Scheduled System Maintenance
On Tuesday, May 22, IEEE Xplore will undergo scheduled maintenance. Single article sales and account management will be unavailable
from 6:00am–5:00pm ET. There may be intermittent impact on performance from noon–6:00pm ET.
We apologize for the inconvenience.

Proceedings Ninth IEEE International Conference on Computer Vision

13-16 Oct. 2003

Filter Results

Displaying Results 1 - 25 of 201
  • Proceedings Ninth IEEE International Conference on Computer Vision

    Publication Year: 2003
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    The following topics are dealt with: image segmentation; image texture; image motion analysis; object detection; tracking; feature selection; clustering; image reconstruction; face recognition; image sequences; computer vision; image sensors; and object recognition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Regression based bandwidth selection for segmentation using Parzen windows

    Publication Year: 2003, Page(s):2 - 9 vol.1
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (670 KB) | HTML iconHTML

    We consider the problem of segmentation of images that can be modelled as piecewise continuous signals having unknown, nonstationary statistics. We propose a solution to this problem which first uses a regression framework to estimate the image PDF, and then mean-shift to find the modes of this PDF. The segmentation follows from mode identification wherein pixel clusters or image segments are iden... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning a classification model for segmentation

    Publication Year: 2003, Page(s):10 - 17 vol.1
    Cited by:  Papers (466)  |  Patents (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (855 KB) | HTML iconHTML

    We propose a two-class classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly matching human segmentations and images. In a preprocessing stage an image is over-segmented into super-pixels. We define a variety of features derived from the classical Gestalt cues, including contour, texture, brightnes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image parsing: unifying segmentation, detection, and recognition

    Publication Year: 2003, Page(s):18 - 25 vol.1
    Cited by:  Papers (44)  |  Patents (37)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (947 KB) | HTML iconHTML

    We propose a general framework for parsing images into regions and objects. In this framework, the detection and recognition of objects proceed simultaneously with image segmentation in a competitive and cooperative manner. We illustrate our approach on natural images of complex city scenes where the objects of primary interest are faces and text. This method makes use of bottom-up proposals combi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing geodesics and minimal surfaces via graph cuts

    Publication Year: 2003, Page(s):26 - 33 vol.1
    Cited by:  Papers (218)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (497 KB) | HTML iconHTML

    Geodesic active contours and graph cuts are two standard image segmentation techniques. We introduce a new segmentation method combining some of their benefits. Our main intuition is that any cut on a graph embedded in some continuous space can be interpreted as a contour (in 2D) or a surface (in 3D). We show how to build a grid graph and set its edge weights so that the cost of cuts is arbitraril... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Epitomic analysis of appearance and shape

    Publication Year: 2003, Page(s):34 - 41 vol.1
    Cited by:  Papers (94)  |  Patents (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (501 KB) | HTML iconHTML

    We present novel simple appearance and shape models that we call epitomes. The epitome of an image is its miniature, condensed version containing the essence of the textural and shape properties of the image. As opposed to previously used simple image models, such as templates or basis functions, the size of the epitome is considerably smaller than the size of the image or object it represents, bu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmenting foreground objects from a dynamic textured background via a robust Kalman filter

    Publication Year: 2003, Page(s):44 - 50 vol.1
    Cited by:  Papers (128)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (374 KB) | HTML iconHTML

    The algorithm presented aims to segment the foreground objects in video (e.g., people) given time-varying, textured backgrounds. Examples of time-varying backgrounds include waves on water, clouds moving, trees waving in the wind, automobile traffic, moving crowds, escalators, etc. We have developed a novel foreground-background segmentation algorithm that explicitly accounts for the nonstationary... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ranking prior likelihood distributions for Bayesian shape localization framework

    Publication Year: 2003, Page(s):51 - 58 vol.1
    Cited by:  Papers (13)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (393 KB) | HTML iconHTML

    We formulate the shape localization problem in the Bayesian framework. In the learning stage, we propose the Constrained Rank-Boost approach to model the likelihood of local features associated with the key points of an object, like face, while preserve the prior ranking order between the ground truth position of a key point and its neighbors; in the inferring stage, a simple efficient iterative a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient, robust and accurate fitting of a 3D morphable model

    Publication Year: 2003, Page(s):59 - 66 vol.1
    Cited by:  Papers (60)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (473 KB) | HTML iconHTML

    3D morphable models, as a means to generate images of a class of objects and to analyze them, have become increasingly popular. The problematic part of this framework is the registration of the model to an image, a.k.a. the fitting. The characteristic features of a fitting algorithm are its efficiency, robustness, accuracy and automation. Many accurate algorithms based on gradient descent techniqu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical background subtraction for a mobile observer

    Publication Year: 2003, Page(s):67 - 74 vol.1
    Cited by:  Papers (89)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (540 KB) | HTML iconHTML

    Statistical background modelling and subtraction has proved to be a popular and effective class of algorithms for segmenting independently moving foreground objects out from a static background, without requiring any a priori information of the properties of foreground objects. We present two contributions on this topic, aimed towards robotics where an active head is mounted on a mobile vehicle. I... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Joint region tracking with switching hypothesized measurements

    Publication Year: 2003, Page(s):75 - 82 vol.1
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (755 KB) | HTML iconHTML

    We propose a switching hypothesized measurements (SHM) model supporting multimodal probability distributions and present the application of the model in handling potential variability in visual environments when tracking multiple objects jointly. For a set of occlusion hypotheses, a frame is measured once under each hypothesis, resulting in a set of measurements at each time instant. A computation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The local projective shape of smooth surfaces and their outlines

    Publication Year: 2003, Page(s):83 - 89 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB) | HTML iconHTML

    We examine projectively invariant local properties of smooth curves and surfaces. Oriented projective differential geometry is proposed as a theoretical framework for establishing such invariants and describing the local shape of surfaces and their outlines. This framework is applied to two problems: a projective proof of Koenderink's famous characterization of convexities, concavities, and inflec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active concept learning for image retrieval in dynamic databases

    Publication Year: 2003, Page(s):90 - 95 vol.1
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (386 KB) | HTML iconHTML

    Concept learning in content-based image retrieval (CBIR) systems is a challenging task. We present an active concept learning approach based on mixture model to deal with the two basic aspects of a database system: changing (image insertion or removal) nature of a database and user queries. To achieve concept learning, we develop a novel model selection method based on Bayesian analysis that evalu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Video input driven animation (VIDA)

    Publication Year: 2003, Page(s):96 - 103 vol.1
    Cited by:  Papers (10)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (554 KB) | HTML iconHTML

    There are many challenges associated with the integration of synthetic and real imagery. One particularly difficult problem is the automatic extraction of salient parameters of natural phenomena in real video footage for subsequent application to synthetic objects. We can ensure that the hair and clothing of a synthetic actor placed in a meadow of swaying grass will move consistently with the wind... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic video summarization by graph modeling

    Publication Year: 2003, Page(s):104 - 109 vol.1
    Cited by:  Papers (18)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (294 KB) | HTML iconHTML

    We propose a unified approach for summarization based on the analysis of video structures and video highlights. Our approach emphasizes both the content balance and perceptual quality of a summary. Normalized cut algorithm is employed to globally and optimally partition a video into clusters. A motion attention model based on human perception is employed to compute the perceptual quality of shots ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A non-iterative greedy algorithm for multi-frame point correspondence

    Publication Year: 2003, Page(s):110 - 115 vol.1
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3654 KB) | HTML iconHTML

    We present a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multiframe point correspondence is NP hard for three or more frames. A polynomial time algorithm for a restriction of this problem is presented, and is used as the basis of proposed greedy algorithm for the general problem. The greedy nature of the proposed algorithm a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Variational frameworks for DT-MRI estimation, regularization and visualization

    Publication Year: 2003, Page(s):116 - 121 vol.1
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (874 KB) | HTML iconHTML

    We address three crucial issues encountered in DT-MRI (diffusion tensor magnetic resonance imaging): diffusion tensor estimation, regularization and fiber bundle visualization. We first review related algorithms existing in the literature and propose then alternative variational formalisms that lead to new and improved schemes, thanks to the preservation of important tensor constraints (positivity... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Counting people in crowds with a real-time network of simple image sensors

    Publication Year: 2003, Page(s):122 - 129 vol.1
    Cited by:  Papers (94)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (502 KB) | HTML iconHTML

    Estimating the number of people in a crowded environment is a central task in civilian surveillance. Most vision-based counting techniques depend on detecting individuals in order to count, an unrealistic proposition in crowded settings. We propose an alternative approach that directly estimates the number of people. In our system, groups of image sensors segment foreground objects from the backgr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fragmentation in the vision of scenes

    Publication Year: 2003, Page(s):130 - 135 vol.1
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB) | HTML iconHTML

    Natural images are highly structured in their spatial configuration. Where one would expect a different spatial distribution for every image, as each image has a different spatial layout, we show that the spatial statistics of recorded images can be explained by a single process of sequential fragmentation. The observation by a resolution limited sensory system turns out to have a profound influen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eye gaze estimation from a single image of one eye

    Publication Year: 2003, Page(s):136 - 143 vol.1
    Cited by:  Papers (52)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (514 KB) | HTML iconHTML

    We present a novel approach, called the "one-circle " algorithm, for measuring the eye gaze using a monocular image that zooms in on only one eye of a person. Observing that the iris contour is a circle, we estimate the normal direction of this iris circle, considered as the eye gaze, from its elliptical image. From basic projective geometry, an ellipse can be back-projected into space onto two ci... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Calibrating pan-tilt cameras in wide-area surveillance networks

    Publication Year: 2003, Page(s):144 - 149 vol.1
    Cited by:  Papers (30)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (926 KB) | HTML iconHTML

    Pan-tilt cameras are often used as components of wide-area surveillance systems. It is necessary to calibrate these cameras in relation to one another in order to obtain a consistent representation of the entire space. Existing methods for calibrating pan-tilt cameras have assumed an idealized model of camera mechanics. In addition, most methods have been calibrated using only a small range of cam... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Calibration of a hybrid camera network

    Publication Year: 2003, Page(s):150 - 155 vol.1
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (660 KB) | HTML iconHTML

    Visual surveillance using a camera network has imposed new challenges to camera calibration. An essential problem is that a large number of cameras may not have a common field of view or even be synchronized well. We propose to use a hybrid camera network that consists of catadioptric and perspective cameras for a visual surveillance task. The relations between multiple views of a scene captured f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image registration with global and local luminance alignment

    Publication Year: 2003, Page(s):156 - 163 vol.1
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (749 KB) | HTML iconHTML

    Inspired by tensor voting, we present luminance voting, a novel approach for image registration with global and local luminance alignment. The key to our modeless approach is the direct estimation of replacement function, by reducing the complex estimation problem to the robust 2D tensor voting in the corresponding voting spaces. No model for replacement function is assumed. Luminance data are fir... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Highlight removal by illumination-constrained inpainting

    Publication Year: 2003, Page(s):164 - 169 vol.1
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB) | HTML iconHTML

    We present a single-image highlight removal method that incorporates illumination-based constraints into image inpainting. Unlike occluded image regions filled by traditional inpainting, highlight pixels contain some useful information for guiding the inpainting process. Constraints provided by observed pixel colors, highlight color analysis and illumination color uniformity are employed in our me... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface reflectance modeling of real objects with interreflections

    Publication Year: 2003, Page(s):170 - 177 vol.1
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (629 KB) | HTML iconHTML

    In mixed reality, especially in augmented virtuality which virtualizes real objects, it is important to estimate object surface reflectance properties to render the objects under arbitrary illumination conditions. Though several methods have been explored to estimate the surface reflectance properties, it is still difficult to estimate surface reflectance parameters faithfully for complex objects ... View full abstract»

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