Proposition of Generic Validation Criteria using stereo-vision for On-Road Obstacle Detection
| Autor: | Alain Lambert, Mathias Perrollaz, Dominique Gruyer, Raphaël Labayrade, Didier Aubert |
|---|---|
| Přispěvatelé: | Geometry and Probability for Motion and Action (E-MOTION), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Informatique de Grenoble (LIG), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS), École Nationale des Travaux Publics de l'État (ENTPE), École Nationale des Travaux Publics de l'État (ENTPE)-Ministère de l'Ecologie, du Développement Durable, des Transports et du Logement, Laboratoire sur les Interactions Véhicules-Infrastructure-Conducteurs (IFSTTAR/COSYS/LIVIC), Institut Français des Sciences et Technologies des Transports, de l'Aménagement et des Réseaux (IFSTTAR), Laboratoire Exploitation, Perception, Simulateurs et Simulations (IFSTTAR/COSYS/LEPSIS), Institut Français des Sciences et Technologies des Transports, de l'Aménagement et des Réseaux (IFSTTAR)-Communauté Université Paris-Est, Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF) |
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Engineering
business.industry Machine vision Poison control [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Advanced driver assistance systems Stereoscopy AIDE ELECTRONIQUE A LA CONDUITE law.invention DETECTION OBSTACLE Stereopsis law Obstacle False positive paradox Computer vision Artificial intelligence CAPTEUR [PHYS.PHYS.PHYS-INS-DET]Physics [physics]/Physics [physics]/Instrumentation and Detectors [physics.ins-det] AIDE A LA CONDUITE business Simulation Reliability (statistics) STEREOVISION |
| Zdroj: | International Journal of Robotics and Automation International Journal of Robotics and Automation, 2014, 29 (1), pp 65-87. ⟨10.2316/Journal.206.2014.1.206-3765⟩ International Journal of Robotics and Automation, ACTA Press, 2014, 29 (1), pp 65-87. ⟨10.2316/Journal.206.2014.1.206-3765⟩ |
| ISSN: | 0826-8185 1925-7090 |
| DOI: | 10.2316/Journal.206.2014.1.206-3765⟩ |
| Popis: | International audience; 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|