基于帧间差分的自适应运动目标检测方法*

本文提出了一种基于帧间差分的自适应运动目标检测算法。算法利用直方图统计各像素点处最大概率灰度的方法提取出连续视频的背景图像；相邻帧利用帧差法得到运动区域图像；利用运动区域图像与背景图像差分的方法提取出运动目标。实验结果表明，该算法能在多个不确定性因素的序列视频中较好的提取背景图像，能及时响应实际场景变化，提高运动目标检测的质量。

Detection algorithm of adaptive moving objects based on frame difference method

A detection algorithm of adaptive moving objects based on frame defference method is proposed.The background image of continuous video frequency is reconstructed by calculating the maximun probability grayscale using grey histogram;Moving regions is gained by frame defference, Moving objects is taked out by subtracting moving regions and background image. Experimental results show that the algorithm can pick up preferably background image from the video sequence including many uncertainties factors, can response timely to the actual scene changes and improve the quality of moving objects detection.