Abstract
The sparse representation-based trackers has attracted much attention in the research community due to its superior performance in spite of its computational complexity. But the assumption that the coding residual follows either the Gaussian or the Laplacian distribution may not accurately describe the coding residual in practical visual tracking scenarios. To deal with such issues as well as to improve the performance of the visual tracking, a novel generative tracker is proposed in a Bayesian inference framework by introducing robust coding (RC) into the PCA reconstruction. Also, it is proposed to collaborate the global and local PCA subspace appearance models to enhance the tracking performance. Further, a robust RC distance is proposed to differentiate the candidate samples from the subspace, and a novel observation likelihood is defined based on both global and local RC distances. In addition, a robust occlusion map generation and a novel appearance model update mechanism are proposed. The quantitative and qualitative performance evaluations on the OTB-50 and VOT2016 dataset demonstrate that the proposed method performs favorably against several methods based on particle filter framework.
Similar content being viewed by others
Notes
There are 18 and 14 sequences with more than 500 frames, and 7 and 2 sequences with more than 1000 frames in OTB-50 and VOT2016 datasets, respectively.
In this work, 2 × 2 cells and gradient orientations of 5 are used to extract the HOG feature and the local patch size of 4 × 4 pixels are considered for local model.
References
Adam A, Rivlin E, Shimshoni I (2006) Robust fragments-based tracking using the integral histogram. In: Proc. of the IEEE conf. on comput. vision and pattern recogn. (CVPR), pp 798–805
Babenko B, Yang M, Belongie S (2009) Visual tracking with online multiple instance learning. In: Proc. of the IEEE conf on comput vision and pattern recogn (CVPR), pp 983–990
Black J, Ellis T, Rosin P, et al (2003) A novel method for video tracking performance evaluation. In: Proc. of the first joint IEEE int workshop on visual surveillance and performance evaluation of tracking and surveillance (VS-PETS-03, pp 125–132
Black MJ, Jepson AD (1998) Eigentracking: robust matching and tracking of articulated objects using a view-based representation. Int J Comput Vision 26(1):63–84
Grabner H, Leistner C, Bischof H (2008) Semi-supervised on-line boosting for robust tracking. In: Proc. of European conf. on comput vision (ECCV), pp 234–247
Jia X, Lu H, Yang M (2012) Visual tracking via adaptive structural local sparse appearance model. In: Proc. of the IEEE conf. comput. vision and pattern recogn. (CVPR), pp 1822–1829
Jiang M, Wang H, Wang B (2012) Robust visual tracking based on maximum likelihood estimation. Int J Digital Content Tech Appl 6(22):467–474
Jiang M-X, Li M, Wang H-Y (2013) Visual object tracking based on 2DPCA and ML. Math Probl Eng 2013:1–7
Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R (2016) The visual object tracking VOT2016 challenge results. In: Proc. of European conf. on comput vision (ECCV), pp 1–45
Lasserre JA, Bishop CM, Minka TP (2006) Principled hybrids of generative and discriminative models. In: Proc. of the IEEE conf on comput vision and pattern recogn (CVPR), pp 87–94
Mei X (2011) Robust visual tracking and vehicle classification via sparse representation. IEEE Trans Pattern Anal Mach Intell (PAMI) 33(11):2259–2272
Mei X, Ling H (2009) Robust visual tracking using L1 minimization. In: Proc. of the IEEE int. conf. comput. vision (ICCV), pp 1436–1443
Ng AY, Jordan MI (2001) On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes. In: Proc. of advances in neural information process systems (NIPS), vol 14, pp 841–848
Qu P (2014) Visual tracking with fragments-based PCA sparse representation. Int J Signal Image Process Pattern Recogn 7(2):23–34
Ross DA, Lim J, Lin R-S, Yang M (2008) Incremental learning for robust visual tracking. Int J Comput Vision 77:125–141
Shreyamsha Kumar BK, Swamy MNS, Omair Ahmad M (2015) Structural local DCT sparse appearance model for visual tracking. In: Proc of the IEEE int symp on circuits and systems (ISCAS), pp 1194–1197
Shreyamsha Kumar BK, Swamy MNS, Omair Ahmad M (2016) Visual tracking via bilateral 2DPCA and robust coding. In: Proc. of the IEEE canadian conf on electrical and comput engineering (CCECE), pp 1–4
Shreyamsha Kumar BK, Swamy MNS, Omair Ahmad M (2016) Weighted residual minimization in PCA subspace for visual tracking. In: Proc. of the IEEE int symp on circuits and systems (ISCAS), pp 986–989
Smeulders AWM, Chu DM, Cucchiara R, Calderara S, Dehghan A, Shah M (2014) Visual tracking: an experimental survey. IEEE Trans Pattern Anal Mach Intell (PAMI) 36(7):1442–1468
Sun M, Du D, Lu H, Zhang L (2015) Visual tracking with a structured local model. In: Proc. of the IEEE int conf on image process (ICIP), pp 2855–2859
Wang D, Lu H (2012) Object tracking via 2DPCA and l1-regularization. Signal Process Letters 19(11):711–714
Wang D, Lu H, Bo C (2015) Fast and robust object tracking via probability continuous outlier model. IEEE Trans Image Process 24(12):5166–5176
Wang D, Lu H, Bo C (2015) Visual tracking via weighted local cosine similarity. IEEE Trans Cybernetics 45(9):1838–1850
Wang D, Lu H, Xiao Z, Yang M-H (2015) Inverse sparse tracker with a locally weighted distance metric. IEEE Trans Image Process 24(9):2646–2657
Wang D, Lu H, Yang M (2013) Online object tracking with sparse prototypes. IEEE Trans Image Process 22(1):314–325
Wang D, Lu H, Yang M-H (2016) Robust visual tracking via least soft-threshold squares. IEEE Trans Circuits Syst Video Technol 26(9):1709–1721
Wang F, Zhang J, Guo Q, Liu P, Tu D (2015) Robust visual tracking via discriminative structural sparse feature. In: Proc. of the Chinese conf. on image and graphics technologies, pp 438–446
Wang H, Ge H, Zhang S (2016) Object tracking via 2DPCA and l2-regularization. J of Electrical Comput Engineering 2016:1–7
Wang N, Yeung D-Y (2013) Learning a deep compact image representation for visual tracking. In: Proc. of advances in neural information process systems (NIPS), pp 809–817
Wu Y, Lim J, Yang M (2013) Online object tracking: a benchmark. In: Proc. of the IEEE Conf. on Comput. Vision and Pattern Recogn. (CVPR), pp 2411–2418
Yan J, Tong M (2011) Weighted sparse coding residual minimization for visual tracking. In: Proc. of visual communications and image process. (VCIP), pp 1–4
Yang H, Shao L, Zheng F, Wang L, Song Z (2011) Recent advances and trends in visual tracking: a review. Neurocomputing 74(18):3823–3831
Yang M, Zhang D, Yang J, Zhang D (2011) Robust sparse coding for face recognition. In: Proc. of the IEEE Conf on Comput Vision and Pattern Recogn (CVPR), pp 625–632
Yilmaz A, Javed O, Shah M (2006) Object tracking: a survey. ACM Comput Surv 38(4):1–45
Yu Q, Dinh T, Medioni G (2008) Online tracking and reacquisition using co-trained generative and discriminative trackers. In: Proc of European conf on comput vision (ECCV), pp 678–691
Zhang X, Xia G-S, Lu Q, Shen W, Zhang L (2018) Visual object tracking by correlation filters and online learning. ISPRS J Photogramm Remote Sens 140:77–89
Zhong W, Lu H, Yang M-H (2014) Robust object tracking via sparse collaborative appearance model. IEEE Trans Image Process 23(5):2356–2368
Zhou T, Bhaskar H, Liu F, Yang J, Cai P (2017) Online learning and joint optimization of combined spatial-temporal models for robust visual tracking. Neurocomputing 226:221–237
Zhou T, Bhaskar H, Xie K, Yang J, He X, Shi P (2015) Online learning of multi-feature weights for robust object tracking. In: Proc. of the IEEE int conf on image process (ICIP), pp 725–729
Zhou T, Liu F, Bhaskar H, Yang J (2018) Robust visual tracking via online discriminative and low-rank dictionary learning. IEEE Trans Cybernetics 48(9):2643–2655
Zhuang B, Wang L, Lu H (2016) Visual tracking via shallow and deep collaborative model. Neurocomputing 218:61–71
http://www.cs.toronto.edu/dross/ivt. Accessed: Jun, 2014
http://faculty.ucmerced.edu/mhyang/project/tip13_prototype/TIP12-SP.htm. Accessed: Mar, 2014
http://faculty.ucmerced.edu/mhyang/project/cvpr13_lss/LSST-MatlabCode-V1.zip. Accessed: Sep, 2015
https://github.com/huchuanlu/15_9. Accessed: Feb, 2016
https://github.com/huchuanlu/15_12. Accessed: Feb, 2016
https://github.com/huchuanlu/14_1. Accessed: Oct, 2015
http://winsty.net/dlt.html. Accessed: Apr, 2017
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kumar, B.K.S., Swamy, M. & Ahmad, M.O. Robust coding in a global subspace model and its collaboration with a local model for visual tracking. Multimed Tools Appl 79, 4525–4551 (2020). https://doi.org/10.1007/s11042-019-7685-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-7685-2