中文摘要：

针对高速密集视频监控序列建立了一种新的简单的背景重构方法。该方法首先基于帧差序列的时空分布特性，利用高阶统计量理论，获取视频序列公共背景区域；然后根据同一背景帧差图像分布特性相似性，去除运动对于背景的干扰，形成路面背帚序列值，从而获得路面背景图像；最后利用计分牌监测的自适应背景更新方法进行背景更新。实验结果表明该方法效果理想，为高速路视频背景重建和运动目标检测提供了新的方法。

英文摘要：

A new and simple technique is proposed to reconstruct the background of high speed dense surveillance sequences. First, the public background of video sequences is extracted by using the space distribution property of a frame difference sequence and the high-order statistics theory. Then, a sequence of road background is formed by removing the background interference caused by motion according to the distribution similarity of a background frame difference image,thus getting a road background image. Finally, the background image is refreshed via an adaptive method of the scoreboard. Results demonstrate the apparent effectiveness of the scheme and it is a new method for reconstructing background and detecting motion target in high Key speed video.