Vehicle detection with stationary cameras for automated traffic monitoring

Human errors are the main cause of road traffic accidents. In order to implement the vision of accident-free road traffic, automatic traffic monitoring offers an approach for assistance systems, which are independent of a protracted penetration of the vehicle fleet. For example, the Multi Functional Detection System is used to detect potential wrong-way drivers at motorway exits and rest areas when driving onto the wrong lane. Typically, stationary measuring platforms are used for this purpose, and camera sensors offer particularly favourable conditions. This contribution therefore considers vehicle detection in camera images for integration into a wrong-way driver warning system. For this application the realization of fast processing times is decisive. Conventional methods for the problem of camera-based object detection perform a complete scan of the recorded image for this purpose. Due to the fixed camera position and the known static traffic elements, however, it is possible to significantly limit this search-space. Therefore in the present work, a method is designed which can realize a reduced search strategy while retaining the advantageous properties of conventional methods for object detection.