Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)

25-25 June 1998

Filter Results

Displaying Results 1 - 25 of 146
  • Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)

    Publication Year: 1998
    Request permission for reuse | PDF file iconPDF (535 KB)
    Freely Available from IEEE
  • Incremental tracking of human actions from multiple views

    Publication Year: 1998, Page(s):2 - 7
    Cited by:  Papers (39)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    This paper proposes a new method for model-based tracking of a human body in 3D motion from multiple views. The tracking is performed by estimating the pose increment of the body parts from multiple image sequences after establishing of fitting an articulated model to the human body at the initial frame. The pose increment can be obtained from solving a system of linear equations. This calculation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking people with twists and exponential maps

    Publication Year: 1998, Page(s):8 - 15
    Cited by:  Papers (343)  |  Patents (20)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (287 KB)

    This paper demonstrates a new visual motion estimation technique that is able to recover high degree-of-freedom articulated human body configurations in complex video sequences. We introduce the use of a novel mathematical technique, the product of exponential maps and twist motions, and its integration into a differential motion estimation. This results in solving simple linear systems, and enabl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Joint probabilistic techniques for tracking multi-part objects

    Publication Year: 1998, Page(s):16 - 21
    Cited by:  Papers (34)  |  Patents (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (319 KB)

    Common objects such as people and cars comprise many visual parts and attributes, yet image-based tracking algorithms are often keyed to only one of a target's identifying characteristics. In this paper, we present a framework for combining and sharing information among several state estimation processes operating on the same underlying visual object. Well-known techniques for joint probabilistic ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using adaptive tracking to classify and monitor activities in a site

    Publication Year: 1998, Page(s):22 - 29
    Cited by:  Papers (245)  |  Patents (38)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1529 KB)

    We describe a vision system that monitors activity in a site over extended periods of time. The system uses a distributed set of sensors to cover the site, and an adaptive tracker detects multiple moving objects in the sensors. Our hypothesis is that motion tracking is sufficient to support a range of computations about site activities. We demonstrate using the tracked motion data to calibrate the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mixtures of local linear subspaces for face recognition

    Publication Year: 1998, Page(s):32 - 37
    Cited by:  Papers (33)  |  Patents (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (297 KB)

    Traditional subspace methods for face recognition compute a measure of similarity between images after projecting them onto a fixed linear subspace that is spanned by some principal component vectors (a.k.a. "eigenfaces") of a training set of images. By supposing a parametric Gaussian distribution over the subspace and a symmetric Gaussian noise model for the image given a point in the subspace, w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rotation invariant neural network-based face detection

    Publication Year: 1998, Page(s):38 - 44
    Cited by:  Papers (93)  |  Patents (24)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (48 KB)

    In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of rotation in the image plane. The system employs multiple networks; a "router" network first processes each input window to determine its orientation and then uses this information to prepare the window for o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic modeling of local appearance and spatial relationships for object recognition

    Publication Year: 1998, Page(s):45 - 51
    Cited by:  Papers (147)  |  Patents (27)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (249 KB)

    In this paper, we describe an algorithm for object recognition that explicitly models and estimated the posterior probability function, P(object/image). We have chosen a functional form of the posterior probability function that captures the joint statistics of local appearance and position on the object as well as the statistics of local appearance in the visual world at large. We use a discrete ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Illumination cones for recognition under variable lighting: faces

    Publication Year: 1998, Page(s):52 - 58
    Cited by:  Papers (103)  |  Patents (12)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1436 KB)

    Due to illumination variability, the same object can appear dramatically different even when viewed in fixed pose. To handle this variability, an object recognition system must employ a representation that is either invariant to, or models this variability. This paper presents an appearance-based method for modeling the variability due to illumination in the images of objects. The method differs f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A theory of selection for gamut mapping colour constancy

    Publication Year: 1998, Page(s):60 - 65
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (355 KB)

    Gamut mapping colour constancy attempts to determine the set of diagonal matrices taking the gamut of image colours under an unknown illuminant into the gamut of colours observed under a standard illuminant. Forsyth (1990) developed such an algorithm in rgb sensor space which Finlayson (1996) later modified to work in a 2-d chromaticity space. In this paper we prove that Forsyth's 3-d solution gam... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generation of the Euclidean skeleton from the vector distance map by a bisector decision rule

    Publication Year: 1998, Page(s):66 - 71
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (223 KB)

    The Euclidean skeleton is essential for general shape representation. This paper provides an efficient method to extract a well-connected Euclidean skeleton by a neighbor bisector decision (NBD) rule on a vector distance map. The shortest vector which generates a pixel's distance is stored when calculating the distance map. A skeletal pixel is extracted by checking the vectors of the pixel and its... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stochastic computation of medial axis in Markov random fields

    Publication Year: 1998, Page(s):72 - 79
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1247 KB)

    In this paper the computation of medial axis is posed as a statistical inference problem not as a mathematical transform. This method provides answers to two essential problems in computing the medial axis representation. I) Prior knowledge are adopted for axes and junctions so that the axes around junctions become well defined. II) A stochastic jump-diffusion process is proposed for estimating me... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Variable-scale smoothing and edge detection guided by stereoscopy

    Publication Year: 1998, Page(s):80 - 85
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (597 KB)

    It is typical in edge detection applications to examine a single scale or to consider some space of scales in the image without knowing which scale is appropriate for each location in the image. However, many images contain a wide variation in the distance to the scene points, and thus objects of the same size can appear at greatly differing scales in the image. We present a method where the scale... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploitation of natural image statistics by biological vision systems: 1/f/sup 2/ power spectra and self-similar bandpass decompositions

    Publication Year: 1998, Page(s):86 - 91
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (30 KB)

    The second-order statistics of natural images can be well characterized by a "self-similar" 1/F/sup 2/ power spectrum and the bandpass decomposition in biological vision systems is characterized by a self-similar, wavelet-like structuring of the "frequency channels". It has thus often been suggested that there might exist a systematic interrelationship between these two properties, but a complete ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimax entropy and learning by diffusion

    Publication Year: 1998, Page(s):92 - 97
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (814 KB)

    A system of coupled differential equations is formulated which learns priors for modelling "preattentive" textures. It is derived from an energy functional consisting of a linear combination of a large number of terms corresponding to the features that the system is capable of learning. The system learns the parameters associated with each feature by applying gradient ascent to the log-likelihood ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image segmentation using local variation

    Publication Year: 1998, Page(s):98 - 104
    Cited by:  Papers (103)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (256 KB)

    We present a new graph-theoretic approach to the problem of image segmentation. Our method uses local criteria and yet produces results that reflect global properties of the image. We develop a framework that provides specific definitions of what it means for an image to be under- or over-segmented. We then present an efficient algorithm for computing a segmentation that is neither under- nor over... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • What is the spectral dimensionality of illumination functions in outdoor scenes?

    Publication Year: 1998, Page(s):105 - 110
    Cited by:  Papers (15)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (141 KB)

    The spectral properties of outdoor illumination functions can vary significantly due to atmospheric conditions and scene geometry. The authors show using a statistical analysis of a comprehensive physical model that the variation in outdoor illumination functions over both the visible range (0.33 /spl mu/m-0.7 /spl mu/m) and the visible/near-infrared range (0.4 /spl mu/m-2.5 /spl mu/m) can be repr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new complex basis for implicit polynomial curves and its simple exploitation for pose estimation and invariant recognition

    Publication Year: 1998, Page(s):111 - 117
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (140 KB)

    New representations are developed for 2D IP (implicit polynomial) curves of arbitrary degree. These representations permit shape recognition and pose estimation with essentially single, rather than iterative, computation, and extract and use all the information in the polynomial coefficients. This is accomplished by decomposing polynomial coefficient space into a union of orthogonal subspaces for ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Salient and multiple illusory surfaces

    Publication Year: 1998, Page(s):118 - 124
    Cited by:  Papers (16)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1124 KB)

    All illusory surface figures yield a perception of a surface occluding another one or the background. Occluded surfaces yield completion, a phenomena known as amodal completions. It is intriguing that for some images illusory surfaces are perceived, but not for other images. Also, illusory surfaces may have portions occlude. We aim to understand these phenomena. Our approach detects intensity edge... View full abstract»

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

    Publication Year: 1998, Page(s):125 - 131
    Cited by:  Papers (58)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1303 KB)

    We propose a method for segmenting gray-value images. By segmentation, we mean a map from the set of pixels to a small set of levels such that each connected component of the set of pixels with the same level forms a relatively large and "meaningful" region. The method finds a set of levels with associated gray values by first finding junctions in the image and then seeking a minimum set of thresh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A coupled PDE model of nonlinear diffusion for image smoothing and segmentation

    Publication Year: 1998, Page(s):132 - 137
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (596 KB)

    Image denoising and segmentation are fundamental problems in the field of image processing and computer vision with numerous applications. We propose a partial differential equation (PDE) based smoothing and segmentation framework wherein the image data are smoothed via an evolution equation that is controlled by a vector field describing a viscous fluid flow. Image segmentation in this framework ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy relational distance for large-scale object recognition

    Publication Year: 1998, Page(s):138 - 143
    Cited by:  Papers (13)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    This paper presents a new similarity measure for object recognition from large libraries of line-patterns. The measure draws its inspiration from both the Hausdorff distance and a recently reported Bayesian consistency measure that has been successfully used for graph-based correspondence matching. The measure uses robust error-kernels to gauge the similarity of pair-wise attribute relations defin... View full abstract»

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

    Publication Year: 1998, Page(s):144 - 149
    Cited by:  Papers (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (157 KB)

    Previous research has shown that aggregated predictors improve the performance of non-parametric function approximation techniques. This paper presents the results of applying aggregated predictors to a computer vision problem, and shows that the method of bagging significantly improves performance. In fact, the results are better than those previously reported on other domains. This paper explain... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A probabilistic formulation for Hausdorff matching

    Publication Year: 1998, Page(s):150 - 156
    Cited by:  Papers (31)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (470 KB)

    Matching images based on a Hausdorff measure has become popular for computer vision applications. However, no probabilistic model has been used in these applications. This limits the formal treatment of several issues, such as feature uncertainties and prior knowledge. In this paper, we develop a probabilistic formulation of image matching in terms of maximum likelihood estimation that generalizes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Moment invariants and quantization effects

    Publication Year: 1998, Page(s):157 - 163
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (70 KB)

    This paper considers the effect of spatial quantization on several moment invariants. Of particular interest are the affine moment invariants, which have emerged in recent years as a useful tool for image reconstruction, image registration, and recognition of deformed objects. Traditional analysis assumes moments and moment invariants for images that are defined in the continuous domain. In practi... View full abstract»

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