Proposition of Generic Validation Criteria using stereo-vision for On-Road Obstacle Detection

Abstract : Real-time obstacle detection is an essential function for the future of Advanced Driver 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. 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 confirms detections by locally using the stereoscopic data. We evaluated and validated our approach with an initial detection based on a vision system and a laser scanner. The evaluation dataset is real on-road data and contains more than 20000 images.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01072526
Contributor : Ifsttar Cadic <>
Submitted on : Wednesday, October 8, 2014 - 12:11:42 PM
Last modification on : Thursday, October 11, 2018 - 8:48:02 AM

Identifiers

Collections

Citation

Mathias Perrollaz, Raphaël Labayrade, Dominique Gruyer, Alain Lambert, Didier Aubert. Proposition of Generic Validation Criteria using stereo-vision for On-Road Obstacle Detection. International Journal of Robotics and Automation, ACTA Press, 2014, 29 (1), pp 65-87. ⟨10.2316/Journal.206.2014.1.206-3765⟩. ⟨hal-01072526⟩

Share

Metrics

Record views

532