Improving backing-up manoeuvre safety with vision-based movement detection

Every year, backing-up crashes are responsible for hundreds of casualties in the world. In order to reduce this number, many automotive suppliers now provide ways for drivers to monitor the rear of their vehicle using sonar - or radar-based systems or wide angle cameras. Yet these systems still do not offer the performance required to consequently reduce the number of fatalities. To overcome the limitations of these systems, we have developed a real-time static obstacle detection system using a wide angle camera. We now propose to add moving obstacle detection and localisation to our camera-based system. Such system is the perfect candidate for next generation of automatic anti-collision systems. Our approach is based on camera movement compensation using inverse perspective mapping and probabilistic reasoning for movement detection. Using shape filtering, our approach can even limit detection to specific types of moving objects (pedestrians, cars etc.). We present the algorithms developed and the evaluation protocol used. We also show results of the system in typical urban situations, some in hard conditions (worst cases), and conclude on which future developments will bring performance improvements