Moving object detection using region tracking

Abstract

For many vision-based systems, it is important to detect moving object automatically. Region-based motion estimation method is one of the popular methods for automatic moving object detection. The region-based method has several advantages that it is robust to noise and variation of illumination. However, there is a critical problem that there exists an occlusion problem, which is caused by the movement of the object. The occlusion problem results in an incorrect motion estimation and faulty-detection of moving objects. That is, stationary background in the occluded region can be classified as moving object. In order to overcome this occlusion problem, a new occlusion detection algorithm is proposed. The proposed occlusion detection algorithm is motivated by the assumption that the distribution of the error histogram of the occlusion region is different from that the non-occlusion region. Proposed algorithm uses the mean and variance value to decide whether the occlusion is occurred in the region. Therefore, the proposed occlusion detection and motion estimation scheme detects the moving regions and estimates the new motion vector, while avoiding mis-detection caused by the occlusion problem. The experimental results for several video sequences demonstrate the robustness of the proposed approach to the occlusion problem.