全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电子学报  2015 

一种基于拓扑约束的多核跟踪算法

DOI: 10.3969/j.issn.0372-2112.2015.02.022, PP. 353-357

Keywords: 多核跟踪,拓扑约束,部分遮挡,尺度变化

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对视觉跟踪中常见的目标部分遮挡和尺度变化问题,提出了一种基于拓扑约束的多核跟踪算法.首先,提取满足空间分布的位于目标与背景所在边界的Harris角点作为多核跟踪器的中心,然后,采用拓扑约束对多个跟踪结果进行优化,选取跟踪性能好的核跟踪器,构造仿射变换模型,进而得到最终跟踪结果和目标尺度变化信息.实验结果表明,本文算法能对目标进行准确跟踪,并能有效地处理目标的部分遮挡和尺度变化问题.

References

[1]  Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[2]  Collins R T.Mean-shift blob tracking through scale space[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Madison,Wisconsin,USA:IEEE,2003.234-240.
[3]  Yilmaz A.Object tracking by asymmetric kernel mean shift with automatic scale and orientation selection[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Minneapolis,USA:IEEE,2007.1-6.
[4]  Shen C H,Kim J and Wang H Z.Generalized kernel-based visual tracking[J].IEEE Transactions on Circuits and Systems for Video Technology,2010,20(1):119-130.
[5]  Adam A,Rivlin E,Shimshoni I.Robust fragments-based tracking using the integral histogram[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].New York,USA:IEEE,2006.798-805.
[6]  Jeyakar J,Babu R V,Ramakrishnan K R.Robust object tracking using local kernels and background information[A].Proceedings of IEEE International Conference on Image Processing[C].San Antonio,USA:IEEE,2007.49-52.
[7]  Wang F L,Yu S Y,Yang J.Robust and efficient fragments-based tracking using mean shift[J].International Journal of Electronics and Communications,2010,64(7):614-623.
[8]  Zhao Fangzhou,Li Junshan,Zhu Yinghong,Wei yang.Invariant feature matching based adaptive bandwidth mean shift and its application to infrared object tracking[A].Proceedings of IEEE International Conference on Computer Science and Information Technology[C].Chengdu,USA:IEEE,2010.37-40.

Full-Text

Contact Us

[email protected]

QQ:3279437679

WhatsApp +8615387084133