Title :
Hydra: multiple people detection and tracking using silhouettes
Author :
Haritaoglu, Ismail ; Harwood, David ; Davis, Larry S.
Author_Institution :
Comput. Vision Lab., Maryland Univ., College Park, MD, USA
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
Keywords :
image matching; image motion analysis; image segmentation; object detection; real-time systems; tracking; Hydra; computational models; correlation-based matching methods; motion model; multiple people detection; occlusion; real-time performance; real-time system; silhouette-based shape model; silhouettes; tracking; Histograms; Motion detection; Motion estimation;
Conference_Titel :
Visual Surveillance, 1999. Second IEEE Workshop on, (VS'99)
Conference_Location :
Fort Collins, CO
Print_ISBN :
0-7695-0037-4
DOI :
10.1109/VS.1999.780263