基于稀疏表示的视频目标跟踪研究综述

黄宏图; 毕笃彦; 侯志强; 胡长城; 高山; 查宇飞; 库涛

doi:10.16383/j.aas.2018.c170209

基于稀疏表示的视频目标跟踪研究综述

doi: 10.16383/j.aas.2018.c170209

黄宏图^1,2, ,,
毕笃彦^1,,
侯志强^3,4,,
胡长城^2,,
高山^1,,
查宇飞^1,,
库涛^1,

1.
空军工程大学航空工程学院西安 710038
2.
中国人民解放军 95972部队酒泉 735018
3.
空军工程大学信息与导航学院西安 710077
4.
西安邮电大学计算机学院西安 710112

基金项目:

国家自然科学基金 61773397

国家自然科学基金 61472442

国家自然科学基金 61473309

详细信息

作者简介:
毕笃彦  空军工程大学航空工程学院教授.主要研究方向为图像处理和模式识别.E-mail:biduyan@126.com

侯志强  空军工程大学信息与导航学院教授, 西安邮电大学计算机学院教授.主要研究方向为模式识别, 计算机视觉, 图像处理, 信息融合.E-mail:hou-zhq@sohu.com

胡长城  中国人民解放军95972部队工程师.主要研究方向为数据处理.E-mail:h_ccemail@163.com

高山  空军工程大学航空工程学院讲师.主要研究方向为图像处理.E-mail:gaoshan1114@126.com

查宇飞  空军工程大学航空工程学院副教授.主要研究方向为计算机视觉和机器学习.E-mail:zhayufei@126.com

库涛  空军工程大学航空工程学院博士研究生.主要研究方向为视频目标跟踪.E-mail:keltloja@163.com

通讯作者:
黄宏图中国人民解放军95972部队工程师.2016年获空军工程大学信号与信息处理专业工学博士学位.主要研究方向为视频目标跟踪.本文通信作者.E-mail:huanghongtu@sina.cn

计量
- 文章访问数: 2897
- HTML全文浏览量: 666
- PDF下载量: 1599
- 被引次数: 0
出版历程
- 收稿日期: 2017-04-19
- 录用日期: 2017-09-23
- 刊出日期: 2018-10-20

Research of Sparse Representation-based Visual Object Tracking: A Survey

HUANG Hong-Tu^{1,2
, ,},
BI Du-Yan^1
,,
HOU Zhi-Qiang^{3,4
,},
HU Chang-Cheng^2
,,
GAO Shan^1
,,
ZHA Yu-Fei^1
,,
KU Tao^1
,

1.
Aeronautics Engineering College, Air Force Engineering University, Xi'an 710038
2.
95972 Troops of PLA, Jiuquan 735018
3.
Information and Navigation Institute, Air Force Engineering University, Xi'an 710077
4.
School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an 710112

Funds:

National Natural Science Foundation of China 61773397

National Natural Science Foundation of China 61472442

National Natural Science Foundation of China 61473309

More Information

Author Bio:
Professor at the Aeronautics Engineering College, Air Force Engineering University. His research interest covers image processing and pattern recognition

Professor at the Information and Navigation Institute, Air Force Engineering University and School of Computer Science and Technology, Xi0an University of Posts and Telecommunications. His research interest covers pattern recognition, computer vision, image processing, and information fusion

Engineer at 95972 Troops of PLA. His main research interest is data processing

Lecturer at the Aeronautics Engineering College, Air Force Engineering University. Her main research interest is image processing

Associate professor at the Aeronautics Engineering College, Air Force Engineering University. His research interest covers computer vision and machine learning

Ph. D. candidate at the Aeronautics Engineering College, Air Force Engineering University. His main research interest is visual object tracking

Corresponding author: HUANG Hong-Tu Engineer at 95972 Troops of PLA. He received his Ph. D. degree of engineering in signal and information processing major from Air Force Engineering University in 2016. His main research interest is visual object tracking. Corresponding author of this paper

摘要

摘要: 视频目标跟踪在计算机视觉领域有着广泛应用，由于目标自身和外界环境变化的复杂性和难以预知性，使得复杂场景下鲁棒实时目标跟踪成为一项亟待解决的关键问题.由于视觉信息可以用少量神经元进行稀疏表示，因此稀疏表示已经广泛应用于人脸识别、目标检测和目标跟踪等计算机视觉领域.本文旨在对基于稀疏表示的视频目标跟踪算法进行综述.首先，介绍了基于稀疏表示的视频目标跟踪算法中的字典组成；其次，介绍了稀疏模型的构建及求解算法和模型更新，并对算法复杂度进行了简要分析；然后，对现有公开代码的稀疏表示跟踪算法在测试数据上进行了实验分析，结合算法模型和实验结果对其进行了分析；最后，对基于稀疏表示的视频跟踪算法存在问题进行了讨论，并对未来的研究趋势进行了展望.
- 视频跟踪 /
- 稀疏表示 /
- 算法评估 /
- 实验分析
Abstract: Visual object tracking has been widely used in computer vision. Due to the complexity and unpredictability of the object itself and surroundings' changes, robust and real-time tracking is a key issue in urgent need of settlement in complex scenes. Since vision information can be expressed by few neurons, sparse representation has already been used in face recognition, object detection, visual tracking and so on. This paper aims to review the state-of-the-art of sparse representation-based visual tracking algorithms. Firstly, we introduce the codebook employed in the sparse representation-based trackers. Secondly, sparse model construction, corresponding solution and model update are described. And the algorithm complexity is briefly analyzed. Thirdly, the open sparse representation-based trackers' codes are conducted on the benchmark datasets, and the experimental results are fully analyzed in combination with models. Finally, we discuss the existing problems of sparse representation-based trackers and prospect the future.
- Visual tracking /
- sparse representation /
- algorithm evaluation /
- experiment analysis
注释:

1) 本文责任编委桑农

HTML全文

图 1 字典构建方法

Fig. 1 The codebook construction method

下载: 全尺寸图片幻灯片

图 2 基于稀疏表示的生成式模型

Fig. 2 The sparse representation-based generative mode

下载: 全尺寸图片幻灯片

图 3 L$_1$跟踪算法框架

Fig. 3 The L$_1$ tracker framework

下载: 全尺寸图片幻灯片

图 4 算法跟踪精度随中心误差阈值的变化曲线

Fig. 4 The tracker$'$s tracking precision versus center error threshold

下载: 全尺寸图片幻灯片

图 5 算法跟踪成功率随重叠率阈值的变化曲线

Fig. 5 The tracker$'$s success rate versus overlap rate threshold

下载: 全尺寸图片幻灯片

表 1 视频跟踪评估基准数据

Table 1 Summary of some visual tracking evaluation benchmark datasets

数据集	时间	视频数量	地址
VOT 2013	2013	16	http://www.votchallenge.net/vot2013/
OTB 50	2013	50	http://visualtracking.net
PTB	2013	100	http://tracking.cs.prince-ton.edu/submit.php
ALOV++	2013	315	http://www.alov300.org/
VOT 2014	2014	25	http://www.votchallenge.net/vot2014/
OTB 100	2015	100	http://pami.visual-tracking.net/
NUS-PRO	2015	365	http://www.lv-nus.org/pro/nus_pro.html

下载: 导出CSV

表 2 算法简称和论文代码地址

Table 2 The sparse tracker$'$s abbreviation, paper and code$'$s URL

算法	论文题目和代码地址
L$_1$	Robust visual tracking using l1 mimization. In ICCV, 2009. http://www.dabi.temple.edu/~hbling/publication-selected.htm
LSK	Robust tracking using local sparse appearance model and k-selection. In CVPR, 2011. http://www.uky.edu/~lya227/spt.html
L1APG	Real time robust l1 tracker using accelerated proximal gradient approach. In CVPR, 2012. http://www.dabi.temple.edu/~hbling/publication-selected.htm
ASLA	Visual tracking via adaptive structural local sparse appearance model. In CVPR, 2012. http://ice.dlut.edu.cn/lu/publications.html
SCM	Robust object tracking via sparsity-based collaborative model. In CVPR, 2012. http://ice.dlut.edu.cn/lu/publications.html
MTT	Robust visual tracking via multi-task sparse learning. In CVPR, 2012. http://faculty.ucmerced.edu/mhyang/pubs.html
LRT	Low-rank sparse learning for robust visual tracking. In ECCV, 2012. http://faculty.ucmerced.edu/mhyang/pubs.html
CT	Real-time compressive tracking. In ECCV, 2012. http://www4.comp.polyu.edu.hk/~cslzhang/papers.htm
DLSR	Online discriminative object tracking with local sparse representation. In WACV, 2012. http://faculty.ucmerced.edu/mhyang/pubs.html
SRPCA	Online object tracking with sparse prototypes. In TIP, 2013. http://ice.dlut.edu.cn/lu/publications.html
DSSM	Visual trcking via discriminative sparse similiarity map. In TIP, 2014. http://ice.dlut.edu.cn/lu/publications.html
SST	Structural sparse tracking. In CVPR, 2015. http://nlpr-web.ia.ac.cn/mmc/homepage/tzzhang/index.html
CST	In defense of sparse tracking: Circulant sparse tracker. In CVPR, 2016 http://nlpr-web.ia.ac.cn/mmc/homepage/tzzhang/index.html

下载: 导出CSV

表 3 算法跟踪成功率(%)比较

Table 3 The tracker$'$s success rate (%) comparison

算法	ASLA	SCM	CST	SST	LRT	LSK	MTT	DSSM	CT	L1APG	L$_1$	DLSR	SRPCA
成功率	70.69	68.96	68.20	59.30	59.02	56.09	54.98	45.80	42.29	41.61	35.56	34.22	25.83

下载: 导出CSV

表 4 算法单帧平均处理时间比较(ms)

Table 4 The comparison of tracker$'$s average processing time (ms)

算法	ASLA	SCM	CST	SST	LRT	LSK	MTT	DSSM	CT	L1APG	L$_1$	DLSR	SRPCA
实现环境	MC	MC	M	M	M	ME	M	M	MC	MC	MC	MC	MC
时间	241	7846	454	450	3152	382	2279	586	12	79	397	23030	249

下载: 导出CSV

表 5 基于稀疏表示的视频跟踪算法模型和重叠率比较

Table 5 The comparison of the sparse representation-based tracker$'$s model and overlap rate mean and std

算法简称	特征字典	运动模型	搜索方案	匹配模式	模型更新	重叠率均值	重叠率标准差
ASLA	局部灰度	仿射运动	粒子滤波	生成式	增量学习	0.5860	0.3225
SCM	局部灰度	仿射运动	粒子滤波	混合式	模板替换	0.5562	0.3436
CST	HOG	仿射运动	粒子滤波	生成式	模板替换	0.5480	0.3063
LRT	全局灰度	仿射运动	粒子滤波	判别式	模板替换	0.4841	0.3247
SST	局部灰度	仿射运动	粒子滤波	生成式	模板替换	0.4840	0.3187
LSK	局部灰度	相似性变换	均值漂移	生成式	加权更新	0.4801	0.3379
MTT	全局灰度	仿射运动	粒子滤波	生成式	模板替换	0.4623	0.3411
CT	扩展类haar	平移运动	稠密采样	判别式	Bayes更新	0.3909	0.2850
DSSM	全局灰度	仿射运动	粒子滤波	判别式	模板替换	0.3818	0.3520
L1APG	全局灰度	仿射运动	粒子滤波	生成式	模板替换	0.3660	0.3565
DLSR	局部灰度	仿射运动	粒子滤波	判别式	SVM更新	0.3116	0.3414
L$_1$	全局灰度	仿射运动	粒子滤波	生成式	模板替换	0.3068	0.3687
SRPCA	全局PCA	仿射运动	粒子滤波	生成式	增量学习	0.2412	0.3321

下载: 导出CSV

参考文献(88)

[1]	Li X, Hu W M, Shen C H, Zhang Z F, Dick A, Van Den Hengel A. A survey of appearance models in visual object tracking. ACM Transactions on Intelligent Systems and Technology, 2013, 4(4):Article No.58 http://d.old.wanfangdata.com.cn/OAPaper/oai_arXiv.org_1303.4803
[2]	王栋. 基于线性表示模型的在线视觉跟踪算法研究博士论文. 大连理工大学, 中国, 2013. http://cdmd.cnki.com.cn/Article/CDMD-10141-1014154759.htm Wang D. Research of online visual tracking algorithms based on linear representation models [Ph.D. dissertation], Dalian University of Technology, China, 2013. http://cdmd.cnki.com.cn/Article/CDMD-10141-1014154759.htm
[3]	Haritaoglu I, Harwood D, Davis L S. W.4:real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8):809-830 doi: 10.1109/34.868683
[4]	Rios-Cabrera R, Tuytelaars T, Van Gool L. Efficient multi-camera vehicle detection, tracking, and identification in a tunnel surveillance application. Computer Vision and Image Understanding, 2012, 116(6):742-753 doi: 10.1016/j.cviu.2012.02.006
[5]	卢莉萍. 目标跟踪算法与检测处理技术研究博士论文. 南京理工大学, 2012. Lu L P. Study on targets tracking algorithm and detection processing technology [Ph.D. dissertation], Nanjing University of Science and Technology, China, 2012.
[6]	Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision. In:Proceedings of the 7th International Joint Conference on Artificial Intelligence. Vancouver, British Columbia, Canada:ACM, 1981. 674-679 https://wenku.baidu.com/view/c7876662caaedd3383c4d307.html
[7]	Wu Y, Lim J, Yang M H. Online object tracking:a benchmark. In:Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland, Oregon, USA:IEEE, 2013. 2411-2418 https://wenku.baidu.com/view/510c17fd27284b73f24250a0.html
[8]	Chu D M, Smeulders A W M. Thirteen hard cases in visual tracking. In:Proceedings of the 7th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). Sydney, Australia:IEEE. 2010. 103-110
[9]	匡金骏. 基于稀疏表示的图像分类与目标跟踪研究[博士论文]. 重庆大学, 2013. http://cdmd.cnki.com.cn/Article/CDMD-10611-1013043071.htm Kuang J J. Study on image classification and target tracking based on sparse representation [Ph.D. dissertation], Chongqing University, China, 2013. http://cdmd.cnki.com.cn/Article/CDMD-10611-1013043071.htm
[10]	练秋生, 石保顺, 陈书贞.字典学习模型、算法及其应用研究进展.自动化学报, 2015, 41(2):240-260 http://www.aas.net.cn/CN/abstract/abstract18604.shtml Lian Qiu-Sheng, Shi Bao-Shun, Chen Shu-Zhen. Research advances on dictionary learning models, algorithms and applications. Acta Automatica Sinica, 2015, 41(2):240-260 http://www.aas.net.cn/CN/abstract/abstract18604.shtml
[11]	Donoho D L. Compressed sensing. IEEE Transactions on Information Theory, 2006, 52(4):1289-1306 doi: 10.1109/TIT.2006.871582
[12]	Olshausen B A, Field D J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 1996, 381(6583):607-609 doi: 10.1038/381607a0
[13]	Olshausen B A, Field D J. Sparse coding with an overcomplete basis set:a strategy employed by V1? Vision Research, 1997, 37(23):3311-3325 doi: 10.1016/S0042-6989(97)00169-7
[14]	Wright J, Yang A Y, Ganesh A, Sastry S S, Ma Y. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227 doi: 10.1109/TPAMI.2008.79
[15]	Oja E, Hyvärinen A, Hoyer P. Image feature extraction and denoising by sparse coding. Pattern Analysis & Applications, 1999, 2(2):104-110 doi: 10.1007/s100440050021
[16]	Yu N N, Qiu T S, Bi F, Wang A Q. Image features extraction and fusion based on joint sparse representation. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(5):1074-1082 doi: 10.1109/JSTSP.2011.2112332
[17]	Li X H, Lu H C, Zhang L H, Ruan X, Yang M H. Saliency detection via dense and sparse reconstruction. In:Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV). Sydney, Australia:IEEE, 2013. 2976-2983 https://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Li_Saliency_Detection_via_2013_ICCV_paper.pdf
[18]	Yuan X T, Liu X B, Yan S C. Visual classification with multitask joint sparse representation. IEEE Transactions on Image Processing, 2012, 21(10):4349-4360 doi: 10.1109/TIP.2012.2205006
[19]	Wright J, Ma Y, Mairal J, Sapiro G, Huang T S, Yan S C. Sparse representation for computer vision and pattern recognition. Proceedings of the IEEE, 2010, 98(6):1031-1044 doi: 10.1109/JPROC.2010.2044470
[20]	Mei X, Ling H B. Robust visual tracking using l₁ minimization. In:Proceedings of the 12th IEEE International Conference on Computer Vision (ICCV). Kyoto, Japan:IEEE, 2009. 1436-1443 http://www.doc88.com/p-2856613370793.html
[21]	Zhang S P, Yao H X, Sun X, Lu X S. Sparse coding based visual tracking:review and experimental comparison. Pattern Recognition, 2013, 46(7):1772-1788 doi: 10.1016/j.patcog.2012.10.006
[22]	Wu Y, Lim J, Yang M H. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9):1834-1848 doi: 10.1109/TPAMI.2014.2388226
[23]	石光明, 刘丹华, 高大化, 刘哲, 林杰, 王良君.压缩感知理论及其研究进展.电子学报, 2009, 37(5):1070-1081 doi: 10.3321/j.issn:0372-2112.2009.05.028 Shi Guang-Ming, Liu Dan-Hua, Gao Da-Hua, Liu Zhe, Lin Jie, Wang Liang-Jun. Advances in theory and application of compressed sensing. Acta Electronica Sinica, 2009, 37(5):1070-1081 doi: 10.3321/j.issn:0372-2112.2009.05.028
[24]	Mei X, Ling H B. Robust visual tracking and vehicle classification via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11):2259-2272 doi: 10.1109/TPAMI.2011.66
[25]	Peng Y G, Ganesh A, Wright J, Xu W L, Ma Y. RASL:robust alignment by sparse and low-rank decomposition for linearly correlated images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2233-2246 doi: 10.1109/TPAMI.2011.282
[26]	Wu Y, Blasch E, Chen G, Bai L, Ling H B. Multiple source data fusion via sparse representation for robust visual tracking. In:Proceedings of the 14th IEEE International Conference on Information Fusion (FUSION). Barcelona, Spain:IEEE, 2011. 1-8 https://ieeexplore.ieee.org/document/5977451/authors#authors
[27]	Han Z J, Jiao J B, Zhang B C, Ye Q X, Liu J Z. Visual object tracking via sample-based Adaptive Sparse Representation (AdaSR). Pattern Recognition, 2011, 44(9):2170-2183 doi: 10.1016/j.patcog.2011.03.002
[28]	Tzimiropoulos G, Zafeiriou S, Pantic M. Sparse representations of image gradient orientations for visual recognition and tracking. In:Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Colorado Springs, CO, USA:IEEE, 2011. 26-33 https://ieeexplore.ieee.org/document/5981809
[29]	Wang Q, Chen F, Yang J M, Xu W L, Yang M H. Transferring visual prior for online object tracking. IEEE Transactions on Image Processing, 2012, 21(7):3296-3305 doi: 10.1109/TIP.2012.2190085
[30]	Zhang T Z, Jia K, Xu C S, Ma Y, Ahuja N. Partial occlusion handling for visual tracking via robust part matching. In:Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, Ohio, USA:IEEE, 2014. 1258-1265 http://nlpr-web.ia.ac.cn/mmc/homepage/tzzhang/opmt.html
[31]	Hong Z B, Mei X, Prokhorov D, Tao D C. Tracking via robust multi-task multi-view joint sparse representation. In:Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV). Sydney, NSW, Australia:IEEE, 2013. 649-656 https://ieeexplore.ieee.org/document/6751190/
[32]	Zhang X Q, Li W, Hu W M, Ling H B, Maybank S. Block covariance based l₁ tracker with a subtle template dictionary. Pattern Recognition, 2013, 46(7):1750-1761 doi: 10.1016/j.patcog.2012.08.015
[33]	Hu W M, Li W, Zhang X Q, Maybank S. Single and multiple object tracking using a multi-feature joint sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(4):816-833 doi: 10.1109/TPAMI.2014.2353628
[34]	Mei X, Ling H B, Wu Y, Blasch E P, Bai L. Efficient minimum error bounded particle resampling L1 tracker with occlusion detection. IEEE Transactions on Image Processing, 2013, 22(7):2661-2675 doi: 10.1109/TIP.2013.2255301
[35]	Bao C L, Wu Y, Ling H B, Ji H. Real time robust L1 tracker using accelerated proximal gradient approach. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, Rhode Island, USA:IEEE, 2012. 1830-1837 https://wenku.baidu.com/view/b03cc272fe4733687e21aa65.html
[36]	Chen F, Wang Q, Wang S, Zhang W D, Xu W L. Object tracking via appearance modeling and sparse representation. Image and Vision Computing, 2011, 29(11):787-796 doi: 10.1016/j.imavis.2011.08.006
[37]	Bai T X, Li Y F. Robust visual tracking with structured sparse representation appearance model. Pattern Recognition, 2012, 45(6):2390-2404 doi: 10.1016/j.patcog.2011.12.004
[38]	Liu B Y, Yang L, Huang J Z, Meer P, Gong L G, Kulikowski C. Robust and fast collaborative tracking with two stage sparse optimization. In:Proceedings of the 11th European Conference on Computer Vision (ECCV). Crete, Greece:Springer, 2010. 624-637 doi: 10.1007%2F978-3-642-15561-1_45
[39]	Jia X, Lu H C, Yang M H. Visual tracking via adaptive structural local sparse appearance model. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, Rhode Island, USA:IEEE, 2012. 1822-1829 https://ieeexplore.ieee.org/document/6247880
[40]	Jia X, Lu H C, Yang M H. Visual tracking via coarse and fine structural local sparse appearance models. IEEE Transactions on Image Processing, 2016, 25(10):4555-4564 doi: 10.1109/TIP.2016.2592701
[41]	Zhong W, Lu H C, Yang M H. Robust object tracking via sparsity-based collaborative model. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, Rhode Island, USA:IEEE, 2012. 1838-1845 http://faculty.ucmerced.edu/mhyang/papers/cvpr12b.pdf
[42]	Zhong W, Lu H C, Yang M H. Robust object tracking via sparse collaborative appearance model. IEEE Transactions on Image Processing, 2014, 23(5):2356-2368 doi: 10.1109/TIP.2014.2313227
[43]	Li H X, Shen C H, Shi Q F. Real-time visual tracking using compressive sensing. In:Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO, USA:IEEE, 2011. 1305-1312 https://ieeexplore.ieee.org/document/5995483
[44]	Zhuang B H, Lu H C, Xiao Z Y, Wang D. Visual tracking via discriminative sparse similarity map. IEEE Transactions on Image Processing, 2014, 23(4):1872-1881 doi: 10.1109/TIP.2014.2308414
[45]	Wang D, Lu H C, Bo C J. Online visual tracking via two view sparse representation. IEEE Signal Processing Letters, 2014, 21(9):1031-1034 doi: 10.1109/LSP.2014.2322389
[46]	Lee H, Battle A, Raina R, Ng A Y. Efficient sparse coding algorithms. In:Proceedings of the 19th International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada:ACM, 2006. 801-808 https://papers.nips.cc/paper/2979-efficient-sparse-coding-algorithms.pdf
[47]	Yang A Y, Sastry S S, Ganesh A, Ma Y. Fast $\ell$₁-minimization algorithms and an application in robust face recognition:a review. In:Proceedings of the 17th IEEE International Conference on Image Processing (ICIP). Hong Kong, China:IEEE, 2010. 1849-1852 https://www2.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-13.html
[48]	胡正平, 李静.基于低秩子空间恢复的联合稀疏表示人脸识别算法.电子学报, 2013, 41(5):987-991 doi: 10.3969/j.issn.0372-2112.2013.05.024 Hu Zheng-Ping, Li Jing. Face recognition of joint sparse representation based on low-rank subspace recovery. Acta Electronica Sinica, 2013, 41(5):987-991 doi: 10.3969/j.issn.0372-2112.2013.05.024
[49]	Kim S J, Koh K, Lustig M, Boyd S, Gorinevsky D. An interior-point method for large-scale $\ell$₁-regularized least squares. IEEE Journal of Selected Topics in Signal Processing, 2007, 1(4):606-617 doi: 10.1109/JSTSP.2007.910971
[50]	Yan J C, Tong M L. Weighted sparse coding residual minimization for visual tracking. In:Proceedings of the 2011 IEEE International Conference on Visual Communications and Image Processing (VCIP). Tainan, China:IEEE, 2011. 1-4 https://ieeexplore.ieee.org/document/6115919
[51]	Wang D, Lu H C, Yang M H. Online object tracking with sparse prototypes. IEEE Transactions on Image Processing, 2013, 22(1):314-325 doi: 10.1109/TIP.2012.2202677
[52]	Pan J S, Lim J W, Su Z X, Yang M H. L₀-regularized object representation for visual tracking. In:Proceedings of the 2014 British Machine Vision Conference (BMVC). Nottingham, England:BMVA Press, 2014. 1-12 http://www.bmva.org/bmvc/2014/papers/paper077/index.html
[53]	Shen Z W, Toh K C, Yun S. An accelerated proximal gradient algorithm for frame-based image restoration via the balanced approach. SIAM Journal on Imaging Sciences, 2011, 4(2):573-596 doi: 10.1137/090779437
[54]	Lu X Q, Yuan Y, Yan P K. Robust visual tracking with discriminative sparse learning. Pattern Recognition, 2013, 46(7):1762-1771 doi: 10.1016/j.patcog.2012.11.016
[55]	Zhang T Z, Ghanem B, Xu C S, Ahuja N. Object tracking by occlusion detection via structured sparse learning. In:Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Portland, Oregon, USA:IEEE, 2013. 1033-1040
[56]	Zhang T Z, Ghanem B, Liu S, Ahuja N. Robust visual tracking via multi-task sparse learning. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, Rhode Island, USA:IEEE, 2012. 2042-2049 https://ieeexplore.ieee.org/document/6247908
[57]	Zhang T Z, Ghanem B, Liu S, Ahuja N. Robust visual tracking via structured multi-task sparse learning. International Journal of Computer Vision, 2013, 101(2):367-383 doi: 10.1007/s11263-012-0582-z
[58]	Chen X, Pan W K, Kwok J T, Carbonell J G. Accelerated gradient method for multi-task sparse learning problem. In:Proceedings of the 9th IEEE International Conference on Data Mining. Miami, FL, USA:IEEE, 2009. 746-751
[59]	Bai Y C, Tang M. Object tracking via robust multitask sparse representation. IEEE Signal Processing Letters, 2014, 21(8):909-913 doi: 10.1109/LSP.2014.2320291
[60]	Hu H W, Ma B, Jia Y D. Multi-task l₀ gradient minimization for visual tracking. Neurocomputing, 2015, 154:41-49 doi: 10.1016/j.neucom.2014.12.021
[61]	Liu B Y, Huang J Z, Yang L, Kulikowsk C. Robust tracking using local sparse appearance model and k-selection. In:Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO, USA:IEEE, 2011. 1313-1320 https://ieeexplore.ieee.org/document/5995730
[62]	Liu B Y, Huang J Z, Kulikowski C, Yang L. Robust visual tracking using local sparse appearance model and K-selection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12):2968-2981 doi: 10.1109/TPAMI.2012.215
[63]	Wang Q, Chen F, Xu W L, Yang M H. Online discriminative object tracking with local sparse representation. In:Proceedings of the 2012 IEEE Workshop on the Applications of Computer Vision (WACV). Breckenridge, Colorado, USA:IEEE, 2012. 425-432 https://ieeexplore.ieee.org/document/6162999
[64]	Zhang T Z, Ghanem B, Liu S, Ahuja N. Low-rank sparse learning for robust visual tracking. In:Proceedings of the 12th European Conference on Computer Vision (ECCV). Firenze, Italy:Springer, 2012. 470-484 doi: 10.1007/978-3-642-33783-3_34
[65]	Zhang T Z, Liu S, Ahuja N, Yang M H, Ghanem B. Robust visual tracking via consistent low-rank sparse learning. International Journal of Computer Vision, 2015, 111(2):171-190 doi: 10.1007/s11263-014-0738-0
[66]	Zou H, Hastie T. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society:Series B (Statistical Methodology), 2005, 67(2):301-320 doi: 10.1111/rssb.2005.67.issue-2
[67]	向馗, 李炳南.主元分析中的稀疏性.电子学报, 2012, 40(12):2525-2532 http://d.old.wanfangdata.com.cn/Periodical/dianzixb201212027 Xiang Kui, Li Bing-Nan. Sparsity in principal component analysis:a survey. Acta Electronica Sinica, 2012, 40(12):2525-2532 http://d.old.wanfangdata.com.cn/Periodical/dianzixb201212027
[68]	付光辉. 高维的强相关数据的模型选择[博士论文]. 中南大学, 2011. http://cdmd.cnki.com.cn/Article/CDMD-10533-1011177901.htm Fu G H. Model selection for analysizing high-dimensional, strongly correlated data [Ph.D. dissertation], Central South University, China, 2011. http://cdmd.cnki.com.cn/Article/CDMD-10533-1011177901.htm
[69]	Ross D A, Lim J, Lin R S, Yang M H. Incremental learning for robust visual tracking. International Journal of Computer Vision, 2008, 77(1-3):125-141 doi: 10.1007/s11263-007-0075-7
[70]	Zarezade A, Rabiee H R, Soltani-Farani A, Khajenezhad A. Patchwise joint sparse tracking with occlusion detection. IEEE Transactions on Image Processing, 2014, 23(10):4496-4510 doi: 10.1109/TIP.2014.2346029
[71]	Huang H T, Bi D Y, Zha Y F, Ma S P, Gao S, Liu C. Robust visual tracking based on product sparse coding. Pattern Recognition Letters, 2015, 56:52-59 doi: 10.1016/j.patrec.2015.01.014
[72]	K Koh, S Kim, S Boyd. l1_ls:Simple Matlab Solver for l1-regularized Least Squares Problems [Online], available:https://web.stanford.edu/~boyd/software.html, October 8, 2018.
[73]	Kristan M, Pflugfelder R, Leonardis A, Matas J, Porikli F, Čehovin L, et al. The visual object tracking VOT2013 challenge results. In:Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops (ICCVW). Sydney, Australia:IEEE, 2013. 98-111
[74]	Song S R, Xiao J X. Tracking revisited using RGBD camera:unified benchmark and baselines. In:Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV). Sydney, Australia:IEEE, 2013. 233-240 https://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Song_Tracking_Revisited_Using_2013_ICCV_paper.pdf
[75]	Smeulders A W M, Chu D M, Cucchiara R, Calderara S, Dehghan A, Shah M. Visual tracking:an experimental survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(7):1442-1468 doi: 10.1109/TPAMI.2013.230
[76]	Li A N, Lin M, Wu Y, Yang M H, Yan S C. NUS-PRO:a new visual tracking challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2):335-349 doi: 10.1109/TPAMI.2015.2417577
[77]	Kristan M, Pflugfelder R, Leonardis A, Matas J, Čehovin L, Nebehay G, Vojíř T, Fernández G, Lukežič A, Dimitriev A, Petrosino A, Saffari A, Li B, Chan C S, Heng C, Ward D, Kearney D, Monekosso D, Karaimer H C, Rabiee H R, Zhu J K, Gao J, Xiao J J, Zhang J G, Xing J L, Huang K Q, Lebeda K, Cao L J, Maresca M E, Lim M K, El Helw M, Felsberg M, Remagnino P, Bowden R, Goecke R, Stolkin R, Lim S Y, Maher S, Poullot S, Wong S, Satoh S, Chen W H, Hu W M, Zhang X Q, Li Y, Niu Z H. The visual object tracking VOT2014 challenge results. In:Proceedings of the 13th European Conference on Computer Vision Workshops (ECCVW). Zurich, Switzerland:Springer, 2014. 191-217 http://votchallenge.net/vot2014/download/vot_2014_paper.pdf
[78]	Cehovin L, Kristan M, Leonardis A. Is my new tracker really better than yours? In:Proceedings of the 2014 IEEE Winter Conference on Applications of Computer Vision (WACV). Steamboat Springs, Colorado, USA:IEEE, 2014. 540-547 https://www.researchgate.net/profile/Luka_Cehovin/publication/269299898_Is_my_new_tracker_really_better_than_yours/links/5506b4960cf24cee3a05e45f.pdf?inViewer=0&origin=publication_detail&pdfJsDownload=0
[79]	Pang Y, Ling H B. Finding the best from the second bests-inhibiting subjective bias in evaluation of visual tracking algorithms. In:Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV). Sydney, Australia:IEEE, 2013. 2784-2791 https://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Pang_Finding_the_Best_2013_ICCV_paper.pdf
[80]	SanMiguel J C, Cavallaro A, Martínez J M. Adaptive online performance evaluation of video trackers. IEEE Transactions on Image Processing, 2012, 21(5):2812-2823 doi: 10.1109/TIP.2011.2182520
[81]	Everingham M, Van Gool L, Williams C K I, Winn J, Zisserman A. The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 2010, 88(2):303-338 doi: 10.1007/s11263-009-0275-4
[82]	Nam H, Han B. Learning multi-domain convolutional neural networks for visual tracking. In:Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, Nevada, USA:IEEE, 2016. 4293-4302 https://arxiv.org/pdf/1510.07945.pdf
[83]	Ning J F, Yang J M, Jiang S J, Zhang L, Yang M H. Object tracking via dual linear structured SVM and explicit feature map. In:Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, Nevada, USA:IEEE, 2016. 4266-4274 https://eng.ucmerced.edu/people/jyang44/papers/cvpr16_tracking.pdf
[84]	Valmadre J, Bertinetto L, Henriques J F, Vedaldi A, Torr P H S. End-to-end representation learning for correlation filter based tracking. arXiv:1704.06036, 2017. http://openaccess.thecvf.com/content_cvpr_2017/papers/Valmadre_End-To-End_Representation_Learning_CVPR_2017_paper.pdf
[85]	Zhang T Z, Liu S, Xu C S, Yan S C, Ghanem B, Ahuja N, Yang M H. Structural sparse tracking. In:Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, Massachusetts, USA:IEEE, 2015. 150-158
[86]	荆楠, 毕卫红, 胡正平, 王林.动态压缩感知综述.自动化学报, 2015, 41(1):22-37 http://www.aas.net.cn/CN/abstract/abstract18580.shtml Jing Nan, Bi Wei-Hong, Hu Zheng-Ping, Wang Lin. A survey on dynamic compressed sensing. Acta Automatica Sinica, 2015, 41(1):22-37 http://www.aas.net.cn/CN/abstract/abstract18580.shtml
[87]	Zhang T Z, Bibi A, Ghanem B. In defense of sparse tracking:circulant sparse tracker. In:Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, Nevada, USA:IEEE, 2016. 3880-3888 https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhang_In_Defense_of_CVPR_2016_paper.pdf
[88]	Bibi A, Itani H, Ghanem B. FFTLasso:large-scale LASSO in the Fourier domain. In:Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, Hawaii, USA:IEEE, 2017. 3820-3829 https://ivul.kaust.edu.sa/Documents/Publications/2017/FFTLasso%20Large-Scale%20LASSO%20in%20the%20Fourier%20Domain.pdf