This paper describes a stereo-vision-based candidate selection method for pedestrian detection from a moving vehicle. Non-dense 3D maps are computed by using epipolar geometry and a robust correlation process. Non-flat road assumption is used for correcting pitch angle variations. Thus, non obstacle points can be easily removed since they lay on the road. Generic obstacles are selected by using Subtractive Clustering algorithm in a 3D space with an adaptive radius. This clustering technique can be configurable for different types of obstacles. An optimal configuration for pedestrian detection is presented in this work.
3D Candidate Selection Method for Pedestrian Detection on Non-Planar Roads
2007 IEEE Intelligent Vehicles Symposium ; 1162-1167
2007-06-01
1099701 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
3D Candidate Selection Method for Pedestrian Detection on Non-Planar Roads
British Library Conference Proceedings | 2007
|Pedestrian risk on rural roads
British Library Conference Proceedings | 2000
|Pedestrian - Vehicle Interactions on Roads in France
British Library Conference Proceedings | 1996
|Signal controlled pedestrian crossings on high-speed roads
IET Digital Library Archive | 2004
|