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...

基于前景概率函数的目标跟踪

Keywords: 目标跟踪,前景概率函数,均值迁移,Bhattacharyya相关系数

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对不规则目标跟踪中初始窗口内包含背景像素导致特征模板不准确的问题,提出前景概率函数以及基于前景概率函数的目标跟踪算法.首先根据目标所在区域与背景区域的颜色分布建立前景概率函数,并以此计算目标区域中像素的前景概率,削弱背景像素的干扰,得到更准确的目标特征模板.将目标区域像素的前景概率引入均值迁移跟踪框架中,实现目标的迭代定位;在跟踪收敛后重新计算收敛区域中的前景概率分布,根据其反向投影图的尺度变化调整跟踪窗宽;最后利用Bhattacharyya相关系数对目标特征模板进行自适应更新.实验表明,该算法能

References

[1]  Hager G D, Dewan M, Stewart C. Multiple kernels tracking with SSD[J]. Computer Vision and Pattern Recognition, 2004(1):791-797.
[2]  Shin J, Kim S, Kang S. Optical flow-based real-time object tracking using non-prior tracking active feature model[J]. Real-Time Image, 2005,11(3):204-218.
[3]  Maggio E, Cavallaro A. Accurate appearance based Bayesian tracking for maneuvering targets[J]. Computer Vision and Image Understanding, 2009,113:544-555.
[4]  姚红革,齐华,郝重阳.复杂情形下目标跟踪的自适应粒子滤波算法[J].电子与信息学报,2009,31(2):275-279. Yao Hongge, Qi Hua, Hao Chongyang. Visual target tracking based on the adaptive particle filter in the complex situation[J]. Journal of Electronics & Information Technology, 2009,31(2):275-279. (in Chinese)
[5]  张涛,蔡灿辉.基于多特征Mean Shift的人脸跟踪算法[J].电子与信息学报,2009,31(8):1816-1820. Zhang Tao, Cai Canhui. A face tracking algorithm based on multiple feature Mean Shift[J]. Journal of Electronics & Information Technology, 2009,31(8):1816-1820. (in Chinese)
[6]  Comaniciu D, Meer P. Kernel-based object tracking[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003,25(5):564-577.
[7]  王永忠,梁彦,赵春晖.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(1):393-399. Wang Yongzhong, Liang Yan, Zhao Chunhui. Kernel-based tracking based on adaptive fusion of multiple cues[J]. Acta Automatica Sinica, 2008,34(1):393-399. (in Chinese)
[8]  Yilmaz A. Object tracking by asymmetric kernel Mean Shift with automatic scale and orientation selection //Proceedings of Computer Vision and Pattern Recognition, CVPR’07. Minneapolis, USA: , 2007:1211-1218.
[9]  Collins R T. Mean-shift blob tracking through scale space //Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. : IEEE, 2003:234-240.
[10]  Sheikh Y, Shah M. Bayesian modeling dynamic scenes for object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27:1778-1792.
[11]  Ren Ying, Chua Chin Seng, Ho Yeong Khing. Motion detection with nonstationary background[J]. Machine Vision and Application, 2003,13(5-6):332-343.
[12]  Maggio E, Cavallaro A. Multi-part target representation for color tracking //Proceedings of International Conference on Image Processing. Genoa, Italy: IEEE,2005:721-725.
[13]  Jeyakar J, Babu R V. Robust object tracking with background-weighted local kernels[J]. Computer Vision and Image Understanding, 2008,112:296-309.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133