M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene
International Journal of Computer Vision
Iterative Figure-Ground Discrimination
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Using Particles to Track Varying Numbers of Interacting People
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Simultaneous Estimation of Segmentation and Shape
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Fixed Point Probability Field for Complex Occlusion Handling
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Human appearance modeling for matching across video sequences
Machine Vision and Applications
Tracking multiple humans in crowded environment
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Probabilistic tracking in joint feature-spatial spaces
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
A multiview approach to tracking people in crowded scenes using a planar homography constraint
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
We describe an approach to segmenting foreground regions corresponding to a group of people into individual humans. Given background subtraction and ground plane homography, hierarchical parttemplate matching is employed to determine a reliable set of human detection hypotheses, and progressive greedy optimization is performed to estimate the best configuration of humans under a Bayesian MAP framework. Then, appearance models and segmentations are simultaneously estimated in an iterative sampling-expectation paradigm. Each human appearance is represented by a nonparametric kernel density estimator in a joint spatial-color space and a recursive probability update scheme is employed for soft segmentation at each iteration. Additionally, an automatic occlusion reasoning method is used to determine the layered occlusion status between humans. The approach is evaluated on a number of images and videos, and also applied to human appearance matching using a symmetric distance measure derived from the Kullback-Leiber divergence.