Learning to track the visual motion of contours
Artificial Intelligence - Special volume on computer vision
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Contour Tracking by Stochastic Propagation of Conditional Density
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
X Vision: Combining Image Warping and Geometric Constraints for Fast Visual Tracking
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
An Assessment of Information Criteria for Motion Model Selection
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Background Modeling for Segmentation of Video-Rate Stereo Sequences
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Joint Probabilistic Techniques for Tracking Multi-Part Objects
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pfinder: real-time tracking of the human body
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
A multi-body factorization method for motion analysis
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Head Detection and Localization from Sparse 3D Data
Proceedings of the 24th DAGM Symposium on Pattern Recognition
Hi-index | 0.00 |
Tracking a number of persons moving in cluttered scenes is an important issue in computer vision. It is the first step of automatic video-based surveillance systems. In this paper we present a binocular vision system using stereo information for moving head detection and tracking. After background subtraction, the remained foreground disparity image is used as a mask to delete background clutter as well as to reduce the search space, which greatly improve the tracking performance when occlusion happens. With a local sampling method together with the stereo information obtained, we are now able to reliably detect and track people in cluttered natural environments at about 5 Hz on standard PC hardware.