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

双向时空连续性轨迹片段关联的目标跟踪方法 被引量：3

Object Tracking Using Bidirectional Spatio-temporal Continuity Tracklet Association
下载PDF
导出
摘要 提出一种使用双向时空连续性关联轨迹片段的目标跟踪方法。首先对检测结果进行简单的帧间匹配关联,生成可靠的轨迹片段;然后对每个轨迹片段通过卡尔曼滤波以及有权重的均值法分别计算修正轨迹片段的速度、位置与颜色特征;最后通过计算轨迹片段之间的双向时空连续性迭代关联,找到最符合时空连续性的轨迹片段关联。实验证明本文方法可以有效解决目标间以及目标被背景遮挡问题,实现对目标的稳定跟踪。 An object tracking algorithm by associating tracklets with the best bidirectional spatio-temporal continuity was proposed.First, reliable tracklets were generated by a primitive frame-by-frame association;then tracklet＇s motion,position and color features were computed and refined by applying Kalman filter and weighted mean method respectively;finally,the best spatio-temporal association of tracklets was achieved through an iterative association by computing spatio-temporal continuity between tracklets.Experimental results prove that multiple objects can be successfully tracked under occlusion both by other object and scene object.
作者 王江峰 张茂军 包卫东 熊志辉
机构地区 国防科技大学信息系统与管理学院
出处 《国防科技大学学报》 EI CAS CSCD 北大核心 2011年第2期44-48,共5页 Journal of National University of Defense Technology
基金 国家自然科学基金资助项目(60705013) 中国博士后科学基金资助项目(20070410977)
关键词 目标跟踪 遮挡 时空连续性 轨迹片段关联 object tracking occlusion spatio-temporal continuity tracklet association
分类号 TP391.4 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献12

  • 1Alper Y, Omar J, Mubarak S. Object Tracking: A Survey [J]. ACM Computer Survey, 2006, 38(4) : 13 - 57.
  • 2Bennett B, Magee D R, Cohn A G, etal. Enhanced Tracking and Recognition ff Moving Objects by Reasoning about Spatio-temporal Continuity [J]. Image and Vision Computing. 2008, 26(1): 67- 81.
  • 3Ingemar J C, Sunita L H. An Efficient Implementation of Reid's Multiple Hypothesis Tracking Algorithm and Its Evaluation for the Purpose of Visual Tracking [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1996, 18(2): 138- 150.
  • 4Bardet F, Chateau T, Laprest' e J T. mumination Aware MCMC Particle Filter for Long-term Outdoor Mulfi-object Simultaneous Tracking and Classification [ C ]//Proceeding of 12th IF-dEE International Conference on Compter Vision, 2009:1623- 1630.
  • 5Xing J L, Ai H Z, Lao S H. Multi-object Tracking Through Occlusions by Loe, al Traeklets Filtering and Global Tracklets Association w/th Detection Responses [C]//Proceeding of 2009 IEEE Computer Vision and Pattern Recognition, 2009:1200 - 1207.
  • 6Perera A, Sfinivas C, Hoogs A, et al. Multi-object Tracking Through Simultaneons Long Occlusions and Split-melge Conditions [C]//Proceeding of 2006 IEEE Computer Vision and Pattem Recognition, 2006:666 - 673.
  • 7Liu S H, Lai S M. Schematic Visualization of Object Trajectories across Multiple Cameras for Indoor Surveillances [ C]//Proceeding of 5th IEEE International Conference on Image and Graphics, 2009: 406-411.
  • 8CAVIAR[ DB ]. http://homepages, inf. ed. ac. uk/rbf/CAVIAR/.
  • 9Zhang L, Li Y, Nevatia R. Global Data Association for Multiobject Tracking using Network Flows[C ]//Proceeding of 2008 IEEE Computer Vision and Pattern Recognition, 2008:666- 673.
  • 10Wang J F, Zhang M J, Cohn A G. Object Tracking and Primitive Event Detection by Spatio-temporal Tracklet Association [ C ]// Proceeding of 5th IEEE International Conference on Image and Graphics, 2009: 457-462.

同被引文献20

  • 1KAUCIC R, PERERA A, BROOKSBY G, et al. A unified framework for tracking through occlusions and across sensor gaps[C]//Proceeding of the 2005. Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 990-997.
  • 2WANG Xiao-gang, TIEU K, GRIMSON E. Learning semantic scene models by trajectory analysis[C]// Proceeding of the 2006 European Conference on Computer Vision. Berlin: Springer, 2006: 110-123.
  • 3HANSON A R, RISEMAN E M. The VISIONS image-understanding system[J]. Advances in Computer Vision. 1988 1 1 - l 14.
  • 4FERNYHOUGH J H, COHN A G, HOGG D C. Generation of semantic regions from image sequences[C]//Proceeding of the 1996 European Conference on Computer Vision. Cambridge: Springer, 1996: 475-484.
  • 5MAKRIS D, ELLIS T. Automatic learning of an activity based semantic scene model[C]//Proceeding of the 2003 AVSS. Miami: IEEE, 2003: 183-188.
  • 6ZHANG Zhang, Huang Kai-qi, Tan Tie-niu, et al. Trajectory series analysis based event rule induction for visual surveUlanee[C]//Proceeding of the 2007 Computer Vision and Pattern Recognition, Minneapolis: IEEE, 2007: 1-8.
  • 7WANG Xiao-gang, MA K T, NG G-W, et al. Trajectory analysis and semantic region modeling using a nonparametrie bayesian model[C]//Proceeding of the 2008 Workshop on Motion and Video Computing. Boston: IEEE, 2008: 1-8.
  • 8XING Jun-liang, AI Hai-zhou, LAO Shi-hong. Multi-object tracking through occlusions by local tracklets filtering and global traldets association with detection responses[C]// Proceeding of the 2009 Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 1200-1207.
  • 9WANG Jiang-feng, ZHANG Mao-jun, COHN A G. Object tracking and primitive event detection by spatiao-temporal tracklet association[C]//Proceeding of the 5th International Conference on Image and Graphics. Xian: IEEE, 2009: 457-462.
  • 10罗鹏飞,张文明.一种多目标跟踪航迹起始新算法及其性能评估[J].国防科技大学学报,1999,21(6):51-54. 被引量：21

引证文献3

二级引证文献5

国防科技大学学报
2011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