Large Scale Traffic Scene Analysis with Multiple Camera Systems

Kurzfassung

The use of camera systems for traffic monitoring is obvious and already in use for about 20 years. However, most of the cameras are operated locally (similar to an induction loop). It has been shown that the two-dimensional areal data analysis offers new possibilities for the determination of traffic parameters. These presentations discuss a trajectory based recognition algorithm for atypical event detection in multi object traffic scenes and to obtain area based types of information (e.g. maps of speed patterns, trajectory curvatures or erratic movements). Different views of the same area by more than one camera are necessary, because of the typical limitations of single camera systems, resulting from occlusions by other cars, trees and traffic signs. Furthermore, distributed cooperative multi-camera system (MCS) enables a significant enlargement of the observation area. The fusion of object data from different cameras is done by a multi-target tracking approach. This approach opens up opportunities to identify and specify traffic objects, their location, speed and other characteristic object information. The use of wide baseline stereo methods can improve object detection and the tracking accuracy. An approach, which describes the interaction of traffic objects, will also be presented.