Obstacle Detection in Road Scene Based on Road Detection and Motion Analysis

This paper deals with the problem of obstacle detection in traffic applications. The proposed device allows a diver to receive the current road and vehicle environment information. The environment perception is performed through a fast processing of image sequence acquired from a vision system embedded in a vehicle. The approach is based on frame motion analysis. Firstly, the road motion is computed through a fast and robust wavelets analysis. Then, we detect the areas which have a different motion thanks to a bayesian modelization. Results shown in the paper prove that the proposed method permits the detection of any obstacle on a road in various image conditions.