DocumentCode :
154783
Title :
Stereo based ROIs generation for detecting pedestrians in close proximity
Author :
Meiqing Wu ; Siew-Kei Lam ; Srikanthan, Thambipillai
Author_Institution :
Centre for High Performance Embedded Syst., Nanyang Technol. Univ., Singapore, Singapore
fYear :
2014
fDate :
8-11 Oct. 2014
Firstpage :
1929
Lastpage :
1934
Abstract :
Region of Interests (ROIs) generation plays a critical role in pedestrian detection systems. The challenge lies in generating as few ROIs as possible at low computational complexity, while ensuring none of the pedestrians in the scene are omitted. However, existing ROIs generation methods either result in a large number of irrelevant ROIs or are compute-intensive. In addition, distinguishing pedestrians who are in close proximity is still a big challenge. In this paper, we propose an efficient stereo based ROIs generation method that is based on a two-level incremental segmentation strategy. An adaptive strategy is first employed to identify a minimal set of clusters from the u-disparity image. The initial clusters are then further refined to distinguish pedestrians in close proximity. Experimental results based on a challenging benchmark show that the proposed algorithm outperforms two state-of-art baseline algorithms by being able to distinguish pedestrians in close proximity with a small number of ROIs.
Keywords :
computational complexity; image segmentation; pedestrians; stereo image processing; traffic engineering computing; adaptive strategy; close proximity; computational complexity; pedestrian detection; region of interests generation; stereo based ROIs generation; two-level incremental segmentation strategy; u-disparity image; Clustering algorithms; Image segmentation; Intelligent vehicles; Labeling; Roads; Stereo vision; Vehicles;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on
Conference_Location :
Qingdao
Type :
conf
DOI :
10.1109/ITSC.2014.6957988
Filename :
6957988
Link To Document :
بازگشت