Fast algorithm for moving target detection
Jian Chen, Feng Mei, Weijing Ye, Hongkai Wang, Xiaojun Shen, Yiyang Yao · 2017
In this paper, a moving target detection algorithm which combines background estimation and BING (Binarized Normed Gradients) Objectness is proposed in video surveillance. A simple background estimation method is used to detect a set of rough moving foreground in image, objectness detection within the foreground set will estimate another set of candidate object windows, and the target (pedestrians/vehicles) region by the intersection of areas derives from the former two steps. Besides, time cost is reduced by the decrease of estimation regions. Experiments on the outdoor datasets show that the combined method can not only achieve a high detection ratio (DR) but also decrease false alarm ratio (FAR), as well as time cost.