Feature extraction from faces using deformable templates
International Journal of Computer Vision
A fully decentralized multi-sensor system for tracking and surveillance
International Journal of Robotics Research
Active vision
A framework for spatiotemporal control in the tracking of visual contours
International Journal of Computer Vision
Learning to track the visual motion of contours
Artificial Intelligence - Special volume on computer vision
International Journal of Computer Vision
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Deformable Templates for Feature Extraction from Medical Images
ECCV '90 Proceedings of the First European Conference on Computer Vision
Real-Time Lip Tracking for Audio-Visual Speech Recognition Applications
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Accurate, Real-Time, Unadorned Lip Tracking
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Visual speech recognition using active shape models and hidden Markov models
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
Automatic Lip Tracking: Bayesian Segmentation and Active Contours in a Cooperative Scheme
ICMCS '99 Proceedings of the IEEE International Conference on Multimedia Computing and Systems - Volume 2
Image-based change detection of areal objects using differential snakes
Proceedings of the 13th annual ACM international workshop on Geographic information systems
Segregation of moving objects using elastic matching
Computer Vision and Image Understanding
Globally Optimal Algorithms for Stratified Autocalibration
International Journal of Computer Vision
Segregation of moving objects using elastic matching
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
| Hi-index | 0.14 |
A new contour tracking algorithm is presented. Tracking is posed as a matching problem between curves constructed out of edges in the image, and some shape space describing the class of objects of interest. The main contributions of the paper are to present an algorithm which solves this problem accurately and efficiently, in a provable manner. In particular, the algorithm's efficiency derives from a novel tree-search algorithm through the shape space, which allows for much of the shape space to be explored with very little effort. This latter property makes the algorithm effective in highly cluttered scenes, as is demonstrated in an experimental comparison with a condensation tracker.