期刊文献+

改进的基于高斯混合模型的运动目标检测算法 预览 被引量:28

Improved moving objects detection algorithm based on Gaussian mixture model
在线阅读 下载PDF
收藏 分享 导出
摘要 针对固定场景视频监控中,由于运动物体在运动目标检测算法初始化时的存在而导致传统的基于高斯混合模型的运动目标检测算法收敛速度慢的问题,提出了改进算法。该改进算法通过采用在线K-均值聚类方法对混合高斯模型进行初始化,提高了算法的收敛速度。同时在模型更新时,通过对匹配准则和新高斯分布生成准则的改进,节约了存储空间。实验结果表明,与传统算法相比,改进算法能够快速、有效地检测运动目标,具有更好的鲁棒性。 In a video surveillance system with static cameras,the moving objects’presence during the initialization to the traditional moving objects detection algorithm based on Gaussian mixture model often results in the low convergence speed.To increase the model convergence speed,an improved detection algorithm is presented.The improved method uses on-line K-means clustering algorithm to initialize the model.It also saves the memory space with the improvement to the matching rule and new Gaussian distribution generation rule during the model update.The experimental results demonstrate the improved algorithm can fast and efficiently detect moving objects,and has better robustness than the traditional algorithm.
作者 李明 赵勋杰 LI Ming,ZHAO Xunjie(Department of Physical Science and Technology,Suzhou University,Suzhou,Jiangsu 215006,China)
出处 《计算机工程与应用》 CSCD 北大核心 2011年第8期 204-206,共3页 Computer Engineering and Applications
基金 国家自然科学基金(the National Natural Science Foundation of China under Grant No.60678051)
关键词 混合高斯模型 运动目标检测 在线K-均值聚类 Gaussian mixture model moving object detection on-line K-means clustering
  • 相关文献

参考文献7

  • 1Stauffer C, Grmson W E L.Adaptive background mixture mod- els for real-time tracking[C]//Proceeding of IEEE International Conference on Computer Vision and Pattern Recognition,Fort Co- lins, Colorado,USA.[S.l.] : IEEE Computer Society, 1999,2: 246-252,. 被引量:1
  • 2王勇,谭毅华,田金文.基于阴影消除和混合高斯模型的视频分割算法[J].光电工程,2008,35(3):21-25. 被引量:14
  • 3彭可,陈燕红,唐宜清.一种室内环境的运动目标检测混合算法[J].计算机工程与应用,2008,44(5):239-241. 被引量:10
  • 4Pavlidis I, Morellas V, Tsiamyrtzis P, et al.Urban surveillance system: From the laboratory to the commercial world[J].Pro- ceedmgs of the IEEE,2001,89(10) : 1478-1497. 被引量:1
  • 5Power P W, Schoonees J A.Understanding background mixture models for foregrounds segmentation[C]//Proceedings of lmage and Vision Computing, New Zealand, Auckland, 2002: 267-271. 被引量:1
  • 6Zhang Yunchu, Liang Zize, Hou Zengguang, et aLAn adaptive mixture gaussian background model with online background re- construction and adjustable foreground .mergence time for mo- tion segmentation[C]//IEEE International Conference on Industri- al Technology,ICIT 2005,14-17 Dec 2005:23-27. 被引量:1
  • 7Duda R O,Hart P E,Stork D G.Pattcm classification[M].2nd cd. New York:John Wiley & Sons,lnc,2001:521-528. 被引量:1

二级参考文献15

  • 1Barron J,Fleet D,Beauchemin S.Performance of optical flow techniques[J].lntemational Journal of Computer Vision, 1994, 12 ( 1 ) : 42-77. 被引量:1
  • 2Anderson C,Burt P,van der Waals G.Change detection and tracking using pyramid transformation techniques[C]//Proc of SPIE-intelligent Robots and CompUter Vision,1985,579:72-78. 被引量:1
  • 3Mittal A,Paragios N.Motion based background subtraction using adaptive kernel density estimation[C]//CVPR,2004-04: 302-309. 被引量:1
  • 4Haritaoglu I,Harwood D,Davis L S.W4:real-time surveillance of people and their activities[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8 ) : 809-830. 被引量:1
  • 5Stauffer C,Grimson W.Adaptive background mixture models for Real-time tracking[C]//Int Conf Computer Vision of Pattern Recognition. 1999 : 246-252. 被引量:1
  • 6Amat J,Casals A,Frigola M.Stereoscopic system for human body tracking in natural scenes[C]//Proceedings of the IEEE International Workshop on Modelling People, Corfu,Greece,September 1999. 被引量:1
  • 7Zivkovic Z, van der Heijden F. Recursive unsupervised learning of finite mixture models[J]. IEEE Trans. on PAMI, 2004, 26(5): 651456. 被引量:1
  • 8Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking[J]. Proc. of IEEE Int. Conf. on CVPR, 1999, 2: 246-252. 被引量:1
  • 9Dar-shyang Lee. Effective Gaussian mixture learning for video background subtraction[J]. IEEE Trans. on PAMI, 2005, 27(5): 827-832. 被引量:1
  • 10Cheng J. Flexible background mixture models for foreground segmentation[J]. Image and Vision Computing, 2006, 24: 473-482. 被引量:1

共引文献21

同被引文献215

引证文献28

二级引证文献81

投稿分析
职称考试

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈