Title :
Pedestrian detection using stereo-vision and graph kernels
Author :
Suard, E. ; Guigue, V. ; Rakotomamonjy, A. ; Benshrair, A.
Author_Institution :
Inst. Nat. des Sci. Appliquees, Rouen, France
Abstract :
This paper presents a method for pedestrian detection with stereovision and graph comparison. Images are segmented thanks to the NCut method applied on a single image, and the disparity is computed from a pair of images. This segmentation enables us to keep only shapes of potential obstacles, by eliminating the background. The comparison between two graphs is accomplished with an inner product for graph, and then the recognition stage is performed learning is done among several pedestrian and non-pedestrian graphs with SVM method. The results that are depicted are preliminary results but they show that this approach is very promising since it clearly demonstrates that our graph representation is able to deal with the variability of pedestrian pose.
Keywords :
collision avoidance; computer vision; graph theory; image segmentation; learning (artificial intelligence); object detection; road traffic; support vector machines; NCut method; SVM method; graph kernels; graph representation; images segmentation; nonpedestrian graph learning; pedestrian detection; pedestrian pose; stereo-vision; Algorithm design and analysis; Artificial neural networks; Image segmentation; Kernel; Machine learning; Machine learning algorithms; Shape; Skeleton; Support vector machines; Testing;
Conference_Titel :
Intelligent Vehicles Symposium, 2005. Proceedings. IEEE
Print_ISBN :
0-7803-8961-1
DOI :
10.1109/IVS.2005.1505113
