首页 | 本学科首页   官方微博 | 高级检索  
     

基于光流场分割和Canny边缘提取 融合算法的运动目标检测
引用本文:张泽旭,李金宗,李宁宁.基于光流场分割和Canny边缘提取 融合算法的运动目标检测[J].电子学报,2003,31(9):1299-1302.
作者姓名:张泽旭  李金宗  李宁宁
作者单位:1. 哈尔滨工业大学电子与通信工程系,黑龙江哈尔滨 150001;2. 北京空间飞行器总体设计部,北京 100087
基金项目:航天创新基金资助项目 (No.2 0 0 1 )
摘    要:在摄像机运动的情况下,提出了一种基于光流场分割和Canny边缘算子融合技术的运动目标检测方法.这种方法可分为三步:第一步利用运动的内极线约束和C-均值聚类算法完成目标区域的分割,并获得分割图;第二步在分割图中利用Canny边缘算子获得细化的目标区域边缘图;第三步根据光流场中的流速值完成分割图和边缘图的融合,并检测出完整的运动目标.实验表明,这种方法可以有效地从复杂自然场景的图像序列中检测出完整的运动目标.

关 键 词:C-均值聚类  边缘融合  内极线约束  延伸焦点  光流  
文章编号:0372-2112(2003)09-1299-04
收稿时间:2002-05-18

Detection of Moving Object Using a Fusion Method Based on Segmentation of Optical Flow Field and Edge Extracted by Canny's Operator
ZHANG Ze xu ,LI Jin zong ,LI Ning ning.Detection of Moving Object Using a Fusion Method Based on Segmentation of Optical Flow Field and Edge Extracted by Canny''''s Operator[J].Acta Electronica Sinica,2003,31(9):1299-1302.
Authors:ZHANG Ze xu  LI Jin zong  LI Ning ning
Affiliation:1. Dept of Electronic & Communication Engineering,Harbin Institute of Technology,Harbin,Heilongjiang 150001,China;2. Beijing Spacecraft General Design Department,Beijing 100087,China
Abstract:We proposed a method on detection of moving object using a fusion algorithm based on segmentation of optical flow field and edge extracted by Canny's operator in the image sequence acquired by a moving camera.This method can be preformed with three steps.In the first step,the segmentation of object area was finished and segmentation map was obtained using motion epipolar constraint and C-Mean value cluster algorithm.In the second step,edge map of object area was established by Canny's edge operator.In the third step,a whole object was detected by a novel fusion method based on segmentation map and edge map.The experiments have shown encouraging results using two sequences of natural images with complex backgrounds.
Keywords:C  Mean cluster  edge fusion  epipolar constraint  focus of expansion  optical flow
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《电子学报》浏览原始摘要信息
点击此处可从《电子学报》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