Multiple Moving Objects Detection Based on Level Set and Shadow Information

In multiple moving object detection, the connection between objects and shadow always leads to the failure of object detection. To solve this problem, a new object extraction algorithm using level set is proposed and applied to detect moving vehicle in intelligent monitoring of motorway. Moving information is extracted via symmetrical difference and used in the velocity function of level set. After the first segmentation, information of object location is found. According to difference between object and shadow, velocity function is modified. After the second segmentation multiple objects and their shadow are separate. Experimental results show that the proposed algorithm is able to extract accurate contour of object effectively. Its processing speed is 24 fps and accuracy rate of shadow elimination reaches 98.6%.