首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于帧差法和边缘检测法的视频分割算法
引用本文:陈春雨,姚秋香,乔玉龙.基于帧差法和边缘检测法的视频分割算法[J].济南大学学报(自然科学版),2012,26(1):31-36.
作者姓名:陈春雨  姚秋香  乔玉龙
作者单位:哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨,150001
摘    要:针对目前常用的视频分割方法易受到噪声、亮度突变的影响,很难提取出完整的运动目标这一问题,提出一种基于帧差法和边缘检测法相结合的视频分割算法.该算法首先对连续三帧图像进行差分得到运动区域,然后对当前帧进行Kirsch边缘检测得到边缘图像,综合二者的检测结果得到更为精准的运动对象边缘.采用边缘连接算法完成对断裂边缘的连接,最后通过区域填充得到运动目标掩模图像,从而分割出完整的运动目标.实验表明,该算法可以实时有效地将运动物体从视频序列中自动地分割出来.

关 键 词:信息处理技术  视频分割  帧差法  Kirsch边缘检测  运动目标检测

Video Segmentation Algorithm Based on Frame Difference and Edge Detection
CHEN Chun-yu,YAO Qiu-xiang,QIAO Yu-long.Video Segmentation Algorithm Based on Frame Difference and Edge Detection[J].Journal of Jinan University(Science & Technology),2012,26(1):31-36.
Authors:CHEN Chun-yu  YAO Qiu-xiang  QIAO Yu-long
Institution:(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China)
Abstract:As the commonly-used methods of video segmentation are easily affected by noise and light,it is difficult to extract a complete moving target,so a new video object segmentation algorithm combining edge detection and inter-frame difference is proposed.Firstly,the difference of three consecutive frames is used to obtain motion regions,and then the boundary of current frame is defined by using Kirsch edge detection.The two test results are synthesized to get the more accurate edge of moving objects.Edge linking algorithm is used to connect the breaking edge.Finally,the template of moving object is formed through area filling,and thus a complete moving object is obtained.Experimental results show that this algorithm can effectively segment accurate moving objects in real time.
Keywords:information processing technology  video segmentation  frame difference  Kirsch edge detection  moving target detection
本文献已被 CNKI 万方数据 等数据库收录!
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