基于稀疏正则约束的子空间视觉跟踪

陈典兵; 王慧利; 杨航

doi:10.3788/OPE.20182604.0989

您当前的位置：

首页 >

文章列表页 >

基于稀疏正则约束的子空间视觉跟踪

信息科学 | 更新时间：2020-07-05

- 基于稀疏正则约束的子空间视觉跟踪
- Visual tracking algorithm based on the sparse-regularized subspace
- 光学精密工程 2018年26卷第4期页码：989-997
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 长春 130033
  2.中国科学院大学, 北京 100039
- 作者简介：
  
  [ "陈典兵(1990-), 男, 吉林长春人, 博士研究生, 2012年于吉林大学获得学士学位, 主要从数字图像处理、稀疏表示、目标跟踪方面的研究。E-mail: chendianbing1934@163.com" ]
- 基金信息：
  
  国家自然科学基金资助项目(61401425)
- DOI：10.3788/OPE.20182604.0989
  中图分类号： TP391.41
- 收稿日期：2017-04-21，
  
  录用日期：2017-5-12，
  
  纸质出版日期：2018-04-25
- 稿件说明：
移动端阅览
陈典兵, 王慧利, 杨航. 基于稀疏正则约束的子空间视觉跟踪[J]. 光学精密工程, 2018,26(4):989-997.

Dian-bing CHEN, Hui-li WANG, Hang YANG. Visual tracking algorithm based on the sparse-regularized subspace[J]. Optics and precision engineering, 2018, 26(4): 989-997.
陈典兵, 王慧利, 杨航. 基于稀疏正则约束的子空间视觉跟踪[J]. 光学精密工程, 2018,26(4):989-997. DOI： 10.3788/OPE.20182604.0989.

Dian-bing CHEN, Hui-li WANG, Hang YANG. Visual tracking algorithm based on the sparse-regularized subspace[J]. Optics and precision engineering, 2018, 26(4): 989-997. DOI： 10.3788/OPE.20182604.0989.

摘要

针对子空间表示跟踪算法处理遮挡问题的能力不足，以及稀疏表示跟踪算法无法满足跟踪实时性要求等问题，本文提出一种稀疏正则约束的子空间视觉跟踪算法。该算法结合了子空间表示与稀疏表示的优势，提升了对于遮挡问题的处理能力，并且降低了算法的计算复杂度。首先，该算法利用PCA子空间基向量集、子空间均值以及表示残差对目标进行表示，同时算法采用

范数作为表示系数以及表示残差的稀疏约束函数。其次，算法采用了一种分步循环迭代的方法求解表示模型的系数与残差。然后，为了保证子空间基向量与空间均值能够持续准确的描述目标在跟踪过程中出现的变化，算法根据经过开运算处理后的表示残差中非零元素的不同比率构建不同的更新模板，并结合增量主成分分析方法在线学习新的基向量与均值。最后，在实验部分，本文将提出算法在10个实验序列上的跟踪结果与8个现今主流跟踪算法进行对比，同时从定性与定量两个方面对实验结果进行分析。本文算法在全部10个实验序列上的平均中心误差为5.3 pixel，平均覆盖率为77%，相比于其他算法，本文算法取得了较高的跟踪精度。本文算法具有更好的鲁棒性，并且满足更多场景下的跟踪需求。

Abstract

Aiming at the problem that the subspace representation tracking algorithm cannot deal with the occlusion problem effectively and the sparse representation tracking algorithm cannot meet the real-time requirements of the tracking

this paper proposed a sparse-regularized subspace visual tracking algorithm. The algorithm combined the advantages of subspace representation and sparse representation

improved the processing ability of the occlusion problem

and reduced the computational complexity. Firstly

the algorithm adopted the PCA subspace basis

the subspace mean and the representation residual to represent the target

and used the L

norm as the regularization of the representation coefficient and the representation residual. Secondly

the algorithm applied an iteration method to compute the coefficients and the residual

then constructed different update templates according to different non-zero ratio of the residual which was preprocessed by opening operator

and employed the incremental principal component analysis method to learn new PCA subspace basis and PCA subspace mean. Through this way

the algorithm enforced the subspace basis and the subspace mean to describe the variation of the target continuously and accurately during tracking progress. Finally

experimental results on qualitative and quantitative aspects analysis showed that average center location error of the proposed algorithm was 5.3 pixels in all 10 experimental sequences

and average overlap rate was 77%. Compared with eight state-of-art algorithms

the proposed algorithm obtains a more precise result and has better robustness and can meet tracking requirements in more situations.

关键词

Keywords

references

王春平, 王暐, 刘江义, 等.基于色度饱和度-角度梯度直方图特征的尺度自适应核相关滤波跟踪[J].光学精密工程, 2016, 24(9):2293-2301.

WANG CH P, WANG W, LIU J Y, et al.. Scale adaptive kernelized correlation filter tracking based on HHS-OG feature[J]. Opt. Precision Eng., 2016, 24(9):2293-2301. (in Chinese)

王暐, 王春平, 李军, 等.特征融合和模型自适应更新相结合的相关滤波目标跟踪[J].光学精密工程, 2016, 24(8):2059-2066.

WANG W, WANG CH P, LI J, et al.. Correlation filter tracking based on feature fusing and model adaptive updating[J]. Opt. Precision Eng., 2016, 24(8):2059-2066. (in Chinese)

毛建森, 屈玉福.基于压缩感知的变尺度目标跟踪技术[J].液晶与显示, 2016, 31(5):497-505.

MAO J S, QU Y F. Tracking of variable scale object based on compressive sensing[J]. Chinese Journal of Liquid Crystals and Displays, 2016, 31(5):497-505. (in Chinese)

孙保基, 张葆, 宋策, 等.基于角点增强改进的TLD目标跟踪算法[J].液晶与显示, 2016, 31(9):921-928.

SUN B J, ZHANG B, SONG C, et al.. Improved TLD object tracking algorithm based on corner reinforced[J]. Chinese Journal of Liquid Crystals and Displays, 2016, 31(9):921-928.(in Chinese)

ROSS D A, 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.

LIU R SH, BAI SH SH, SU ZH X, et al.. Robust visual tracking via L0 regularized local low-rank feature learning[J]. Journal of Electronic Imaging, 2015, 24(3):033012.

WRIGHT J, YANG A Y, GANESH A, et al.. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227.

唐中奇, 付光远, 陈进, 等.基于多尺度分割的高光谱图像稀疏表示与分类[J].光学精密工程, 2015, 23(9):2708-2714.

TANG ZH Q, FU G Y, CHEN J, et al.. Multiscale segmentation-based sparse coding for hyperspectral image classification[J]. Opt. Precision Eng., 2015, 23(9):2708-2714. (in Chinese)

隋中山, 李俊山, 张姣, 等.张量低秩表示和时空稀疏分解的视频前景检测[J].光学精密工程, 2017, 25(2):529-536.

SUI ZH SH, LI J SH, ZHANG J, et al.. Video foreground detection of tensor low-rank representation and spatial-temporal sparsity decomposition[J]. Opt. Precision Eng., 2017, 25(2):529-536. (in Chinese)

MEI X, LING H B. Robust visual tracking using l 1 minimization[C]. Proceedings of the 12 th International Conference on Computer Vision , IEEE , 2009: 1436-1443.

MEI X, LING H B, WU Y, et al. . Minimum error bounded efficient l 1 tracker with occlusion detection[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition , IEEE , 2011: 1257-1264.

BAO C L, WU Y, LING H B, et al. . Real time robust L1 tracker using accelerated proximal gradient approach[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition , IEEE , 2012: 1830-1837.

XIAO Z Y, LU H CH, WANG D. L2-RLS-based object tracking[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(8):1301-1309.

WANG D, LU H CH, YANG M H. Least soft-threshold squares tracking[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition , IEEE , 2013: 2371-2378.

XING J L, GAO J, LI B, et al. . Robust object tracking with online multi-lifespan dictionary learning[C]. Proceedings of IEEE International Conference on Computer Vision , IEEE , 2013: 665-672.

BAI T X, LI Y F. Robust visual tracking with structured sparse representation appearance model[J]. Pattern Recognition, 2012, 45(6):2390-2404.

KUMAR B K S, SWAMY M N S, AHMAD M O. Weighted residual minimization in PCA subspace for visual tracking[C]. Proceedings of IEEE International Symposium on Circuits and Systems , IEEE , 2016: 986-989.

WANG D, LU H CH. Object Tracking via 2DPCA and l 1 -regularization[J]. IEEE Signal Processing Letters, 2012, 19(11):711-714.

ZHANG T ZH, GHANEM B, LIU S, et al. . Robust visual tracking via multi-task sparse learning[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition , 2012: 2042-2049.

ZHONG W, LU H CH, YANG M H. Robust object tracking via sparse collaborative appearance model[J]. IEEE Transactions on Image Processing, 2014, 23(5):2356-2368.

KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7):1409-1422.

BABENKO B, YANG M H, BELONGIE S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(8):1619-1632.

ZHANG K H, ZHANG L, YANG M H. Real-time compressive tracking[C]. Proceedings of the 12 th European Conference on Computer Vision , Springer , 2012: 864-877.

HENRIQUES J F, CASEIRO R, MARTINS P, et al. . Exploiting the circulant structure of tracking-by-detection with kernels[C]. Proceedings of the 12 th European Conference on Computer Vision , Springer , 2012: 702-715.

EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al.. The Pascal visual object classes (VOC) challenge[J]. International Journal of Computer Vision, 2010, 88(2):303-338.

浏览量

281

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于跨尺度字典学习的图像盲解卷积算法

改进的稀疏表示遥感图像超分辨重建

基于场景辅助特征的T-S目标跟踪

自适应交互式融合的视觉跟踪

稀疏表示下的噪声图像超分辨率重构