IMRA has been working on a static obstacles detection system for a few years now. We propose to complement this with a real-time moving obstacles detection and localization system. This system is based on camera movement compensation using IPM (Inverse Perspective Mapping) and probabilistic reasoning for movement detection. Using shape filtering our approach can even detect only specific types of moving objects (pedestrians, cars…). In this paper we present the algorithms developed, the evaluation protocol used, show some results of the system and conclude on which future developments will bring performance improvements.
展开▼
