期刊文献+

一种多视角跟踪系统中的自行标定方法

An Auto-calibration method in Multi-view tracking system
下载PDF
导出
摘要 多视角的标定和自标定是多视角系统部署和应用中的重要限制环节。文章针对基于单应关系的多视角跟踪应用场景,提出了一种使用跟踪结果本身进行视角几何关系标定的方法,避免了预先标定环节,可以配合现有的各种跟踪算法。理论分析和仿真实验表明,此方法具有高效率、高可靠性、易于实施的特点。 A multi-view tracking system can gain better performance than single-view ones through information exchange. Nevertheless, it relies on the known projective relationship among views. Calibra- tion or self-calibration plays a very important role in both the deployment and the operation of multi-view tracking systems. In this paper, a method to tackle the homography relationship with locations of tracked objects is proposed, which needs no pre-calibration process of information and can cooperate with existing muhi-view tracking framework. By theoretical analysis and simulation experiment, this method is proved to be efficient, reliable and easy to be deployed.
出处 《信息与电子工程》 2012年第3期305-311,共7页 information and electronic engineering
基金 国家重大专项资助项目(2011ZX03003-001-02 2012ZX03001007-003) 华为合作资助项目(YBWL2010190)
关键词 多视角跟踪 标定 单应关系 multi-view tracking calibration homography
  • 相关文献

参考文献15

  • 1Taj M,Cavallaro A. Distributed and decentralized multicamera tracking[J]. Signal Processing Magazine,IEEE, 2011,28(3): 46-58.
  • 2Hemayed Elsayed E. A survey of camera self-calibration[C]//Proceedings IEEE Conference on Advanced Video and Signal Based Surveillance. Egypt:Cairo Univ., 2003:351-357.
  • 3Khan S,Shah M. Tracking multiple occluding people by localizing on multiple scene planes[J]. IEEE Trans. Pattern Anal. Machine Intell., 2009,31 (3):505-519.
  • 4Liu J,Chu M,Reich J. Multi target tracking in distributed sensor networks[J]. IEEE Signal Processing Magazine, 2007,24(3): 36-46.
  • 5Kim K,Davis L S. Multi-camera tracking and segmentation of occluded people on ground plane using search-guided particle filtering[C]//Ninth European Conf. Computer Vision. [S.1.]:Springer, 2006:98-109.
  • 6Sheng X,Hu Y H,Ramanathan P. Distributed particle filter with GMM approximation for multiple targets localization and tracking in wireless sensor network[C]//PSN '05 Proceedings of the 4th international symposium on information processing in sensor networks. Piscataway,NJ,USA:IEEE Press, 2005.
  • 7Hartley R,Zisserman A. Multiple view geometry in computer vision[M]. Cambridge,U.K.:Cambridge Univ. Press, 2003.
  • 8Radke R J. A survey of distributed computer vision algorithms[C]//Handbook of Ambient Intelligence and Smart Environments. New York:Springer Verlag, 2010:35-55.
  • 9Begelfor E,Werman M. How to put probabilities on homographies[J]. IEEE Trans. Pattern Anal. Mach. Intell., 2005,27(10): 1666-1670.
  • 10Sankaranarayanan A C,Chellappa R. Optimal multi-view fusion of object locations[C]//IEEE Workshop on Motion and Video Computing(WMVC). Washington:[s.n.], 2008.

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