Vehicles Detection in Stereo Vision Based on Disparity Map Segmentation and Objects Classification - Archive ouverte HAL Access content directly
Conference Papers Year :

Vehicles Detection in Stereo Vision Based on Disparity Map Segmentation and Objects Classification

Abstract

This paper presents a coarse to fine approach of on-road vehicles detection and distance estimation based on the disparity map segmentation supervised by stereo vision. Scene segmentation is first performed relying on the robustness of the UV-disparity maps to generate free space and obstacles space. This last is investigated for on-road vehicles detection. The detection process starts with off-road objects sub-straction based on the connected component labeling algorithm which is also used for on-road segments extraction instead of the traditional hough transform for more robust, precise and fast detection. Objects classification is then applied to the on-road segments by using some cues describing the geometry of vehicles like width, height. However, these latter have been measured not in meter but rather in pixels in function of the disparity. The whole approach is presented and the experimental results of evaluation are shown.
Fichier principal
Vignette du fichier
DjamilaDekkiche (3).pdf (2.15 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01697760 , version 1 (31-01-2018)

Identifiers

  • HAL Id : hal-01697760 , version 1

Cite

Djamila Dekkiche, Bastien Vincke, Alain Mérigot. Vehicles Detection in Stereo Vision Based on Disparity Map Segmentation and Objects Classification. Symposium on Visual Computing, Jan 2016, Las vegas, United States. ⟨hal-01697760⟩
116 View
996 Download

Share

Gmail Facebook Twitter LinkedIn More