A practical updating background method in moving target detection
Junfang Song, Cao Huang, Ru Xue · 2012
Background subtraction is a powerful mechanism typically for segmenting moving regions in image sequences taken from a data acquisition system. It compares each new image to a model of the scene background image. In this paper, we present a novel method for the reconstruction of background image in background subtraction. This method firstly calculates the difference of two neighboring images, then deals with this result to determine whether the background image needs to be updated and finally reconstructs the background image by a simple weight formula. The experiment result shows that the proposed method could update background image quickly and timely in the scene of traffic flow monitoring. Using this method we can get a more accurate background, which is conducive to the segmentation of the target.