首页 > 论文 > 光学学报 > 39卷 > 4期(pp:415002--1)

基于形变多样相似性的空间正则化相关滤波跟踪

Spatial Regularization Correlation Filtering Tracking via Deformable Diversity Similarity

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出了一个基于形变多样相似性的空间正则化相关滤波跟踪算法。在核相关滤波(KCF)跟踪算法基础上引入了空间正则化权重和子网格检测方法, 利用形变多样相似性匹配算法构建了目标重检测模块, 利用主成分分析(PCA)算法和k维树一致近似最近邻(TreeCANN)算法解决了匹配算法中的最近邻搜索问题; 通过自适应模板更新策略, 解决了遮挡情况下模板误更新问题。实验结果表明, 所提算法的精确度得分为0.825, 成功率得分为0.625, 相比KCF算法分别提升了18.5%和31.0%。所提算法能较好地解决目标尺度变化、遮挡、快速运动、旋转和背景杂乱情况下的跟踪问题, 具有广泛的应用前景。

Abstract

The spatial regularization correlation filtering tracking algorithm based on deformable diversity similarity is proposed. The spatial regularization weight and the sub-grid detection method are introduced on the basis of the kernelized correlation filtering (KCF) tracking algorithm. The target re-detection module is constructed with deformable diversity similarity matching algorithm, the nearest neighbor search problem in the matching algorithm is solved via the principal component analysis (PCA) algorithm and the k-direction tree coherence approximate nearest neighbor (TreeCANN) algorithm. Through the adaptive template updating strategy, the problem of false updating of the template under occlusion is solved. Experimental results show that the precision score and success score of the proposed algorithm are 0.825 and 0.625, which are 18.5% and 31.0% higher than those of the KCF algorithm, respectively. The proposed algorithm can better solve the tracking problems of the target scale variation, occlusion, fast motion, rotation and background clutter, showing a wide range of application prospect.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/aos201939.0415002

所属栏目:机器视觉

基金项目:河北省自然科学基金(F2017202009)

收稿日期:2018-09-20

修改稿日期:2018-10-23

网络出版日期:--

作者单位    点击查看

毛宁:河北工业大学人工智能与数据科学学院, 天津 300130
杨德东:河北工业大学人工智能与数据科学学院, 天津 300130
李勇:河北工业大学人工智能与数据科学学院, 天津 300130
韩亚君:河北工业大学人工智能与数据科学学院, 天津 300130

联系人作者:杨德东(ydd12677@163.com)

【1】Li C, Lu C Y, Zhao X, et al. Scale adaptive correlation filtering tracing algorithm based on feature fusion[J]. Acta Optica Sinica, 2018, 38(5): 0515001.
李聪, 鹿存跃, 赵珣, 等. 特征融合的尺度自适应相关滤波跟踪算法[J]. 光学学报, 2018, 38(5): 0515001.

【2】Gao M F, Zhang X X. Scale adaptive kernel correlation filtering for target tracking[J]. Laser & Optoelectronics Progress, 2018, 55(4): 041501.
高美凤, 张晓玄. 尺度自适应核相关滤波目标跟踪[J]. 激光与光电子学进展, 2018, 55(4): 041501.

【3】Zhang T Z, Ghanem B, Liu S, et al. Robust visual tracking via structured multi-task sparse learning[J]. International Journal of Computer Vision, 2013, 101(2): 367-383.

【4】Mei X, Ling H. Robust visual tracking using l(1) minimization[C]∥Proceedings of International Conference on Computer Vision, 29 Sept-2 Oct, 2009. Kyoto, Japan. New York: IEEE, 2009: 1436-1443.

【5】Kalal Z, Mikolajczyk K, Matas J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422.

【6】Zhong W, Lu H C, Yang M H. Robust object tracking via sparsity-based collaborative model[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 16-21 June, 2012. Providence, RI, USA. New York: IEEE, 2012: 1838-1845.

【7】Henriques J F, Caseiro R, Martins P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[M]∥Henriques J F, Caseiro R, Martins P, et al. eds. Computer Vision-ECCV 2012. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012: 702-715.

【8】Danelljan M, Hger G, Khan F, et al. Accurate scale estimation for robust visual tracking[M]∥Valstar M, French A, Pridmore T. Proceedings of British Machine Vision Conference. Nottingham: BMVA Press, 2014: 65. 1-65. 11.

【9】Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596.

【10】Danelljan M, Hger G, Khan F S, et al. Learning spatially regularized correlation filters for visual tracking[C]∥Proceedings of IEEE International Conference on Computer Vision, 7-13 Dec , 2015. Santiago, Chile. New York: IEEE, 2015: 4310-4318.

【11】Talmi I, Mechrez R, Zelnik-Manor L. Template matching with deformable diversity similarity[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 21-26 July, 2017. Honolulu, HI, USA. New York: IEEE, 2017: 1311-1319.

【12】Wu Y, Lim J, Yang M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834-1848.

【13】Wold S, Esbensen K, Geladi P. Principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1987, 2(1/2/3): 37-52.

【14】Olonetsky I, Avidan S. TreeCANN: k-d tree coherence approximate nearest neighbor algorithm[M]∥Olonetsky I, Avidan S. eds. Computer Vision-ECCV 2012. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012: 602-615.

【15】Yang D D, Mao N, Yang F C, et al. Improved SRDCF object tracking via the best-buddies similarity[J]. Optics and Precision Engineering, 2018, 26(2): 492-502.
杨德东, 毛宁, 杨福才, 等. 利用最佳伙伴相似性的改进空间正则化判别相关滤波目标跟踪[J]. 光学 精密工程, 2018, 26(2): 492-502.

【16】Zhang J M, Ma S G, Sclaroff S. MEEM: robust tracking via multiple experts using entropy minimization[M]∥Zhang J M, Ma S G, Sclaroff S. eds. Computer Vision-ECCV 2014, Part III. Cham: Springer International Publishing, 2014: 188-203.

【17】Bertinetto L, Valmadre J, Golodetz S, et al. Staple: complementary learners for real-time tracking[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 27-30 June, 2016. Las Vegas, NV, USA. New York: IEEE, 2016: 1401-1409.

【18】Wang Q, Gao J, Xing J, et al. DCFNet: discriminant correlation filters network for visual tracking[EB/OL]. [2018-09-03]. https: ∥arxiv.org/pdf/1704.04057v1.pdf.

【19】Gao J, Ling H B, Hu W M, et al. Transfer learning based visual tracking with Gaussian processes regression[M]∥Gao J, Ling H B, Hu W M, et al. eds. Computer Vision-ECCV 2014, Part VI. Cham: Springer International Publishing, 2014: 188-203.

【20】Hong Z B, Chen Z, Wang C H, et al. Multi-store tracker (MUSTer): a cognitive psychology inspired approach to object tracking[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 7-12 June, 2015. Boston, MA, USA. New York: IEEE, 2015: 749-758.

【21】Bertinetto L, Valmadre J, Henriques J F, et al. Fully-convolutional siamese networks for object tracking[M]∥Bertinetto L, Valmadre J, Henriques J F, et al. eds. Lecture notes in computer science. Cham: Springer International Publishing, 2016: 850-865.

引用该论文

Mao Ning,Yang Dedong,Li Yong,Han Yajun. Spatial Regularization Correlation Filtering Tracking via Deformable Diversity Similarity[J]. Acta Optica Sinica, 2019, 39(4): 0415002

毛宁,杨德东,李勇,韩亚君. 基于形变多样相似性的空间正则化相关滤波跟踪[J]. 光学学报, 2019, 39(4): 0415002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF