基于典型相关性分析的稀疏表示目标追踪

康彬; 曹雯雯; 颜俊; 张索非

doi:10.11999/JEIT170939

基于典型相关性分析的稀疏表示目标追踪

doi: 10.11999/JEIT170939

^①(南京邮电大学物联网学院南京 210003) ^②(南京邮电大学江苏省通信与网络技术工程研究中心南京 210003) ^③(南京邮电大学通信与信息工程学院南京 210003)

基金项目:

国家自然科学基金(61771256, 61471205, 61771258, 61701252)，江苏省自然科学基金青年基金(BK20170915)，江苏省高校自然科学面上项目(17KJD510005)，南京邮电大学引进人才启动基金(NY 216023)，南京邮电大学江苏省通信与网络技术工程研究中心开放课题

详细信息

作者简介:
康彬：康彬：男，1985年生，讲师，研究方向为稀疏表示理论、目标检测以及追踪等. 曹雯雯：女，1993年生，硕士生，研究方向为智能信号处理. 颜俊：男，1981年生，副教授，研究方向为智能信号处理. 张索非：男，1982年生，讲师，研究方向为目标检测以及追踪.

中图分类号: TP391
计量
- 文章访问数: 1617
- HTML全文浏览量: 165
- PDF下载量: 59
- 被引次数: 0
出版历程
- 收稿日期: 2017-10-11
- 修回日期: 2018-03-14
- 刊出日期: 2018-07-19

Canonical Correlation Analysis Based Sparse Representation Model for Robust Visual Tracking

KANG Bin^①② CAO Wenwen^③ YAN Jun^③ ZHANG Suofei^①

Funds:

The National Natural Science Foundation of China (61771256, 61471205, 61771258, 61701252), The Natural Science Foundation of Jiangsu Province (BK20170915), The Natural Science Foundation of Jiangsu Higher Education Institutions (17KJD510005), The Nanjing University of Posts and Telecommunications Program (NY 216023), Supported by Open Research Fund of Jiangsu Engineering Research Center of Communication and Network Technology, Nanjing University of Posts and Telecommunications

摘要

摘要: 传统稀疏表示目标追踪算法首先通过粒子滤波方法对状态粒子进行采样，然后利用灰度特征表征采样粒子观测向量，最后构造基于观测向量的稀疏表示模型来进行目标追踪。与传统稀疏表示模型不同，该文提出一个基于典型相关性分析的稀疏表示模型，此模型首先使用两种特征来表征粒子观测向量，然后对两种观测向量的子空间投影结果进行稀疏建模。所构建的模型可通过在子空间中探究特征间的相关性来实现不同特征的互补融合，提升稀疏表示模型在复杂监控环境下的鲁棒性。
- 目标追踪 /
- 稀疏表示 /
- 典型相关性分析
Abstract: In traditional sparse representation based visual tracking, particle sampling is first achieved by particle filter method. Then the particle observations are represented by intensity feature. Finally, the visual tracking is achieved by the intensity feature based sparse representation model. Different from traditional sparse representation model, a canonical correlation analysis based sparse representation model is proposed in this paper. The proposed model first uses two kinds of features to represent the particle observations, then, the projections of particle observations are used to build the sparse representation model. The advantage of the proposed model lies in that it can give a proper multi-feature fusing through canonical correlation analysis, which explores the relation between two features in a latent common subspace.
- Visual tracking、Sparse representation、Canonical correlation analysis /

HTML全文

参考文献(24)

[2] ROSS D A, LIM Jongwoo, LIN Rueisung, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77(1/3): 125141. doi: 10.1007/ s11263-007-0075-7.

ZDENEK K, KRYSTIAN M, and JIRI M. Tracking- learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422. doi: 10.1109/TPAMI.2011.239.

[3] ZHANNG Shengping, YAO Hongxun, SUN Xin, et al. Sparse coding based visual tracking: Review and experimental comparison[J]. Pattern Recognition, 2013, 46(7): 1772-1788. doi: 10.1016/j.patcog.2012.10.006.

[4] JOHN W, YANG A, GANESH A, et al. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227. doi: 10.1109/TPAMI.2008.79.

[5] MEI Xue and LING Haibin. Robust visual tracking and vehicle classification via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11): 1257-1264. doi: 10.1109/TPAMI.2011.66.

[6] BAO Chenglong, WU Yi, LING Haibin, et al. Real time robust tracker using accelerated proximal gradient approach [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, 2012: 1830-1837. doi: 10.1109/CVPR.2012.6247881.

[7] LI Hanxi, SHEN Chunhua, and SHI Qinfeng. Real-time visual tracking using compressive sensing[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, 2011, 42(7): 1305-1312. doi: 10.1109/CVPR.2011.5995483.

[8] ZHANG Tianzhu, GHANEM Bernard, LIU Si, et al. Robust visual tracking via structured multi-task sparse learning[J]. International Journal of Computer Vision, 2013, 101(2): 367383. doi: 10.1007/s11263-012-0582-z.

[9] ZHANG Tianzhu, LIU Si, AHUJA Narendra, et al. Robust visual tracking via consistent low-rank sparse learning[J]. International Journal of Computer Vision, 2015, 111(2): 171190. doi: 10.1007/s11263-014-0738-0.

[10] WANG Dong, LU Huchuan, BO Chunjuan, et al. Online visual tracking via two view sparse representation[J]. IEEE Signal Processing Letters, 2014, 21(9): 1031-1034. doi: 10.1109/LSP.2014.2322389.

[11] BAI Tianxiang, LI Youfu, and ZHOU Xiaolong. Learning local appearances with sparse representation for robust and fast visual tracking[J]. IEEE Transactions on Cybernetics, 2015, 45(4): 663-675. doi: 10.1109/TCYB.2014.2332279.

[12] FAN Heng and XIANG Jinhai. Robust visual tracking with multitask joint dictionary learning[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(5): 1018-1030. doi: 10.1109/TCSVT.2016.2515738.

[13] ZHOU Yun, HAN Jianghong, YUAN Xiaohui, et al. Inverse sparse group Lasso model for robust object tracking[J]. IEEE Transactions on Multimedia, 2017, 19(8): 1798-1810. doi: 10.1109/TMM.2017.2689918.

[14] AKAHO Shotaro. A kernel method for canonical correlation analysis[C]. Proceedings of the International Meeting of Psychometric Society, Tsukuba, 2006: 263-269.

[15] YUAN Xiaodong, LIU Xiaobai, and YAN Shuicheng. Visual classification with multitask joint sparse representation[J]. IEEE Transactions on Image Processing, 2012, 21(10): 4349-4360. doi: 10.1109/TIP.2012.2205006.

[16] SCHMIDT M W, BERG E Van Den, FRIEDLANDER M, et al. Optimizing costly functions with simple constraints: A limited-memory projected quasi-Newton algorithm[C]. Proceedings of the International Conference on Artificial Intelligence and Statistics, Clearwater Beach, 2009: 355-357.

[18] HENRIQUES J F, CASEIRO Rui, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernel[C]. Proceedings of the European Conference on Computer Vision, Florence, 2012: 702715. doi: 10.1007/ 978-3-642-33765-9_50.

[19] ZHANG Kaihua, ZHANG Lei, and YANG Ming-hsuan. Real-time compressive tracking[C]. Proceedings of the European Conference on Computer Vision, Florence, 2012: 864877. doi: 10.1007/978-3-642-33712-3_62.

[20] OMANICIU D, RAMESH V, and MEER P. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577. doi: 10.1109 /TPAMI.2003.1195991.

[21] BABENKO B, YANG Ming-hsuan, and BELONGIE S. Visual tracking with online multiple instance learning[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, 2009: 983-990. doi: 10.1109 /CVPR.2009.5206737.

[22] HARE S, SAFFARI A, and TORR P H S. Struck: Structured output tracking with kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(10): 2096-2109. doi: 10.1109/TPAMI.2015.2509974.

[23] KWON Junseok and LEE Kyoung. Visual tracking decomposition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, 2010: 1269-1276. doi: 10.1109/CVPR.2010.5539821.

[24] ADAM A, RIVLIN E, and SHIMSHONI I. Robust fragments-based tracking using the integral histogram[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, 2006: 798-805. doi: 10.1109/CVPR.2006.256.

[25] GRABNER H, GRABNER M, and BISCHOF H. Real-time tracking via on-line boosting[C]. Proceedings of the British Machine Vision Conference, Edinburgh, 2006: 47-56.

施引文献

资源附件(0)

访问统计