首页 | 本学科首页   官方微博 | 高级检索  
     

视频监控系统中运动目标检测的阴影去除方法
引用本文:付萍,方帅,徐心和,薛定宇.视频监控系统中运动目标检测的阴影去除方法[J].计算机工程,2007,33(10):22-24.
作者姓名:付萍  方帅  徐心和  薛定宇
作者单位:1. 东北大学人工智能与机器人研究所,沈阳,110004
2. 合肥工业大学计算机与信息学院,合肥,230009
基金项目:国家高技术研究发展计划(863计划) , 国防科技预研项目
摘    要:在分析了阴影产生的原因及视觉特性的基础上,针对固定场景的运动目标检测问题,提出了一种具有实际应用价值的阴影检测与去除方法。该方法通过背景建模和背景差分方法分割出运动目标及其可能存在的阴影,采用光照评估方法判断阴影是否存在,进而运用多梯度分析和二值图像的快速聚类算法检测出阴影,去除阴影并分割运动目标。实验验证了该方法的有效性。

关 键 词:视频监控系统  阴影去除  运动目标检测  梯度分析
文章编号:1000-3428(2007)10-0022-03
修稿时间:2006-06-20

Approach for Shadow Removal of Moving Object Detection in Surveillance System
FU Ping,FANG Shuai,XU Xinhe,XUE Dingyu.Approach for Shadow Removal of Moving Object Detection in Surveillance System[J].Computer Engineering,2007,33(10):22-24.
Authors:FU Ping  FANG Shuai  XU Xinhe  XUE Dingyu
Affiliation:(1. Institute of Artificial Intelligence and Robotics, Northeastern University, Shenyang 110004; 2. School of Computer & Information, Hefei University of Technology, Hefei 230009)
Abstract:The method of the shadow detection and remove which has application value is proposed based on analyzing visual properties concerning shadows for visual surveillance purposes. The method proposed is essentially based on background modeling and background subtraction which aim to segment moving object and the corresponding shadow. It decides whether there are shadows in a given foreground figures. A method based on illumination assessment is developed for this purpose. Multi-gradient analysis and a fast clustering algorithm for thresholded image are employed to detect the shadow. Shadow is removed and the object is segmented. Experimental results are given to demonstrate the effectiveness and practicality of the method.
Keywords:Surveillance system  Shadow removal  Moving object detection  Gradient analysis
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程》浏览原始摘要信息
点击此处可从《计算机工程》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