Moving object detection based on T-test combined with kirsch operator

Moving object detection is a hot topic in computer vision. It is widely used in many areas, such as video monitoring, and intelligent traffic. This paper proposes a new method, which combines the T-test with the kirsch operator. First, the T-test method can detect the moving area between two frames of the video sequences while the kirsch operator can detect the contour of the objects. Second, the moving information fuses the contour information, so the experimental results can obtain both the moving information and the contour information. The morphologic operation is used to get the accurate information of the moving object. Finally, the moving objects are labeled in the video sequences. Experimental results prove that the proposed method is effective and robust.