Shadow detecting algorithms research for moving objects base on self-adaptive background

摘要

The main difficulties in intelligent video monitor is how to detect and eliminate the shadow in the scene. It uses an improved detecting algorithm which is based on self-adaptive background to detect the position and the shape of objects. Then according to the shadow's characters such as the color variation and the structure, two shadow detection algorithms which respectively based on the RGB color model and the HSV color model are introduced. In simulation experiment, the two shadow detection algorithms are analyzed on the shadow detection rate, the shadow discriminating rate, the complexity and the real-time capability, and made the comparison with them. The results of experiment show that the shadow detection algorithms are adaptive and favourable effect on detecting shadow, and can be applied on different fields according to their advantages and disadvantages.