By Topic

Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on

Date 27 June-2 July 2004

Go

Filter Results

Displaying Results 1 - 25 of 148
  • Probability models for high dynamic range imaging

    Publication Year: 2004, Page(s):II-173 - II-180 Vol.2
    Cited by:  Papers (25)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1525 KB) | HTML iconHTML

    Methods for expanding the dynamic range of digital photographs by combining images taken at different exposures have recently received a lot of attention. Current techniques assume that the photometric transfer function of a given camera is the same (modulo an overall exposure change) for all the input images. Unfortunately, this is rarely the case with today's camera, which may perform complex no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A flexible projector-camera system for multi-planar displays

    Publication Year: 2004, Page(s):II-165 - II-172 Vol.2
    Cited by:  Papers (25)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (661 KB) | HTML iconHTML

    We present a novel multi-planar display system based on an uncalibrated projector-camera pair. Our system exploits the juxtaposition of planar surfaces in a room to create ad-hoc visualization and display capabilities. In an office setting, for example, a desk pushed against a wall provides two perpendicular surfaces that can simultaneously display elevation and plan views of an architectural mode... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An unsupervised, online learning framework for moving object detection

    Publication Year: 2004, Page(s):II-317 - II-324 Vol.2
    Cited by:  Papers (48)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (818 KB) | HTML iconHTML

    Object detection with a learned classifier has been applied successfully to difficult tasks such as detecting faces and pedestrians. Systems using this approach usually learn the classifier offline with manually labeled training data. We present a framework that learns the classifier online with automatically labeled data for the specific case of detecting moving objects from video. Motion informa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eye typing off the shelf

    Publication Year: 2004, Page(s):II-159 - II-164 Vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (331 KB) | HTML iconHTML

    The goal of this work is using off-the-shelf components for gaze-based interaction, with focus on eye typing. Avoiding the use of dedicated hardware such as IR light emitters makes eye tracking significantly more difficult and requires robust methods capable of handling large changes in image quality. We employ an active-contour method to obtain robust iris tracking. The main strength of the metho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-normalized linear tests

    Publication Year: 2004, Page(s):II-616 - II-622 Vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (562 KB) | HTML iconHTML

    Making decisions based on a linear combination L of features is of course very common in pattern recognition. For distinguishing between two hypotheses or classes, the test is of the form sign (L - τ) for some threshold τ. Due mainly to fixing τ, such tests are sensitive to changes in illumination and other variations in imaging conditions. We propose a special case, a "self-normalized... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion-based background subtraction using adaptive kernel density estimation

    Publication Year: 2004, Page(s):II-302 - II-309 Vol.2
    Cited by:  Papers (194)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (689 KB) | HTML iconHTML

    Background modeling is an important component of many vision systems. Existing work in the area has mostly addressed scenes that consist of static or quasi-static structures. When the scene exhibits a persistent dynamic behavior in time, such an assumption is violated and detection performance deteriorates. In this paper, we propose a new method for the modeling and subtraction of such scenes. Tow... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High-zoom video hallucination by exploiting spatio-temporal regularities

    Publication Year: 2004, Page(s):II-151 - II-158 Vol.2
    Cited by:  Papers (18)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (590 KB) | HTML iconHTML

    In this paper, we consider the problem of super-resolving a human face video by a very high (× 16) zoom factor. Inspired by the literature on hallucination and example-based learning, we formulate this task using a graphical model that encodes, (1) spatio-temporal consistencies, and (2) image formation & degradation processes. A video database of facial expressions is used to learn a domain-... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting and reading text in natural scenes

    Publication Year: 2004, Page(s):II-366 - II-373 Vol.2
    Cited by:  Papers (89)  |  Patents (30)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1061 KB) | HTML iconHTML

    This paper gives an algorithm for detecting and reading text in natural images. The algorithm is intended for use by blind and visually impaired subjects walking through city scenes. We first obtain a dataset of city images taken by blind and normally sighted subjects. From this dataset, we manually label and extract the text regions. Next we perform statistical analysis of the text regions to det... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Orthogonal complement component analysis for positive samples in SVM based relevance feedback image retrieval

    Publication Year: 2004, Page(s):II-586 - II-591 Vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (379 KB) | HTML iconHTML

    Relevance feedback (RF) is an important tool to improve the performance of content-based image retrieval system. Support vector machine (SVM) based RF is popular because it can generalize better than most other classifiers. However, directly using SVM in RF may not be appropriate, since SVM treats the positive and negative feedbacks equally. Given the different properties of positive samples and n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modelling the effects of walking speed on appearance-based gait recognition

    Publication Year: 2004, Page(s):II-783 - II-790 Vol.2
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (731 KB) | HTML iconHTML

    Researchers in the gait community propose various features, either appearance or model based, which they believe encode certain individual traits. One of the main assumptions made in many gait recognition techniques is constant walking-speed. Even though the gait patterns are repeatable, changes in walking speed can influence the gait patterns themselves. In this work we explore how changes in wal... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High-speed videography using a dense camera array

    Publication Year: 2004, Page(s):II-294 - II-301 Vol.2
    Cited by:  Papers (33)  |  Patents (78)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (462 KB) | HTML iconHTML

    We demonstrate a system for capturing multi-thousand frame-per-second (fps) video using a dense array of cheap 30 fps CMOS image sensors. A benefit of using a camera array to capture high-speed video is that we can scale to higher speeds by simply adding more cameras. Even at extremely high frame rates, our array architecture supports continuous streaming to disk from all of the cameras. This allo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model for dynamic shape and its applications

    Publication Year: 2004, Page(s):II-129 - II-134 Vol.2
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (317 KB) | HTML iconHTML

    Variation in object shape is an important visual cue for deformable object recognition and classification. In this paper, we present an approach to model gradual changes in the 2-D shape of an object. We represent 2-D region shape in terms of the spatial frequency content of the region contour using Fourier coefficients. The temporal changes in these coefficients are used as the temporal signature... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised learning of image manifolds by semidefinite programming

    Publication Year: 2004, Page(s):II-988 - II-995 Vol.2
    Cited by:  Papers (7)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (596 KB) | HTML iconHTML

    Can we detect low dimensional structure in high dimensional data sets of images and video? The problem of dimensionality reduction arises often in computer vision and pattern recognition. In this paper, we propose a new solution to this problem based on semidefinite programming. Our algorithm can be used to analyze high dimensional data that lies on or near a low dimensional manifold. It overcomes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature selection for classifying high-dimensional numerical data

    Publication Year: 2004, Page(s):II-251 - II-258 Vol.2
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (297 KB) | HTML iconHTML

    Classifying high-dimensional numerical data is a very challenging problem. In high dimensional feature spaces, the performance of supervised learning methods suffers from the curse of dimensionality, which degrades both classification accuracy and efficiency. To address this issue, we present an efficient feature selection method to facilitate classifying high-dimensional numerical data. Our metho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion segmentation with missing data using PowerFactorization and GPCA

    Publication Year: 2004, Page(s):II-310 - II-316 Vol.2
    Cited by:  Papers (45)  |  Patents (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (557 KB) | HTML iconHTML

    We consider the problem of segmenting multiple rigid motions from point correspondences in multiple affine views. We cast this problem as a subspace clustering problem in which the motion of each object lives in a subspace of dimension two, three or four. Unlike previous work, we do not restrict the motion subspaces to be four-dimensional or linearly independent. Instead, our approach deals gracef... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dual-space linear discriminant analysis for face recognition

    Publication Year: 2004, Page(s):II-564 - II-569 Vol.2
    Cited by:  Papers (54)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (258 KB) | HTML iconHTML

    Linear discriminant analysis (LDA) is a popular feature extraction technique for face recognition. However, it often suffers from the small sample size problem when dealing with the high dimensional face data. Some approaches have been proposed to overcome this problem, but they are often unstable and have to discard some discriminative information. In this paper, a dual-space LDA approach for fac... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Accurate face models from uncalibrated and ill-lit video sequences

    Publication Year: 2004, Page(s):II-1034 - II-1041 Vol.2
    Cited by:  Papers (25)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (706 KB) | HTML iconHTML

    We propose a face reconstruction technique that produces models that not only look good when texture mapped, but are also metrically accurate. Our method is designed to work with short uncalibrated video or movie sequences, even when the lighting is poor resulting in specularities and shadows that complicate the algorithm's task. Our approach relies on optimizing the shape parameters of a sophisti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Propagation networks for recognition of partially ordered sequential action

    Publication Year: 2004, Page(s):II-862 - II-869 Vol.2
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (481 KB) | HTML iconHTML

    We present propagation networks (P-nets), a novel approach for representing and recognizing sequential activities that include parallel streams of action. We represent each activity using partially ordered intervals. Each interval is restricted by both temporal and logical constraints, including information about its duration and its temporal relationship with other intervals. P-nets associate one... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • What image information is important in silhouette-based gait recognition?

    Publication Year: 2004, Page(s):II-776 - II-782 Vol.2
    Cited by:  Papers (47)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (355 KB) | HTML iconHTML

    Gait recognition has recently gained significant attention, especially in vision-based automated human identification at a distance in visual surveillance and monitoring applications. Silhouette-based gait recognition is one of the most popular methods for recognising moving shapes. This paper aims to investigate the important features in silhouette-based gait recognition from point of view of sta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reconstructing open surfaces from unorganized data points

    Publication Year: 2004, Page(s):II-653 - II-660 Vol.2
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (896 KB) | HTML iconHTML

    In this paper a method for fitting open surfaces to an unorganized set of data points is presented using a level set representation of the surface. This is done by tracking a curve, representing the boundary, on the implicitly defined surface. This curve is given as the intersection of the level set describing the surface and an auxiliary level set. These two level sets are propagated using the sa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrating and employing multiple levels of zoom for activity recognition

    Publication Year: 2004, Page(s):II-928 - II-935 Vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (558 KB) | HTML iconHTML

    To facilitate activity recognition, analysis of the scene at multiple levels of detail is necessary. Required prerequisites for our activity recognition are tracking objects across frames and establishing a consistent labeling of objects across cameras. This paper makes several innovative uses of the epipolar constraint in the context of activity recognition. We first demonstrate how we track head... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Representation and matching of articulated shapes

    Publication Year: 2004, Page(s):II-342 - II-349 Vol.2
    Cited by:  Papers (12)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1601 KB) | HTML iconHTML

    We consider the problem of localizing the articulated and deformable shape of a walking person in a single view. We represent the non-rigid 2D body contour by a Bayesian graphical model whose nodes correspond to point positions along the contour. The deformability of the model is constrained by learned priors corresponding to two basic mechanisms: local non-rigid deformation, and rotation motion o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic cascade training with perturbation bias

    Publication Year: 2004, Page(s):II-276 - II-283 Vol.2
    Cited by:  Papers (13)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (327 KB) | HTML iconHTML

    Face detection methods based on cascade architecture have demonstrated fast and robust performance. Cascade learning is aided by the modularity of the architecture in which nodes are chained together to form a cascade. In this paper we present two new cascade learning results which address the decoupled nature of the cascade learning task. First, we introduce a cascade indifference curve framework... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian face recognition using support vector machine and face clustering

    Publication Year: 2004, Page(s):II-374 - II-380 Vol.2
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (276 KB) | HTML iconHTML

    In this paper, we first develop a direct Bayesian based support vector machine by combining the Bayesian analysis with the SVM. Unlike traditional SVM-based face recognition method that needs to train a large number of SVMs, the direct Bayesian SVM needs only one SVM trained to classify the face difference between intra-personal variation and extra-personal variation. However, the added simplicity... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear model hashing and batch RANSAC for rapid and accurate object recognition

    Publication Year: 2004, Page(s):II-121 - II-128 Vol.2
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (426 KB) | HTML iconHTML

    This paper proposes a joint feature-based model indexing and geometric constraint based alignment pipeline for efficient and accurate recognition of 3D objects from a large model database. Traditional approaches either first prune the model database using indexing without geometric alignment or directly perform recognition based alignment. The indexing based pruning methods without geometric const... View full abstract»

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