By Topic

First Canadian Conference on Computer and Robot Vision, 2004. Proceedings.

17-19 May 2004

Filter Results

Displaying Results 1 - 25 of 78
  • Proceedings 1st Canadian Conference on Computer and Robot Vision 2004

    Publication Year: 2004, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (1226 KB)
    Freely Available from IEEE
  • About the cover images

    Publication Year: 2004, Page(s): ii
    Request permission for commercial reuse | PDF file iconPDF (1243 KB)
    Freely Available from IEEE
  • Proceedings 1st Canadian Conference on Computer and Robot Vision 2004

    Publication Year: 2004, Page(s): iii
    Request permission for commercial reuse | PDF file iconPDF (1262 KB)
    Freely Available from IEEE
  • Proceedings 1st Canadian Conference on Computer and Robot Vision 2004 Copyright Page

    Publication Year: 2004, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (1260 KB)
    Freely Available from IEEE
  • Proceedings 1st Canadian Conference on Computer and Robot Vision 2004 Table of contents

    Publication Year: 2004, Page(s):v - ix
    Request permission for commercial reuse | PDF file iconPDF (1267 KB)
    Freely Available from IEEE
  • Message from the Conference Co-Chairs

    Publication Year: 2004, Page(s): x
    Request permission for commercial reuse | PDF file iconPDF (1247 KB) | HTML iconHTML
    Freely Available from IEEE
  • Program committee

    Publication Year: 2004, Page(s): xi
    Request permission for commercial reuse | PDF file iconPDF (1235 KB)
    Freely Available from IEEE
  • Visual tracking using active appearance models

    Publication Year: 2004, Page(s):2 - 9
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1534 KB) | HTML iconHTML

    Visual tracking is one of the fundamental problems in computer vision. The pose of an object extracted through consecutive frames has a variety of applications ranging from robot navigation to camera based man-machine interfaces. In this paper we examine the use of Active Appearance Models(AAM) for the task of visual tracking. The original Active Appearance Model is limited to have all points of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The extension of statistical face detection to face tracking

    Publication Year: 2004, Page(s):10 - 17
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (786 KB) | HTML iconHTML

    A real time probablistic face tracking system using monocular vision is presented based on face target acquisition and subsequent particle filtering techniques. First, the face target acquisition and initialization stage used a skin color classification and statistical face model matching apprroach to find the face target. Subsequently, the particle filtering technique is used to track the state s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object tracking: feature selection and confidence propagation

    Publication Year: 2004, Page(s):18 - 21
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1471 KB) | HTML iconHTML

    Choosing unique and invariant features is the first important step in object tracking. In this paper, we present a method to find proper-sized and irregularlyshaped trackable features, the use of which can outperform procedures using normal square features. The notion of confidence associated with each feature is introduced as the feature propagates. The use of confidence results in robust trackin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An optical-inertial tracking system for fully-enclosed VR displays

    Publication Year: 2004, Page(s):22 - 29
    Cited by:  Papers (2)  |  Patents (23)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1653 KB) | HTML iconHTML

    This paper describes a hybrid optical-inertial tracking technology for fully-immersive projective displays. In order to track the operator, the operatorwears a 3DOF commercial inertial tracking system coupledwith a set of laser diodes arranged in a known configuration. The projection of this laser constellation on the display walls are tracked visually to compute the 6DOF absolute head pose of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time motion tracker for a robotic vision system

    Publication Year: 2004, Page(s):30 - 34
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1510 KB) | HTML iconHTML

    Estimation of distance to nearby landscape features is an essential navigation capability for an autonomous mobile robot. The ability to track targets in video sequences, combined with the concept of motion vision, allows a robot to rely on vision-based navigation techniques and avoid using active sensors or sophisticated stereo imagers for distance measurement. We present recent developments of o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian segmentation supported by neighborhood configurations

    Publication Year: 2004, Page(s):36 - 42
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1754 KB) | HTML iconHTML

    From the statistical point of view, segmentation methods are dependent upon how the characteristics in image are formulated and where they are extracted from. In this paper, the joint conditional probability is exploited to characterize the statistical properties and is also localized to better capture the local properties of the neighborhood. Two different neighborhood configurations are defined ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised segmentation of synthetic aperture radar sea ice imagery using MRF models

    Publication Year: 2004, Page(s):43 - 50
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2060 KB) | HTML iconHTML

    Due to both environmental and sensor reasons, it is challenging to develop computer-assisted algorithms to segment SAR (synthetic aperture radar) sea ice imagery. In this research, images containing either ice and water or multiple ice classes are segmented. This paper proposes to use the image intensity to discriminate ice from water and to use texture features to separate different ice types. In... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture analysis using gaussian weighted grey level co-occurrence probabilities

    Publication Year: 2004, Page(s):51 - 57
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1577 KB) | HTML iconHTML

    The discrimination of textures is a significant aspect in segmenting SAR sea ice imagery. Texture features calculated from grey level co-occurring probabilities (GLCP) are well accepted and applied in the analysis of many images. When calculating GLCPs, each co-occurring pixel pair within the image window is given a uniform weighting. Although a novel technique, co-occurring texture features have ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneous segmentation of range and color images based on Bayesian decision theory

    Publication Year: 2004, Page(s):58 - 63
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1504 KB) | HTML iconHTML

    This paper describe a new algorithm to segment in continuous parametric regions registered color and range images. The algorithm starts with an initial partition of small first order regions using a robust fitting method constrained by the detection of depth and orientation discontinuities in the range signal and color edges in the color signal. The algorithm then optimally group these regions int... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A generic methodology for partitioning unorganised 3D point clouds for robotic vision

    Publication Year: 2004, Page(s):64 - 71
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1615 KB) | HTML iconHTML

    Range image segmentation has many applications in computer vision areas such as computer graphics and robotic vision. A generic methodology for 3D point set analysis in which planar structures play an important role is defined. It consists mainly of a specific K-means algorithm which is able to process different shapes in cluster. At the same time, within geometric and topologic considerations, a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Machine sensing for mining optimization

    Publication Year: 2004, Page(s): 74
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1278 KB) | HTML iconHTML

    In this talk, I will present some of the recent research activities in the Centre for Intelligent Mining Systems (CIMS) on applying machine sensing technologies to the optimization of oil sand mining operations. Much of the research effort is concerned with the development of the capability to accurately measure the sizes of ore fragments as they are processed and moved along the production pipeli... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape from contours and multiple stereo a hierarchical, mesh-based approach

    Publication Year: 2004, Page(s):76 - 83
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3889 KB) | HTML iconHTML

    Start of the above-titled section of the conference proceedings record. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of four surface normal approximations and optimization of light direction for robust shape reconstruction from single images

    Publication Year: 2004, Page(s):84 - 91
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1776 KB) | HTML iconHTML

    We present a robust shape-from-shading method, by which we are able to estimate accurate shapes from single shading images whose slant angles are relatively large. First, we derive four iterative relations for shape estimation by applying the Jacobi??s iterative method and by using four approximations of the surface normal, and combine them with weights to get a single relation. This enables us to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recovering the shading image under known illumination

    Publication Year: 2004, Page(s):92 - 96
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1346 KB) | HTML iconHTML

    Given a standard RGB color image, an approach to recovering the shading image, an intrinsic image that depends only on the geometry of the viewing situation, is presented. The approach is formulated for scenes that exhibit both diffuse and specular properties. It is discriminative in the sense that variations in intensity caused by material changes are first detected and then removed. Material cha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Location by involution

    Publication Year: 2004, Page(s):97 - 103
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1426 KB) | HTML iconHTML

    In this paper, we propose an iterative method of 3D location of 2D parallelogram or 3D parallelepiped shapes by monocular vision from a single image. The method we propose assumes that the camera is calibrated and that the size of the polygonal object is known. The 3D location is obtained in the following way. First we try to find the orientation of a geometric model of the object imaged such that... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic object recognition within an of .ce environment

    Publication Year: 2004, Page(s):104 - 109
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1768 KB) | HTML iconHTML

    The visionary goal of an easy to use service robot implies some key features like spatial cognition, speech understanding and object recognition. Therefore such a system needs techniques to identify objects in scenes, i.e. to assign the natural category (e.g. ??door??, ??chair??, ??table??) to new objects based on their prototypical geometry. Our approach uses 21 2 D laser range data to recognize ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Approximating the visuomotor function for visual servoing

    Publication Year: 2004, Page(s):112 - 119
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (732 KB) | HTML iconHTML

    This paper introduces a new approach to visual servoing by learning to perform tasks such as centering. The system uses function approximation from reinforcement learning to learn the visuomotor function of a task which relates actions to perceptual variations. The function model is linear and tile coding is used for generalization. The gradient-descent SARSA algorithm is used to determine the par... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new integrative approach to time varying image interpretation

    Publication Year: 2004, Page(s):120 - 128
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1399 KB) | HTML iconHTML

    This paper presents a global method to process monocular image sequences for mobile robot obstacle detection. We do not aim to achieve a complete scene reconstruction, but only to evaluate the time to collision and surface orientation useful for robot obstacle avoidance. Using a planar facet representation we first calculate formally the velocity field generated by the camera undergoing an arbitra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.