Obstacle detection for start-inhibit and low speed driving

Abstract

The work described in this paper has been developed in the framework of the integrated project APALACI-PReVENT, a research activity funded by the European Commission to contribute to road safety by developing and demonstrating preventive safety technologies and applications. The goal of the system presented in this work is the development of a vision system for detecting potential obstacles in front of a slowly moving or still vehicle. When the vehicle is still, a background subtraction approach is used assuming that the background keeps stationary for a limited amount of time; thus, a reference background is computed and used to detect changes into the scene. A different approach is used when the vehicle is moving. The system, by means of inertial sensors, can detect ego-motion and correct background information accordingly. A temporal stereo match technique, able to detect obstacles in moving situations, completes the system. According to experimental results, the proposed algorithm can be useful in different automotive applications, requiring real-time segmentation without assumptions on background motion.