Title :
Pedestrian detection using stereo night vision
Author :
Liu, Xia ; Fujimu, Kikuo
Author_Institution :
Ohio State Univ., Columbus, OH, USA
Abstract :
This paper presents a method for pedestrian detection using a stereo night vision system installed on the vehicle. Motion information extracted from an image sequence is used to locate possible pedestrians, as moving people have motions that are not consistent with the movement of the background. Experimental results are shown to validate our approach and comparisons have been carried out between our approach and frame-by-frame based pattern recognition approaches.
Keywords :
image sequences; motion estimation; night vision; object detection; road vehicles; stereo image processing; frame by frame based pattern recognition; image sequence; motion information; pedestrian detection; pedestrians location; stereo night vision system; vehicle; Cameras; Data mining; Humans; Infrared heating; Layout; Night vision; Object detection; Roads; Stereo vision; Vehicle detection;
Conference_Titel :
Intelligent Transportation Systems, 2003. Proceedings. 2003 IEEE
Print_ISBN :
0-7803-8125-4
DOI :
10.1109/ITSC.2003.1251973
