liu.seSearch for publications in DiVA
Change search
Refine search result
12 1 - 50 of 85
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.
    Eilertsen, Gabriel
    et al.
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Unger, Jonas
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    BriefMatch: Dense binary feature matching for real-time optical flow estimation2017In: Proceedings of the Scandinavian Conference on Image Analysis (SCIA17) / [ed] Puneet Sharma, Filippo Maria Bianchi, Springer, 2017, Vol. 10269, p. 221-233Conference paper (Refereed)
    Abstract [en]

    Research in optical flow estimation has to a large extent focused on achieving the best possible quality with no regards to running time. Nevertheless, in a number of important applications the speed is crucial. To address this problem we present BriefMatch, a real-time optical flow method that is suitable for live applications. The method combines binary features with the search strategy from PatchMatch in order to efficiently find a dense correspondence field between images. We show that the BRIEF descriptor provides better candidates (less outlier-prone) in shorter time, when compared to direct pixel comparisons and the Census transform. This allows us to achieve high quality results from a simple filtering of the initially matched candidates. Currently, BriefMatch has the fastest running time on the Middlebury benchmark, while placing highest of all the methods that run in shorter than 0.5 seconds.

  • 2.
    Felsberg, Michael
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Forssen, P.-E.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Scharr, H.
    IEEE Computer Society, Forschungszentrum Jülich GmbH, ICG-III, 52425 Jülich, Germany.
    Channel smoothing: Efficient robust smoothing of low-level signal features2006In: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 28, no 2, p. 209-222Article in journal (Refereed)
    Abstract [en]

    In this paper, we present a new and efficient method to implement robust smoothing of low-level signal features: B-spline channel smoothing. This method consists of three steps: encoding of the signal features into channels, averaging of the channels, and decoding of the channels. We show that linear smoothing of channels is equivalent to robust smoothing of the signal features if we make use of quadratic B-splines to generate the channels. The linear decoding from B-spline channels allows the derivation of a robust error norm, which is very similar to Tukey's biweight error norm. We compare channel smoothing with three other robust smoothing techniques: nonlinear diffusion, bilateral filtering, and mean-shift filtering, both theoretically and on a 2D orientation-data smoothing task. Channel smoothing is found to be superior in four respects: It has a lower computational complexity, it is easy to implement, it chooses the global minimum error instead of the nearest local minimum, and it can also be used on nonlinear spaces, such as orientation space. © 2006 IEEE.

  • 3.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Scharr, Hanno
    n/a.
    B-Spline Channel Smoothing for Robust Estimation2004Report (Other academic)
    Abstract [en]

    In this paper we present a new method to implement a robust estimator: B-spline channel smoothing. We show that linear smoothing of channels is equivalent to a robust estimator, where we make use of the channel representation based upon quadratic B-splines. The linear decoding from B-spline channels allows to derive a robust error norm which is very similar to Tukey's biweight error norm. Using channel smoothing instead of iterative robust estimator implementations like non-linear diffusion, bilateral filtering, and mean-shift approaches is advantageous since channel smoothing is faster, it is easy to implement, it chooses the global minimum error instead of the nearest local minimum, and it can also be used on non-linear spaces, such as orientation space. As an application, we implemented orientation smoothing and compared it to the other three approaches.

  • 4.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Scharr, Hanno
    n/a.
    Efficient Robust Smoothing of Low-Level Signal Features2004Report (Other academic)
    Abstract [en]

    In this paper we present a new and efficient method to implement robust smoothing of low-level signal features: B-spline channel smoothing. This method consists of three steps: encoding of the signal features into channels, averaging of the channels, and decoding of the channels. We show that linear smoothing of channels is equivalent to robust smoothing of the signal features, where we make use of quadratic B-splines to generate the channels. The linear decoding from B-spline channels allows to derive a robust error norm which is very similar to Tukey's biweight error norm. Channel smoothing is superior to iterative robust smoothing implementations like non-linear diffusion, bilateral filtering, and mean-shift approaches for four reasons: it has lower computational complexity, it is easy to implement, it chooses the global minimum error instead of the nearest local minimum, and it can also be used on non-linear spaces, such as orientation space. In the experimental part of the paper we compare channel smoothing and the previously mentioned three other approaches for 2D orientation data.

  • 5.
    Felsberg, Michael
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Forssén, Per-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.
    A COSPAL Subsystem: Solving a Shape-Sorter Puzzle2005In: AAAI Fall Symposium: From Reactive to Anticipatory Cognitive Embedded Systems, FS-05-05, AAAI Press , 2005, p. 65-69Conference paper (Refereed)
    Abstract [en]

     To program a robot to solve a simple shape-sorter puzzle is trivial. To devise a Cognitive System Architecture, which allows the system to find out by itself how to go about a solution, is less than trivial. The development of such an architecture is one of the aims of the COSPAL project, leading to new techniques in vision based Artificial Cognitive Systems, which allow the development of robust systems for real dynamic environments. The systems developed under the project itself remain however in simplified scenarios, likewise the shape-sorter problem described in the present paper. The key property of the described system is its robustness. Since we apply association strategies of local features, the system behaves robustly under a wide range of distortions, as occlusion, colour and intensity changes. The segmentation step which is applied in many systems known from literature is replaced with local associations and view-based hypothesis validation. The hypotheses used in our system are based on the anticipated state of the visual percepts. This state replaces explicit modeling of shapes. The current state is chosen by a voting system and verified against the true visual percepts. The anticipated state is obtained from the association to the manipulator actions, where reinforcement learning replaces the explicit calculation of actions. These three differences to classical schemes allow the design of a much more generic and flexible system with a high level of robustness. On the technical side, the channel representation of information and associative learning in terms of the channel learning architecture are essential ingredients for the system. It is the properties of locality, smoothness, and non-negativity which make these techniques suitable for this kind of application. The paper gives brief descriptions of how different system parts have been implemented and show some examples from our tests.

  • 6.
    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.

  • 7.
    Felsberg, Michael
    et al.
    Linköping University, Department of Electrical Engineering.
    Scharr, Hanno
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering.
    B-spline channel smoothing for robust estimation 2004Report (Other academic)
  • 8.
    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.

  • 9.
    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.

  • 10.
    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.

  • 11.
    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.

  • 12.
    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.

  • 13.
    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.

  • 14.
    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.

  • 15.
    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.

  • 16.
    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.

  • 17.
    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.

  • 18.
    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.

  • 19.
    Forssen, Per-Erik
    et al.
    Univ British Columbia, Dept Comp Sci, Vancouver, BC V6T 1Z4 Canada.
    Moe, Anders
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    View matching with blob features2009In: Image and Vision Computing, ISSN 0262-8856, E-ISSN 1872-8138, Vol. 27, no 1-2, p. 99-107Article in journal (Refereed)
    Abstract [en]

    This article introduces a new region based feature for object recognition and image matching. In contrast to many other region based features, this one makes use of colour in the feature extraction stage. We perform experiments on the repeatability rate of the features across scale and inclination angle changes, and show that avoiding to merge regions connected by only a few pixels improves the repeatability. We introduce two voting schemes that allow us to find correspondences automatically, and compare them with respect to the number of valid correspondences they give, and their inlier ratios. We also demonstrate how the matching procedure can be applied to colour correction.

  • 20.
    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.

  • 21.
    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)
  • 22.
    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.

  • 23.
    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.

  • 24.
    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.

  • 25.
    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.

  • 26.
    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)
  • 27.
    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)
  • 28.
    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)
  • 29.
    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)
  • 30.
    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.

  • 31.
    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.

  • 32.
    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.

  • 33.
    Forssén, Per-Erik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Ringaby, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Rectifying rolling shutter video from hand-held devices2010In: IEEE  Conference on  Computer Vision and Pattern Recognition (CVPR), 2010, Los Alamitos, CA, USA: IEEE Computer Society, 2010, p. 507-514Conference paper (Other academic)
    Abstract [en]

    This paper presents a method for rectifying video sequences from rolling shutter (RS) cameras. In contrast to previous RS rectification attempts we model distortions as being caused by the 3D motion of the camera. The camera motion is parametrised as a continuous curve, with knots at the last row of each frame. Curve parameters are solved for using non-linear least squares over inter-frame correspondences obtained from a KLT tracker. We have generated synthetic RS sequences with associated ground-truth to allow controlled evaluation. Using these sequences, we demonstrate that our algorithm improves over to two previously published methods. The RS dataset is available on the web to allow comparison with other methods

  • 34.
    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.  

  • 35.
    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.

  • 36.
    Hanning, Gustav
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forslöw, Nicklas
    Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Ringaby, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Törnqvist, David
    Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
    Callmer, Jonas
    Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
    Stabilizing Cell Phone Video using Inertial Measurement Sensors2011In: The Second IEEE International Workshop on Mobile Vision, Barcelona Spain, 2011, p. 1-8Conference paper (Other academic)
    Abstract [en]

    We present a system that rectifies and stabilizes video sequences on mobile devices with rolling-shutter cameras. The system corrects for rolling-shutter distortions using measurements from accelerometer and gyroscope sensors, and a 3D rotational distortion model. In order to obtain a stabilized video, and at the same time keep most content in view, we propose an adaptive low-pass filter algorithm to obtain the output camera trajectory. The accuracy of the orientation estimates has been evaluated experimentally using ground truth data from a motion capture system. We have conducted a user study, where the output from our system, implemented in iOS, has been compared to that of three other applications, as well as to the uncorrected video. The study shows that users prefer our sensor-based system.

  • 37.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Fast and Accurate Ego-Motion Estimation2009Conference paper (Refereed)
    Abstract [en]

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

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

  • 38.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Synthetic Ground Truth for Feature Trackers2008In: Swedish Symposium on Image Analysis 2008, 2008Conference paper (Other academic)
    Abstract [en]

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

  • 39.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Fast and Accurate Structure and Motion Estimation2009In: International Symposium on Visual Computing / [ed] George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin, Yoshinori Kuno, Junxian Wang, Jun-Xuan Wang, Junxian Wang, Renato Pajarola and Peter Lindstrom et al., Berlin Heidelberg: Springer-Verlag , 2009, p. 211-222Conference paper (Refereed)
    Abstract [en]

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

  • 40.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Ringaby, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Rolling Shutter Bundle Adjustment2012Conference paper (Refereed)
    Abstract [en]

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

  • 41.
    Hedborg, Johan
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Ringaby, Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Structure and Motion Estimation from Rolling Shutter Video2011In: IEEE International Conference onComputer Vision Workshops (ICCV Workshops), 2011, IEEE Xplore , 2011, p. 17-23Conference paper (Refereed)
    Abstract [en]

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

  • 42.
    Helmer, Scott
    et al.
    UBC.
    Meger, David
    UBC.
    Forssén, Per-Erik
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Southey, Tristram
    UBC.
    McCann, Sancho
    UBC.
    Fazli, Pooyan
    UBC.
    Little, James J.
    UBC.
    Lowe, David G.
    UBC.
    The UBC Semantic Robot Vision System2007In: AAAI,2007, Vancouver: AAAI Press , 2007Conference paper (Refereed)
  • 43.
    Johansson, Björn
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Elfving, Tommy
    Linköping University, The Institute of Technology. Linköping University, Department of Mathematics, Scientific Computing.
    Kozlov, Vladimir
    Linköping University, The Institute of Technology. Linköping University, Department of Mathematics, Applied Mathematics.
    Censor, Y.
    Department of Mathematics, University of Haifa, Mt. Carmel, Haifa 31905, Israel.
    Forssén, Per-Erik
    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.
    The application of an oblique-projected Landweber method to a model of supervised learning2006In: Mathematical and computer modelling, ISSN 0895-7177, E-ISSN 1872-9479, Vol. 43, no 7-8, p. 892-909Article in journal (Refereed)
    Abstract [en]

    This paper brings together a novel information representation model for use in signal processing and computer vision problems, with a particular algorithmic development of the Landweber iterative algorithm. The information representation model allows a representation of multiple values for a variable as well as an expression for confidence. Both properties are important for effective computation using multi-level models, where a choice between models will be implementable as part of the optimization process. It is shown that in this way the algorithm can deal with a class of high-dimensional, sparse, and constrained least-squares problems, which arise in various computer vision learning tasks, such as object recognition and object pose estimation. While the algorithm has been applied to the solution of such problems, it has so far been used heuristically. In this paper we describe the properties and some of the peculiarities of the channel representation and optimization, and put them on firm mathematical ground. We consider the optimization a convexly constrained weighted least-squares problem and propose for its solution a projected Landweber method which employs oblique projections onto the closed convex constraint set. We formulate the problem, present the algorithm and work out its convergence properties, including a rate-of-convergence result. The results are put in perspective with currently available projected Landweber methods. An application to supervised learning is described, and the method is evaluated in an experiment involving function approximation, as well as application to transient signals. © 2006 Elsevier Ltd. All rights reserved.

  • 44.
    Johansson, Björn
    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.
    Forssén, Per-Erik
    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.
    Combining shadow detection and simulation for estimation of vehicle size and position2009In: PATTERN RECOGNITION LETTERS, ISSN 0167-8655, Vol. 30, no 8, p. 751-759Article in journal (Refereed)
    Abstract [en]

    This paper presents a method that combines shadow detection and a 3D box model including shadow simulation, for estimation of size and position of vehicles. We define a similarity measure between a simulated image of a 3D box, including the box shadow, and a captured image that is classified into background/foreground/shadow. The similarity Measure is used in all optimization procedure to find the optimal box state. It is shown in a number of experiments and examples how the combination shadow detection/simulation improves the estimation compared to just using detection or simulation, especially when the shadow detection or the simulation is inaccurate. We also describe a tracking system that utilizes the estimated 3D boxes, including highlight detection, spatial window instead of a time based window for predicting heading, and refined box size estimates by weighting accumulated estimates depending oil view. Finally, we show example results.

  • 45.
    Järemo Lawin, Felix
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Danelljan, Martin
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Khan, Fahad Shahbaz
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Density Adaptive Point Set Registration2018In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018, p. 3829-3837Conference paper (Refereed)
    Abstract [en]

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

  • 46.
    Järemo-Lawin, Felix
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Ovrén, Hannes
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
    Efficient Multi-frequency Phase Unwrapping Using Kernel Density Estimation2016In: Computer Vision – ECCV 2016 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV / [ed] Bastian Leibe, Jiri MatasNicu Sebe and Max Welling, Springer, 2016, p. 170-185Conference paper (Refereed)
    Abstract [en]

    In this paper we introduce an efficient method to unwrap multi-frequency phase estimates for time-of-flight ranging. The algorithm generates multiple depth hypotheses and uses a spatial kernel density estimate (KDE) to rank them. The confidence produced by the KDE is also an effective means to detect outliers. We also introduce a new closed-form expression for phase noise prediction, that better fits real data. The method is applied to depth decoding for the Kinect v2 sensor, and compared to the Microsoft Kinect SDK and to the open source driver libfreenect2. The intended Kinect v2 use case is scenes with less than 8m range, and for such cases we observe consistent improvements, while maintaining real-time performance. When extending the depth range to the maximal value of 18.75 m, we get about 52% more valid measurements than libfreenect2. The effect is that the sensor can now be used in large depth scenes, where it was previously not a good choice.

  • 47. Källhammer, Jan-Erik
    et al.
    Eriksson, Dick
    Granlund, Gösta
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Felsberg, Michael
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Moe, Anders
    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.
    Wiklund, Johan
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Forssén, Per-Erik
    Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
    Near Zone Pedestrian Detection using a Low-Resolution FIR Sensor2007In: Intelligent Vehicles Symposium, 2007 IEEE, Istanbul, Turkey: IEEE , 2007, , p. 339-345Conference paper (Refereed)
    Abstract [en]

    This paper explores the possibility to use a single low-resolution FIR camera for detection of pedestrians in the near zone in front of a vehicle. A low resolution sensor reduces the cost of the system, as well as the amount of data that needs to be processed in each frame.

    We present a system that makes use of hot-spots and image positions of a near constant bearing to detect potential pedestrians. These detections provide seeds for an energy minimization algorithm that fits a pedestrian model to the detection. Since false alarms are hard to tolerate, the pedestrian model is then tracked, and the distance-to-collision (DTC) is measured by integrating size change measurements at sub-pixel accuracy, and the car velocity. The system should only engage braking for detections on a collision course, with a reliably measured DTC.

    Preliminary experiments on a number of recorded near collision sequences indicate that our method may be useful for ranges up to about 10m using an 80x60 sensor, and somewhat more using a 160x120 sensor. We also analyze the robustness of the evaluated algorithm with respect to dead pixels, a potential problem for low-resolution sensors.

  • 48.
    Larsson, Fredrik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssen, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Correlating Fourier descriptors of local patches for road sign recognition2011In: IET Computer Vision, ISSN 1751-9632, E-ISSN 1751-9640, Vol. 5, no 4, p. 244-254Article in journal (Refereed)
    Abstract [en]

    The Fourier descriptors (FDs) is a classical but still popular method for contour matching. The key idea is to apply the Fourier transform to a periodic representation of the contour, which results in a shape descriptor in the frequency domain. FDs are most commonly used to compare object silhouettes and object contours; the authors instead use this well-established machinery to describe local regions to be used in an object-recognition framework. Many approaches to matching FDs are based on the magnitude of each FD component, thus ignoring the information contained in the phase. Keeping the phase information requires us to take into account the global rotation of the contour and shifting of the contour samples. The authors show that the sum-of-squared differences of FDs can be computed without explicitly de-rotating the contours. The authors compare correlation-based matching against affine-invariant Fourier descriptors (AFDs) and WARP-matched FDs and demonstrate that correlation-based approach outperforms AFDs and WARP on real data. As a practical application the authors demonstrate the proposed correlation-based matching on a road sign recognition task.

  • 49.
    Larsson, Fredrik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Patch Contour Matching by Correlating Fourier Descriptors2009In: Digital Image Computing: Techniques and Applications (DICTA), IEEE Computer Society , 2009, p. 40-46Conference paper (Refereed)
    Abstract [en]

    Fourier descriptors (FDs) is a classical but still popular method for contour matching. The key idea is to apply the Fourier transform to a periodic representation of the contour, which results in a shape descriptor in the frequency domain. Fourier descriptors have mostly been used to compare object silhouettes and object contours; we instead use this well established machinery to describe local regions to be used in an object recognition framework. We extract local regions using the Maximally Stable Extremal Regions (MSER) detector and represent the external contour by FDs. Many approaches to matching FDs are based on the magnitude of each FD component, thus ignoring the information contained in the phase. Keeping the phase information requires us to take into account the global rotation of the contour and shifting of the contour samples. We show that the sum-of-squared differences of FDs can be computed without explicitly de-rotating the contours. We compare our correlation based matching against affine-invariant Fourier descriptors (AFDs) and demonstrate that our correlation based approach outperforms AFDs on real world data.

  • 50.
    Larsson, Fredrik
    et al.
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Forssén, Per-Erik
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Felsberg, Michael
    Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
    Using Fourier descriptors for local region matching2009In: SSBA, 2009Conference paper (Other academic)
12 1 - 50 of 85
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