Video background removing method

The invention discloses a video background removing method which relates to the technical field of video analysis, and in particular relates to a background removing method based on an image block, a Gaussian mixture model and a stochastic process. The method comprises the steps that the block concept is defined, and a foreground and a background are determined by comparing differences between blocks; the Gaussian mixture model is used to automatically adjust a threshold, and at the same time the idea of the stochastic process is used to update the background; and finally, an experiment is carried out on a BMC data set. According to the invention, the method is beyond most of advanced algorithms in the prior art, has the advantages of high accuracy and wide applicability, can be applied to monitor the background reduction of a video, and has a very important application in the field of video analysis. 本发明公布了种视频的背景去除方法，涉及视频分析技术领域，尤其涉及种基于图像块、高斯混合模型、随机过程的背景去除方法；首先定义了块的概念，通过比较块之间的不同来确定前景与背景；使用高斯混合模型来自动的调整阈值，同时采用随