在线鲁棒判别式字典学习视觉跟踪

doi:10.3969/j.issn.0372-2112.2016.04.012

电子学报 ›› 2016, Vol. 44 ›› Issue (4): 838-845.DOI: 10.3969/j.issn.0372-2112.2016.04.012

在线鲁棒判别式字典学习视觉跟踪

薛模根¹, 朱虹¹, 袁广林²

1. 陆军军官学院偏振光成像探测技术安徽省重点实验室, 安徽合肥 230031;
2. 陆军军官学院十一系, 安徽合肥 230031

收稿日期:2014-09-16 修回日期:2015-01-20 出版日期:2016-04-25 发布日期:2016-04-25
作者简介:薛模根 男,1964年10月出生于安徽合肥.博士,教授,合肥工业大学博士生导师.主要研究方向为图像处理、计算机视觉、光电防御等. E-mail:xuemogen@126.com;朱虹 女,1987年10月出生于新疆乌鲁木齐.现为陆军军官学院硕士研究生.主要研究方向为图像处理、计算机视觉等. E-mail:729039126@qq.com
基金资助:
国家自然科学基金(No.61175035,No.61379105);中国博士后科学基金(No.2014M562535);安徽省自然科学基金(No.1508085QF114)

Online Robust Discrimination Dictionary Learning for Visual Tracking

XUE Mo-gen¹, ZHU Hong¹, YUAN Guang-lin²

1. Anhui Province Key Laboratory of Polarization Imaging Detection Technology, Army Officer Academy of PLA, Hefei, Anhui 230031, China; (;
2. Eleventh Department, Army Officer Academy of PLA, Hefei, Anhui 230031, China

Received:2014-09-16 Revised:2015-01-20 Online:2016-04-25 Published:2016-04-25

摘要/Abstract

摘要：

传统子空间跟踪较好解决了目标表观变化和遮挡问题,但其仍存在对复杂背景下目标跟踪鲁棒性不足和模型漂移等问题.针对这两个问题,本文首先通过增大背景样本的重构误差和利用L1范数损失函数建立一种在线鲁棒判别式字典学习模型;其次,利用块坐标下降设计了该模型的在线学习算法用于视觉跟踪模板更新;最后,以粒子滤波为框架,结合提出的模板更新方法实现了鲁棒的视觉跟踪.实验结果表明:与IVT(Incremental Visual Tracking)、L1APG(L1-tracker using Accelerated Proximal Gradient)、ONNDL(Online Non-Negative Dictionary Learning)和PCOM(Probability Continuous Outlier Model)等典型跟踪方法相比,本文方法具有较强的鲁棒性和较高的跟踪精度.

关键词: 视觉跟踪, 模板更新, 字典学习, 粒子滤波

Abstract:

The traditional subspaces based visual trackers well solved appearance changes and occlusions.However,they were weakly robust for complex background and prone to model drifting.To deal with these two problems,this paper enlarges reconstruction errors of the background samples and uses L1-norm loss function to establish an online robust discrimination dictionary learning model.Then an online robust discrimination dictionary learning algorithm for template updating in visual tracking is designed via the block coordinate descent (BCD).Finally,robust visual tracking is achieved with the proposed template updating method in particle filter framework.The experimental results show that the proposed method has better performance in robustness and accuracy than the state-of-the-art trackers such as IVT(Incremental Visual Tracking),L1APG(L1-tracker using Accelerated Proximal Gradient),ONNDL(Online Non-Negative Dictionary Learning) and PCOM(Probability Continuous Outlier Model).

Key words: visual tracking, template updating, dictionary learning, particle filter

中图分类号:

TP391.4

薛模根, 朱虹, 袁广林. 在线鲁棒判别式字典学习视觉跟踪[J]. 电子学报, 2016, 44(4): 838-845.

XUE Mo-gen, ZHU Hong, YUAN Guang-lin. Online Robust Discrimination Dictionary Learning for Visual Tracking[J]. Acta Electronica Sinica, 2016, 44(4): 838-845.

参考文献

[1] Li Xi,Hu Wei-ming,Shen Chun-hua,et al.A survey of appearance models in visual object tracking[J].ACM Transactions on Intelligent Systems and Technology,2013,4(4):58(1)-58(48).
[2] Black M J,Jepson A D.Eigentracking:Robust matching and tracking of articulated objects using a view-based representation[A].European Conference on Computer Vision[C].London:Springer-Verlag Berlin,1996.329-342.
[3] Ross D,Lim J,Lin R S,et al.Incremental learning for robust visual tracking[J].International Journal of Computer Vision,2008,77(1-3):125-141.
[4] Mei Xue,Ling Hai-bin,Wu Yi,et al.Minimum error bounded efficient L1 tracker with occlusion detection[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Colorado:Springer-Verlag Berlin,2011.1257-1264.
[5] Bao Cheng-long,Wu Yi,Ling Hai-bin,et al.Real time robust L1 tracker using accelerated proximal gradient approach[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Providence:IEEE Computer Society Press,2012.1830-1837.
[6] Xing Jun-liang,Gao Jin,Li Bing,et al.Robust object tracking with online multi-lifespan dictionary learning[A].IEEE International Conference on Computer Vision[C].Sydney:IEEE Computer Society Press,2013.665-672.
[7] Wang Nai-yan,Wang Jing-dong,Yeung D.Online robust non-negative dictionary learning for visual tracking[A].IEEE International Conference on Computer Vision[C].Sydney:IEEE Computer Society Press,2013.657-664.
[8] Wang Dong,Lu Hu-chuan.Visual tracking via probability continuous outlier model[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Columbus:IEEE Computer Society Press,2014.3478-3485.
[9] Wagner A,Wright J,Ganesh A,et al.Towards a practical face recognition system:Robust alignment and illumination by sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):372-386.
[10] Lu Ce-wu,Shi Jian-ping,Jia Jia-ya.Online robust dictionary learning[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Portland:IEEE Computer Society Press,2013.415-422.
[11] Nojun K.Principal component analysis based on L1-norm maximization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(9):1672-1680.
[12] Mairal J,Bach F,Ponce J,et al.Online dictionary learning for sparse coding[A].The 26th International Conference on Machine Learning[C].Montreal:IEEE Computer Society Press,2009.539-547.
[13] Bissantz N,Dmbgen L,Munk A,et al.Convergence analysis of generalized iteratively reweighted least squares algorithms on convex function spaces[J].SIAM Journal on Optimization,2009,19:1828-1845.
[14] Richtarik P,Takac M.Iteration complexity of randomized block-coordinate decent methods for minimizing a composite function[J].Mathematical Programming,2014,144(1-2):1-38.
[15] Wu Yi,Lim J,Yang M.Online object tracking:a benchmark[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Portland:IEEE Computer Society Press,2013.2411-2418.
[16] Babenko B,Yang M H,Belongie S.Robust object tracking with online multiple instance learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632.

在线鲁棒判别式字典学习视觉跟踪

Online Robust Discrimination Dictionary Learning for Visual Tracking

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘晓燕, 陈亮, 焦振航, 卢祥晨. 单基站DTMB信号约束的PDR运动参数修正[J]. 电子学报, 2022, 50(4): 860-868.
[2]	蒋林, 向超, 朱建阳, 刘奇. 加载语义似然估计的粒子滤波重定位[J]. 电子学报, 2021, 49(2): 306-314.
[3]	朱铮宇, 廖丽平, 杨春玲, 王泳, 蔡君, 邱华愉. 基于韵母发音事件匹配与位置时延分析的音唇一致性判决方法[J]. 电子学报, 2021, 49(1): 140-148.
[4]	仇祝令, 查宇飞, 吴敏, 王青. 基于注意力学习的正则化相关滤波跟踪算法[J]. 电子学报, 2020, 48(9): 1762-1768.
[5]	蒲磊, 冯新喜, 侯志强, 余旺盛. 基于二阶池化网络的鲁棒视觉跟踪算法[J]. 电子学报, 2020, 48(8): 1472-1478.
[6]	金泽芬芬, 侯志强, 余旺盛, 王鑫, 寇人可. 基于量子遗传算法的视觉目标跟踪[J]. 电子学报, 2020, 48(8): 1493-1501.
[7]	蒲磊, 冯新喜, 侯志强, 查宇飞, 余旺盛. 基于深度空间正则化的相关滤波跟踪算法[J]. 电子学报, 2020, 48(10): 2025-2032.
[8]	曹晔. 一种基于局部排序的约束稀疏编码的图像分类方法[J]. 电子学报, 2019, 47(4): 832-836.
[9]	夏楠, 王珏, 李博. 基于粒子滤波和交互多模型的移动定位方法[J]. 电子学报, 2019, 47(1): 197-203.
[10]	李亚峰. 一种基于多字典学习的图像分割模糊方法[J]. 电子学报, 2018, 46(7): 1700-1709.
[11]	陈志敏, 吴盘龙, 薄煜明, 田梦楚, 岳聪, 顾福飞. 基于自控蝙蝠算法智能优化粒子滤波的机动目标跟踪方法[J]. 电子学报, 2018, 46(4): 886-894.
[12]	范舜奕, 管桦, 侯志强, 余旺盛, 戴铂. 基于多表观特征子模型更新的鲁棒视觉跟踪[J]. 电子学报, 2018, 46(2): 440-446.
[13]	王延江, 李蕙, 齐玉娟. 一种受人脑三阶段记忆机制启发的鲁棒运动目标跟踪方法[J]. 电子学报, 2017, 45(9): 2065-2070.
[14]	卢锦, 王鑫, 章为川. 基于代价参考粒子滤波的存在概率检测算法[J]. 电子学报, 2017, 45(6): 1498-1505.
[15]	孙巧, 张胜修, 张正新, 曹立佳, 李小锋. 基于加权重叠率的单目标视觉跟踪评价指标[J]. 电子学报, 2017, 45(3): 753-761.