Scheduled System Maintenance
On Friday, October 20, IEEE Xplore will be unavailable from 9:00 PM-midnight ET. We apologize for the inconvenience.
Notice: There is currently an issue with the citation download feature. Learn more.

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 7 • July 2003

Filter Results

Displaying Results 1 - 14 of 14
  • Guest editors' introduction to the special section on graphical models in computer vision

    Publication Year: 2003, Page(s):785 - 786
    Cited by:  Papers (2)
    Request permission for commercial reuse | PDF file iconPDF (229 KB) | HTML iconHTML
    Freely Available from IEEE
  • Unsupervised learning of human motion

    Publication Year: 2003, Page(s):814 - 827
    Cited by:  Papers (96)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4579 KB) | HTML iconHTML

    An unsupervised learning algorithm that can obtain a probabilistic model of an object composed of a collection of parts (a moving human body in our examples) automatically from unlabeled training data is presented. The training data include both useful "foreground" features as well as features that arise from irrelevant background clutter - the correspondence between parts and detected features is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical cue integration in DAG deformable models

    Publication Year: 2003, Page(s):801 - 813
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1818 KB) | HTML iconHTML

    Deformable models are a useful modeling paradigm in computer vision. A deformable model is a curve, a surface, or a volume, whose shape, position, and orientation are controlled through a set of parameters. They can represent manufactured objects, human faces and skeletons, and even bodies of fluid. With low-level computer vision and image processing techniques, such as optical flow, we extract re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stereo matching using belief propagation

    Publication Year: 2003, Page(s):787 - 800
    Cited by:  Papers (522)  |  Patents (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3948 KB) | HTML iconHTML

    In this paper, we formulate the stereo matching problem as a Markov network and solve it using Bayesian belief propagation. The stereo Markov network consists of three coupled Markov random fields that model the following: a smooth field for depth/disparity, a line process for depth discontinuity, and a binary process for occlusion. After eliminating the line process and the binary process by intr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision making and uncertainty management in a 3D reconstruction system

    Publication Year: 2003, Page(s):852 - 858
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2272 KB) | HTML iconHTML

    This paper presents a control structure for a general-purpose image understanding system. It addresses the high level of uncertainty in local hypotheses and the computational complexity of image interpretation. The control of vision algorithms is done by an independent subsystem that uses Bayesian networks and utility theory to compute marginal value of information and selects the algorithm with t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple motion scene reconstruction with uncalibrated cameras

    Publication Year: 2003, Page(s):884 - 894
    Cited by:  Papers (17)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (929 KB) | HTML iconHTML

    In this paper, we describe a reconstruction method for multiple motion scenes, which are scenes containing multiple moving objects, from uncalibrated views. Assuming that the objects are moving with constant velocities, the method recovers the scene structure, the trajectories of the moving objects, the camera motion, and the camera intrinsic parameters (except skews) simultaneously. We focus on t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Class conditional density estimation using mixtures with constrained component sharing

    Publication Year: 2003, Page(s):924 - 928
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1281 KB) | HTML iconHTML

    We propose a generative mixture model classifier that allows for the class conditional densities to be represented by mixtures having certain subsets of their components shared or common among classes. We argue that, when the total number of mixture components is kept fixed, the most efficient classification model is obtained by appropriately determining the sharing of components among class condi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A graphical model for audiovisual object tracking

    Publication Year: 2003, Page(s):828 - 836
    Cited by:  Papers (45)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1202 KB) | HTML iconHTML

    We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it by developing a new algorithm for tracking a moving object in a cluttered, noisy scene using two microphones and a camera. Our model uses unobserved variables to describe the data in terms of the process that generates them. It i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image modeling with position-encoding dynamic trees

    Publication Year: 2003, Page(s):859 - 871
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1447 KB) | HTML iconHTML

    This paper describes the position-encoding dynamic tree (PEDT). The PEDT is a probabilistic model for images that improves on the dynamic tree by allowing the positions of objects to play a part in the model. This increases the flexibility of the model over the dynamic tree and allows the positions of objects to be located and manipulated. This paper motivates and defines this form of probabilisti... 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: 2003, Page(s):895 - 911
    Cited by:  Papers (35)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2967 KB) | HTML iconHTML

    The main question we address is: What is the minimal information required to generate closed, nonintersecting planar boundaries? For this paper, we restrict "shape" to this meaning. More precisely, we examine whether the medial axis, together with dynamics, can serve as a language to design shapes and to effect shape changes. We represent the medial axis together with a direction of flow along the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evidential reasoning for object recognition

    Publication Year: 2003, Page(s):837 - 851
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5790 KB) | HTML iconHTML

    The authors present a framework to guide development of evidential reasoning in object recognition systems. Principles of evidential reasoning processes for open-world object recognition are proposed and applied to build evidential reasoning capabilities. The principles summarize research and findings by the authors up through the mid-1990s, including seminal results in object-centered computer vi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rate-distortion analysis of discrete-HMM pose estimation via multiaspect scattering data

    Publication Year: 2003, Page(s):872 - 883
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (994 KB) | HTML iconHTML

    We consider the problem of estimating the pose of a target based on a sequence of scattered waveforms measured at multiple target-sensor orientations. Using a hidden Markov model (HMM) representation of the scattered-waveform sequence, pose estimation reduces to estimating the underlying HMM states from a sequence of observations. It is assumed that each scattered waveform must be quantized via an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lines in one orthographic and two perspective views

    Publication Year: 2003, Page(s):912 - 917
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1586 KB) | HTML iconHTML

    We introduce a linear algorithm to recover the Euclidean motion between an orthographic and two perspective cameras from straight line correspondences filling the gap in the analysis of motion estimation from line correspondences for various projection models. The general relationship between lines in three views is described by the trifocal tensor. Euclidean structure from motion for three perspe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting moving shadows: algorithms and evaluation

    Publication Year: 2003, Page(s):918 - 923
    Cited by:  Papers (410)  |  Patents (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1876 KB) | HTML iconHTML

    Moving shadows need careful consideration in the development of robust dynamic scene analysis systems. Moving shadow detection is critical for accurate object detection in video streams since shadow points are often misclassified as object points, causing errors in segmentation and tracking. Many algorithms have been proposed in the literature that deal with shadows. However, a comparative evaluat... View full abstract»

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

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Sven Dickinson
University of Toronto
e-mail: sven@cs.toronto.edu