Moving Object Detection and Shadow Elimination Based on Video Image
Xiuhong Chen · Microcomputer Information · 2009
Moving object detection is the important technology of scene monitoring. The shape of the object is affected mostly by its shadow,which the true object detection is interfered. In this paper,we proposed a method based on hybrid Gaussian model. We use background subtraction to obtain object image. In order to eliminate shadow,we use lightness,chromaticity and normalized cross correlation. At last,mathematical morphology is used to repair the image. Experiment indicates that the method is feasible and effective.