Integration of information from several vision systems for a common task of surveillance

In this paper we describe the integration of vision information obtained by a fixed camera and the information obtained by a binocular active vision system. Both systems acquire images from the same environment. The information redundancy is exploited to achieve a higher degree of robustness in detecting and tracking intruders. Global information about intruders is obtained by the fixed vision system whereas information about a specific intruder (that invades a critical area, for example) is obtained by the binocular system. © 2000 Elsevier Science B.V. All rights reserved.