Moving object detection and shadow removal in video surveillance
Tinggui Yan, Shaohua Hu, Xiaofeng Su, Xinhua He · 2016
The automatic analysis of digital video scenes often requires the segmentation of moving objects from a static background. The most popular approach involves subtracting the current frame from the background image. How to correctly and efficiently model and update the background model and how to deal with shadows are two of the most distinguishing and challenging aspects of such approach. In order to solve these problems, we presented an adaptive background subtract method based on improved mixture Gaussian and an effective shadow removal algorithm based on shadow attributes. Experimental results with lots of video data and comparative analysis with recent adaptive object detection techniques show the strength of the proposed technique in eliminating noise, shadow, and trailing effect while maintaining better stability across variable operating speeds.