CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
The visual analysis of human movement: a survey
Computer Vision and Image Understanding
Contour Tracking by Stochastic Propagation of Conditional Density
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Visual Surveillance of Human Activity
ACCV '98 Proceedings of the Third Asian Conference on Computer Vision-Volume II
Elliptical Head Tracking Using Intensity Gradients and Color Histograms
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Human Head Tracking Using Adaptive Appearance Models with a Fixed-Viewpoint Pan-Tilt-Zoom Camera
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Indoor Monitoring Via the Collaboration Between a Peripheral Sensor and a Fovea1 Sensor
VS '98 Proceedings of the 1998 IEEE Workshop on Visual Surveillance
Face Recognition from Video: A CONDENSATION Approach
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Hi-index | 0.00 |
We propose a method for tracking human heads, where interaction between hypotheses plays a key role. We model appearances of the human head and generate hypotheses for a human head in the image in the model space. We then propagate and reform hypotheses over time in turn to realize tracking human heads. During tracking, we bring about interaction between hypotheses to eliminate the hypotheses denoting false positives and, at the same time, to maintain the hypotheses denoting human heads.