Moving Object Detection Based On Kirsch Operator Combined With Optical Flow

Moving object detection is a very popular subject in the area of image processing, computer vision, pattern recognition; it is widely used in the areas such as video surveillance, intelligent traffic, so it has important theoretical significance and application value. Although there are some methods for the moving object detection, it is still a challenging area. This paper did some researches on moving object detection and made some improvement, lots of experiments were done to demonstrate the validity. The main work of the paper is as follows:First, this paper discussed the three classical methods:the frame difference, background subtraction method and the optical flow method. The paper analyzed the advantages and disadvantages of the three classical methods. Frame difference method has less computational complexity, and it is easy to implement, but generally does a poor job of extracting the complete shapes of certain types of moving objects; Optical flow method can detect the moving object even when the camera moves, but it needs more time for its computational complexity, and it is very sensitive to the noise;In order to increase the recognition rate, this paper proposed the new method which combined the edge detection operator with the optical flow. The paper uses lots of the edge detection operators for experiment, the Kirsch operator is used to compute the contour of the objects in the video. At the same time, the Optical Flow method is adopted to establish the motion vector field. Otsu method is implemented after the Optical Flow method in order to distinguish the moving object and the background clearly. Then the contour information fuses the information of motion vector field, finally, the morphologic operators are used to process the results, the moving objects are obtained.The experiment results prove that the proposed method not only can overcome the disadvantages that the frame difference can not detect the exact boundary of the moving objects,but also can overcome the disadvantages that the optical flow is sensitive to the noise. It can detect the moving objects precisely. Contrast with the three traditional moving object detection methods, the propose method has the higher recognition rate. This paper also constructs a video monitoring system which based on the Arm nine chip. It is important for further application of the algorithm.