期刊文献+

重叠视野域内多摄像机目标交换算法 被引量:6

Multi-camera object handoff algorithm in overlapping fields of view
下载PDF
导出
摘要 多摄像机之间重叠视野区域内目标交接问题是实现多摄像机监控系统持续目标跟踪的关键,传统方法是在摄像机重叠视野区域内采用特征匹配方法或基于视野分界线的目标交接算法。但是特征匹配计算量较大,受摄像机参数设置因素影响较大,实用性不高。而基于视野分界线的目标交接算法由于新目标的检测存在延时,仅利用该方法来实现一致性标号容易出错。近年来,出现了利用投影不变量,计算目标在相邻摄像机中的投影位置来进行目标交接的方法,取得较好效果。但在多个目标相距较近的情况下,投影过程中产生的误差会造成目标对应错误。文中提出一种投影不变量和直方图匹配相结合的改进算法,实验表明能较好解决了上述问题。 The implementation of object handoff in overlapping fields of view is one of the key techniques of continual object tracking in multi-camera tracking systems. Feature matching methods and the algorithm based on field of view are adopted in conventional solutions towards this problem. However, FM is not practical in application because it is not computationally efficient and the results heavily depend on the parameter settings of the cameras. The approaches based on FOV suffer from the delay of the detection of newly appeared objects, causing the results of consistent labe- ling are not reliable. Recently,projective invariants method is used to handoff object,but it will make mistakes in the case of multiple objects appear closely. The paper proposes a novel scheme for object handoff based on projective invariants and histogram matching. The experimental results show that our method could solve the problem above.
作者 欧阳宁 刘钊
出处 《激光与红外》 CAS CSCD 北大核心 2009年第9期995-998,共4页 Laser & Infrared
基金 桂科基(No.0731020) 桂科能(No.063006-5G-4)基金项目资助
关键词 多摄像机 目标交接 投影不变量 直方图匹配 multi-camera object handoff projective invariants histogram matching
  • 相关文献

参考文献10

  • 1T H Chang, S Gong. Tracking multiple people with a multi-camera system [ C ]. Proc. of IEEE Workshop Multi- Object Tracking,2001 : 19 - 26. 被引量:1
  • 2L Lee, R Romano, G Stein. Monitoring activities from multiple video streams: Establishing a common coordinate frame [ J ]. IEEE Trans. on PAMI ,2000 :758 - 768. 被引量:1
  • 3D Comaniciu, V Ramesh, P Meer. Real-time tracking of non-rigid objects using mean shift [ C ]. Proc. of CVPR, 2000, (2) :142 - 149. 被引量:1
  • 4V Kettnaker, R Zabih. Bayesian multi-camera surveillance [ C ]. Proc. of CVPR, 1999 : 253 - 259. 被引量:1
  • 5T Darrel, G Gordon, M Harville, et al. Integrated person tracking using stereo, color, and pattern detection [ C ]. IEEE Conference on Computer Vision and Pattern Recog- nition, Santa Barbara, CA, 1998:601 - 608. 被引量:1
  • 6G Wei,V Petrushin, A Gershman. Multiple-camera people localization in a cluttered environment [ C ]. Proceedings of the Fifth International Workshop on Multimedia Data Mining, 2004 : 52 - 60. 被引量:1
  • 7Utsumi A, Tetsutani N. Human tracking using multiplecamera-based head appearance modeling [ C ]. Proceedings. Sixth IEEE International Conference on Automatic Face and Gesture Recognition ,2004:657 - 662. 被引量:1
  • 8S Khan, M Shah. Consistent labeling of tracked objects in multiple cameras with overlapping fields of view [ J ]. IEEE Trans on PAMI. Oct,2003,25 (10) :1355 - 1360. 被引量:1
  • 9Senem Velipasalar, Wayne Wolf. Recovering field of view by using projective invariants [ C ]. International Conference on Image Processing,2004:3069 -3072. 被引量:1
  • 10S Velipasalar, W Wolf. Multiple object tracking and occlusion handling by information exchange between uncalibrated cameras[ C]. IEEE International Conference on Image Processing,2005:418 - 421. 被引量:1

同被引文献58

  • 1赵锋,周颖,王雪松,肖顺平,王国玉.预警信息引导条件下雷达最优搜索空域研究[J].现代雷达,2008,30(11):26-31. 被引量:9
  • 2周颖,王雪松,冯德军,丹梅.基于弹道预报的相控阵雷达监视空域研究[J].电子与信息学报,2006,28(7):1209-1214. 被引量:14
  • 3牛恩国,程咏梅,潘泉,赵春晖,杨涛.多摄像机视野分界线快速自动生成算法[J].计算机应用研究,2007,24(3):297-299. 被引量:6
  • 4Blackman S S, Popoli R. Design and analysis of modem tracking system[ M]. Massachusetts : Artech House, 1999. 被引量:1
  • 5Kastella K. Discrimination gain to optimize detection and classification [ J ]. IEEE Transactions on Systems, Man, and Cybernetics, 1997, 27(1) :112 - 116. 被引量:1
  • 6Vilmorin M G, Duflos E, Vanheeghe P. Radar optimal ti- mes detection allocation in muhitarget environment [ J ]. IEEE Systems Journal, 2009, 3 (2) : 210 - 220. 被引量:1
  • 7Stone L D, Barlow C A, Corwin T L. Bayesian multiple target tracking[ M ]. London: Artech House, 1999. 被引量:1
  • 8Ristic B, Arulampalam S, Gordon N. Beyond the kalman filter: particle filters for tracking applications [ M ]. Lon- don : Artech House, 2004. 被引量:1
  • 9Matthiesen P J. Optimal search[ C ]//IEEE International Radar Conference on Phased Array Systems and Technolo- gy. [ S. l. ] : IEEE Press, 2003. 被引量:1
  • 10Khan S, Shah M. Consistent labeling of tracked objects in multiple eameras with overlapping fields of view[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(10) : 1355-1360. 被引量:1

引证文献6

二级引证文献27

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