Abstract: With the development of object-based video applications，the segmentation of video objects becomes one of the hotspots that people research.This paper presents a method for the fast segmentation of video objects based on the change detection.Firstly，the difference image is produced between two continuous frames，and then the moving area of the video object is obtained.The threshold is determined according to the median（MED） and absolute difference of medain（MAD） of the difference image and average of original image，and the noise is filtered.After the obtained result is processed with mathematical morphology，the video object can be extracted.Experimental results prove that this method can effectively segment the video object from the sequence with static background and the proposed method is simple，fast and accurate.

Key words: video segmentation, change detection, difference image, mathematical morphology

摘要： 随着基于对象视频应用的发展，视频对象的分割成为人们研究的热点。提出了一种基于变化检测的视频对象分割算法。该算法首先求出连续两帧图像之间的差分，利用帧间变化信息可以得到视频对象的运动区域，根据差分图像的中值（MED）和中值绝对差（MAD）及原始图像均值确定阈值并滤除噪声，用数学形态学方法进行后处理，最终得到精确的视频运动对象。实验结果表明，该方法能够从背景不变的视频序列中较好地提取出视频运动对象，而且算法简单、高效、准确。

关键词: 视频分割, 变化检测, 差分图像, 数学形态学