By Topic

Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on

Date 20-25 June 2005

Go

Filter Results

Displaying Results 1 - 25 of 201
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Cover

    Publication Year: 2005 , Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (1226 KB)  
    Freely Available from IEEE
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Title Page

    Publication Year: 2005 , Page(s): i - iii
    Save to Project icon | Request Permissions | PDF file iconPDF (39 KB)  
    Freely Available from IEEE
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Copyright Page

    Publication Year: 2005 , Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (46 KB)  
    Freely Available from IEEE
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Table of contents

    Publication Year: 2005 , Page(s): v - xxiii
    Save to Project icon | Request Permissions | PDF file iconPDF (85 KB)  
    Freely Available from IEEE
  • Preface

    Publication Year: 2005 , Page(s): xxiv - xxviii
    Save to Project icon | Request Permissions | PDF file iconPDF (78 KB) |  | HTML iconHTML  
    Freely Available from IEEE
  • Conference organization

    Publication Year: 2005 , Page(s): xxix - xxx
    Save to Project icon | Request Permissions | PDF file iconPDF (17 KB)  
    Freely Available from IEEE
  • Program Committee

    Publication Year: 2005 , Page(s): xxxi - xxxiii
    Save to Project icon | Request Permissions | PDF file iconPDF (19 KB)  
    Freely Available from IEEE
  • Additional reviewers

    Publication Year: 2005 , Page(s): xxxiv - xxxv
    Save to Project icon | Request Permissions | PDF file iconPDF (17 KB)  
    Freely Available from IEEE
  • Video Proceedings Welcome

    Publication Year: 2005 , Page(s): xxxvi
    Save to Project icon | Request Permissions | PDF file iconPDF (17 KB)  
    Freely Available from IEEE
  • Demo Proceedings Welcome

    Publication Year: 2005 , Page(s): xxxvii
    Save to Project icon | Request Permissions | PDF file iconPDF (16 KB) |  | HTML iconHTML  
    Freely Available from IEEE
  • Particle filtering for geometric active contours with application to tracking moving and deforming objects

    Publication Year: 2005 , Page(s): 2 - 9 vol. 2
    Cited by:  Papers (30)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (416 KB) |  | HTML iconHTML  

    Geometric active contours are formulated in a manner which is parametrization independent. As such, they are amenable to representation as the zero level set of the graph of a higher dimensional function. This representation is able to deal with singularities and changes in topology of the contour. It has been used very successfully in static images for segmentation and registration problems where the contour (represented as an implicit curve) is evolved until it minimizes an image based energy functional. But tracking involves estimating the global motion of the object and its local deformations as a function of time. Some attempts have been made to use geometric active contours for tracking, but most of these minimize the energy at each frame and do not utilize the temporal coherency of the motion or the deformation. On the other hand, tracking algorithms using Kalman filters or particle filters have been proposed for finite dimensional representations of shape. But these are dependent on the chosen parametrization and cannot handle changes in curve topology. In the present work, we formulate a particle filtering algorithm in the geometric active contour framework that can be used for tracking moving and deforming objects. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Illumination-invariant tracking via graph cuts

    Publication Year: 2005 , Page(s): 10 - 17 vol. 2
    Cited by:  Papers (13)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (256 KB) |  | HTML iconHTML  

    Illumination changes are a ubiquitous problem in computer vision. They present a challenge in many applications, including tracking: for example, an object may move in and out of a shadow. We present a new tracking algorithm which is insensitive to illumination changes, while at the same time using all of the available photometric information. The algorithm is based on computing an illumination-invariant optical flow field; the computation is made robust by using a graph cuts formulation. Experimentally, the new technique is shown to quite reliable in both synthetic and real sequences, dealing with a variety of illumination changes that cause problems for density based trackers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual tracking in the presence of motion blur

    Publication Year: 2005 , Page(s): 18 - 25 vol. 2
    Cited by:  Papers (13)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (544 KB) |  | HTML iconHTML  

    We consider the problem of visual tracking of regions of interest in a sequence of motion blurred images. Traditional methods couple tracking with deblurring in order to correctly account for the effects of motion blur. Such coupling is usually appropriate, but computationally wasteful when visual tracking is the lone objective. Instead of deblurring images, we propose to match regions by blurring them. The matching score for two image regions is governed by a cost function that only involves the region deformation parameters and two motion blur vectors. We present an efficient algorithm to minimize the proposed cost function and demonstrate it on sequences of real blurred images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Appearance modeling for tracking in multiple non-overlapping cameras

    Publication Year: 2005 , Page(s): 26 - 33 vol. 2
    Cited by:  Papers (62)  |  Patents (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (392 KB) |  | HTML iconHTML  

    When viewed from a system of multiple cameras with non-overlapping fields of view, the appearance of an object in one camera view is usually very different from its appearance in another camera view due to the differences in illumination, pose and camera parameters. In order to handle the change in observed colors of an object as it moves from one camera to another, we show that all brightness transfer functions from a given camera to another camera lie in a low dimensional subspace and demonstrate that this subspace can be used to compute appearance similarity. In the proposed approach, the system learns the subspace of inter-camera brightness transfer functions in a training phase during which object correspondences are assumed to be known. Once the training is complete, correspondences are assigned using the maximum a posteriori (MAP) estimation framework using both location and appearance cues. We evaluate the proposed method under several real world scenarios obtaining encouraging results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time tracking using level sets

    Publication Year: 2005 , Page(s): 34 - 41 vol. 2
    Cited by:  Papers (42)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1064 KB) |  | HTML iconHTML  

    In this paper we propose a novel implementation of the level set method that achieves real-time level-set-based video tracking. In our fast algorithm, the evolution of the curve is realized by simple operations such as switching elements between two linked lists and there is no need to solve any partial differential equations. Furthermore, a novel procedure based on Gaussian filtering is introduced to incorporate boundary smoothness regularization. By replacing the standard curve length penalty with this new smoothing procedure, further speedups are obtained. Another advantage of our fast algorithm is that the topology of the curves can be controlled easily. For the tracking of multiple objects, we extend our fast algorithm to maintain the desired topology for multiple object boundaries based on ideas from discrete topology. With our fast algorithm, a real-time system has been implemented on a standard PC and only a small fraction of the CPU power is used for tracking. Results from standard test sequences and our realtime system are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Higher-order image statistics for unsupervised, information-theoretic, adaptive, image filtering

    Publication Year: 2005 , Page(s): 44 - 51 vol. 2
    Cited by:  Papers (11)  |  Patents (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (304 KB) |  | HTML iconHTML  

    The restoration of images is an important and widely studied problem in computer vision and image processing. Various image filtering strategies have been effective, but invariably make strong assumptions about the properties of the signal and/or degradation. Therefore, these methods typically lack the generality to be easily applied to new applications or diverse image collections. This paper describes a novel unsupervised, information-theoretic, adaptive filter (UINTA) that improves the predictability of pixel intensities from their neighborhoods by decreasing the joint entropy between them. Thus UINTA automatically discovers the statistical properties of the signal and can thereby restore a wide spectrum of images and applications. This paper describes the formulation required to minimize the joint entropy measure, presents several important practical considerations in estimating image-region statistics, and then presents results on both real and synthetic data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Addressing radiometric nonidealities: a unified framework

    Publication Year: 2005 , Page(s): 52 - 59 vol. 2
    Cited by:  Papers (14)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2504 KB) |  | HTML iconHTML  

    Cameras may have non-ideal radiometric aspects, including spatial non-uniformity, e.g., due to vignetting; a nonlinear radiometric response of the sensor; and temporal variations due to automatic gain control (AGC). Often, these characteristics exist simultaneously, and are typically unknown. They thus hinder consistent photometric measurements. In particular, they create annoying seams in image mosaics. Prior studies approached part of these problems while excluding others. We handle all these problems in a unified framework. We suggest an approach for simultaneously estimating the radiometric response, the spatial non-uniformity and the temporally varying gain. The approach does not rely on dedicated processes that intentionally vary exposure settings. Rather, it is based on an ordinary frame sequence acquired during camera motion. The estimated non-ideal characteristics are then compensated for. We state fundamental ambiguities associated with this recovery problem, while exposing a novel image invariance. The method is demonstrated in several experiments, where different frames are brought into mutual radiometric consistency. The accuracy achieved is sufficient for seamless mosaicing, with no need to resort to dedicated seam-feathering methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A non-local algorithm for image denoising

    Publication Year: 2005 , Page(s): 60 - 65 vol. 2
    Cited by:  Papers (439)  |  Patents (25)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (304 KB) |  | HTML iconHTML  

    We propose a new measure, the method noise, to evaluate and compare the performance of digital image denoising methods. We first compute and analyze this method noise for a wide class of denoising algorithms, namely the local smoothing filters. Second, we propose a new algorithm, the nonlocal means (NL-means), based on a nonlocal averaging of all pixels in the image. Finally, we present some experiments comparing the NL-means algorithm and the local smoothing filters. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Determining the radiometric response function from a single grayscale image

    Publication Year: 2005 , Page(s): 66 - 73 vol. 2
    Cited by:  Papers (17)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB) |  | HTML iconHTML  

    A method is presented for computing the radiometric response function of a camera from a single grayscale image. While most previous techniques require a set of registered images with different exposures to obtain response data, our approach capitalizes on a statistical feature of graylevel histograms at edge regions to gain information for radio-metric calibration. Appropriate edge regions are automatically determined by our technique, and a prior model of radiometric response functions is employed to deal with incomplete data. With this single-image method, radiometric calibration becomes possible to perform in many instances where the camera is unknown. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A generative model of human hair for hair sketching

    Publication Year: 2005 , Page(s): 74 - 81 vol. 2
    Cited by:  Papers (1)  |  Patents (7)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (712 KB) |  | HTML iconHTML  

    Human hair is a very complex visual pattern whose representation is rarely studied in the vision literature despite its important role in human recognition. In this paper, we propose a generative model for hair representation and hair sketching, which is far more compact than the physically based models in graphics. We decompose a color hair image into three bands: a color band (a) (by Luv transform), a low frequency band (b) for lighting variations, and a high frequency band (c) for the hair pattern. Then we propose a three level generative model for the hair image (c). In this model, image (c) is generated by a vector field (d) that represents hair orientation, gradient strength, and directions; and this vector field is in turn generated by a hair sketch layer (e). We identify five types of primitives for the hair sketch each specifying the orientations of the vector field on the two sides of the sketch. With the five-layer representation (a-e) computed, we can reconstruct vivid hair images and generate hair sketches. We test our algorithm on a large data set of hairs and some results are reported in the experiments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active polyhedron: surface evolution theory applied to deformable meshes

    Publication Year: 2005 , Page(s): 84 - 91 vol. 2
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (640 KB) |  | HTML iconHTML  

    This paper presents a novel 3D deformable surface that we call an active polyhedron. Rooted in surface evolution theory, an active polyhedron is a polyhedral surface whose vertices deform to minimize a regional and/or boundary-based energy functional. Unlike continuous active surface models, the vertex motion of an active polyhedron is computed by integrating speed terms over polygonal faces of the surface. The resulting ordinary differential equations (ODEs) provide improved robustness to noise and allow for larger time steps compared to continuous active surfaces implemented with level set methods. We describe an electrostatic regularization technique that achieves global regularization while better preserving sharper local features. Experimental results demonstrate the effectiveness of an active polyhedron in solving segmentation problems as well as surface reconstruction from unorganized points. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Corrected Laplacians: closer cuts and segmentation with shape priors

    Publication Year: 2005 , Page(s): 92 - 98 vol. 2
    Cited by:  Papers (2)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (472 KB) |  | HTML iconHTML  

    We optimize over the set of corrected Laplacians (CL) associated with a weighted graph to improve the average case normalized cut (NCut) of a graph. Unlike edge-relaxation SDPs, optimizing over the set CL naturally exploits the matrix sparsity by operating solely on the diagonal. This structure is critical to image segmentation applications because the number of vertices is generally proportional to the number of pixels in the image. CL optimization provides a guiding principle for improving the combinatorial solution over the spectral relaxation, which is important because small improvements in the cut cost often result in significant improvements in the perceptual relevance of the segmentation. We develop an optimization procedure to accommodate prior information in the form of statistical shape models, resulting in a segmentation method that produces foreground regions which are consistent with a parameterized family of shapes. We validate our technique with ground truth on MRI medical images, providing a quantitative comparison against results produced by current spectral relaxation approaches to graph partitioning. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneous modeling and tracking (SMAT) of feature sets

    Publication Year: 2005 , Page(s): 99 - 105 vol. 2
    Cited by:  Papers (2)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (424 KB) |  | HTML iconHTML  

    A novel method for the simultaneous modeling and tracking (SMAT) of a feature set during motion sequence is proposed. The method requires no prior information. Instead the a posteriori distribution of appearance and shape is built up incrementally using an exemplar based approach. The resulting model is less optimal than when a priori data is used, but can be built in real-time. Data in any form may be used, provided a distance measure and a means to classify outliers exists. Here, a two tier implementation of SMAT is used: at the feature level, mutual information is used to track image patches; and at the object level, a structure model is built from the feature positions. As experiments demonstrate, the tracker is robust and operates in real-time without requiring prelearned data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining object and feature dynamics in probabilistic tracking

    Publication Year: 2005 , Page(s): 106 - 113 vol. 2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (872 KB) |  | HTML iconHTML  

    Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image features that are then used as input to a system for tracking the entire object using a global dynamic model. Approximate local dynamics may be brittle - point trackers drift due to image noise and adaptive background models adapt to foreground objects that become stationary - but constraints from the global model can make them more robust. We propose a probabilistic framework for incorporating global dynamics knowledge into the local feature extraction processes. A global tracking algorithm can be formulated as a generative model and used to predict feature values that are incorporated into an observation process of the feature extractor. We combine such models in a multichain graphical model framework. We show the utility of our framework for improving feature tracking and thus shape and motion estimates in a batch factorization algorithm. We also propose an approximate filtering algorithm appropriate for online applications, and demonstrate its application to background subtraction. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Localization in urban environments: monocular vision compared to a differential GPS sensor

    Publication Year: 2005 , Page(s): 114 - 121 vol. 2
    Cited by:  Papers (14)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1296 KB) |  | HTML iconHTML  

    In this paper we present a method for computing the localization of a mobile robot with reference to a learning video sequence. The robot is first guided on a path by a human, while the camera records a monocular learning sequence. Then a 3D reconstruction of the path and the environment is computed off line from the learning sequence. The 3D reconstruction is then used for computing the pose of the robot in real time (30 Hz) in autonomous navigation. Results from our localization method are compared to the ground truth measured with a differential GPS. View full abstract»

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