Tracking multiple humans in crowded environment

by: Tao Zhao, R Nevatia

Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, Vol. 2 (2004), pp. II-406-II-413 Vol.2.

View FullText article

DOI, IEEE Explore

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

SamueleSalti, anelson

Find related articles with these CiteULike tags

ee520, ee520_part1, no-tag

Abstract

Tracking of humans in dynamic scenes has been an important topic of research. Most techniques, however, are limited to situations where humans appear isolated and occlusion is small. Typical methods rely on appearance models that must be acquired when the humans enter the scene and are not occluded. We present a method that can track humans in crowded environments, with significant and persistent occlusion by making use of human shape models in addition to camera models, the assumption that humans walk on a plane and acquired appearance models. Experimental results and a quantitative evaluation are included.

@inproceedings{citeulike:353330, abstract = {Tracking of humans in dynamic scenes has been an important topic of research. Most techniques, however, are limited to situations where humans appear isolated and occlusion is small. Typical methods rely on appearance models that must be acquired when the humans enter the scene and are not occluded. We present a method that can track humans in crowded environments, with significant and persistent occlusion by making use of human shape models in addition to camera models, the assumption that humans walk on a plane and acquired appearance models. Experimental results and a quantitative evaluation are included.}, author = {Zhao, Tao and Nevatia, R. }, citeulike-article-id = {353330}, doi = {http://dx.doi.org/10.1109/CVPR.2004.1315192}, journal = {Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on}, keywords = {ee520, ee520\_part1}, pages = {II-406--II-413 Vol.2}, posted-at = {2005-10-17 23:02:04}, priority = {2}, title = {Tracking multiple humans in crowded environment}, url = {http://dx.doi.org/10.1109/CVPR.2004.1315192}, volume = {2}, year = {2004} }

RIS record

TY - CONF ID - citeulike:353330 L3 - citeulike-article-id:353330 N2 - Tracking of humans in dynamic scenes has been an important topic of research. Most techniques, however, are limited to situations where humans appear isolated and occlusion is small. Typical methods rely on appearance models that must be acquired when the humans enter the scene and are not occluded. We present a method that can track humans in crowded environments, with significant and persistent occlusion by making use of human shape models in addition to camera models, the assumption that humans walk on a plane and acquired appearance models. Experimental results and a quantitative evaluation are included. JF - Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on EP - II-413 Vol.2 TI - Tracking multiple humans in crowded environment VL - 2 SP - II-406 KW - ee520 KW - ee520_part1 AU - Zhao, Tao AU - Nevatia, R PY - 2004/// UR - http://dx.doi.org/10.1109/CVPR.2004.1315192 ER -

RIS BibTeX