首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于边缘检测的时空视频对象分割算法
引用本文:王新卫,周利莉,陈 刚,郭 戈.一种基于边缘检测的时空视频对象分割算法[J].信息工程大学学报,2007,8(2):206-209.
作者姓名:王新卫  周利莉  陈 刚  郭 戈
作者单位:信息工程大学,信息工程学院,河南,郑州,450002
摘    要:提出了一种基于边缘检测的时空视频对象分割算法。首先提出一种基于高阶统计量的帧间差分图像处理方法,然后运用边缘检测得到空域分割结果和用累计差分与对称差分得到时域分割结果,综合时空域分割结果得到运动目标的边缘,最后对边缘图进行区域填充与数学形态学处理,得到运动目标掩模图像。实验结果表明本文算法能够得到较准确的分割结果。

关 键 词:高阶统计量  帧差图像  视频分割  边缘检测  空域分割  时域分割
文章编号:1671-0673(2007)02-0206-04
修稿时间:2006-09-062007-04-05

Spatial-Temporal Segmentation Algorithm Based on Edge Detection for Video Object Segmentation
WANG Xin-wei,ZHOU Li-li,CHEN Gang,GUO Ge.Spatial-Temporal Segmentation Algorithm Based on Edge Detection for Video Object Segmentation[J].Journal of Information Engineering University,2007,8(2):206-209.
Authors:WANG Xin-wei  ZHOU Li-li  CHEN Gang  GUO Ge
Affiliation:Institute of Information Engineering, Information Engineering University, Zhengzhou 450002, China
Abstract:A spatial-temporal segmentation algorithm based on edge detection for video object segmentation is proposed in this paper.At first,a method of processing difference frame image based on higher order statistic is proposed.Edge detection is used to obtain the spatial segmentation result.Symmetry differences and accumulative differences are used to obtain temporal segmentation result.The spatial-temporal result is used to get the moving edge map.The next step is filling the regions of the moving edge map,followed by applying morphological, and then the mask of video object is obtained.Experimental results show that this algorithm can give accurate object segmentation.
Keywords:higher order statistics  difference frame  video segmentation  edge detection  spatial segmentation  temporal segmentation
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《信息工程大学学报》浏览原始摘要信息
点击此处可从《信息工程大学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号