期刊文献+

运动图像快速跟踪技术研究 被引量:8

Research for the Technology of Motion Image Fast Tracking
下载PDF
导出
摘要 针对运动图像目标检测需人工干预,跟踪核窗固定、目标易丢失等问题,提出了融合背景差分、帧间差分和灰度阈值技术的变背景帧间差分法,并结合灰度质心定位和自适应核窗宽改进了MeanShift跟踪算法。该方法能够在复杂环境下检测出各种运动目标,并进行实时跟踪,当目标发生尺度、旋转、无规律大位移变化时都能够快速准确地检出并跟踪。大量实验仿真表明,本算法检出率高,迭代次数少,实时性强,具有很好的适应性和鲁棒性。 according to some problems,such as requiring the manual intervention for motion image target detection,tracking the core window to be fixed,the goal easy to lose and so on,the paper proposes a method that changes the background frame difference based on background difference,frame difference and threshold value,and combines with the grayscale centroid location and auto-adapted core window width,then improved the MeanShift tracking algorithm.This method can detecte all variety of moving targets in a complex environment,and carry on real-time tracking,even when the target makes big changes in the scale, rotation,and disorder large displacement situation,it also can carry on the fast and accurate detection and tracking.A large number of simulation experiments show that this algorithm has the high detection rate,fewer iteration numbers, strong real-time,good adaptability and robustness.
出处 《重庆师范大学学报(自然科学版)》 CAS 2011年第1期44-48,共5页 Journal of Chongqing Normal University:Natural Science
基金 福建省教育厅科技项目(No.JA09240) 武夷学院智能计算网格科研团队(2009)
关键词 图像 跟踪 自适应 MEANSHIFT 检测 image track adaptability MeanShift detection
  • 相关文献

参考文献16

  • 1Doucet A, Gordon N, Krishnamurthy V. Particle filter for state estimation of jump Markov linear systems [ J ]. IEEE Transactions on Signal Processing, 2001,49 ( 3 ) : 613-624.
  • 2Haritaoglu I, Harwood D D, Davis L. W4 : real-ftime surveillance of people and their activities [ J ]. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8) :809-830.
  • 3Mckenna S. Tracking groups of people[ J]. Computer Vision and Image Understanding, 2000,80 (1) :42-56.
  • 4Xia L M. Image restoration based on particle filter [ C ]// In: Proceedings of 7th International Conference on Signal Processing. Beijing ,2004 : 1084-1087.
  • 5兰晓红.基于VG2的多制式图形视频叠加系统设计[J].重庆师范大学学报(自然科学版),2006,23(1):25-26. 被引量:2
  • 6Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-frigid objects using MeanShift [ C]//In: Proeeedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, South Carolina, USA, 2000 : 142-149.
  • 7Fukunaga K, Hostetler L D. The estimation of the gradient of a density function,with applications in pattern recognition [ J ]. IEEE Trans Information Theory, 1975,21 : 32-40.
  • 8龙兴明,郭世刚.三维测量中基于脊波变换的图像预处理及拐点检测[J].重庆师范大学学报(自然科学版),2007,24(2):46-49. 被引量:4
  • 9Elgammal A, Duraiswami R, Davis L. Probabilistic tracking in joint feature-fspatial spaces [ J ]. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003 (1) : 781-788.
  • 10Yang C, Duraiswami R, Davis L. Efficient MeanShifl tracking via a new similarity measure [ J ]. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition ,2005 (1) : 176-183.

二级参考文献63

共引文献212

同被引文献46

引证文献8

二级引证文献22

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