期刊文献+

基于变尺度全局搜索的运动目标跟踪算法 被引量:1

Moving object tracking algorithm based on variable scale global search
在线阅读 下载PDF
导出
摘要 为了获得更加理想的运动目标跟踪效果,提出一种基于变尺度全局搜索的运动目标跟踪算法。首先对于没有发生严重遮挡运动目标,采用MS算法实现目标跟踪,然后当目标受到严重遮挡时,通过全局搜索策略缩小搜索窗尺度,逐渐逼近跟踪目标,实现对目标准确跟踪,最后采用多个实验对算法的性能仿真测试。仿真结果表明,相对其它的目标跟踪算法,本文算法不仅提高了运动目标的跟踪精度,而且加快运动目标跟踪速度,尤其对于严重遮挡目标跟踪问题,具有十分明显的优势,具有较强的鲁棒性。 In order to obtain more ideal effect of moving target tracking,a novel object tracking algorithm based on variable scale global search is proposed in this paper. Firstly,First of all,for no serious occluded moving objects,MS algorithm is used to track for target,and then when the target is severely occluded,global search strategy is used to reduce the search window scale,gradually approaching the tracking target to achieve the target accurate tracking,finally,several simulation experiments are used to test performance of algorithm. The simulation results show that,compared with to other target tracking algorithms,the proposed algorithm not only improves the moving target tracking accuracy,but also accelerate the tracking speed of moving target,especially for serious occlusion target tracking problem,and it has very obvious advantages,so it has strong robustness.
出处 《激光杂志》 CAS 北大核心 2015年第2期30-34,共5页 Laser Journal
基金 广东省自然科学基金(32208005)
关键词 运动目标跟踪 颜色直方图 均值偏移算法 自适应搜索窗 moving object tracking color histogram Mean Shift algorithm Adaptive search window
  • 相关文献

参考文献17

二级参考文献157

共引文献125

同被引文献17

  • 1Fukunaga K,Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition [J]. IEEE Transactions on Information Theory, 1975,21, ( 1 ) :32-40.
  • 2Yizong Cheng. Mean Shift, Mode Seeking, and Clustering [ J]. IEEE, Transactions on Pattern Analysis and Machine Intelligence, 1995,17, ( 8 ) :790-799.
  • 3D. Comaniciu, V. Ramesh, P. Meer. Real-Time Tracking of Non-Rigid Objects using Mean Shift [ J]. 1EEE, Conference on Computer Vision and Pattern Recognition, Proceedings, 2000,2 : 142-149.
  • 4Comaniciu D, V. Ramesh V, P. Meer P. Real-Time Tracking of Non-Rigid Objects using Mean Shift [ J ]. IEEE, Confer-ence on Computer Vision and Pattern Recognition, Proceed- ings ,2000,2 : 142-149.
  • 5Mark Fashing, Carlo Tomasi. Mean Shift Is a Bound Optimi- zation [ J ]. IEEE, Transactions on Pattern Analysis and Ma- chine Intelligence,2005,27, (3) :471-474.
  • 6Robert T. Collins,Y. Liu, M. Leordeanu. Online Selection of Discriminative Tracking Features [ J ]. IEEE, Transactions on Pattern Analysis and Machine Intelligence ,2005,27, (10) : 1631-1643.
  • 7Robert T. COLLINS . Mean-Shift Blob Tracking through Scale Space [ C ]. Canada: 2003 IEEE Computer Society Conferences on Computer Vision and Pattern Recognition ( CVPR'03 ). Vancouver, 2003.
  • 8Manoj D, Pawan K P, Kunal G, et al. Object Tracking Using Joint Enhanced Color-Texture Histogram [ J ]. 2013 IEEE Second International Conference on Image Information Pro- cessing. 2013,10 : 160-165.
  • 9Ning J,Zhang L, Wu C. Robust mean shift tracking with cor-rected background- weighted histogram [ J ]. IET Computer Vision,2012,6( 1 ) :62-69.
  • 10Leichter I, Lindenbaum M, Rivlin E. Mean shift tracking with multiple references color histograms [ J ]. Computer Vi- sion and Image Understanding, 2010,114, ( 3 ) :400 -408.

引证文献1

二级引证文献3

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