DocumentCode :
2798088
Title :
4-D Tensor Voting motion segmentation for obstacle detection in autonomous guided vehicle
Author :
Dumortier, Yann ; Herlin, Isabelle ; Ducrot, André
Author_Institution :
IMARA project team, INRIA, Le Chesnay
fYear :
2008
fDate :
4-6 June 2008
Firstpage :
379
Lastpage :
384
Abstract :
Creating an obstacle detection system is an important challenge to improve safety for road vehicles. A way to meet the industrial cost requirements is to gather a monocular vision sensor. This paper tackles this problem and defines an highly parallelisable image motion segmentation method for taking into account the current evolution of multi processor computer technology. A complete and modular solution is proposed, based on the Tensor Voting framework extended to the 4D space (x, y, dx, dy), where surfaces describe homogeneous moving areas in the image plan.Watershed segmentation is applied on the result to obtain closed boundaries. Cells are then clustered and labeled with respect to planar parallax rigidity constraints. A visual odometry method, based on texture learning and tracking, is used to estimate residual parallax displacement.
Keywords :
collision avoidance; image motion analysis; image segmentation; road safety; road vehicles; traffic information systems; 4D tensor voting motion segmentation; autonomous guided vehicle; image motion segmentation method; monocular vision sensor; obstacle detection; obstacle detection system; planar parallax rigidity constraints; road vehicle safety; texture learning; visual odometry method; watershed segmentation; Computer vision; Mobile robots; Motion detection; Motion segmentation; Remotely operated vehicles; Road safety; Space technology; Tensile stress; Vehicle detection; Voting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Vehicles Symposium, 2008 IEEE
Conference_Location :
Eindhoven
ISSN :
1931-0587
Print_ISBN :
978-1-4244-2568-6
Electronic_ISBN :
1931-0587
Type :
conf
DOI :
10.1109/IVS.2008.4621203
Filename :
4621203
Link To Document :
بازگشت