首页 | 本学科首页   官方微博 | 高级检索  
     

图切割支持的融合颜色和梯度特征的实时背景减除方法
引用本文:邓宇,李振波,李华. 图切割支持的融合颜色和梯度特征的实时背景减除方法[J]. 计算机辅助设计与图形学学报, 2006, 18(11): 1741-1747
作者姓名:邓宇  李振波  李华
作者单位:中国科学院计算技术研究所智能信息处理重点实验室,北京,100080;国家智能计算机研究中心,北京,100080;中国科学院研究生院,北京,100049;中国科学院计算技术研究所智能信息处理重点实验室,北京,100080;国家智能计算机研究中心,北京,100080
基金项目:国家科技攻关项目;国家重点基础研究发展计划(973计划);国家自然科学基金
摘    要:通过融合图像的颜色和梯度特征,实现了一种实时背景减除方法.首先融合颜色和梯度特征建立新的能量函数;然后基于图切割算法最小化能量函数,并对前景/背景进行分割;最后使用光流验证前景区域的真实性,并更新背景模型.对不同场景的实验结果表明:该方法可以实时地检测出视频序列中的运动物体,结果准确、有效.

关 键 词:背景减除  颜色和梯度特征  能量函数  图切割  实时检测
收稿时间:2005-12-22
修稿时间:2006-03-01

A Fusing Color and Gradient Features Approach to Real-time Background Subtraction using Graph Cuts
Deng Yu,Li Zhenbo,Li Hua. A Fusing Color and Gradient Features Approach to Real-time Background Subtraction using Graph Cuts[J]. Journal of Computer-Aided Design & Computer Graphics, 2006, 18(11): 1741-1747
Authors:Deng Yu  Li Zhenbo  Li Hua
Affiliation:1.Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100080;2. National Research Center for Intelligent Computing Systems, Beijing 100080;3.Graduate University of Chinese Academy of Sciences, Beijing 100049
Abstract:Based on the fusion of color and gradient features, this paper implements a novel approach to real-time background subtraction. Firstly, an energy function is defined based on the fusion of color and gradient features. Secondly, the graph cuts based algorithm is employed to minimize energy function and segment the foreground. Finally, average optical flow is used to make inference about the validity of foreground regions, background models are then updated. The experimental results of different real scenes show that the proposed approach can produce real-time detection and promising results.
Keywords:background subtraction   color and gradient feature   energy function   graph cuts   real-time detection
本文献已被 CNKI 维普 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