期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于光流场核密度估计的动态目标分割 被引量：2

Detection of moving objects based on optical flow kernel density estimation
原文传递
导出
摘要 在经典的核心密度估计模型中,基于像素亮度的估计能够将同一目标更好地连通显示,具有集中的像素分布规律.利用这一规律,可将经典核密度模型的计算维度扩展到二维,用其分割像素对应的光流场,并称该方法为基于光流场核密度估计的动态目标分割模型.实验证明,该方法能够从运动背景中很好地检测出较完整的运动目标. In classical kernel density estimation, for the estimation is based on pixels＇ brightness it can offer the target a better connectivity and the inherent concentrated pixel distribution. To make use of the advantages, the calculation of dimensions can be expanded to be enabled to segment the optical flow relative to a pixel, and the method can be named as Detection of Moving Object Based on Optical Flow Ker nel Density Estimation. Experiments show that the method can extract more complete moving objects from a moving background.
作者 王洋 李征 孙嘉
机构地区 四川大学计算机学院
出处 《四川大学学报（自然科学版）》 CAS CSCD 北大核心 2012年第2期309-314,共6页 Journal of Sichuan University(Natural Science Edition)
基金 四川省科技厅应用基础研究基金(2006J13-092)
关键词 光流场 核密度估计 运动背景 动态目标分割 optical flow,kernel density estimation, moving background, detection of moving objects
分类号 TP751 [自动化与计算机技术—检测技术与自动化装置]
  • 相关文献

参考文献11

  • 1陈延涛.一种改进的混合高斯模型运动目标检测方法[J].四川大学学报（自然科学版）,2009,46(5):1296-1300. 被引量：9
  • 2Sasa G,Loncaric S. Spatio-temporal image segmentation using optical flow and clustering algorithm[A].USA:IEEE Publishers,2000.
  • 3张磊,项学智,赵春晖.基于光流场与水平集的运动目标检测[J].计算机应用,2009,29(4):972-975. 被引量：7
  • 4Foresti G L,Micheloni C. A robust feature tracker for active surveillance of out-door scenes[J].Electronics Letters on Computer Vision and Image Analysis,2003,(01):21.
  • 5Yilmaz A,Shafique K,Lobo N. Target-tracking in FLIR imagery using mean-shift and global motion compensation[M].Kauai,Hawaii:IEEE,2001.
  • 6Leeuwen M B,Groen F C A. Motion interpretation for in-car vision systems[M].USA:IEEE Publishers,2002.
  • 7Behrad A,Shahrokni A,Motamedi S A. A robust vision-based moving target detection and tracking system[M].New Zealand:IEEE,2001.
  • 8吴新根,罗立民.一种改进的光流场计算方法[J].电子学报,2000,28(1):130-131. 被引量：20
  • 9Zheng L,Jiang P H,Ma H. A model for dynamic object segementation with kernel density estimation based on gradient features[J].Image and Vision Computing,2009,(6):817.doi:10.1016/j.imavis.2008.08.004.
  • 10Elgmmal A,Duraiswami R. Background and foregroud modeling using nonpar-ametric kerneldensity estimation for visual surveillance[M].USA:IEEE Publishers,2002.

二级参考文献19

  • 1于慧敏,徐艺,刘继忠,高晓颖.基于水平集的多运动目标时空分割与跟踪[J].中国图象图形学报,2007,12(7):1218-1223. 被引量：8
  • 2THOMPSON W B, PONG T C. Detecting moving object[ J]. International Journal of Computer Vision, 1990, 4(1) : 39 -57.
  • 3ADIV G. Determining three-dimensional motion and structure from optical flow generated by several moving objects[ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1985, 7(4): 384 -401.
  • 4SASA G, LONCARIC S. Spatio-temporal.image segmentation using optical flow and clustering algorithm[ C]//Proceedings of the I st International Workshop on Image and Signal Processing and Analysis: IWISPA 2000. Pula, Croatia: [ s. n. ], 2000:63 - 68.
  • 5FREEDMAN D, ZHANG TAO. Active contours for tracking distributions [J]. IEEE Transaclions on Image Processing, 2004, 13(4): 518 -526.
  • 6MANSOURI A R, KONRAD J. Multiple motion segmentation with level sets[ J]. IEEE Transactions on Image Processing, 2003, 12 (2): 201 -220.
  • 7FEGHALI R, MITICHE A. Spatiotemporal motion boundary detection and motion boundary velocity estimation for tracking moving objects with a moving camera A level sets PDEs approach with concurrent camera motion compensation[ J]. IEEE Transactions on Image Processing, 2004, 13(11) : 1473 - 1490.
  • 8BARRON J L, FLEET D J. Systems and experiment: Performance of optical flow techniques[ J]. International Journal of Computer Vision, 1994, 12(1): 43-77.
  • 9OSHER S, SETHIAN J. Fronts propagating with curvature dependent speed: Algorithms based on the Hamihon-Jacobi formulation[ J]. Journal of Computational Physics, 1988, 79(1) : 12 -49.
  • 10ADALSTEINSSON D, SETHIAN J A. A fast level set method for propagating interface[ J]. Journal of Computational Physics, 1995, 118(2) : 269 -277.

共引文献33

同被引文献20

  • 1刘映杰,马若飞,朱望飞,者昊,绽琨,马义德.基于多阈值PCNN的运动目标检测算法[J].计算机应用,2009,29(3):739-741. 被引量：2
  • 2Caulfield, H. John,Kinser, Jason M.Finding the shortest path in the shortest time using PCNN’s[].IEEE Transactions on Neural Networks.1999
  • 3Kuntimad, G.,Ranganath, H.S.Perfect image segmentation using pulse coupled neural networks[].IEEE Transactions on Neural Networks.1999
  • 4Yu, Bo,Zhang, Liming.Pulse-coupled neural networks for contour and motion matchings[].IEEE Transactions on Neural Networks;Temporal Coding for Neural Information Processing.2004
  • 5Vasconcelos, Nuno,Lippman, Andrew.Empirical Bayesian motion segmentation[].IEEE Transactions on Pattern Analysis and Machine Intelligence.2001
  • 6Eckhorn R,Reitboeck HJ,Arndt M,et al.Feature linking via synchronization among distributed assemblies: simulation of results form cat visual cortex[].Neural Computation.1990
  • 7B. Due,P. Schroeter,J. Bigtin.Motion Segmentation by Fuzzy Clustering with Au-tomatic Determination of the ber of Motions[].Proceedings of ICPR.1996
  • 8Ester M,Kriegel HP,Sander J,Xu X.A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise[].Proceedings of the Second International Conference on Knowledge Discovery and Data Mining.1996
  • 9侯伟,卢炎麟,郑河荣,潘翔,陈永清.固定背景下的视频分割及在交通视频流的应用[J].计算机技术与发展,2008,18(9):191-193. 被引量：8
  • 10李毅,孙正兴,远博,张岩.一种改进的帧差和背景减相结合的运动检测方法[J].中国图象图形学报,2009,14(6):1162-1168. 被引量：35

引证文献2

二级引证文献4

四川大学学报（自然科学版）
2012年 第2期

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