By Topic

Computer Vision, 1998. Sixth International Conference on

Date 7-7 Jan. 1998

Filter Results

Displaying Results 1 - 25 of 170
  • Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)

    Publication Year: 1998
    Request permission for commercial reuse | PDF file iconPDF (65 KB)
    Freely Available from IEEE
  • Contents

    Publication Year: 1998, Page(s):iv - xiii
    Request permission for commercial reuse | PDF file iconPDF (550 KB)
    Freely Available from IEEE
  • Comparing curved-surface range image segmenters

    Publication Year: 1998, Page(s):286 - 291
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (948 KB)

    This work focuses on creating a framework for objectively evaluating the performance of range image segmentation algorithms. The algorithms are evaluated in terms of correct segmentation, over- and under-segmentation, missed and noise regions. A set of images with ground truth was created for this work. The images were captured using a structured light scanner. Images used in the evaluation contai... View full abstract»

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

    Publication Year: 1998, Page(s):1161 - 1164
    Request permission for commercial reuse | PDF file iconPDF (236 KB)
    Freely Available from IEEE
  • When is it possible to identify 3D objects from single images using class constraints?

    Publication Year: 1998, Page(s):541 - 548
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (816 KB)

    One approach to recognizing objects seen from arbitrary viewpoint is by extracting invariant properties of the objects from single images. Such properties are found in images of 3D objects only when the objects are constrained to belong to certain classes (e.g., bilaterally symmetric objects). Existing studies that follow this approach propose how to compute invariant representations for a handful... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding the epipole from uncalibrated optical flow

    Publication Year: 1998, Page(s):987 - 991
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (624 KB)

    This paper presents a novel method for determining the location of the instantaneous epipole in a sequence of images acquired by an uncalibrated camera and containing a single, rigid motion (e.g., the camera moves in a static environment). The method uses the full perspective camera model and requires the estimation of the optical flow at a minimum of six image locations. The key observation is th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Illumination-invariant color object recognition via compressed chromaticity histograms of color-channel-normalized images

    Publication Year: 1998, Page(s):533 - 540
    Cited by:  Papers (29)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (860 KB)

    Several color object recognition methods that are based on image retrieval algorithms attempt to discount changes of illumination in order to increase performance when test image illumination conditions differ from those that obtained when the image database was created. Here we extend the seminal method of Swain and Ballard to discount changing illumination. The new method is based on the first s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • What can projections of flow fields tell us about the visual motion

    Publication Year: 1998, Page(s):979 - 986
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (984 KB)

    The dimensionality of visual motion analysis can be reduced by analyzing projections of flow vector fields. In contrast to motion vector fields, these projections exhibit simple geometric properties which are invariant to the scene structure and depend only on the camera motion. Using these properties, structure and motion can be either completely or partially decoupled. We estimate motion paramet... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Separation of transparent layers using focus

    Publication Year: 1998, Page(s):1061 - 1066
    Cited by:  Papers (15)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (740 KB)

    Consider situations where the depth at each point in the scene is multi-valued due to the presence of a virtual image semi-reflected by a transparent surface. The semi-reflected image is linearly superimposed on the image of the object that is behind the transparent surface. A novel approach is proposed for the recovery of the superimposed layers. By searching for the images in which either of the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Which shape from motion?

    Publication Year: 1998, Page(s):689 - 695
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (596 KB)

    In a practical situation, the rigid transformation relating different views is recovered with errors. In such a case, the recovered depth of the scene contains errors, and consequently a distorted version of visual space is computed. What then are meaningful shape representations that can be computed from the images? The result presented in this paper states that if the rigid transformation betwee... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A task driven 3D object recognition system using Bayesian networks

    Publication Year: 1998, Page(s):527 - 532
    Cited by:  Papers (6)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (748 KB)

    In this paper we propose a general framework to build a task oriented 3D object recognition system for CAD based vision (CBV). Features from 3D space curves representing the object's rims provide sufficient information to allow identification and pose estimation of industrial CAD models. However, features relying on differential surface properties tend to be very vulnerable with respect to noise. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual motion estimation and prediction: a probabilistic network model for temporal coherence

    Publication Year: 1998, Page(s):973 - 978
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    We develop a theory for the temporal integration of visual motion motivated by psychophysical experiments. The theory proposes that input data are temporally grouped and used to predict and estimate motion flows in the image sequences. Our theory is expressed in terms of the Bayesian generalization of standard Kalman filtering which allows us to solve temporal grouping in conjunction with predicti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information-conserving object recognition

    Publication Year: 1998, Page(s):145 - 152
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (808 KB)

    Following the theory of statistical estimation, the problem of recognizing objects imaged in complex real-world scenes is examined from a parametric perspective. A scalar measure of an object's complexity, which is invariant under affine transformation and changes in image noise level, is extracted from the object's Fisher information. The volume of Fisher information is shown to provide an overal... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion segmentation and tracking using normalized cuts

    Publication Year: 1998, Page(s):1154 - 1160
    Cited by:  Papers (70)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (948 KB)

    We propose a motion segmentation algorithm that aims to break a scene into its most prominent moving groups. A weighted graph is constructed on the image sequence by connecting pixels that are in the spatiotemporal neighborhood of each other. At each pixel, we define motion profile vectors which capture the probability distribution of the image velocity. The distance between motion profiles is use... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Geotensity: combining motion and lighting for 3D surface reconstruction

    Publication Year: 1998, Page(s):1053 - 1060
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1120 KB)

    This paper is about automatically reconstructing the full 3D surface of an object observed in motion by a single static camera. We introduce the geotensity constraint that governs the relationship between four images of a moving object under fairly general lighting conditions. We show that it is possible in theory to solve for 3D surface structure for both the case of a single point light source a... View full abstract»

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

    Publication Year: 1998, Page(s):683 - 688
    Cited by:  Papers (39)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (840 KB)

    We describe a flexible model for representing images of objects of a certain class, known a priori, such as faces, and introduce a new algorithm for matching it to a novel image and thereby performing image analysis. We call this model a multidimensional morphable model or just a, morphable model. The morphable model is learned from example images (called prototypes) of objects of a class. In this... View full abstract»

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

    Publication Year: 1998, Page(s):608 - 613
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (716 KB)

    A system to retrieve images using a description of the image intensity surface is presented. Gaussian derivative filters at several scales are applied to the image and low order 2D differential invariants are computed. The resulting multi-scale representation is indexed for rapid retrieval. Queries are designed by the users from an example image by selecting appropriate regions. The invariant vect... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking meteorological structures through curves matching using geodesic paths

    Publication Year: 1998, Page(s):396 - 401
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (604 KB)

    This paper is concerned with the problem of tracking clouds structures like vortices in meteorological images. For this purpose we characterize the deformation between two successive occurrences, by matching their two boundary curves. Our approach is based on the computation of the set of paths connecting the two curves to be matched. It minimizes a cost function which measures the local similarit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning to identify and track faces in image sequences

    Publication Year: 1998, Page(s):317 - 322
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (648 KB)

    We address the problem of robust face identification in the presence of pose, lighting, and expression variation. Previous approaches to the problem have assumed similar models of variation for each individual, estimated from pooled training data. We describe a method of updating a first order global estimate of identity by learning the class-specific correlation between the estimate and the resid... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stereo matching with transparency and matting

    Publication Year: 1998, Page(s):517 - 524
    Cited by:  Papers (36)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1124 KB)

    This paper formulates and solves a new variant of the stereo correspondence problem: simultaneously recovering the disparities, true colors, and opacities of visible surface elements. This problem arises in newer applications of stereo reconstruction, such as view interpolation and the layering of real imagery with synthetic graphics for special effects and virtual studio applications. While this ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • GRADE: Gibbs reaction and diffusion equations

    Publication Year: 1998, Page(s):847 - 854
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1076 KB)

    Recently there have been increasing interests in using nonlinear PDEs for applications in computer vision and image processing. In this paper, we propose a general statistical framework for designing a new class of PDEs. For a given application, a Markov random field model p(I) is learned according to the minimax entropy principle so that p(I) should characterize the ensemble of images in our appl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Egomotion estimation using log-polar images

    Publication Year: 1998, Page(s):967 - 972
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (820 KB)

    We address the problem of egomotion estimation of a monocular observer moving with arbitrary translation and rotation in an unknown environment, using log-polar images. The method we propose is uniquely based on the spatio-temporal image derivatives, or the normal flow. Thus, we avoid computing the complete optical flow field, which is an ill-posed problem due to the aperture problem. We use a sea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hyperbolic “Smoothing” of shapes

    Publication Year: 1998, Page(s):215 - 221
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (676 KB)

    We have been developing a theory of generic 2-D shape based on a reaction-diffusion model from mathematical physics. The description of a shape is derived from the singularities of a curve evolution process driven by the reaction (hyperbolic) term. The diffusion (parabolic) term is related to smoothing and shape simplification. However, the unification of the two is problematic, because the slight... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing Ritz approximations of primary images

    Publication Year: 1998, Page(s):139 - 144
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (816 KB)

    Ritz vectors approximate eigenvectors that are a common choice for primary images in content based indexing. They can be computed efficiently even when the images are accessed through slow communication such as the Internet. We develop an algorithm that computes Ritz vectors in one pass through the images. When iterated, the algorithm can recover the exact eigenvectors. In applications to image in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters

    Publication Year: 1998, Page(s):90 - 95
    Cited by:  Papers (168)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB)

    In this paper the feasibility of self-calibration in the presence of varying internal camera parameters is under investigation. A self-calibration method is presented which efficiently deals with all kinds of constraints on the internal camera parameters. Within this framework a practical method is proposed which can retrieve metric reconstruction from image sequences obtained with uncalibrated zo... View full abstract»

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