By Topic

Workshop on Motion and Video Computing, 2002. Proceedings.

9-9 Dec. 2002

Filter Results

Displaying Results 1 - 25 of 40
  • Proceedings Workshop on Motion and Video Computing (MOTION 2002)

    Publication Year: 2002
    Request permission for commercial reuse | PDF file iconPDF (260 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2002, Page(s): 257
    Request permission for commercial reuse | PDF file iconPDF (160 KB)
    Freely Available from IEEE
  • Indexing key positions between multiple videos

    Publication Year: 2002, Page(s):65 - 71
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (518 KB) | HTML iconHTML

    Given two or more video sequences containing similar human activities (running, jumping, etc.), we want to devise a method which extracts spatio-temporal signatures associated with these activities, compares these signatures, and aligns key positions from different videos. We introduce a method which, in conjunction with a number of hypotheses, allows the analysis of the motion of specific body pa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust probabilistic estimation of uncertain appearance for model-based tracking

    Publication Year: 2002, Page(s):28 - 33
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (405 KB) | HTML iconHTML

    We present a method for appearance management for model-based visual tracking. The approach provides a concise mechanism for mapping image information to a model surface by taking into consideration uncertainties from the mapping process and by propagating appearance information from visible high-confidence surface regions to hidden or low-confidence regions. The method allows acquiring and utiliz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A linear model for simultaneous estimation of 3D motion and depth

    Publication Year: 2002, Page(s):220 - 225
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (435 KB) | HTML iconHTML

    A novel model for simultaneous estimation of full 3D motion and 3D position in world coordinates from multi camera sequences is presented. To this end scene flow (see Vedula, S. et al., ICCV 1999, p.722-9, 1999) and disparity are estimated in a single estimation step. The key idea is to interpret sequences of 2 or more cameras as one 4D data set. In this 4D space, a given motion model, a camera mo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A variational framework for active and adaptative segmentation of vector valued images

    Publication Year: 2002, Page(s):56 - 61
    Cited by:  Papers (79)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (629 KB) | HTML iconHTML

    Much effort has been made in integrating different information in a variational framework to segment images. Recent works on curve propagation were able to incorporate stochastic information (see Paragios, N. and Deriche, R., J. Visual Commun. and Image Representation, 2002; Zhu, S. and Yuille, A., 1996) and prior knowledge on shapes (see Cremers, D. et al., 2002; Rousson M. and Paragios, N., 2002... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical approach to robust background subtraction using color and gradient information

    Publication Year: 2002, Page(s):22 - 27
    Cited by:  Papers (148)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (338 KB) | HTML iconHTML

    We present a background subtraction method that uses multiple cues to detect objects robustly in adverse conditions. The algorithm consists of three distinct levels, i.e., pixel level, region level and frame level. At the pixel level, statistical models of gradients and color are separately used to classify each pixel as belonging to background or foreground. In the region level, foreground pixels... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical approach for obtaining structure from two-frame optical flow

    Publication Year: 2002, Page(s):214 - 219
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4332 KB) | HTML iconHTML

    A hierarchical iterative algorithm is proposed for extracting structure from two-frame optical flow. The algorithm exploits two facts: one is that in many applications, such as face and gesture recognition, the depth variation of the visible surface of an object in a scene is small compared to the distance between the optical center and the object; the other is that the time aliasing problem is al... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Joint space-time motion-based segmentation of image sequences with level set PDEs

    Publication Year: 2002, Page(s):50 - 55
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (544 KB) | HTML iconHTML

    We present a novel approach to motion segmentation by formulating it as the computation of the volume spanned by moving regions in the 3-dimensional spatio-temporal domain, in contrast to standard approaches to motion segmentation which are based on 2-dimensional spatial segmentations. We propose a Bayesian formulation for motion-based segmentation of image sequences, and we solve this Bayesian es... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Particle filter with analytical inference for human body tracking

    Publication Year: 2002, Page(s):159 - 165
    Cited by:  Papers (14)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (569 KB) | HTML iconHTML

    The paper introduces a framework that integrates analytical inference into the particle filtering scheme for human body tracking. The analytical inference is provided by body parts detection, and is used to update subsets of state parameters representing the human pose. This reduces the degree of randomness and decreases the required number of particles. This new technique is a significant improve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shadow elimination for robust video surveillance

    Publication Year: 2002, Page(s):15 - 21
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (995 KB) | HTML iconHTML

    Variation in illumination conditions, caused by weather, season, time of day, etc., makes the task difficult when building surveillance systems of real world scenes. Especially, cast shadows produce troublesome appearance variations to accomplish monitoring with computer vision techniques, typically moving object tracking from a stationary viewpoint. To eliminate lighting effects robustly from ima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A three-mode expressive feature model of action effort

    Publication Year: 2002, Page(s):139 - 144
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (291 KB) | HTML iconHTML

    We present an expressive feature model for recognizing the performance effort of human actions. A set of low and high effort examples for an action are initially factored into its three-mode principal components, followed by a learning phase to compute the expressive features required to bring the model estimation of effort into agreement with perceptual judgements. The approach is demonstrated us... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the binding mechanism of synchronised visual events

    Publication Year: 2002, Page(s):112 - 117
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (514 KB) | HTML iconHTML

    We address the problem of interpreting visual surveillance data by learning appropriate spatio-temporal subspaces of active image regions caused by scene activities. We focus on identifying regions of sustained change for recognising key stages of a visual behaviour. Our behaviour representation is based on the asynchrony or delay patterns of occurrence among local events which need not be spatial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interactive indoor scene reconstruction from image mosaics using cuboid structure

    Publication Year: 2002, Page(s):208 - 213
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (359 KB) | HTML iconHTML

    We describe a method for reconstructing indoor scenes from image mosaics using prior knowledge of the cuboid structure of the environment. The method is inspired by traditional approaches to the camera pose estimation problems known as the PnL (perspective n lines) and PnA (perspective n angles) problems. We show that a cuboid can be reconstructed from the images of three of its corners. The neces... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of dynamic scenes from image intensities

    Publication Year: 2002, Page(s):44 - 49
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (344 KB) | HTML iconHTML

    We present an algebraic geometric approach for segmenting both static and dynamic scenes from image intensities. We introduce the multibody affine constraint as a geometric relationship between the motion of multiple objects and the image intensities generated by them. This constraint is satisfied by all the pixels, regardless of the body to which they belong and regardless of depth discontinuitie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid Monte Carlo filtering: edge-based people tracking

    Publication Year: 2002, Page(s):151 - 158
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1851 KB) | HTML iconHTML

    Statistical inefficiency often limits the effectiveness of particle filters for high-dimensional Bayesian tracking problems. To improve sampling efficiency on continuous domains, we propose the use of a particle filter with hybrid Monte Carlo (HMC), an MCMC (Markov chain Monte Carlo) method that follows posterior gradients toward. high probability states, while ensuring a properly weighted approxi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stochastic human segmentation from a static camera

    Publication Year: 2002, Page(s):9 - 14
    Cited by:  Papers (21)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (620 KB) | HTML iconHTML

    Segmenting individual humans in a high-density scene (e.g., a crowd) acquired from a static camera is challenging mainly due to object inter-occlusion. We define this problem as a "model-based segmentation" problem and the solution is obtained using a Markov chain Monte Carlo (MCMC) approach. Knowledge of various aspects including human shape, human height, camera model, and image cues including h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time tracking of quad-marked surfaces

    Publication Year: 2002, Page(s):253 - 256
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (861 KB) | HTML iconHTML

    We introduce a real-time tracking procedure for a collection of quads marked on a surface. A fast image alignment is used for tracking individual quads, and local mutual relations are enforced for the corresponding collection of quad homographies. The resulting procedure runs at the video frame rate for a variety of moving surfaces. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Directed acyclic graph representation of deformable models

    Publication Year: 2002, Page(s):84 - 89
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3531 KB) | HTML iconHTML

    Deformable models are a useful tool in computer vision and computer graphics. A deformable model is a curve (in two dimensions) or a surface (in three dimensions), whose shape, position, and orientation are controlled through a set of parameters. Deformable models can represent manufactured objects, human faces and skeletons, and even bodies of fluid. In computer graphics, we use deformable models... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Density estimation-based information fusion for multiple motion computation

    Publication Year: 2002, Page(s):241 - 246
    Cited by:  Papers (3)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1180 KB) | HTML iconHTML

    Vision tasks, such as motion analysis, object tracking, robot localization, and 3D modeling, often require the fusion of estimates coming from different sources. Most of the fusion algorithms, however, are not robust with respect to outliers and only consider one source models. Their performance deteriorates when initial assumptions are not valid (e.g., the presence of outliers in the data or data... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Continuous multi-views tracking using tensor voting

    Publication Year: 2002, Page(s):181 - 186
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1028 KB) | HTML iconHTML

    The paper presents a new approach for continuous tracking of moving objects observed by multiple fixed cameras. The continuous tracking of moving objects in each view is realized using a tensor voting based approach. We infer objects' trajectories by performing a perceptual grouping in 2D+t using tensor voting. Also, a multi-scale approach to bridge gaps in object trajectories is presented The tra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time posture and activity recognition

    Publication Year: 2002, Page(s):133 - 138
    Cited by:  Papers (7)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (497 KB) | HTML iconHTML

    We propose an algorithm for human posture and activity recognition for uncompressed and compressed (MPEG) video inputs. A real-time compression domain technique is developed to recognize different postures such as standing, pointing left/right, opening arms, etc. by using an eigenspace representation of human silhouettes obtained from AC-DCT coefficients. The system stores frames with specific pos... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation and tracking of interacting human body parts under occlusion and shadowing

    Publication Year: 2002, Page(s):105 - 111
    Cited by:  Papers (29)  |  Patents (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB) | HTML iconHTML

    The paper presents a system to segment and track multiple body parts of interacting humans in the presence of mutual occlusion and shadow. The color image sequence is processed at three levels: pixel level, blob level, and object level. A Gaussian mixture model is used at the pixel level to train and classify individual pixel colors. A Markov random field (MRF) framework is used at the blob level ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • From video sequences to motion panoramas

    Publication Year: 2002, Page(s):201 - 207
    Cited by:  Papers (12)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (354 KB) | HTML iconHTML

    We address the problem of constructing mosaics from video sequences taken by rotating cameras. In particular we investigate the widespread case where the scene is not only static but may also contain large dynamic areas, induced by moving or deforming objects. Most of the existing techniques fail to produce reliable results on such video sequences. For such alignment purposes, two classes of techn... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Video frame categorization using sort-merge feature selection

    Publication Year: 2002, Page(s):72 - 77
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (281 KB) | HTML iconHTML

    Feature selection for video categorization is impractical with existing techniques. We present a novel algorithm to select a very small subset of image features. We reduce the cardinality of the input data by sorting the individual features by their effectiveness in categorization, and then merging pairwise these features into feature sets of cardinality two. Repeating this sort-merge process seve... View full abstract»

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