A computer vision system for tracking multiple people in relatively unconst
rained environments is described. Tracking is performed at three levels of
abstraction: regions, people, and groups. A novel, adaptive background subt
raction method that combines color and gradient information is used to cope
with shadows and unreliable color cues. People are tracked through mutual
occlusions as they form groups and separate from one another. Strong use is
made of color information to disambiguate occlusion and to provide qualita
tive estimates of depth ordering and position during occlusion. Simple inte
ractions with objects can also be detected. The system is tested using both
indoor and outdoor sequences. It is robust and should provide a useful mec
hanism for bootstrapping and reinitialization of tracking using more specif
ic but less robust human models. (C) 2000 Academic Press.