期刊文献+

基于概率图模型目标建模的视觉跟踪算法 被引量:4

Visual tracking based on object modeling using probabilistic graphical model
原文传递
导出
摘要 提出了一种视觉跟踪任务中基于局部特征和概率图模型的目标建模方法,将目标表示为一组具有仿射不变性的区域特征,并通过概率图模型描述特征之间的空间约束关系。在目标跟踪过程中,首先在空域上利用信任传播算法,推断概率图模型中各个特征的状态,然后根据推断的结果设计改进的重要性采样函数,采用粒子滤波算法在时间域上对目标进行跟踪。为了适应目标在运动中的变化,模型根据特征的稳定程度自适应地进行更新。实验结果表明,该方法具有较强的鲁棒性,能够有效实现复杂场景下的目标跟踪。 A novel method of object modeling for visual tracking based on local features and probabilistic graphical model is proposed.The tracked object is represented using a collection of regional affine invariant features,among which the spatial constraints are described by a probabilistic graphical model.During tracking,belief propagation algorithm is first applied to infer the state of each feature in spatial domain.Then,the inferred results are employed to construct the proposal sampling function,by which a particle filter is adopted to estimate the target state.To adapt to changes in object appearance,object model will be updated adaptively according to the stability score of the features.The experimental results show that the proposed method can get reliable track even under complex real world conditions.
出处 《光电子.激光》 EI CAS CSCD 北大核心 2010年第1期124-129,共6页 Journal of Optoelectronics·Laser
基金 国家自然科学基金资助项目(60705005) 国家自然科学基金民航联合基金重点资助项目(60736046) 教育部博士点基金资助项目(20070610031)
关键词 视频目标跟踪 仿射不变特征 概率图模型 信任传播 粒子滤波 visual object tracking affine invariant feature probabilistic graphical model belief propagation particle filter
  • 相关文献

参考文献17

  • 1KANGWen-jing DINGXue-mei LIUGong-liang etal.Bandwidth-a- daptive mean shift tracking algorithm.光电子.激光,2008,19:135-138.
  • 2胡昭华,宋耀良,梁德群,樊鑫.复杂背景下多信息融合的粒子滤波跟踪算法[J].光电子.激光,2008,19(5):680-685. 被引量:14
  • 3Comaniciu D, Ramesh V, Meet P. Kemel-based object tracking[J]. IEEE Transactions ol Pattern Analysis and Machine intelligence, 2003,25(5) : 564-575.
  • 4江淑红,汪沁,张建秋,胡波.基于目标中心距离加权和图像特征识别的跟踪算法[J].电子学报,2006,34(7):1175-1180. 被引量:12
  • 5Isard M,Blake A. Contour tracking by stochastic propagation of conditional density[A]. European Conference on Computer Vision[C]. 1996,343-356.
  • 6孙正.基于T-snake模型的冠状动脉血管提取和运动跟踪[J].光电子.激光,2007,18(10):1260-1264. 被引量:6
  • 7Mansouri A R. Region tracking via level set PDEs without motion cornputation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(7) : 947-961.
  • 8Ozuysal M,Lepetit V,FleuretF,et al. Feature harvesting for tracking- by-detection[A]. European Conference on Computer Vision [C]. 2006,592-- 605.
  • 9Tran S,Davis L. Robust object tracking with regional affine invariant features[A]. IEEE Conference onComputer Vision and Pattern Recognition[C]. 2007,14-20.
  • 10Zhao T,Nevatia R. Tracking multiple humans in crowded environment [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. 2004,406-413.

二级参考文献34

共引文献29

同被引文献66

  • 1向桂英,艾斯卡尔.艾木都拉,于伟俊,地里木拉提.吐尔逊.基于粒子滤波和数据关联的多目标跟踪算法[J].光电子.激光,2009,20(2):244-247. 被引量:9
  • 2常发亮,马丽,乔谊正.视频序列中面向人的多目标跟踪算法[J].控制与决策,2007,22(4):418-422. 被引量:16
  • 3宋宇,李满天,孙立宁.基于相似度函数的图像椒盐噪声自适应滤除算法[J].自动化学报,2007,33(5):474-479. 被引量:42
  • 4HU Wei-ming, ZHOU Xue, HU Min, et al. Occlusion reasoning for tracking multiple people[J]. IEEE Transactions on Circuits and Systems for Video Technology ,2009, 19(1) : 114-121.
  • 5Khan Z, Balch T, Dellaert F. MCMC-based particle filtering for tracking a variable number of interacting targets [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,11(27) :1805-1819.
  • 6Qian Y, Mediono G. Multiple-target tracking by spatiotemporal Monte carlo Markov Chain data association[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31 (12) :2196-2210.
  • 7Senior A,Hampapur A,Tian Y L. Appearance models for occlusions handling[J]. International Journal of Image and Vision Computing,2006,24(11) : 1233-1243.
  • 8Nguyen H T,Smeulders A W M. Fast occluded object tracking by a robust appearance filter[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1099-1104.
  • 9Nguyen H T, Worring M, Boomgaard R van den. Occlusion robust adaptive template tracking[A]. IEEE Proceedings of International Conference on Computer Vision[C]. Vancouver, British Columbia, Canada, 2001, 678-683.
  • 10Collins R, Liu Y. On-line selection of discriminative tracking features[A]. IEEE Proceedings of International Conference on Computer Vision[C]. Nice, France, 2003,346-352.

引证文献4

二级引证文献19

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