一种累积帧差视频对象分割算法  

A video segmentation algorithm based on accumulated frame differences

作　　者：许悦雷[1] 左继章[1] 张雄[1] 毕笃彦[1] 

机构地区：[1]空军工程大学工程学院航空电子工程系,陕西西安710038

出　　处：《光电工程》2004年第7期69-72,共4页Opto-Electronic Engineering

摘　　要：经过对视频序列的多帧累积,利用帧间变化信息可求得帧差之和,并用数学形态学方法处理之后,即可提取出对象边界。由此,提出了一种累积帧差的视频对象分割算法。实验结果表明,该算法能对低比特率视频序列中运动较为缓慢、背景相对简单的对象进行有效的分割,而且所用时间较短,算法简单、高效。Through multi-frame accumulation for video sequence, the sum of frame differences can be obtained with interframe variation information. After the obtained results being processed with mathematical morphology, the object boundary can be extracted. A video segmentation algorithm based on accumulated frame differences is proposed from this point. The experimental results show that the object with slower motion velocity and relative simple background in a low bit rate video sequence can be effectively segmented by this algorithm.

关 键 词：图像分割 帧差图像 数学形态学 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TN941[自动化与计算机技术—计算机科学与技术]