Real-Time Detection and Tracking of Moving Object
Jianguo Tao, Changhong Yu · 2008
This paper presents a novel an adaptive background subtraction method to segment the moving regions and locate the positions of human bodies. Most methods proposed so far adjust the permissible range of the background image variations according to the training samples of background images. Thus, the detection sensitivity decreases at those pixels having wide permissible ranges. If we can narrow the ranges by analyzing input images, the detection sensitivity can be improved. For this narrowing, we employ the property that image variations at neighboring image blocks have strong correlation, also known as Correlation Based Block Matching Method. This approach is essentially different from chronological background image updating or morphological postprocessing. In this system, we combine the TI TMS320DM642 EVM with CCS software system to be the research developing platform. Experimental results show that the proposed system performs well in indoor, complex environments.