Temporal knowledge for cooperative distributed vision

The development of a distributed vision system (DVS) performing continuous surveillance is an interesting area of investigation. We are interested in the interpretation of wide areas, this constraint means that numerous sensors have to be distributed in space and have to cooperate in order to obtain a global interpretation. In the European community the SMART project, close to the video surveillance and monitoring (VSAM) field has been defined. The main area of research concerns: 2/3D object and event recognition, sensor fusion and active perception. The final objective of this work is the ability to track multiple objects in a wide outdoor area. Also in general, it is not possible to cover the whole of a scene, so the sensors are generally separated into blind zones, for which we do not have any observation. One of the principal difficulties is to ensure a robust recognition of the mobile objects perceived by the different sensors from different points of view at different moments. We decided to use fuzzy temporal curves of events (DOP: domain occurrence possibility) described by Dubois and Prade (1989) in order to predict object motion in blind zones.