VISION-BASED SAFE BACKING-UP MANEUVERS WITH OBSTACLE-FREE SPACE DETECTION
Christophe Vestri, Sylvain Bougnoux · 2010
Every year, backing-up maneuvers are responsible for hundreds of accidents in the world. There is lots of R&D to find systems that can avoid these accidents. Vision-based obstacle sensors are promising systems because they have abi lity to understand the outdoor environment. But they have difficulties with lighti ng conditions such as strong shadows and highlights. This paper presents a real-time wide-an gle stereovision system that monitors a 6m area at the back of the vehicle in typical urban dr iving. Detection is achieved by extracting both obstacles and road surfaces. The main challeng e is to recover the complete road surface when stereo fails, mainly with difficult lighting c onditions: dynamic change of lighting conditions, shadows, highlights… Marking ground regions as unknown where 3D stereo information is missing will stop the road surface e xtraction and create false alarms. The contribution of this paper is an algorithm that rep airs missing information of the stereo disparity map to have dense information of the scen e. We show detection results under difficult lighting conditions. Road surface is corr ectly marked and obstacles are detected up to 6 meters. TECHNICAL PAPER BACKGROUND