The Community for Technology Leaders
Image Analysis and Processing, International Conference on (1999)
Venice, Italy
Sept. 27, 1999 to Sept. 29, 1999
ISBN: 0-7695-0040-4
pp: 280
Ismail Haritaoglu , University of Maryland at College Park
David Harwood , University of Maryland at College Park
Larry S. Davis , University of Maryland at College Park
ABSTRACT
Hydra is a real-time system for detecting and tracking multiple people when they appear in a group. We describe the computational models employed by Hydra to track multiple people before, during and after occlusion. Hydra combines a silhouette-based shape model, a motion model, and correlation-based matching methods to classify whether or not a foreground region contains multiple people, and to segment the region into its constituent people and track them. Experimental results demonstrate robustness and real-time performance of the algorithm.
INDEX TERMS
CITATION

L. S. Davis, I. Haritaoglu and D. Harwood, "Hydra: Multiple People Detection and Tracking Using Silhouettes," Image Analysis and Processing, International Conference on(ICIAP), Venice, Italy, 1999, pp. 280.
doi:10.1109/ICIAP.1999.797608
81 ms
(Ver 3.3 (11022016))