The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
ISBN: 978-1-4244-2242-5
pp: 1-7
Zhang-Sheng John Liang , Electrical and Computer Engineering Department, University of California, San Diego, USA
Antoni B. Chan , Electrical and Computer Engineering Department, University of California, San Diego, USA
Nuno Vasconcelos , Electrical and Computer Engineering Department, University of California, San Diego, USA
ABSTRACT
We present a privacy-preserving system for estimating the size of inhomogeneous crowds, composed of pedestrians that travel in different directions, without using explicit object segmentation or tracking. First, the crowd is segmented into components of homogeneous motion, using the mixture of dynamic textures motion model. Second, a set of simple holistic features is extracted from each segmented region, and the correspondence between features and the number of people per segment is learned with Gaussian Process regression. We validate both the crowd segmentation algorithm, and the crowd counting system, on a large pedestrian dataset (2000 frames of video, containing 49,885 total pedestrian instances). Finally, we present results of the system running on a full hour of video.
INDEX TERMS
CITATION
Zhang-Sheng John Liang, Antoni B. Chan, Nuno Vasconcelos, "Privacy preserving crowd monitoring: Counting people without people models or tracking", 2013 IEEE Conference on Computer Vision and Pattern Recognition, vol. 00, no. , pp. 1-7, 2008, doi:10.1109/CVPR.2008.4587569
84 ms
(Ver )