommer, Gerald
    n/a.
    Image Features Based on a New Approach to 2D Rotation Invariant Quadrature Filters2002In: Computer Vision - ECCV 2002 eds A. Heyden and G. Sparr and M. Nielsen and P. Johansen, 2002, Vol. 2350, p. 369-383Conference paper (Refereed)
    Abstract [en]

    Quadrature filters are a well known method of low-level computer vision for estimating certain properties of the signal, as there are local amplitude and local phase. However, 2D quadrature filters suffer from being not rotation invariant. Furthermore, they do not allow to detect truly 2D features as corners and junctions unless they are combined to form the structure tensor. The present paper deals with a new 2D generalization of quadrature filters which is rotation invariant and allows to analyze intrinsically 2D signals. Hence, the new approach can be considered as the union of properties of quadrature filters and of the structure tensor. The proposed method first estimates the local orientation of the signal which is then used for steering some basis filter responses. Certain linear combination of these filter responses are derived which allow to estimate the local isotropy and two perpendicular phases of the signal. The phase model is based on the assumption of an angular band-limitation in the signal. As an application, a simple and efficient point-of-interest operator is presented and it is compared to the Plessey detector.

  • 156.
    Felsberg, Michael
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Sommer, Gerald
    The Monogenic Scale-Space: A Unifying Approach to Phase-Based Image Processing in Scale-Space2004In: Journal of Mathematical Imaging and Vision, ISSN 0924-9907, E-ISSN 1573-7683, Vol. 21Article in journal (Refereed)
    Abstract [en]

    In this paper we address the topics of scale-space and phase-based image processing in a unifying framework. In contrast to the common opinion, the Gaussian kernel is not the unique choice for a linear scale-space. Instead, we chose the Poisson kernel since it is closely related to the monogenic signal, a 2D generalization of the analytic signal, where the Riesz transform replaces the Hilbert transform. The Riesz transform itself yields the flux of the Poisson scale-space and the combination of flux and scale-space, the monogenic scale-space, provides the local features phase-vector and attenuation in scale-space. Under certain assumptions, the latter two again form a monogenic scale-space which gives deeper insight to low-level image processing. In particular, we discuss edge detection by a new approach to phase congruency and its relation to amplitude based methods, reconstruction from local amplitude and local phase, and the evaluation of the local frequency.

     

  • 157.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Sommer, Gerald
    n/a.
    The monogenic signal2001In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 49, no 12, p. 3136-3144Article in journal (Refereed)
    Abstract [en]

    This paper introduces a two-dimensional generalization of the analytic signal. This novel approach is based on the Riesz transform, which is used instead of the Hilbert transform. The combination of a 2D signal with the Riesz transformed one yields a sophisticated 2D analytic signal, the monogenic signal. The approach is derived analytically from irrotational and solenoidal vector fields. Based on local amplitude and local phase, an appropriate local signal representation is presented which preserves the split of identity, i.e., the invariance – equivariance property of signal decomposition. This is one of the central properties of the 1D analytic signal that decomposes a signal into structural and energetic information. We show that further properties of the analytic signal concerning symmetry, energy, allpass transfer function, and orthogonality are also preserved, and we compare this to the behavior of other approaches for a 2D analytic signal. As a central topic of this paper, a geometric phase interpretation is introduced which is based on the relation between the 1D analytic signal and the 2D monogenic signal established by the Radon transform. Possible applications of this relationship are sketched and references to other applications of the monogenic signal are given. This report is a revised version of the technical report 2009 [7], and therefore supercedes it.

  • 158.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Sommer, Gerald
    n/a.
    The Poisson Scale-Space: A Unified Approach to Phase-Based Image Processing in Scale-Space2002Report (Other academic)
    Abstract [en]

    In this paper we address the topics of scale-space and phase-based signal processing in a common framework. The involved linear scale-space is no longer based on the Gaussian kernel but on the Poisson kernel. The resulting scale-space representation is directly related to the monogenic signal, a 2D generalization of the analytic signal. Hence, the local phase arises as a natural concept in this framework which results in several advanced relationships that can be used in image processing.

  • 159.
    Felsberg, Michael
    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.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Exploratory learning structures in artificial cognitive systems2009In: Image and Vision Computing, ISSN 0262-8856, Vol. 27, no 11, p. 1671-1687Article in journal (Refereed)
    Abstract [en]

    The major goal of the COSPAL project is to develop an artificial cognitive system architecture, with the ability to autonomously extend its capabilities. Exploratory learning is one strategy that allows an extension of competences as provided by the environment of the system. Whereas classical learning methods aim at best for a parametric generalization, i.e., concluding from a number of samples of a problem class to the problem class itself, exploration aims at applying acquired competences to a new problem class, and to apply generalization on a conceptual level, resulting in new models. Incremental or online learning is a crucial requirement to perform exploratory learning. In the COSPAL project, we mainly investigate reinforcement-type learning methods for exploratory learning, and in this paper we focus on the organization of cognitive systems for efficient operation. Learning is used over the entire system. It is organized in the form of four nested loops, where the outermost loop reflects the user-reinforcement-feedback loop, the intermediate two loops switch between different solution modes at symbolic respectively sub-symbolic level, and the innermost loop performs the acquired competences in terms of perception-action cycles. We present a system diagram which explains this process in more detail. We discuss the learning strategy in terms of learning scenarios provided by the user. This interaction between user (teacher) and system is a major difference to classical robotics systems, where the system designer places his world model into the system. We believe that this is the key to extendable robust system behavior and successful interaction of humans and artificial cognitive systems. We furthermore address the issue of bootstrapping the system, and, in particular, the visual recognition module. We give some more in-depth details about our recognition method and how feedback from higher levels is implemented. The described system is however work in progress and no final results are available yet. The available preliminary results that we have achieved so far, clearly point towards a successful proof of the architecture concept.

  • 160.
    Felsberg, Michael
    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.
    Jonsson, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Moe, Anders
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Exploratory Learning Structure in Artificial Cognitive Systems2006Report (Other academic)
    Abstract [en]

    One major goal of the COSPAL project is to develop an artificial cognitive system architecture with the capability of exploratory learning. Exploratory learning is a strategy that allows to apply generalization on a conceptual level, resulting in an extension of competences. Whereas classical learning methods aim at best possible generalization, i.e., concluding from a number of samples of a problem class to the problem class itself, exploration aims at applying acquired competences to a new problem class. Incremental or online learning is an inherent requirement to perform exploratory learning.

    Exploratory learning requires new theoretic tools and new algorithms. In the COSPAL project, we mainly investigate reinforcement-type learning methods for exploratory learning and in this paper we focus on its algorithmic aspect. Learning is performed in terms of four nested loops, where the outermost loop reflects the user-reinforcement-feedback loop, the intermediate two loops switch between different solution modes at symbolic respectively sub-symbolic level, and the innermost loop performs the acquired competences in terms of perception-action cycles. We present a system diagram which explains this process in more detail.

    We discuss the learning strategy in terms of learning scenarios provided by the user. This interaction between user (’teacher’) and system is a major difference to most existing systems where the system designer places his world model into the system. We believe that this is the key to extendable robust system behavior and successful interaction of humans and artificial cognitive systems.

    We furthermore address the issue of bootstrapping the system, and, in particular, the visual recognition module.We give some more in-depth details about our recognition method and how feedback from higher levels is implemented. The described system is however work in progress and no final results are available yet. The available preliminary results that we have achieved so far, clearly point towards a successful proof of the architecture concept.

  • 161.
    Felsberg, Michael
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Wiklund, Johan
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Jonsson, Erik
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Moe, Anders
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Granlund, Gösta
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Exploratory Learning Strucutre in Artificial Cognitive Systems2007In: International Cognitive Vision Workshop, Bielefeld: eCollections , 2007Conference paper (Other academic)
    Abstract [en]

    One major goal of the COSPAL project is to develop an artificial cognitive system architecture with the capability of exploratory learning. Exploratory learning is a strategy that allows to apply generalization on a conceptual level, resulting in an extension of competences. Whereas classical learning methods aim at best possible generalization, i.e., concluding from a number of samples of a problem class to the problem class itself, exploration aims at applying acquired competences to a new problem class. Incremental or online learning is an inherent requirement to perform exploratory learning.

    Exploratory learning requires new theoretic tools and new algorithms. In the COSPAL project, we mainly investigate reinforcement-type learning methods for exploratory learning and in this paper we focus on its algorithmic aspect. Learning is performed in terms of four nested loops, where the outermost loop reflects the user-reinforcement-feedback loop, the intermediate two loops switch between different solution modes at symbolic respectively sub-symbolic level, and the innermost loop performs the acquired competences in terms of perception-action cycles. We present a system diagram which explains this process in more detail.

    We discuss the learning strategy in terms of learning scenarios provided by the user. This interaction between user ('teacher') and system is a major difference to most existing systems where the system designer places his world model into the system. We believe that this is the key to extendable robust system behavior and successful interaction of humans and artificial cognitive systems.

    We furthermore address the issue of bootstrapping the system, and, in particular, the visual recognition module. We give some more in-depth details about our recognition method and how feedback from higher levels is implemented. The described system is however work in progress and no final results are available yet. The available preliminary results that we have achieved so far, clearly point towards a successful proof of the architecture concept.

  • 162.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Autonomous Navigation using Active Perception2001Report (Other academic)
    Abstract [en]

    This report starts with an introduction to the concepts active perception, reactive systems, and state dependency, and to fundamental aspects of perception such as the perceptual aliasing problem, and the number-of-percepts vs. number-of-states trade-off. We then introduce finite state machines, and extend them to accommodate active perception. Finally we demonstrate a state-transition mechanism that is applicable to autonomous navigation.

  • 163.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Channel Smoothing using Integer Arithmetic2003In: Proceedings SSAB03 Symposium on Image Analysis, 2003Conference paper (Refereed)
    Abstract [en]

    This paper presents experiments on using integer arithmetic with the channel representation. Integer arithmetic allows reduction of memory requirements, and allows efficient implementations using machine code vector instructions, integer-only CPUs, or dedicated programmable hardware such as FPGAs possible. We demonstrate the effects of discretisation on a non-iterative robust estimation technique called channel smoothing, but the results are also valid for other applications.

  • 164.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Image Analysis using Soft Histograms2001In: Proceedings of the SSAB Symposium on Image Analysis: Norrköping, 2001, p. 109-112Conference paper (Refereed)
    Abstract [en]

    This paper advocates the use of overlapping bins in histogram creation. It is shown how conventional histogram creation has an inherent quantisation that cause errors much like those in sampling with insufficient band limitation. The use of overlapping bins is shown to be the deterministic equivalent to dithering. Two applications of soft histograms are shown: Improved peak localisation in an estimated probability density function (PDF) without requiring more samples, and accurate estimation of image rotation.

  • 165.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Observations Concerning Reconstructions with Local Support2002Report (Other academic)
    Abstract [en]

    This report describes how the choice of kernel affects a non-parametric density estimation. Methods for accurate localisation of peaks in the estimated densities are developed for Gaussian and cos2 kernels. The accuracy and robustness of the peak localisation methods are studied with respect to noise, number of samples, and interference between peaks. Although the peak localisation is formulated in the framework of non-parametric density estimation, the results are also applicable to associative learning with localised responses.

  • 166.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Successive Recognition using Local State Models2002In: Proceedings SSAB02 Symposium on Image Analysis: Lund, 2002, p. 9-12Conference paper (Refereed)
    Abstract [en]

    This paper describes how a world model for successive recognition can be learned using associative learning. The learned world model consists of a linear mapping that successively updates a high-dimensional system state using performed actions and observed percepts. The actions of the system are learned by rewarding actions that are good at resolving state ambiguities. As a demonstration, the system is used to resolve the localisation problem in a labyrinth.

  • 167.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Updating Camera Location and Heading using a Sparse Displacement Field2000Report (Other academic)
    Abstract [en]

    This report describes the principles of an algorithm developed within the WITAS project. The goal of the WITAS project is to build an autonomous helicopter that can navigate autonomously, using differential GPS, GIS-data of the underlying terrain (elevation models and digital orthophotographs) and a video camera. Using differential GPS and other non-visual sensory equipment, the system is able to obtain crude estimates of its position and heading direction. These estimates can be refined by matching of camera-images and the on-board GIS-data. This refinement process, however is rather time consuming, and will thus only be made every once in a while. For real-time refinement of camera position and heading, the system will iteratively update the estimates using frame to frame correspondence only. In each frame a sparse set of image displacement estimates is calculated, and from these the perspective in the current image can be found. Using the calculated perspective and knowledge of the camera parameters, new values of camera position and heading can be obtained. The resultant camera position and heading can exhibit a slow drift if the original alignment was not perfect, and thus a corrective alignment with GIS-data should be performed once every minute or so.

  • 168.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Window Matching using Sparse Templates2001Report (Other academic)
    Abstract [en]

    This report describes a novel window matching technique. We perform window matching by transforming image data into sparse features, and apply a computationally efficient matching technique in the sparse feature space. The gain in execution time for the matching is roughly 10 times compared to full window matching techniques such as SSD, but the total execution time for the matching also involves an edge filtering step. Since the edge responses may be used for matching of several regions, the proposed matching technique is increasingly advantageous when the number of regions to keep track of increases, and when the size of the search window increases. The technique is used in a real-time ego-motion estimation system in the WITAS project. Ego-motion is estimated by tracking of a set of structure points, i.e. regions that do not have the aperture problem. Comparisons with SSD, with regard to speed and accuracy are made.

  • 169.
    Forssen, Per-Erik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta
    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.
    Channel Representation of Colour Images2002Report (Other academic)
    Abstract [en]

    In this report we describe how an RGB component colour image may be expanded into a set of channel images, and how the original colour image may be reconstructed from these. We also demonstrate the effect of averaging on the channel images and how it differs from conventional averaging. Finally we demonstrate how boundaries can be detected as a change in the confidence of colour state.

  • 170.
    Forssen, Per-Erik
    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.
    Fractal Coding by Means of Local Feature Histograms2000Report (Other academic)
    Abstract [en]

    This report describes an experimental still image coder that grew out of a project in the graduate course ``Advanced Video Coding'' in spring 2000. The project has investigated the idea to use local orientation histograms in fractal coding. Instead of performing a correlation-like grey-level matching of image regions, the block search is made by matching feature histograms of the block contents. The feature investigated in this report is local orientation, but in principle other features could be used as well. In its current state the coder does not outperform state of the art still image coders, but the block-search strategy seems promising, and will probably prove useful in several other applications.

  • 171.
    Forssen, Per-Erik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Moe, Anders
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Automatic Estimation of Epipolar Geometry from Blob Features2004Report (Other academic)
    Abstract [en]

    This report describes how blob features can be used for automatic estimation of the fundamental matrix from two perspective projections of a 3D scene. Blobs are perceptually salient, homogeneous, compact image regions. They are represented by their average colour, area, centre of gravity and inertia matrix. Coarse blob correspondences are found by voting using colour and local similarity transform matching on blob pairs. We then do RANSAC sampling of the coarse correspondences, and weight each estimate according to how well the approximating conics and colours of two blobs correspond. The initial voting significantly reduces the number of RANSAC samples required, and the extra information besides position, allows us to reject false matches more accurately than in RANSAC using point features.

  • 172.
    Forssen, Per-Erik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Moe, Anders
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Contour Descriptors for View-Based Object Recognition2005Report (Other academic)
    Abstract [en]

    This report introduces a robust contour descriptor for view-based object recognition. In recent years great progress has been made in the field of view based object recognition mainly due to the introduction of texture based features such as SIFT and MSER. Although these are remarkably successful for textured objects, they have problems with man-made objects with little or no texture. For such objects, either explicit geometrical models, or contour and shading based features are also needed. This report introduces a robust contour descriptor which we hope can be combined with texture based features to obtain object recognition systems that work in a wider range of situations. Each detected contour is described as a sequence of line and ellipse segments, both which have well defined geometrical transformations to other views. The feature detector is also quite fast, this is mainly due to the idea of first detecting chains of contour points, these chains are then split into line segments, which are later either kept, grouped into ellipses or discarded. We demonstrate the robustness of the feature detector with a repeatability test under general homography transformations of a planar scene. Through the repeatability test, we find that using ellipse segments instead of lines, where this is appropriate improves repeatability. We also apply the features in a robotic setting where object appearances are learned by manipulating the objects.

  • 173.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Detection of Man-made Objects in Satellite Images1997Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    In this report, the principles of man-made object detection in satellite images is investigated. An overview of terminology and of how the detection problem is usually solved today is given. A three level system to solve the detection problem is proposed. The main branches of this system handle road, and city detection respectively. To achieve data source flexibility, the Logical Sensor notion is used to model the low level system components. Three Logical Sensors have been implemented and tested on Landsat TM and SPOT XS scenes. These are: BDT (Background Discriminant Transformation) to construct a man-made object property field; Local-orientation for texture estimation and road tracking; Texture estimation using local variance and variance of local orientation. A gradient magnitude measure for road seed generation has also been tested.

  • 174.
    Forssén, Per-Erik
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Learning Saccadic Gaze Control via Motion Prediction2007In: IEEE Canadian CRV,2007, Montreal: IEEE Computer Society , 2007Conference paper (Refereed)
  • 175.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Low and Medium Level Vision Using Channel Representations2004Doctoral thesis, monograph (Other academic)
    Abstract [en]

    This thesis introduces and explores a new type of representation for low and medium level vision operations called channel representation. The channel representation is a more general way to represent information than e.g. as numerical values, since it allows incorporation of uncertainty, and simultaneous representation of several hypotheses. More importantly it also allows the representation of “no information” when no statement can be given. A channel representation of a scalar value is a vector of channel values, which are generated by passing the original scalar value through a set of kernel functions. The resultant representation is sparse and monopolar. The word sparse signifies that information is not necessarily present in all channels. On the contrary, most channel values will be zero. The word monopolar signifies that all channel values have the same sign, e.g. they are either positive or zero. A zero channel value denotes “no information”, and for non-zero values, the magnitude signifies the relevance.

    In the thesis, a framework for channel encoding and local decoding of scalar values is presented. Averaging in the channel representation is identified as a regularised sampling of a probability density function. A subsequent decoding is thus a mode estimation technique.'

    The mode estimation property of channel averaging is exploited in the channel smoothing technique for image noise removal. We introduce an improvement to channel smoothing, called alpha synthesis, which deals with the problem of jagged edges present in the original method. Channel smoothing with alpha synthesis is compared to mean-shift filtering, bilateral filtering, median filtering, and normalized averaging with favourable results.

    A fast and robust blob-feature extraction method for vector fields is developed. The method is also extended to cluster constant slopes instead of constant regions. The method is intended for view-based object recognition and wide baseline matching. It is demonstrated on a wide baseline matching problem.

    A sparse scale-space representation of lines and edges is implemented and described. The representation keeps line and edge statements separate, and ensures that they are localised by inhibition from coarser scales. The result is however still locally continuous, in contrast to non-max-suppression approaches, which introduce a binary threshold.

    The channel representation is well suited to learning, which is demonstrated by applying it in an associative network. An analysis of representational properties of associative networks using the channel representation is made.

    Finally, a reactive system design using the channel representation is proposed. The system is similar in idea to recursive Bayesian techniques using particle filters, but the present formulation allows learning using the associative networks.

  • 176.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Sparse Representations for Medium Level Vision2001Licentiate thesis, monograph (Other academic)
    Abstract [en]

    In this thesis a new type of representation for medium level vision operations is explored. We focus on representations that are sparse and monopolar. The word sparse signifies that information in the feature sets used is not necessarily present at all points. On the contrary, most features will be inactive. The word monopolar signifies that all features have the same sign, e.g. are either positive or zero. A zero feature value denotes ``no information'', and for non-zero values, the magnitude signifies the relevance.

    A sparse scale-space representation of local image structure (lines and edges) is developed.

    A method known as the channel representation is used to generate sparse representations, and its ability to deal with multiple hypotheses is described. It is also shown how these hypotheses can be extracted in a robust manner.

    The connection of soft histograms (i.e. histograms with overlapping bins) to the channel representation, as well as to the use of dithering in relaxation of quantisation errors is shown. The use of soft histograms for estimation of unknown probability density functions (PDF), and estimation of image rotation are demonstrated.

    The advantage with the use of sparse, monopolar representations in associative learning is demonstrated.

    Finally we show how sparse, monopolar representations can be used to speed up and improve template matching.

  • 177.
    Forssén, Per-Erik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Robust multi-scale extraction of blob features2003In: Proceedings or the 13th Scandinavian Conference, SCIA 2003 / [ed] Josef Bigun and Tomas Gustavsson, Berlin, Heidelberg: Springer Berlin/Heidelberg, 2003, Vol. 2749, p. 769-769Conference paper (Refereed)
    Abstract [en]

    This paper presents a method for detection of homogeneous regions in grey-scale images, representing them as blobs. In order to be fast, and not to favour one scale over others, the method uses a scale pyramid. In contrast to most multi-scale methods this one is non-linear, since it employs robust estimation rather than averaging to move through scale-space. This has the advantage that adjacent and partially overlapping clusters only affect each other's shape, not each other's values. It even allows blobs within blobs, to provide a pyramid blob structure of the image.

  • 178.
    Forssén, Per-Erik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Sparse feature maps in a scale hierarchy2000In: Algebraic Frames for the Perception-Action Cycle, Proceedings Second International Workshop, AFPAC 2000 / [ed] Gerald Sommer and Yehoshua Y. Zeevi, Berlin, Heidelberg: Springer Berlin/Heidelberg, 2000, Vol. 1888, p. 186-196Conference paper (Refereed)
    Abstract [en]

    This article describes an essential step towards what is called a view centered representation of the low-level structure in an image. Instead of representing low-level structure (lines and edges) in one compact feature map, we will separate structural information into several feature maps, each signifying features at a characteristic phase, in a specific scale. By characteristic phase we mean the phases 0, pi, and +/-pi/2, corresponding to bright, and dark lines, and edges between different intensity levels, or colours. A lateral inhibition mechanism selects the strongest feature within each local region of scale represented. The scale representation is limited to maps one octave apart, but can be interpolated to provide a continous representation. The resultant image representation is sparse, and thus well suited for further processing, such as pattern detection.

  • 179.
    Forssén, Per-Erik
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Johansson, Björn
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Granlund, Gösta
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Channel Associative Networks for Multiple Valued Mappings2006In: 2nd International Cognitive Vision Workshop, 2006, p. 4-11Conference paper (Other academic)
  • 180.
    Forssén, Per-Erik
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Johansson, Björn
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Granlund, Gösta
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Learning under Perceptual Aliasing2005Report (Other academic)
  • 181.
    Forssén, Per-Erik
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Lowe, David G.
    University of British Columbia.
    Maximally Stable Colour Regions for Recognition and Matching2007Conference paper (Refereed)
  • 182.
    Forssén, Per-Erik
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Lowe, David G.
    UBC.
    Shape Descriptors for Maximally Stable Extremal Regions2007In: IEEE ICCV,2007, Rio de Janeiro, Brazil: IEEE Computer Society , 2007Conference paper (Refereed)
  • 183.
    Forssén, Per-Erik
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Meger, David
    UBC.
    Lai, Kevin
    UBC.
    Helmer, Scott
    UBC.
    Little, James J.
    UBC.
    Lowe, David G.
    UBC.
    Informed Visual Search: Combining Attention and Object Recognition2008In: Proceedings - IEEE International Conference on Robotics and Automation, Pasadena: IEEE Robotics and Automation Society , 2008, p. 935-942Conference paper (Refereed)
    Abstract [en]

    This paper studies the sequential object recognition problem faced by a mobile robot searching for specific objects within a cluttered environment. In contrast to current state-of-the-art object recognition solutions which are evaluated on databases of static images, the system described in this paper employs an active strategy based on identifying potential objects using an attention mechanism and planning to obtain images of these objects from numerous viewpoints. We demonstrate the use of a bag-of-features technique for ranking potential objects, and show that this measure outperforms geometric matching for invariance across viewpoints. Our system implements informed visual search by prioritising map locations and re-examining promising locations first. Experimental results demonstrate that our system is a highly competent object recognition system that is capable of locating numerous challenging objects amongst distractors.

  • 184.
    Forssén, Per-Erik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Moe, Anders
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Autonomous Learning of Object Appearances using Colour Contour Frames2006In: 3rd Canadian Conference on Computer and Robot Vision, CRV06, Québec City, Québec, Canada, Québec, Canada: IEEE Computer Society , 2006, p. 3-3Conference paper (Refereed)
    Abstract [en]

    In this paper we make use of the idea that a robot can autonomously discover objects and learn their appearances by poking and prodding at interesting parts of a scene. In order to make the resultant object recognition ability more robust, and discriminative, we replace earlier used colour histogram features with an invariant texture-patch method. The texture patches are extracted in a similarity invariant frame which is constructed from short colour contour segments. We demonstrate the robustness of our invariant frames with a repeatability test under general homography transformations of a planar scene. Through the repeatability test, we find that defining the frame using using ellipse segments instead of lines where this is appropriate improves repeatability. We also apply the developed features to autonomous learning of object appearances, and show how the learned objects can be recognised under out-of-plane rotation and scale changes.

  • 185.
    Forssén, Per-Erik
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Moe, Anders
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Blobs in Epipolar Geometry2004In: Blobs in Epipolar Geometry,2004, 2004, p. 82-85Conference paper (Other academic)
    Abstract [en]

     Epipolar geometry is the geometry situation of two cameras depicting the same scene. For un-calibrated cameras epipolar geometry is compactly described by the fundamental matrix. Estimation of the fundamental matrix is trivial if we have a set of corresponding points in the two images. Corresponding points are often found using e.g. the Harris interest point detector, but there are several advantages with using richer features instead. In this paper we will use blob features. Blobs are homogeneous regions which are compactly described by their colour, area, centroid and inertia matrix. Using blobs to establish correspondences is fast, and the extra information besides position, allows us to reject false matches more accurately.

  • 186.
    Forssén, Per-Erik
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Spies, Hagen
    RnD ContextVision AB.
    Multiple Motion Estimation using Channel Matrices2007In: International Workshop on Complex Motion IWCM,2004, LNCS 3417: Springer , 2007, p. 54-Conference paper (Refereed)
    Abstract [en]

     The motion field from image sequences of a dynamic 3D scene is in general piecewise continuous. Since two neighbouring regions may have completely different motions, motion estimation at the discontinuities is problematic. In particular spatial averaging of motion vectors is inappropriate at such positions. We avoid this problem by channel encoding brightness change constraint equations (BCCE) for each spatial position into a channel matrix. By spatial averaging of this channel representation and subsequently decoding we are able to estimate all significantly different motions occurring at the discontinuity, as well as their covariances. This paper extends and improves this multiple motion estimation scheme by locally selecting the appropriate scale for the spatial averaging.  

  • 187.
    Granlund, Gösta
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    A Cognitive Vision Architecture Integrating Neural Networks with Symbolic Processing2006In: Künstliche Intelligenz, ISSN 0933-1875, no 2, p. 18-24Article in journal (Other academic)
    Abstract [en]

    A fundamental property of cognitive vision systems is that they shall be extendable, which requires that they can both acquire and store information autonomously. The paper discusses organization of systems to allow this, and proposes an architecture for cognitive vision systems. The architecture consists of two parts. The first part, step by step learns a mapping from percepts directly onto actions or states. In the learning phase, action precedes perception, as action space is much less complex. This requires a semantic information representation, allowing computation and storage with respect to similarity. The second part uses invariant or symbolic representations, which are derived mainly from system and action states. Through active exploration, a system builds up concept spaces or models. This allows the system to subsequently acquire information using passive observation or language. The structure has been used to learn object properties, and constitutes the basic concepts for a European project COSPAL, within the IST programme.

  • 188.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Biological vision: a source of challenges and ideas1995In: DSAGM, Dansk Selskab for Genkendelse af Mønstre: Copenhagen, Denmark, 1995Conference paper (Other academic)
  • 189.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Description of texture using the general operator approch1980In: 5th International Conference on Pattern Recognition, 1980, p. 776-779Conference paper (Refereed)
  • 190.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision . Linköping University, The Institute of Technology.
    Does Vision Inevitably Have to be Active?1999In: Proceedings of the 11th Scandinavian Conference on Image Analysis: Kangerlussuaq, Greenland, 1999Conference paper (Refereed)
    Abstract [en]

    There is no indication that it will ever be possible to find some simple trick that miraculously solves most problems in vision. It turns out that the processing system must be able to implement a model structure, the complexity of which is directly related to the structural complexity of the problem under consideration in the external world. It has become increasingly apparent that Vision cannot be treated in isolation from the response generation, because a very high degree of integration is required between different levels of percepts and corresponding response primitives. The response to be produced at a given instance is as much dependent upon the state of the system, as the percepts impinging upon the system. In addition, it has become apparent that many classical aspects of perception, such as geometry, probably do not belong to the percept domain of a Vision system, but to the response domain. This article will focus on what are considered crucial problems in Vision for robotics for the future, rather than on the classical solutions today. It will discuss hierarchical architectures for combination of percept and response primitives. It will discuss the concept of combined percept–response invariances as important structural elements for Vision. It will be maintained that learning is essential to obtain the necessary flexibility and adaptivity. In consequence, it will be argued that invariances for the purpose of Vision are not abstractly geometrical, but derived from the percept–response interaction with the environment. The issue of information representation becomes extremely important in distributed structures of the types foreseen, where uncertainty of information has to be stated for update of models and associated data. The question of object representation is central to the paper. Equivalence is established between the representations of response, geometry and time. Finally an integrated percept–response structure is proposed for flexible response control.

  • 191.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Does Vision Inevitably Have to be Active?1998Report (Other academic)
  • 192.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    ESPRIT Project BRA 3038: Vision as Process, Final Report1993Report (Other academic)
  • 193.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Images and Computers1984Report (Other academic)
  • 194.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Organization of Architectures for Cognitive Vision Systems2006In: Cognitive Vision Systems: Sampling the Spectrum of Approaches / [ed] Henrik I. Christensen and Hans-Hellmut Nagel, Springer, 2006, 1, p. 37-55Chapter in book (Refereed)
    Abstract [en]

    This volume is a post-event proceedings volume and contains selected papers based on the presentations given, and the lively discussions that ensued, during a seminar held in Dagstuhl Castle, Germany, in October 2003. Co-sponsored by ECVision, the cognitive vision network of excellence, it was organized to further strengthen cooperation between research groups from different countries working in the field of cognitive vision systems.

  • 195.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Special issue on Perception, Action and Learning2009In: Image and Vision Computing, ISSN 0262-8856, E-ISSN 1872-8138, Vol. 27, no 11, p. 1639-1640Article in journal (Refereed)
  • 196.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision . Linköping University, The Institute of Technology.
    The Complexity of Vision1999In: Signal Processing, ISSN 0165-1684, E-ISSN 1872-7557, Vol. 74, no 1, p. 101-126Article in journal (Refereed)
    Abstract [en]

    There is no indication that it will ever be possible to find some simple trick that miraculously solves most problems in vision. It turns out that the processing system must be able to implement a model structure, the complexity of which is directly related to the structural complexity of the problem under consideration in the external world. It has become increasingly apparent that Vision cannot be treated in isolation from the response generation, because a very high degree of integration is required between different levels of percepts and corresponding response primitives. The response to be produced at a given instance is as much dependent upon the state of the system, as the percepts impinging upon the system. In addition, it has become apparent that many classical aspects of perception, such as geometry, probably do not belong to the percept domain of a Vision system, but to the response domain. This article will focus on what are considered crucial problems in Vision for robotics for the future, rather than on the classical solutions today. It will discuss hierarchical architectures for combination of percept and response primitives. It will discuss the concept of combined percept-response invariances as important structural elements for Vision. It will be maintained that learning is essential to obtain the necessary flexibility and adaptivity. In consequence, it will be argued that invariances for the purpose of Vision are not abstractly geometrical, but derived from the percept-response interaction with the environment. The issue of information representation becomes extremely important in distributed structures of the types foreseen, where uncertainty of information has to be stated for update of models and associated data. The question of object representation is central to the paper. Equivalence is established between the representations of response, geometry and time. Finally an integrated percept-response structure is proposed for flexible response control.

  • 197.
    Granlund, Gösta
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    The Dichotomy of Strategies for Spatial-Cognitive Information Processing2000Report (Other academic)
  • 198.
    Granlund, Gösta
    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.
    Johansson, Björn
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    HiperLearn: A High Performance Learning Architecture2002Report (Other academic)
    Abstract [en]

    A new architecture for learning systems has been developed. A number of particular design features in combination result in a very high performance and excellent robustness. The architecture uses a monopolar channel information representation. The channel representation implies a partially overlapping mapping of signals into a higher-dimensional space, such that a flexible but continuous restructuring mapping can be made. The high-dimensional mapping introduces locality in the information representation, which is directly available in wavelets or filter outputs. Single level maps using this representation can produce closed decision regions, thereby eliminating the need for costly back-propagation. The monopolar property implies that data only utilizes one polarity, say positive values, in addition to zero, allowing zero to represent no information. This leads to an efficient sparse representation.

    The processing mode of the architecture is association where the mapping of feature inputs onto desired state outputs is learned from a representative training set. The sparse monopolar representation together with locality, using individual learning rates, allows a fast optimization, as the system exhibits linear complexity. Mapping into multiple channels gives a strategy to use confidence statements in data, leading to a low sensitivity to noise in features. The result is an architecture allowing systems with a complexity of some hundred thousand features described by some hundred thousand samples to be trained in typically less than an hour. Experiments that demonstrate functionality and noise immunity are presented. The architecture has been applied to the design of hyper complex operations for view centered object recognition in robot vision.

  • 199.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    An Associative Perception-Action Structure using a Localized Space Variant Information Representation2000In: Algebraic Frames for the Perception-Action Cycle: second international workshop, AFPAC 2000, Kiel, Germany, September 10-11, 2000 : proceedings / [ed] Gerald Sommer and Yehoshua Y. Zeevi, Springer, 2000, p. 48-68Chapter in book (Refereed)
    Abstract [en]

    Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separation between data and operations. This also goes well with conventional Cartesian representation of data. Currently, there is a trend towards context dependent processing in various forms. This implies that operations will no longer be spatially invariant, but vary over the image dependent upon the image content. There are many ways in which such a contextual control can be implemented. Mechanisms can be added for the modification of operator behavior within the conventional computing structure. This has been done e.g. for the implementation of adaptive filtering. In order to obtain sufficient flexibility and power in the computing structure, it is necessary to go further than that. To achieve sufficiently good adaptivity, it is necessary to ensure that sufficiently complex control strategies can be represented. It is becoming increasingly apparent that this can not be achieved through prescription or program specification of rules. The reason being that these rules will be dauntingly complex and can not be be dealt with in sufficient detail. At the same time that we require the implementation of a spatially variant processing, this implies the requirement for a spatially variant information representation. Otherwise a sufficiently effective and flexible contextual control can not be implemented. This paper outlines a new structure for effective space variant processing. It utilises a new type of localized information representation, which can be viewed as outputs from band pass filters such as wavelets. A unique and important feature is that convex regions can be built up from a single layer of associating nodes. The specification of operations is made through learning or action controlled association.

  • 200.
    Granlund, Gösta H.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Bi-Directionally Adaptive Models in Image Analysis1988Report (Other academic)
1234567 151 - 200 of 595
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