DocumentCode :
3283247
Title :
Stereo based region of interest generation for pedestrian detection in driver assistance systems
Author :
Mesmakhosroshahi, Maral ; Joohee Kim ; Yunsik Lee ; Jong-bok Kim
Author_Institution :
Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA
fYear :
2013
fDate :
15-18 Sept. 2013
Firstpage :
3386
Lastpage :
3389
Abstract :
Pedestrian detection is one of the major goals in advanced driver assistance systems (ADAS) which has become an active research area in recent years. In this paper, we present a stereo based pedestrian detection system by fusing the depth and color data provided by a stereo vision camera on a moving platform. The proposed method uses an adaptive window for region of interest (ROI) generation using dense depth map. The extracted candidates are then applied to a Histogram of Oriented Gradients (HOG) feature descriptor to refine ROIs and Support Vector Machine (SVM) is used to classify them into pedestrian and non-pedestrian classes. The system is tested on a stereo based DAS dataset and results show that our system is able to detect pedestrians with different scales and illumination conditions and in presence of partial occlusion.
Keywords :
cameras; computer vision; driver information systems; feature extraction; image colour analysis; image fusion; object detection; pedestrians; stereo image processing; support vector machines; ADAS; HOG feature descriptor; ROI generation; SVM; adaptive window; advanced driver assistance systems; dense depth map; depth-color data fusion; histogram of oriented gradients feature descriptor; illumination conditions; partial occlusion; scales condition; stereo based DAS dataset; stereo based pedestrian detection system; stereo based region of interest generation; stereo vision camera; support vector machine; Advanced driver assistance system; ROI generation; depth map; pedestrian detection; stereo vision;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2013 20th IEEE International Conference on
Conference_Location :
Melbourne, VIC
Type :
conf
DOI :
10.1109/ICIP.2013.6738698
Filename :
6738698
Link To Document :
بازگشت