Color Space Selection for Moving Shadow Elimination
Yong Shan, Fan Yang, Runsheng Wang · 2007
Moving shadow elimination is an important step in many applications of video. And pixels belonging shadow region are often misclassified as object during segmentation and tracking. There are many algorithms that deal with shadow in different color spaces in literatures. However, it is difficult to determine the optimal color space in which to remove shadow. In this paper, we study the features of moving object and shadow in different color spaces to solve the problem, and a moving object detecting model is given by using grey and gradient of shadow.