Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition

18-20 June 1996

Filter Results

Displaying Results 1 - 25 of 139
  • Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [front cover]

    Publication Year: 1996
    Request permission for reuse | PDF file iconPDF (928 KB)
    Freely Available from IEEE
  • Bayesian image restoration and segmentation by constrained optimization

    Publication Year: 1996, Page(s):1 - 6
    Cited by:  Papers (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (791 KB)

    A constrained optimization method, called the Lagrange-Hopfield (LH) method, is presented for solving Markov random field (MRF) based Bayesian image estimation problems for restoration and segmentation. The method combines the augmented Lagrangian multiplier technique with the Hopfield network to solve a constrained optimization problem into which the original Bayesian estimation problem is reform... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparse representations for image decomposition with occlusions

    Publication Year: 1996, Page(s):7 - 12
    Cited by:  Papers (8)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (603 KB)

    We study the problem of how to detect "interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis, and also account for occlusions, where the basis superposition principle is no longer valid. Since the basis (a library of image templates) is over-redundant, there are infinitely many ways to decompose I. We are... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extracting salient curves from images: an analysis of the saliency network

    Publication Year: 1996, Page(s):13 - 20
    Cited by:  Papers (11)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (910 KB)

    The Saliency Network proposed by Shashua and Ullman (1988) is a well-known approach to the problem of extracting salient curves from images while performing gap completion. This paper analyzes the Saliency Network. Although the network is attractive for a number reasons, our analysis reveals certain weaknesses with the method. In particular, we show cases in which the most salient element does not... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Blurring strategies for image segmentation using a multiscale linking model

    Publication Year: 1996, Page(s):21 - 26
    Cited by:  Papers (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1234 KB)

    Multiscale approaches are an invaluable tool for image segmentation. A vast amount of research has been devoted to the construction of different multiscale representations of an image. In this paper we use the hyperstack-a multiscale linking model for image segmentation-for an in-depth comparison of four different scale space generators with respect to segmentation results. We consider the linear ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scale space localization, blur, and contour-based image coding

    Publication Year: 1996, Page(s):27 - 34
    Cited by:  Papers (20)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1249 KB)

    We have recently proposed a scale-adaptive algorithm for reliable edge detection and blur estimation. The algorithm produces a contour code which consists of estimates of position, brightness, contrast and blur for each edge point in the image. Here we address two questions: 1. Can scale adaptation be used to achieve precise localization of blurred edges? 2. How much of the perceptual content of a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing 3D objects by generating random actions

    Publication Year: 1996, Page(s):35 - 40
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (664 KB)

    This paper presents a formal model of an active recognition system that can be programmed by learning. At each time step the system decides between producing an action to generate new data and stopping to issue the name of the object observed. The actions can be directed either towards the external environment or towards the internal perceptual system of the agent. The decision strategy is based o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Viewpoint variation in the noise sensitivity of pose estimation

    Publication Year: 1996, Page(s):41 - 46
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (825 KB)

    The paper presents an analysis of the stability of pose estimation. The investigated pose estimation technique is based on orientations of three edge segments and provides the rotation part of object pose. The specific emphasis of the analysis is on determining how the stability varies with view point relative to an object. The stability investigation propagates the uncertainty in edge segment ori... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gauging relational consistency and correcting structural errors

    Publication Year: 1996, Page(s):47 - 54
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (831 KB)

    The aim of this paper is to provide a comparative evaluation of a number of contrasting approaches to relational matching. Unique to this study is the way in which we show how a diverse family of algorithms relate to one-another using a common Bayesian framework. Broadly speaking there are two main aspects to this study. Firstly we focus on the issue of how relational inexactness may be quantified... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eigenfeatures for planar pose measurement of partially occluded objects

    Publication Year: 1996, Page(s):55 - 60
    Cited by:  Papers (24)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (823 KB)

    Planar pose measurement from images is an important problem for automated assembly and inspection. In addition to accuracy and robustness, ease of use is very important for real world applications. Recently, Murase and Nayar have presented the "parametric eigenspace " for object recognition and pose measurement based on training images. Although their system is easy to use, it has potential proble... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding corresponding points based on Bayesian triangulation

    Publication Year: 1996, Page(s):61 - 66
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (600 KB)

    In this paper, we consider the problems of finding corresponding points from multiple perspective projection images (the correspondence problem), and estimating the 3-D point from which these points have arisen (the triangulation problem). We pose the triangulation problem as that of finding the Bayesian maximum, a posteriori estimate of the 3-D point, given its projections in N images, assuming a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active face tracking and pose estimation in an interactive room

    Publication Year: 1996, Page(s):67 - 72
    Cited by:  Papers (61)  |  Patents (28)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (732 KB)

    We demonstrate real-time face tracking and pose estimation in an unconstrained office environment with an active foveated camera. Using vision routines previously implemented for an interactive environment, we determine the spatial location of a user's head and guide an active camera to obtain foveated images of the face. Faces are analyzed using a set of eigenspaces indexed over both pose and wor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3-D model-based tracking of humans in action: a multi-view approach

    Publication Year: 1996, Page(s):73 - 80
    Cited by:  Papers (279)  |  Patents (25)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (995 KB)

    We present a vision system for the 3-D model-based tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D body pose at each time instant without the use of markers. The pose-recovery problem is formulated as a search problem and entails finding the pose parameters of a graphical human model whose synthesized appearance is mos... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection

    Publication Year: 1996, Page(s):81 - 87
    Cited by:  Papers (112)  |  Patents (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (771 KB)

    We present a new method for the 3D model-based tracking of human body parts. To mitigate the difficulties arising due to occlusion among body parts, we employ multiple calibrated cameras in a mutually orthogonal configuration. In addition, we develop criteria for a time varying active selection of a set of cameras to track the motion of a particular human part. In particular, at every frame, each ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hand segmentation using learning-based prediction and verification for hand sign recognition

    Publication Year: 1996, Page(s):88 - 93
    Cited by:  Papers (19)  |  Patents (32)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (734 KB)

    This paper presents a prediction-and-verification segmentation scheme wing attention images from multiple fixations. A major advantage of this scheme is that it can handle a large number of different deformable objects presented in complex backgrounds. The scheme is also relatively efficient since the segmentation is guided by the past knowledge through a prediction-and-verification scheme. The sy... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Further constraints on visual articulated motions

    Publication Year: 1996, Page(s):94 - 99
    Cited by:  Papers (4)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (615 KB)

    This paper derives what we term the Euclidean hinge constraint for projective reconstruction of objects displaying articulated motion. A Euclidean hinge is defined here to be an articulation axis with the proviso that any plane perpendicular to the articulation axis in link 1 has a coincident plane which is perpendicular to the articulation ads in link 2 and that these planes remain coincident und... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Invariant histograms and deformable template matching for SAR target recognition

    Publication Year: 1996, Page(s):100 - 105
    Cited by:  Papers (20)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (637 KB)

    Recognizing a target in synthetic-aperture radar (SAR) images is an important, yet challenging, application of the model-based vision technique. This paper describes a model-based SAR recognition system based on invariant histograms and deformable template matching techniques. An invariant histogram is a histogram of invariant values defined by geometric features such as points and lines in SAR im... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling clutter and context for target detection in infrared images

    Publication Year: 1996, Page(s):106 - 113
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (885 KB)

    In order to reduce false alarms and to improve the target detection performance of an automatic target detection and recognition system operating in a cluttered environment, it is important to develop the models not only for man-made targets bat also of natural background clutters. Because of the high complexity of natural clutters, this clutter model can only be reliably built through learning fr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-stage target recognition using modular vector quantizers and multilayer perceptrons

    Publication Year: 1996, Page(s):114 - 119
    Cited by:  Papers (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (699 KB)

    An automatic target recognition (ATR) classifier is proposed that uses modularly cascaded vector quantizers (VQs) and multilayer perceptrons (MLPs). A dedicated VQ codebook is constructed for each target class at a specific range of aspects, which is trained with the K-means algorithm and a modified learning vector quantization (LVQ) algorithm. Each final codebook is expected to give the lowest me... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On a spectral attentional mechanism

    Publication Year: 1996, Page(s):120 - 127
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1212 KB)

    This paper describes an attentional mechanism based on the interpretation of spectral signatures for detecting regular object configurations in areas of an image delineated using context information. The proposed global operator relies on the spectral analyse's of edge structure and exploits spatial as well as frequency domain constraints derived from known geometrical models of monitored objects.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Polarization phase-based method for material classification and object recognition in computer vision

    Publication Year: 1996, Page(s):128 - 135
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1014 KB)

    A robust and accurate polarization phase-based technique for material classification is presented. The novelty of this technique is three-fold In (i) its theoretical development, (ii) its application, and, (iii) its experimental implementation. The concept of phase of polarization of a light wave is introduced to computer vision for discrimination between materials according to their intrinsic ele... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A common framework for curve evolution, segmentation and anisotropic diffusion

    Publication Year: 1996, Page(s):136 - 142
    Cited by:  Papers (98)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (782 KB)

    In recent years, curve evolution has developed into an important tool in Computer Vision and has been applied to a wide variety of problems such as smoothing of shapes, shape analysis and shape recovery. The underlying principle is the evolution of a simple closed curve whose points move in the direction of the normal with prescribed velocity. A fundamental limitation of the method as it stands is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of edge detectors: a methodology and initial study

    Publication Year: 1996, Page(s):143 - 148
    Cited by:  Papers (47)  |  Patents (32)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (671 KB)

    The purpose of this paper is to describe a new (to computer vision) experimental framework which allows us to make quantitative comparisons using subjective ratings made by people. This approach avoids the issue of pixel-level ground truth. As a result, it does not allow us to make statements about the frequency of false positive and false negative errors at the pixel level. Instead, using experim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical approach to high resolution edge contour reconstruction

    Publication Year: 1996, Page(s):149 - 154
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (678 KB)

    Efficient edge detection algorithms such as Canny's (1986) fail near curve singularities. Moreover, the standard linking algorithms used on top of these detectors often fail because of instabilities in the tracking process (due to multiple responses to the same edge and interference of nearby edges). We propose a hierarchical approach to edge detection based on a graph stabilization method that al... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual organization for figure/ground separation

    Publication Year: 1996, Page(s):155 - 160
    Cited by:  Papers (17)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (556 KB)

    A common factor in all illusory contour figures is the perception of a surface occluding part of a background. In our previous work, we have shown we could diffuse a proper set of junction hypothesis (what is salient or background) to obtain a surface where their boundaries represented illusory contours. Amodal completions emerge at the overlapping surfaces. We address the problem of selecting the... View full abstract»

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