Target recognition method based on image sequence multiple differences

The invention relates to a target recognition method based on image sequence multiple differences, and the method comprises the steps: removing a dynamic target in an image based on a sequence image multiple difference recognition algorithm, wherein the sequence image is a continuous three-frame image containing a target and a large number of fixed stars, and the dynamic target is a fixed star. Background noise, especially interference signals of fixed stars and the like, can be effectively eliminated, and the target recognition rate is greatly improved. 本发明涉及一种基于图像序列多重差分的目标识别方法，基于序列图像多重差分识别算法，去除图像中的动态目标；所述序列图像为包含有目标和大量恒星的连续三帧图像，所述动态目标为恒星。本发明能够有效剔除背景噪声，尤其是恒星等干扰信号，大大提高目标识别率。