Traffic surveillance using video image detection systems

Sie sind hier: Homepage > Suche

Traffic surveillance using video image detection systems

Bauer, S. / Döring, T. / Meysel, F. / Reulke, R.

To expand the common approach for new types of information (queue length or erratic movements), the authors use a trajectory based recognition algorithm, which is related to the detection and tracking of individual vehicles in an image sequence. As an essential application for this algorithm it will be demonstrated how the usual characteristic traffic parameters can be derived from the measured trajectories. This facilitates a direct comparison between the video based and the classic inductive loop measurement of the traffic parameters. The presented approach for a traffic surveillance system has been implemented and tested. Thus, it could be shown that standard traffic parameters can be derived based on video detection, tracking and trajectory analysis. This step is essential on the way to future traffic surveillance systems. Still, the robustness of the processing chain needs to be improved. Accumulated data is not very much affected by small errors. However, detection errors and tracking problems can deteriorate the trajectory data and lead to less usable trajectories for analysis or less reliable traffic parameters.