30 October 2009 A target detection algorithm based on neighborhood structure measurement in video surveillance
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74954D (2009) https://doi.org/10.1117/12.833133
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
Video surveillance is to monitor the moving targets for detection, tracking and behavior analysis, but one of its problems is the accuracy of detection. In this paper, an effective algorithm for moving targets detection and background separation in video surveillance was proposed. We used the vector field based on neighborhood structure measurement to detect the moving target and eliminate the impact of moving target detection caused by shadow. Meanwhile we compared the traditional methods with our algorithm to illustrate the efficiency in detecting the whole moving targets in video.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tiancheng He, Tiancheng He, Jihong Pei, Jihong Pei, Qianzhen He, Qianzhen He, "A target detection algorithm based on neighborhood structure measurement in video surveillance", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74954D (30 October 2009); doi: 10.1117/12.833133; https://doi.org/10.1117/12.833133
PROCEEDINGS
8 PAGES


SHARE
Back to Top