Abstract
It is of great importance in smart transportation surveillance to track object reliably from multimedia streaming data. Sparse representation based target tracking methods often suffer from tracking failure when target is under occlusions, pose changes or illumination changes conditions. In this paper, we propose a novel robust reweighted local multi-task sparse tracking algorithm. In the algorithm, local patches of all candidate targets are represented as a linear combination of the corresponding local patches from the template dictionary. Furthermore, in order to efficiently capture the frequently emerging outlier tasks, we decompose the sparse coefficient matrix to two collaborative matrices to make sure that the same type of particles share the same sparse structure. Observing that the edge of the candidate object contains background information, this paper gives a lower weight coefficient to the reconstruction error regularization located in the edge of the local patches than the middle local patches. Experimental evaluations on challenging sequences demonstrate the effectiveness, accuracy and robustness of our proposed algorithm in comparison with state-of-the-art algorithms.
Similar content being viewed by others
References
Adam A, Rivlin E, Shimshoni I (2006) Robust fragments-based tracking using the integral histogram[C]. IEEE Conf Comput Vis Pattern Recognit 2006(1):798–805
Ali NH, Hassan GM (2014) Kalman filter tracking[J]. Int J Comput Appl89(9)
Avidan S (2004) Support vector tracking[J]. IEEE Trans Pattern Anal Mach Intell 26(8):1064–1072
Avidan S (2007) Ensemble tracking[J]. IEEE Trans Pattern Anal Mach Intell 29(2):261–271
Babenko B, Yang M H, Belongie S (2009) Visual tracking with online multiple instance learning[C]. Comput Vis Pattern Recogn
Bai S, Liu R, Su Z et al (2014) Incremental robust local dictionary learning for visual tracking[C]. IEEE Int Conf Multimedia Expo 2014:1–6
Bai Y, Tang M (2014) Object tracking via robust multitask sparse representation[J]. IEEE Signal Process Lett 21(8):909–913
Bao C, Wu Y, Ling H et al (2012) Real time robust l1 tracker using accelerated proximal gradient approach[C]. IEEE Conf Comput Vis Pattern Recognit 2012:1830–1837
Benfold B, Reid I (2011) Stable multi-target tracking in real-time surveillance video[C]. IEEE Conf Comput Vis Pattern Recognit 2011:3457–3464
Black MJ, Jepson AD (1998) Eigentracking: robust matching and tracking of articulated objects using a view-based representation[J]. Int J Comput Vis 26(1):63–84
Bo C, Zhang J, He J et al (2016) Online object tracking via bounded error distance[J]. Neurocomputing 171:1175–1184
Bucak SS, Gunsel B (2009) Incremental subspace learning via non-negative matrix factorization[J]. Pattern Recogn 42(5):788–797
Chen X, Pan W, Kwok JT et al (2009) Accelerated gradient method for multi-task sparse learning problem[C]. Data Min. ICDM’09. Ninth IEEE Int Conf IEEE 746–751
Chen Y, Yang X, Zhong B et al (2015) CNNTracker: online discriminative object tracking via deep convolutional neural network[J]. Appl Soft Comput
Comaniciu D, Ramesh V, Meer P (2003) Kernel-based object tracking[J]. IEEE Trans Pattern Anal Mach Intell 25(5):564–577
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection[C]. IEEE Conf Comput Vision Pattern Recogn Comput Soc 2005(1):886–893
Fan J, Shen X, Wu Y (2012) Scribble tracker: a matting-based approach for robust tracking[J]. IEEE Trans Pattern Anal Mach Intell 34(8):1633–1644
Fu C, Zhang P, Jiang J et al (2015) A Bayesian approach for sleep and wake classification based on dynamic time warping method[J]. Multimedia Tool Appl 1–20
Gong P, Ye J, Zhang C () 2012Robust multi-task feature learning[C]. Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM 895–903
Grabner H, Grabner M, Bischof H (2006) Real-time tracking via on-line boosting[C]. BMVC 1(5):6
Guo C, Guo Q, Jin M, Lv Z (2015) Dynamic systems based on preference graph and distance [J]. Discrete Contin Dyn Syst Ser S 8(6):1139–1154
Guo C, Liu X, Jin M et al (2015) The research on optimization of auto supply chain network robust model under macroeconomic fluctuations[J]. Chaos Solitons Fractals
Hare S, Saffari A, Torr PHS (2011) Struck: structured output tracking with kernels[C]. IEEE Int Conf Comput Vis 2011:263–270
He L, Bo Y, Zhao G (2014) Multifeatures based compressive sensing tracking[J]. Math Probl Eng
He L, Bo Y, Zhao G (2015) Accelerated multi-feature based compressive sensing tracking[J]. Infrared Phys Technol 71:424–431
Hong Z, Mei X, Prokhorov D et al (2013) Tracking via robust multi-task multi-view joint sparse representation[C]. IEEE Int Conf Comput Vis 2013:649–656
Hsieh JW, Yu SH, Chen YS et al (2006) Automatic traffic surveillance system for vehicle tracking and classification[J]. IEEE Trans Intell Transp Syst 7(2):175–187
Hua G, Wu Y (2006) Measurement integration under inconsistency for robust tracking[C]. IEEE Conf Comput Vis Pattern Recognit 2006(1):650–657
Huang L, Ma B (2015) Tensor pooling for online visual tracking[C]. EEE Int Conf Multimedia Expo 2015:1–6
Jiang N, Liu W, Wu Y (2011) Adaptive discriminative metric differential tracking[C]. IEEE Conf Comput Vis Pattern Recognit 2011:1161–1168
Jiang D, Wang Y, Yao C et al (2015) An effective dynamic spectrum access algorithm for multi-hop cognitive wireless networks. Comput Netw 84(19):1–16
Jiang D, Xu Z, Chen Z et al (2011) Joint time-frequency sparse estimation of large-scale network traffic. Comput Netw 55(10):3533–3547
D. Jiang, Z. Xu, W. Li et al (2014) Topology control-based collaborative multicast routing algorithm with minimum energy consumption. Int J Commun Syst. online available
Jiang D, Xu Z, Li W et al (2015) Network coding-based energy-efficient multicast routing algorithm for multi-hop wireless networks. J Syst Softw 104:152–165
Jiang D, Xu Z, Liu J et al (2015) An optimization-based robust routing algorithm to energy-efficient networks for cloud computing. Telecommun Syst. online available
Jiang D, Xu Z, Wang W et al (2015) A collaborative multi-hop routing algorithm for maximum achievable rate. J Netw Comput Appl 57(2015):182–191
Jiang D, Xu Z, Xu H et al (2011) An approximation method of origin–destination flow traffic from link load counts. Comput Electr Eng 37(6):1106–1121
Jiang D, Xu Z, Zhang P et al (2014) A transform domain-based anomaly detection approach to network-wide traffic. J Netw Comput Appl 40(2):292–306
Jiang D, Xu Z, Xu H (2015) A novel hybrid prediction algorithm to network traffic. Ann Telecommun 70(9):427–439
Jiang D, Yao C, Xu Z et al (2015) Multi-scale anomaly detection for high-speed network traffic. Trans Emerg Telecommun Technol 26(3):308–317
Jiang D, Zhao Z, Xu Z et al (2014) How to reconstruct end-to-end traffic based on time-frequency analysis and artificial neural network. AEU Int J Electron Commun 68(10):915–925
Kalal Z, Matas J, Mikolajczyk K (2010) Pn learning: bootstrapping binary classifiers by structural constraints[C]. IEEE Conf Comput Vis Pattern Recognit 2010:49–56
Kim H, Paik J (2014) Low-rank representation-based object tracking using multitask feature learning with joint sparsity[C]. Abst Appl Anal. Hindawi Publishing Corporation
Kwon J, Lee KM (2010) Visual tracking decomposition[C]. IEEE Conf Comput Vis Pattern Recognit 2010:1269–1276
Li X, Hu W, Shen C et al (2013) A survey of appearance models in visual object tracking[J]. ACM Trans Intell Syst Technol 4(4):58
Li F, Lu H, Wang D et al (2015) Dual group structured tracking[J]
Li H, Shen C, Shi Q (2011) Real-time visual tracking using compressive sensing[C]. IEEE Conf Comput Vis Pattern Recognit 2011:1305–1312
Liu J, Ji S, Ye J (2009) Multi-task feature learning via efficient l 2, 1-norm minimization[C]. Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press 339–348
Liu B, Yang L, Huang J et al (2010) Robust and fast collaborative tracking with two stage sparse optimization[M]//Comput Vis–ECCV 2010. Springer Berlin Heidelberg 624–637
Liu Y, Zhang H, Su Z et al (2014) Visual tracking with multi-level dictionary learning[C]. Digital home (ICDH). 5th Int Conf IEEE 8–13
Lowe DG (2004) Distinctive image features from scale-invariant keypoints[J]. Int J Comput Vis 60(2):91–110, SIFT
Lu Y, Wang L, Hartley R et al (2011) Compressive evaluation in human motion tracking[M]. Computer Vision–ACCV 2010. Springer Berlin Heidelberg 177–188
Lv Z, Halawani A, Fen S et al (2015) Touch-less interactive augmented reality game on vision based wearable device[J]. Pers Ubiquit Comput 19(3):551–567
Lv Z, Tek A, Da Silva F et al (2013) Game on, science-how video game technology may help biologists tackle visualization challenges[J]. PLoS One 8(3):57990
Lv Z, Yin T, Han Y et al (2011) WebVR—web virtual reality engine based on P2P network[J]. J Net 6(7):990–998
Ma R, Yao L, Jin M et al (2015) Robust environmental closed-loop supply chain design under uncertainty[J]. Chaos Solitons Fractals
Mei X, Ling H (2011) Robust visual tracking and vehicle classification via sparse representation[J]. IEEE Trans Pattern Anal Mach Intell 33(11):2259–2272
Mei X, Ling H, Wu Y et al (2011) Minimum error bounded efficient ℓ 1 tracker with occlusion detection[C]. IEEE Conf Comput Vis Pattern Recognit 2011:1257–1264
Nejhum SMS, Ho J, Yang MH (2008) Visual tracking with histograms and articulating blocks[C]. IEEE Conf Comput Vis Pattern Recognit 2008:1–8
Nesterov Y (2007) Gradient methods for minimizing composite objective function[J]
Ning J, Zhang L, Zhang D et al (2012) Scale and orientation adaptive mean shift tracking[J]. IET Comput Vis 6(1):52–61
Olfati-Saber R, Jalalkamali P (2011) Collaborative target tracking using distributed Kalman filtering on mobile sensor networks[C]. IEEE Am Control Conf 2011:1100–1105
Qian C, Zhuang Y, Xu Z (2014) Visual tracking with structural appearance model based on extended incremental non-negative matrix factorization[J]. Neurocomputing 136:327–336
Ross DA, Lim J, Lin RS et al (2008) Incremental learning for robust visual tracking[J]. Int J Comput Vis 77(1–3):125–141
Sevilla-Lara L, Learned-Miller E (2012) Distribution fields for tracking[C]. IEEE Conf Comput Vis Pattern Recognit 2012:1910–1917
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features[C]//Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proc IEEE Comput Society Conf IEEE 1:I-511-I-518
Viola P, Jones MJ (2004) Robust real-time face detection[J]. Int J Comput Vis 57(2):137–154
Wang Q, Chen F, Xu W et al (2012) Online discriminative object tracking with local sparse representation[C]. IEEE Workshop Appl Comput Vis 2012:425–432
Wang K, Liu N, Sadooghi I et al (2015) Overcoming hadoop scaling limitations through distributed task execution[C]. IEEE Int Conf Clust Comput 2015:236–245
Wang D, Lu H (2013) On-line learning parts-based representation via incremental orthogonal projective non-negative matrix factorization[J]. Signal Process 93(6):1608–1623
Wang D, Lu H, Yang MH (2013) Least soft-threshold squares tracking[C]. IEEE Conf Comput Vis Pattern Recognit 2013:2371–2378
Wang W, Lv Z, Li X et al (2015) Virtual reality based GIS analysis platform[C]. Neural Inf Proc. Springer International Publishing 638–645
Wang Y, Su Y, Agrawal G (2015) A novel approach for approximate aggregations over arrays[C]//Proceedings of the 27th International Conference on Scientific and Statistical Database Management. ACM 4
Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark[C]. IEEE Conf Comput Vis Pattern Recognit 2013:2411–2418
Wu Y, Shen B, Ling H (2014) Visual tracking via online nonnegative matrix factorization[J]. IEEE Trans Circuits Syst Video Technol 24(3):374–383
Xiong J, Tang Q (2014) 1-bit compressive data gathering for wireless sensor networks. J Sens 1(1):1–8
Yan Y, Yang Y, Meng D, Liu G, Tong W, Hauptmann A, Sebe N (2015) Event oriented dictionary learning for complex event detection. IEEE Trans Image Process 24(6):1867–1878
Yang J, He S, Lin Y et al (2015) Multimedia cloud transmission and storage system based on internet of things[J]. Multimedia Tool Appl 1–16
Yang Y, Xie Y, Zhang W et al (2015) Global coupled learning and local consistencies ensuring for sparse-based tracking[J]. Neurocomputing 160:191–205
Yang T, Yu B, Wang H et al (2015) Cryptanalysis and improvement of Panda-public auditing for shared data in cloud and internet of things[J]. Multimedia Tool Appl 1–18
Yang J, Zhou J, Lv Z et al (2015) A real-time monitoring system of industry carbon monoxide based on wireless sensor networks[J]. Sensors 15(11):29535–29546
Yao R, Shi Q, Shen C et al (2013) Part-based visual tracking with online latent structural learning[C. IEEE Conf Comput Vis Pattern Recognit 2013:2363–2370
Yilmaz A, Javed O, Shah M (2006) Object tracking: A survey[J]. ACM Comput Surv (CSUR) 38(4)
Yu Q, Dinh T B, Medioni G (2008) Online tracking and reacquisition using co-trained generative and discriminative trackers[M]. Computer Vision–ECCV 2008. Springer Berlin Heidelberg 678–691
Zarezade A, Rabiee HR, Soltani-Farani A et al (2014) Patchwise joint sparse tracking with occlusion detection[J]. IEEE Trans Image Process 23(10):4496–4510
Zhang T, Ghanem B, Liu S et al (2012) Robust visual tracking via multi-task sparse learning[C]. IEEE Conf Comput Vis Pattern Recognit 2012:2042–2049
Zhang T, Ghanem B, Liu S et al (2012) Low-rank sparse learning for robust visual tracking[M]. Computer Vision–ECCV 2012. Springer Berlin Heidelberg 470–484
Zhang T, Ghanem B, Liu S et al (2015) Robust visual tracking via exclusive context modeling[J]
Zhang X, Han Y, Hao D S et al (2015) ARPPS: Augmented Reality Pipeline Prospect System[C]. Neural Inf Process. Springer International Publishing 647–656
Zhang T, Jia K, Xu C et al (2014) Partial occlusion handling for visual tracking via robust part matching[C]. IEEE Conf Comput Vis Pattern Recognit 2014:1258–1265
Zhang T, Liu S, Xu C et al (2015) Structural sparse tracking[C]. Proc IEEE Conf Comput Vis Pattern Recogn 150–158
Zhang S, Yao H, Sun X et al (2013) Sparse coding based visual tracking: review and experimental comparison[J]. Pattern Recogn 46(7):1772–1788
Zhang S, Zhang X, Ou X et al (2015) Assessing attack surface with component-based package dependency[M]//network and system security. Springer International Publishing 405–417
Zhang K, Zhang L, Yang MH (2014) Fast compressive tracking[J]. IEEE Trans Pattern Anal Mach Intell 36(10):2002–2015
Zhang S, Zhou H, Jiang F et al (2015) Robust visual tracking using structurally random projection and weighted least squares[J]
Zhong W, Lu H, Yang MH (2012) Robust object tracking via sparsity-based collaborative model[C. IEEE Conf Comput Vis Pattern Recognit 2012:1838–1845
Zhong B, Yao H, Chen S et al (2014) Visual tracking via weakly supervised learning from multiple imperfect oracles[J]. Pattern Recogn 47(3):1395–1410
Zhou S, Hu P, Li K et al (2012) A new target tracking scheme based on improved mean shift and adaptive kalman filter[J]. Int J Adv Comput Technol 4(2)
Acknowledgments
This work was supported in part by Zhejiang Provincial Natural Science Foundation of China(ZJNSF LY14F010008) and NSFC(61572023).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xiong, J., Tang, Q., He, X. et al. Tracking in multimedia data via robust reweighted local multi-task sparse representation for transportation surveillance. Multimed Tools Appl 75, 17531–17552 (2016). https://doi.org/10.1007/s11042-016-3464-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3464-5