TY - GEN
T1 - An adaptive object detection scope algorithm based on SIFT
AU - Lu, Yuanyuan
AU - Xu, Xiangyang
AU - Dai, Yaping
AU - Zheng, Bin
PY - 2012
Y1 - 2012
N2 - For camera movement causes moving objects detecting and tracking problems under complex background, we propose an adaptive object detection scope algorithm based on SIFT features. Firstly, let camera stationary and obtain three images to detect the moving object by using three-framedifference method, then extract the object SIFT features. Secondly, according to the location and displacement of the object in the dynamic background, we determine the detection scope which matches the object well and obtain the minimum rectangle which can surround the right matching points in the detection scope, and then update the object template. The algorithm avoids the analysis of the complex relative motion between the object and the background, and reduces mismatch points and the calculation amount. This algorithm can quickly and accurately track the object without occlusion, and performs robust in small occlusion case.
AB - For camera movement causes moving objects detecting and tracking problems under complex background, we propose an adaptive object detection scope algorithm based on SIFT features. Firstly, let camera stationary and obtain three images to detect the moving object by using three-framedifference method, then extract the object SIFT features. Secondly, according to the location and displacement of the object in the dynamic background, we determine the detection scope which matches the object well and obtain the minimum rectangle which can surround the right matching points in the detection scope, and then update the object template. The algorithm avoids the analysis of the complex relative motion between the object and the background, and reduces mismatch points and the calculation amount. This algorithm can quickly and accurately track the object without occlusion, and performs robust in small occlusion case.
KW - Dynamic background
KW - Object tracking
KW - SIFT
KW - Three-frame-difference method
UR - http://www.scopus.com/inward/record.url?scp=84868100665&partnerID=8YFLogxK
U2 - 10.1109/IHMSC.2012.120
DO - 10.1109/IHMSC.2012.120
M3 - Conference contribution
AN - SCOPUS:84868100665
SN - 9780769547213
T3 - Proceedings of the 2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2012
SP - 100
EP - 103
BT - Proceedings of the 2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2012
T2 - 2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2012
Y2 - 26 August 2012 through 27 August 2012
ER -