Proceedings of the Seventh IEEE International Conference on Computer Vision

20-27 Sept. 1999

Go

Filter Results

Displaying Results 1 - 25 of 81
  • Index of authors

    Publication Year: 1999, Page(s):xxiv - xxvii
    Request permission for commercial reuse | |PDF file iconPDF (230 KB)
    Freely Available from IEEE
  • Three-dimensional scene flow

    Publication Year: 1999, Page(s):722 - 729 vol.2
    Cited by:  Papers (108)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (176 KB)

    Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the two-dimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. We present a framework for the computation of dense, non-rigid scene flow from optical flow. Our approach leads to straightforward linear algorithms and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Empirical evaluation of dissimilarity measures for color and texture

    Publication Year: 1999, Page(s):1165 - 1172 vol.2
    Cited by:  Papers (99)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (592 KB)

    This paper empirically compares nine image dissimilarity measures that are based on distributions of color and texture features summarizing over 1,000 CPU hours of computational experiments. Ground truth is collected via a novel random sampling scheme for color and via an image partitioning method for texture. Quantitative performance evaluations are given for classification, image retrieval, and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monocular perception of biological motion-detection and labeling

    Publication Year: 1999, Page(s):805 - 812 vol.2
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (208 KB)

    Computer perception of biological motion is key to developing convenient and powerful human-computer interfaces. Successful body tracking algorithms have been developed; however initialization is done by hand. We propose a method for detecting a moving human body and for labeling its parts automatically. It is based on maximizing the joint probability density function (PDF) of the position and vel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D articulated models and multi-view tracking with silhouettes

    Publication Year: 1999, Page(s):716 - 721 vol.2
    Cited by:  Papers (65)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (284 KB)

    We propose a method to estimate the motion of a person filmed by two or more fixed cameras. The novelty of our technique is its ability to cope with fast movements, self-occlusions and noisy images. Our algorithms are based on the latest works on calibration and image segmentation developed in our lab. We compare the projections of a 3D model of a person on the images to the detected silhouettes o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Projective alignment with regions

    Publication Year: 1999, Page(s):1158 - 1164 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (152 KB)

    We consider a recent approach to recognition that uses regions to determine the pose of objects while allowing for partial occlusion of the regions. We further analyze properties of the method for planar objects undergoing projective transformations. We prove that three visible regions are sufficient to determine the transformation uniquely, and that for a large class of objects two regions are in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting salient motion by accumulating directionally-consistent flow

    Publication Year: 1999, Page(s):797 - 804 vol.2
    Cited by:  Papers (3)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (260 KB)

    Motion detection can play an important role in many vision tasks. Yet image motion can arise from “uninteresting” events as well as interesting ones. In this paper, salient motion is defined as motion that is likely to result from a typical surveillance target (e.g., a person or vehicle traveling with a sense of direction through a scene) as opposed to other distracting motions (e.g., ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture synthesis by non-parametric sampling

    Publication Year: 1999, Page(s):1033 - 1038 vol.2
    Cited by:  Papers (757)  |  Patents (91)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (328 KB)

    A non-parametric method for texture synthesis is proposed. The texture synthesis process grows a new image outward from an initial seed, one pixel at a time. A Markov random field model is assumed, and the conditional distribution of a pixel given all its neighbors synthesized so far is estimated by querying the sample image and finding all similar neighborhoods. The degree of randomness is contro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transformed component analysis: joint estimation of spatial transformations and image components

    Publication Year: 1999, Page(s):1190 - 1196 vol.2
    Cited by:  Papers (36)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (324 KB)

    A simple, effective way to model images is to represent each input pattern by a linear combination of “component” vectors, where the amplitudes of the vectors are modulated to match the input. This approach includes principal component analysis, independent component analysis and factor analysis. In practice, images are subjected to randomly selected transformations of a known nature, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Hamilton-Jacobi skeleton

    Publication Year: 1999, Page(s):828 - 834 vol.2
    Cited by:  Papers (39)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (368 KB)

    The eikonal equation and variants of it are of significant interest for problems in computer vision and image processing. It is the basis for continuous versions of mathematical morphology, stereo, shape-from-shading and for recent dynamic theories of shape. Its numerical simulation can be delicate, owing to the formation of singularities in the evolving front, and is typically based or, level set... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-view subspace constraints on homographies

    Publication Year: 1999, Page(s):710 - 715 vol.2
    Cited by:  Papers (17)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (264 KB)

    The motion of a planar surface between two camera views induces a homography. The homography depends on the camera intrinsic and extrinsic parameters, as well as on the 3D plane parameters. While camera parameters vary across different views, the plane geometry remains the same. Based on this fact, the paper derives linear subspace constraints on the relative motion of multiple (⩾2) planes acr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object recognition from local scale-invariant features

    Publication Year: 1999, Page(s):1150 - 1157 vol.2
    Cited by:  Papers (4000)  |  Patents (285)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (232 KB)

    An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are effici... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semantic organization of scenes using discriminant structural templates

    Publication Year: 1999, Page(s):1253 - 1258 vol.2
    Cited by:  Papers (14)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (152 KB)

    In this paper, we present a procedure for organizing real world scenes along semantic axes. The approach is based on the output energies of linear discriminant filters that take into account, or not, spatial information. We introduce three semantic axes along which pictures are ordered. The main semantic axis computes the degree of naturalness of a scene. Then, urban pictures are evaluated accordi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic feature ordering for efficient registration

    Publication Year: 1999, Page(s):1084 - 1091 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (452 KB)

    Existing sequential feature based registration algorithms involving search typically either select features randomly (e.g. the RANSAC approach (M. Fischler and R. Bolles, 1981)) or assume a predefined, intuitive ordering for the features (e.g. based on size or resolution). The paper presents a formal framework for computing an ordering for features which maximizes search efficiency. Features are r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Independent component analysis of textures

    Publication Year: 1999, Page(s):1054 - 1060 vol.2
    Cited by:  Papers (21)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (224 KB)

    A common method for texture representation is to use the marginal probability densities over the outputs of a set of multi-orientation, multi-scale filters as a description of the texture. We propose a technique, based on independent component analysis, for choosing the set of filters that yield the most informative marginals, meaning that the product over the marginals most closely approximates t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Illumination distribution from brightness in shadows: Adaptive estimation of illumination distribution with unknown reflectance properties in shadow regions

    Publication Year: 1999, Page(s):875 - 882 vol.2
    Cited by:  Papers (33)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (3476 KB)

    This paper describes a new method for estimating the illumination distribution of a real scene from a radiance distribution inside shadows cast by an object in the scene. First, the illumination distribution of the scene is approximated by discrete sampling of an extended light source. Then the illumination distribution of the scene is estimated from a radiance distribution inside shadows cast by ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rigid and articulated motion seen with an uncalibrated stereo rig

    Publication Year: 1999, Page(s):789 - 796 vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (136 KB)

    This paper establishes a link between uncalibrated stereo vision and the motion of rigid and articulated bodies. The variation in the projective reconstruction of a dynamic scene over time allows an uncalibrated stereo rig to be used as a faithful motion capturing device. We introduce an original theoretical framework-projective kinematics-which allows rigid and articulated motion to be represente... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian fusion of color and texture segmentations

    Publication Year: 1999, Page(s):956 - 962 vol.2
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (208 KB)

    In many applications one would like to use information from both color and texture features in order to segment an image. We propose a novel technique to combine “soft” segmentations computed for two or more features independently. Our algorithm merges models according to a maximum descriptiveness criterion, and allows us to choose any number of classes for the final grouping. This tec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Equivalence of Julesz and Gibbs texture ensembles

    Publication Year: 1999, Page(s):1025 - 1032 vol.2
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (412 KB)

    Research on texture has been pursued along two different lines. The first line of research, pioneered by Julesz (1962), seeks the essential ingredients in terms of features and statistics in human texture perception. This leads us to a mathematical definition of texture as a Julesz ensemble. A Julesz ensemble is the maximum set of images that share the same value of some basic feature statistics a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding correspondences of patches by means of affine transformations

    Publication Year: 1999, Page(s):1117 - 1122 vol.2
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (184 KB)

    We present a novel method for finding the optimal affine transformation for matching of images. The method requires no feature points, does not rely on normalization of images and can be tuned to highlight interesting parts in the images. Furthermore, the method does not need any derivatives for obtaining the affine transformation and it has a computational cost proportional to n2logn f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New algorithms for two-frame structure from motion

    Publication Year: 1999, Page(s):737 - 744 vol.2
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (272 KB)

    We describe two new algorithms for two-frame structure from motion from tracked point features. One is the first fast algorithm for computing an exact least-squares estimate. It exploits our observation that the rotationally invariant least-squares error can be written in a simple form that depends just on the motion. The other is essentially as accurate as the least-squares estimate and is more e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning low-level vision

    Publication Year: 1999, Page(s):1182 - 1189 vol.2
    Cited by:  Papers (94)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2148 KB)

    We show a learning-based method for low-level vision problems-estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images. We model that world with a Markov network, learning the network parameters from the examples. Bayesian belief propagation allows us to efficiently find a local maximum of the posterior probability for the scene, given the imag... View full abstract»

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

    Publication Year: 1999, Page(s):820 - 827 vol.2
    Cited by:  Papers (156)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (328 KB)

    Current vision systems are designed to perform in clear weather. Needless to say, in any outdoor application, there is no escape from “bad” weather. Ultimately, computer vision systems must include mechanisms that enable them to function (even if somewhat less reliably) in the presence of haze, fog, rain, hail and snow. We begin by studying the visual manifestations of different weathe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Textons, contours and regions: cue integration in image segmentation

    Publication Year: 1999, Page(s):918 - 925 vol.2
    Cited by:  Papers (92)  |  Patents (16)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (228 KB)

    The paper makes two contributions: it provides (1) an operational definition of textons, the putative elementary units of texture perception, and (2) an algorithm for partitioning the image into disjoint regions of coherent brightness and texture, where boundaries of regions are defined by peaks in contour orientation energy and differences in texton densities across the contour. B. Julesz (1981) ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time motion analysis with linear-programming

    Publication Year: 1999, Page(s):703 - 709 vol.2
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (188 KB)

    A method to compute motion models in real time from point-to-line correspondences using linear programming is presented. Point-to-line correspondences are the most reliable motion measurements given the aperture effect, and it is shown how they can approximate other motion measurements as well. Using an L1 error measure for image alignment based on point-to-line correspondences and mini... View full abstract»

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