Abstract: To extract good background image from complex scenes，this paper proposes an algorithm of background extraction based on both frame-difference and background subtraction，and using multi-level adaptive background update strategy，it can avoid the effect of new objects to the background and eliminate the ghosts caused by the move-away of background objects.Experiment shows it is a practical method that is robust under lighting variations，fast in speed，satisfactory in updating performance.

Key words: background extraction, background updating, frame-difference, background subtraction

摘要： 为了从复杂环境中获取高质量背景图像，提出一种基于帧间差分和背景减除法相结合的背景提取算法，采用多层次自适应背景更新的策略，能够克服新增物体对背景的影响，并能及时消除由于背景物体移出而造成的鬼影。实验证明该算法对光线变化鲁棒性高、速度快、更新效果好。

关键词: 背景提取, 背景更新, 帧间差分, 背景差分