[1]周建强,刘怀,张海龙,等.一种改进的背景提取与更新方法[J].南京师范大学学报(工程技术版),2012,12(04):067-72.
 Zhou Jianqiang,Liu Huai,Zhang Hailong,et al.An Improved Method on Background Extraction and Update[J].Journal of Nanjing Normal University(Engineering and Technology),2012,12(04):067-72.
点击复制

一种改进的背景提取与更新方法
分享到:

南京师范大学学报(工程技术版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
12卷
期数:
2012年04期
页码:
067-72
栏目:
出版日期:
2012-12-20

文章信息/Info

Title:
An Improved Method on Background Extraction and Update
作者:
周建强刘怀张海龙李振
南京师范大学电气与自动化工程学院,江苏南京210042
Author(s):
Zhou JianqiangLiu HuaiZhang HailongLi Zhen
School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210042,China
关键词:
背景提取概率分布统计直方图递归算法
Keywords:
background extractionprobability distribution statistics histogram recursive algorithm
分类号:
TP391.41
摘要:
在分析背景提取的特点、均值算法准确度低和高斯混合模型法实时性差等不足的基础上,提出了一种改进的背景提取和更新的算法.该算法通过结合概率分布和统计直方图来得到初始背景,以降低环境变化的影响;利用高斯分布和递归算法来提高区域背景更新的实时性和准确度.结果表明,与均值算法和混合高斯模型法相比,该算法实现简单,具有很好的准确性,并且抑制了目标运动过慢造成的干扰,提高了背景更新的实时性.
Abstract:
The paper introduces an improved method on background extraction and update based on the features of background extraction and the disadvantages of the low accurancy of mean algorithm and the bad real-time of mixture Gaussian model. The method obtains the initial background with probability distribution and statistics of histogram to reduce the impact of environmental changes. Then to increase the real-time and accurancy, it combines the Gaussian distribution with recursive algorithm to update the background. Compared with means algorithm and mixture Gaussian model,it is easier to be operated,has better real-time and accurancy,and can effectively inhibit the noise caused by the slow targets.

参考文献/References:

[1] 钟珞,刘剑. 基于混合高斯和均值滤波法的运动检测方法[J]. 武汉理工大学学报: 信息与管理工程版, 2010, 32( 5) : 691-693. Zhong Luo,Liu Jian. Moving object detection based on mixture Gaussian and mean filter method[J]. Journal of WUT: Information and Management Engineering Edition, 2010, 32( 5) : 691-693. ( in Chinese)
[2] 李晓飞,梅中辉. 一种基于直方图统计与多帧平均混合的背景提取算法[J]. 南京邮电大学学报: 自然科学版, 2008, 28( 6) : 74-77. Li Xiaofei,Mei Zhonghui. An algorithm of background extraction based on statistics of histogram combining with multi-frame average[J]. Journal of Nanjing University of Posts and Telecommunications: Natural Science Edition,2008,28 ( 6) : 74-77. ( in Chinese)
[3] 娄路. 基于概率算法自适应更新背景的运动车辆检测[J]. 计算机工程与应用, 2012, 48( 25) : 243-248. Lou Lu. Adaptive real-time cehicle detection based on Bayesian rule background model[J]. Computer Engineering and Application, 2012, 48( 25) : 243-248. ( in Chinese)
[4] 刘怀,黄建新. 彩色图像的矢量阈值自适应分割算法[J]. 南京师范大学学报: 工程技术版, 2006,6 ( 2) : 18-22. Liu Huai,Huang Jianxin. Adaptive vector threshold segmentation algorithm for color image[J]. Journal of Nanjing Normal University: Engineering and Technology Edition, 2006,6 ( 2) : 18-22. ( in Chinese)
[5] 魏晓慧,李良福,钱钧. 基于混合高斯模型的运动目标检测方法研究[J]. 应用光学, 2010, 31( 4) : 574-578. Wei Xiaohui,Li Liangfu,Qian Jun. Moving object detection based on mixture Gaussian model[J]. Journal of Applied Optics, 2010, 31( 4) : 574-578. ( in Chinese)
[6] Wren C,Azarba Y,Darrel T, et al. Pfinder: real-time tracking of the human body[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19( 7) : 780-785.
[7] 严勇,黄席樾,刘爱君. Kalman 滤波在运动图像背景提取及更新中的应用[J]. 自动化与仪器仪表, 2006( 2) : 28-30. Yan Yong,Huang Xiyue,Liu Aijun. Application of Kalman filter in update of moving background images[J]. Automation and Instrumentation, 2006( 2) : 28-30. ( in Chinese)

相似文献/References:

[1]王 丹,刘 怀.基于改进混合高斯模型的背景提取与更新[J].南京师范大学学报(工程技术版),2015,15(02):060.
 Wang Dan,Liu Huai.Background Extraction and Updating Based on Improved Gaussion Mixture Model[J].Journal of Nanjing Normal University(Engineering and Technology),2015,15(04):060.

备注/Memo

备注/Memo:
基金项目:国家自然科学基金( 51075215) .
通讯联系人:刘怀,副教授. 研究方向: 网络控制与图像处理. E-mail: liuhuai@ njnu. edu. Cn
更新日期/Last Update: 2013-03-21