Sensor Data Fusion for Road Obstacle Detection: A Validation Framework
Résumé
Real-time obstacle detection is an essential function for the future of Advanced Driving Assistance Systems (ADAS), but its applications to the driving safety require a very high reliability: the detection rate must be high, while the false detection rate must remain extremely low. Such features seem antinomic for obstacle detection systems, especially when using a single sensor. Therefore, multi-sensor fusion is often considered as a mean to reduce this limitation. In this paper, we propose to use stereo-vision as a post-process to improve the reliability of any obstacle detection system, by reducing the number of false positives. Our algorithm, which is both generic and real-time con firms detections by locally using the stereoscopic data.
Fichier principal
InTech-Sensor_data_fusion_for_road_obstacle_detection.pdf (1017.56 Ko)
Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...