Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)

23-25 June 1999

Go

Filter Results

Displaying Results 1 - 25 of 99
  • Proceedings 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. Two

    Publication Year: 1999, Page(s):i - xviii
    Request permission for reuse | PDF file iconPDF (1376 KB)
    Freely Available from IEEE
  • Shape from recognition and learning: recovery of 3-D face shapes

    Publication Year: 1999, Page(s):2 - 7 Vol. 2
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (777 KB)

    In this paper a novel framework for the recovery of 3D surfaces of faces from single images is developed. The underlying principle is shape from recognition, i.e. the idea that pre-recognizing face parts can constrain the space of possible solutions to the image irradiance equation, thus allowing robust recovery of the 3D structure of a specific part. Shape recovery of the recognized part is based... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning 2D shape models

    Publication Year: 1999, Page(s):8 - 14 Vol. 2
    Cited by:  Papers (20)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (823 KB)

    A new fully automated shape learning method is presented. It is based on clustering a set of training shapes in the original shape space (defined by the coordinates of the contour points) and performing a Procrustes analysis on each cluster to obtain cluster prototypes and information about shape variation. The main difference from previously reported methods is that the training set is first auto... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrating shape from shading and range data using neural networks

    Publication Year: 1999, Page(s):15 - 20 Vol. 2
    Cited by:  Papers (12)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (664 KB)

    This paper presents a framework for integrating multiple sensory data, sparse range data and dense depth maps from shape from shading in order to improve the 3D reconstruction of visible surfaces of 3D objects. The integration process is based on propagating the error difference between the two data sets by fitting a surface to that difference and using it to correct the visible surface obtained f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deformable shape detection and description via model-based region grouping

    Publication Year: 1999, Page(s):21 - 27 Vol. 2
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (936 KB)

    A method for deformable shape detection and recognition is described. Deformable shape templates are used to partition the image into a globally consistent interpretation, determined in part by the minimum description length principle. Statistical shape models enforce the prior probabilities on global, parametric deformations for each object class. Once trained, the system autonomously segments de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implicit representation and scene reconstruction from probability density functions

    Publication Year: 1999, Page(s):28 - 34 Vol. 2
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (575 KB)

    A technique is presented for representing linear features as probability density functions in two or three dimensions. Three chief advantages of this approach are (1) a unified representation and algebra for manipulating points, lines, and planes, (2) seamless incorporation of uncertainty information, and (3) a very simple recursive solution for maximum likelihood shape estimation. Applications to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Algebraic curves that work better

    Publication Year: 1999, Page(s):35 - 41 Vol. 2
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (695 KB)

    An algebraic curve is defined as the zero set of a polynomial in two variables. Algebraic curves are practical for modeling shapes much more complicated than conics or superquadrics. The main drawback in representing shapes by algebraic curves has been the lack of repeatability in fitting algebraic curves to data. A regularized fast linear fitting method based on ridge regression and restricting t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ligature instabilities in the perceptual organization of shape

    Publication Year: 1999, Page(s):42 - 48 Vol. 2
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (706 KB)

    Although the classical Blum skeleton has long been considered unstable, many have attempted to alleviate this defect through pruning. Unfortunately, these methods have an arbitrary basis, and, more importantly, they do not prevent internal structural alterations due to slight changes in an object's boundary. The result is a relative lack of development of skeleton representations for indexing obje... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape reconstruction in projective grid space from large number of images

    Publication Year: 1999, Page(s):49 - 54 Vol. 2
    Cited by:  Papers (31)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (607 KB)

    This paper proposes a new scheme for multi-image projective reconstruction based on a projective grid space. The projective grid space is defined by two basis views and the fundamental matrix relating these views. Given fundamental matrices relating other views to each of the two basis views, this projective grid space can be related to any view. In the projective grid space as a general space tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient iterative solution to M-view projective reconstruction problem

    Publication Year: 1999, Page(s):55 - 61 Vol. 2
    Cited by:  Papers (11)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (588 KB)

    We propose an efficient solution to the general M-view projective reconstruction problem, using matrix factorization and iterative least squares. The method can accept input with missing data, meaning that not all points are necessarily visible in all views. It runs much faster than the often-used non-linear minimization method, while preserving the accuracy of the latter. The key idea is to conve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Trajectory triangulation of lines: reconstruction of a 3D point moving along a line from a monocular image sequence

    Publication Year: 1999, Page(s):62 - 66 Vol. 2
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (647 KB)

    We consider the problem of reconstructing the location of a moving 3D point seen from a monocular moving camera, i.e., to reconstruct moving objects from line-of-sight measurements only. Since the point is moving while the camera is moving, then even if the camera motion is known, it is impossible to reconstruct the 3D location of the point under general circumstances. However we show that if the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parameterized image varieties and estimation with bilinear constraints

    Publication Year: 1999, Page(s):67 - 72 Vol. 2
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (885 KB)

    This paper addresses the problem of reliably estimating the coefficients of the parameterized image variety (PIV) associated with the set of weak perspective images of a rigid scene, with applications in image-based rendering. Exploiting the fact that the constraints defining the PIV are linear in its coefficients and bilinear in the image data, the estimation procedure is cast in the errors-in-va... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extending superquadrics with exponent functions: modeling and reconstruction

    Publication Year: 1999, Page(s):73 - 78 Vol. 2
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (944 KB)

    Superquadrics are a family of parametric shapes which can model a diverse set of objects. They have received significant attention because of their compact representation and robust methods for recovery of 3D models. However, their assumption of intrinsical symmetry fails in modeling numerous real-world examples such as human, body, animals, and other naturally occurring objects. In this paper, we... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the intrinsic reconstruction of shape from its symmetries

    Publication Year: 1999, Page(s):79 - 84 Vol. 2
    Cited by:  Papers (9)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (545 KB)

    We address the issue of the use of symmetry-based representations, such as the medial axis and an augmented form of it, the shock structure, to regenerate shapes. First, we address pointwise reconstruction of the boundary from points of the medial axis. As classified into three generic types (A/sup 2//1 mid-branch, A/sub 3/ end point of a branch, and A/sub 1//sup 3/ junction). Second, we examine t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pose clustering with density estimation and structural constraints

    Publication Year: 1999, Page(s):85 - 91 Vol. 2
    Cited by:  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (698 KB)

    This paper describes a statistical framework for object alignment by pose clustering. The idea underlying pose clustering is to transform the alignment process from the image domain to that of the appropriate transformation parameters. It commence by taking k-tuples from the primitive-sets for the model and the data. The size of the k-tuples is such that there are sufficient measurements available... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Independent motion: the importance of history

    Publication Year: 1999, Page(s):92 - 97 Vol. 2
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (720 KB)

    We consider a problem central in aerial visual surveillance applications-detection and tracking of small, independently moving objects in long and noisy video sequences. We directly use spatiotemporal image intensity gradient measurements to compute an exact model of background motion. This allows the creation of accurate mosaics over many frames and the definition of a constraint violation functi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gesture localization and recognition using probabilistic visual learning

    Publication Year: 1999, Page(s):98 - 103 Vol. 2
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (887 KB)

    A generic approach for the extraction and recognition of gesture using raw grey-level images is presented. The probabilistic visual learning approach, a learning method recently proposed by B. Moghaddam and A. Pentland (1997), is used to create a set of compact statistical representations of gesture appearance on low dimensional eigenspaces. The same probabilistic modeling framework is used to ext... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic recognition of activity using local appearance

    Publication Year: 1999, Page(s):104 - 109 Vol. 2
    Cited by:  Papers (50)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (645 KB)

    This paper addresses the problem of probabilistic recognition of activities from local spatio-temporal appearance. Joint statistics of space-time filters are employed to define histograms which characterize the activities to be recognized. These histograms provide the joint probability density functions required for recognition using Bayes rule. The result is a technique for recognition of activit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vision-based speaker detection using Bayesian networks

    Publication Year: 1999, Page(s):110 - 116 Vol. 2
    Cited by:  Papers (25)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (660 KB)

    The development of user interfaces based on vision and speech requires the solution of a challenging statistical inference problem: The intentions and actions of multiple individuals must be inferred from noisy and ambiguous data. We argue that Bayesian network models are an attractive statistical framework for cue fusion in these applications. Bayes nets combine a natural mechanism for expressing... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D trajectory recovery for tracking multiple objects and trajectory guided recognition of actions

    Publication Year: 1999, Page(s):117 - 123 Vol. 2
    Cited by:  Papers (72)  |  Patents (14)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (855 KB)

    A mechanism is proposed that integrates low-level (image processing), mid-level (recursive 3D trajectory estimation), and high level (action recognition) processes. It is assumed that the system observes multiple moving objects via a single, uncalibrated video camera. A novel extended Kalman filter formulation is used in estimating the relative 3D motion trajectories up to a scale factor. The recu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dependency-based framework of combining multiple experts for the recognition of unconstrained handwritten numerals

    Publication Year: 1999, Page(s):124 - 129 Vol. 2
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (569 KB)

    Although Behavior-Knowledge Space (BKS) method does not need any assumptions in combining multiple experts, it should build theoretically exponential storage spaces for storing and managing jointly observed K decisions from K experts. That is, combining K experts needs a (K+1)st-order probability distribution. However, it is well known that the distribution becomes unmanageable in storing and esti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining information using hard constraints

    Publication Year: 1999, Page(s):132 - 138 Vol. 2
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (870 KB)

    In this paper we show how the use of hard constraints in solving estimation problems, by allowing multiple sources of information to be taken into account during optimization, increases robustness and improves efficiency over alternative methods such as the statistical combination of separate optimization results. Our argument is based on an empirical evaluation of the technique which uses a model... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image interpolation by joint view triangulation

    Publication Year: 1999, Page(s):139 - 145 Vol. 2
    Cited by:  Papers (26)  |  Patents (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (911 KB)

    Creating novel views by interpolating prestored images or view morphing has many applications in visual simulation. We present in this paper a new method of automatically interpolating two images which tackles two most difficult problems of morphing due to the lack of depth informational pixel matching and visibility handling. We first describe a quasi-dense matching algorithm based on region grow... View full abstract»

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

    Publication Year: 1999, Page(s):146 - 151 Vol. 2
    Cited by:  Papers (6)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (607 KB)

    This paper presents a novel technique for recovering the shape of a static scene from a video sequence due to a rigidly moving camera. The solution procedure consists of two stages. In the first stage, the rigid motion of the camera at each instant in time is recovered. This provides the transformation between successive viewing positions. The solution is achieved through new constraints which rel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatial filter selection for illumination-invariant color texture discrimination

    Publication Year: 1999, Page(s):154 - 159 Vol. 2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (769 KB)

    Color texture contains a large amount of spectral and spatial structure that can be exploited for recognition. Recent work has demonstrated that spatial filters offer a convenient means of extracting illumination invariant spatial information from a color image. In this paper, we address the problem of deriving optimal fillers for illumination-invariant color texture discrimination. Color textures... View full abstract»

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