Study On Video Monitoring Of Moving Object Detection Algorithms

With the development of computer technology, moving target detection in artificial intelligence, image processing, pattern recognition and computer vision and other fields are more extensive. In the optical flow method, the frame difference method, and background subtraction, and many of the moving target detection algorithms, the background subtraction method of moving object detection in real time and the performance is better. Therefore, in this study, detect moving objects is investigated with the background subtraction method, and the corresponding analysis model and method are presented.Firstly, the Gaussian mixture background model and the concrete realization of this model code have been studied. However, Gaussian mixture background model using the obtained test results are not perfect for moving object outline information. Gradient information of pixels in the image, is just a reflection of the outline of objects and convenience, and relative to the color information that is concerned, and it is not sensitive to noise. In this paper, the background of the traditional Gaussian mixture model was proposed to improve the temporal and spatial information based on the gradient of the Gaussian mixture background model. When the shining light changes greatly, codebook background model is less effective for the strong scene of moving target detection. In this paper, the integration of gradient information is introduced to the traditional codebook background model to change the traditional range of brightness. And the traditional measure of the color word from columnar structure is also changed with the YUV color model to create a codebook background model, which reduces the sensitivity of frequent changes in light shining that holding in the traditional code of the background model. And through the application of a typical set of background video to the improved algorithms, the validation gives a proof of the improved algorithm which can indeed achieve better target detection results.