Moving target detection method with adjacent frame difference method and Gaussian mixture models combined

Abstract

The invention provides a moving target detection method with an adjacent frame difference method and Gaussian mixture models combined. The method includes the following steps that (1) an image sequence is obtained, wherein the image sequence comprises a current-frame image and a previous-frame image; (2) the current-frame image is divided into a temporary moving area and a temporary background area by the utilization of the improved adjacent frame difference method; (3) matching is performed on the two areas generated in the step (2) through the Gaussian mixture models, the two areas are divided into different areas according to matching results; (4) different updating is performed on the Gaussian mixture models in the different areas; (5) final moving target areas are determined according to the areas generated in the step (3). Gradient comparison and median filtering are added in the improved adjacent frame difference method, and the boundary and the anti-noise-interference capability of a moving target are highlighted. The adaptability to background and foreground conversion of the Gaussian mixture models is improved through changes of the updating rate of the Gaussian mixture models. The detection result of the method alleviates the problem of cavities generated through the adjacent frame difference method, and problem of the shadow generated by the fact that a background object is converted into a moving object suddenly is eliminated.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a video moving target detection method. Background technique [0002] Video surveillance is a very effective tool for personal and public safety. It processes the video data captured by the camera, enabling relevant personnel to monitor some important regional places in real time. Intelligent video surveillance generally includes moving target detection, target tracking, target classification and recognition, and behavior analysis. Therefore, moving object detection is the basis for realizing intelligent video surveillance, and the quality of moving object detection results will directly affect the subsequent processing and analysis. [0003] The general moving object detection technology is based on detecting changes in image pixels. Commonly used moving target detection methods include optical flow method, background subtraction method and adjacent frame difference meth...

AI Technical Summary

Problems solved by technology

The background difference method based on the mixed Gaussian model establishes multiple Gaussian models for each pixel, which can improve the adaptability to environmental changes, but the convergence speed is slow, and for objects that change suddenly, there will be "shadows" left by moving objects

Adjacent frame difference method uses the difference between adjacent frames for target detection. The algorithm is simple and has good real-time performance, but it will cause holes inside the object.

Images