Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3553–3577 | Cite as

Robust dictionary learning with graph regularization for unsupervised person re-identification

Article

Abstract

Most existing approaches for person re-identification are designed in a supervised way, undergoing a prohibitively high labeling cost and poor scalability. Besides establishing effective similarity distance metrics, these supervised methods usually focus on constructing discriminative and robust features, which is extremely difficult due to the significant viewpoint variations. To overcome these challenges, we propose a novel unsupervised method, termed as Robust Dictionary Learning with Graph Regularization (RDLGR), which can guarantee view-invariance through learning a dictionary shared by all the camera views. To avoid the significant degradation of performance caused by outliers, we employ a capped l 2,1-norm based loss to make our model more robust, addressing the problem that traditional quadratic loss is known to be easily dominated by outliers. Considering the lack of labeled cross-view discriminative information in our unsupervised method, we further introduce a cross-view graph Laplacian regularization term into the framework of dictionary learning. As a result, the geographical structure of original data space can be preserved in the learned latent subspace as discriminative information, making it possible to further boost the matching accuracy. Extensive experimental results over four widely used benchmark datasets demonstrate the superiority of the proposed model over the state-of-the-art methods.

Keywords

Robust dictionary learning Graph regularization Unsupervised person re-identification 

Notes

Acknowledgments

This work was funded by the National Science Foundation of China (Nos. 61502377, 61532004), the National Key Research and Development Program of China (No. 2016YFB1000903); Ministry of Education Innovation Research Team (No. IRT_17R86); Project of China Knowledge Center for Engineering Science and Technology, and China Postdoctoral Science Foundation (No. 2015M582662).

References

  1. 1.
    An L, Chen X, Yang S, Bhanu B (2016) Sparse representation matching for person re-identification. Inf Sci 355:74–89CrossRefGoogle Scholar
  2. 2.
    Bird ND, Masoud O, Papanikolopoulos NP, Isaacs A (2005) Detection of loitering individuals in public transportation areas. IEEE Trans Intell Trans Syst 6(2):167–177CrossRefGoogle Scholar
  3. 3.
    Cai D, He X, Han J, Huang TS (2011) Graph regularized nonnegative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell 33(8):1548–1560CrossRefGoogle Scholar
  4. 4.
    Chang X, Nie F, Yang Y, Zhang C, Huang H (2016) Convex sparse pca for unsupervised feature learning. ACM Trans Knowl Discov Data 11(1):3CrossRefGoogle Scholar
  5. 5.
    Chang X, Yang Y (2016) Semisupervised feature analysis by mining correlations among multiple tasks. IEEE Trans Neural Netw Learn Syst.  https://doi.org/10.1109/TNNLS.2016.2582746
  6. 6.
    Chang X, Yu YL, Yang Y, Xing EP (2016) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell 39(8):1617–1632CrossRefGoogle Scholar
  7. 7.
    Chen D, Yuan Z, Chen B, Zheng N (2016) Similarity learning with spatial constraints for person re-identification. In: CVPRGoogle Scholar
  8. 8.
    Cheng DS, Cristani M, Stoppa M, Bazzani L, Murino V (2011) Custom pictorial structures for re-identification. In: BMVCGoogle Scholar
  9. 9.
    Cheng D, Gong Y, Zhou S, Wang J, Zheng N (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In: CVPRGoogle Scholar
  10. 10.
    Davis JV, Kulis B, Jain P, Sra S, Dhillon IS (2007) Information-theoretic metric learning. In: ICMLGoogle Scholar
  11. 11.
    Dikmen M, Akbas E, Huang TS, Ahuja N (2010) Pedestrian recognition with a learned metric. In: ACCVGoogle Scholar
  12. 12.
    Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: CVPRGoogle Scholar
  13. 13.
    Gheissari N, Sebastian TB, Hartley R (2006) Person reidentification using spatiotemporal appearance. In: CVPRGoogle Scholar
  14. 14.
    Gong S, Cristani M, Yan S, Loy CC (2014) Person re-identification, vol 1. SpringerGoogle Scholar
  15. 15.
    Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: PETSGoogle Scholar
  16. 16.
    Guo X (2015) Robust subspace segmentation by simultaneously learning data representations and their affinity matrix. In: IJCAIGoogle Scholar
  17. 17.
    Harandi M, Sanderson C, Shen C, Lovell BC (2013) Dictionary learning and sparse coding on grassmann manifolds: an extrinsic solution. In: ICCVGoogle Scholar
  18. 18.
    Hirzer M, Beleznai C, Roth PM, Bischof H (2011) Person re-identification by descriptive and discriminative classification. In: SCIAGoogle Scholar
  19. 19.
    Hirzer M, Roth PM, Bischof H (2012) Person re-identification by efficient impostor-based metric learning. In: AVSSGoogle Scholar
  20. 20.
    Jing XY, Zhu X, Wu F, You X, Liu Q, Yue D, Hu R, Xu B (2015) Super-resolution person re-identification with semi-coupled low-rank discriminant dictionary learning. In: CVPRGoogle Scholar
  21. 21.
    Karanam S, Li Y, Radke RJ (2015) Person re-identification with discriminatively trained viewpoint invariant dictionaries. In: ICCVGoogle Scholar
  22. 22.
    Kodirov E, Xiang T, Gong S (2015) Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification. In: BMVCGoogle Scholar
  23. 23.
    Koestinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. In: CVPRGoogle Scholar
  24. 24.
    Li S, Yin H, Fang L (2012) Group-sparse representation with dictionary learning for medical image denoising and fusion. IEEE Trans Biomed Eng 59(12):3450–3459CrossRefGoogle Scholar
  25. 25.
    Li Z, Chang S, Liang F, Huang TS, Cao L, Smith JR (2013) Learning locally-adaptive decision functions for person verification. In: CVPRGoogle Scholar
  26. 26.
    Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: CVPRGoogle Scholar
  27. 27.
    Li S, Shao M, Fu Y (2015) Cross-view projective dictionary learning for person re-identification. In: IJCAIGoogle Scholar
  28. 28.
    Lisanti G, Masi I, Del Bimbo A (2014) Matching people across camera views using kernel canonical correlation analysis. In: ICDSCGoogle Scholar
  29. 29.
    Lisanti G, Masi I, Bagdanov AD, Del Bimbo A (2015) Person re-identification by iterative re-weighted sparse ranking. IEEE Trans Pattern Anal Mach Intell 37(8):1629–1642CrossRefGoogle Scholar
  30. 30.
    Liu BD, Wang YX, Zhang YJ, Shen B (2013) Learning dictionary on manifolds for image classification. Pattern Recogn 46(7):1879–1890CrossRefGoogle Scholar
  31. 31.
    Liu X, Song M, Tao D, Zhou X, Chen C, Bu J (2014) Semi-supervised coupled dictionary learning for person re-identification. In: CVPRGoogle Scholar
  32. 32.
    Ma B, Su Y, Jurie F (2012) Bicov: a novel image representation for person re-identification and face verification. In: BMVCGoogle Scholar
  33. 33.
    Mairal J, Bach F, Ponce J, Sapiro G (2009) Online dictionary learning for sparse coding. In: ICMLGoogle Scholar
  34. 34.
    Matsukawa T, Okabe T, Sato Y (2014) Person re-identification via discriminative accumulation of local features. In: ICPRGoogle Scholar
  35. 35.
    Mignon A, Jurie F (2012) Pcca: a new approach for distance learning from sparse pairwise constraints. In: CVPRGoogle Scholar
  36. 36.
    Nie F, Yuan J, Huang H (2014) Optimal mean robust principal component analysis. In: ICMLGoogle Scholar
  37. 37.
    Nie L, Zhang L, Wang M, Hong R, Farseev A, Chua TS (2017) Learning user attributes via mobile social multimedia analytics. ACM Trans Intell Syst Technol 8(3):36CrossRefGoogle Scholar
  38. 38.
    Pedagadi S, Orwell J, Velastin S, Boghossian B (2013) Local fisher discriminant analysis for pedestrian re-identification. In: CVPRGoogle Scholar
  39. 39.
    Peng P, Xiang T, Wang Y, Pontil M, Gong S, Huang T, Tian Y (2016) Unsupervised cross-dataset transfer learning for person re-identification. In: CVPRGoogle Scholar
  40. 40.
    Qi M, Han J, Jiang J, Liu H (2017) Deep feature representation and multiple metric ensembles for person re-identification in security surveillance system. Multimed Tools Appl.  https://doi.org/10.1007/s11042-017-4649-2
  41. 41.
    Skretting K, Engan K (2010) Recursive least squares dictionary learning algorithm. IEEE Trans Signal Process 58(4):2121–2130MathSciNetCrossRefGoogle Scholar
  42. 42.
    Song X, Nie L, Zhang L, Liu M, Chua TS (2015) Interest inference via structure-constrained multi-source multi-task learning. In: IJCAIGoogle Scholar
  43. 43.
    Varior RR, Wang G, Lu J, Liu T (2016) Learning invariant color features for person reidentification. IEEE Trans Image Process 25(7):3395–3410MathSciNetCrossRefGoogle Scholar
  44. 44.
    Wang H, Gong S (2014) Xiang. Unsupervised learning of generative topic saliency for person re-identification, T.Google Scholar
  45. 45.
    Wang Z, Hu R, Liang C, Yu Y, Jiang J, Ye M, Chen J, Leng Q (2016) Zero-shot person re-identification via cross-view consistency. IEEE Trans Multimedia 18(2):260–272CrossRefGoogle Scholar
  46. 46.
    Weinberger KQ, Saul LK (2009) Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res 10:207–244MATHGoogle Scholar
  47. 47.
    Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: CVPRGoogle Scholar
  48. 48.
    Xiong F, Gou M, Camps O, Sznaier M (2014) Person re-identification using kernel-based metric learning methods. In: ECCVGoogle Scholar
  49. 49.
    Xu Y, Guo J, Huang Z, Qiu W (2017) Sparse coding with cross-view invariant dictionaries for person re-identification. Multimed Tools Appl.  https://doi.org/10.1007/s11042-017-4893-5
  50. 50.
    Yang Y, Wen L, Lyu S, Li SZ (2017) Unsupervised learning of multi-level descriptors for person re-identification. In: AAAIGoogle Scholar
  51. 51.
    Yu K, Zhang T, Gong Y (2009) Nonlinear learning using local coordinate coding. In: NIPSGoogle Scholar
  52. 52.
    Zhang T (2009) Multi-stage convex relaxation for learning with sparse regularization. In: NIPSGoogle Scholar
  53. 53.
    Zhang Q, Li B (2010) Discriminative k-svd for dictionary learning in face recognition. In: CVPRGoogle Scholar
  54. 54.
    Zhao R, Ouyang W, Wang X (2013) Person re-identification by salience matching. In: ICCVGoogle Scholar
  55. 55.
    Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: CVPRGoogle Scholar
  56. 56.
    Zhao R, Ouyang W, Wang X (2014) Learning mid-level filters for person re-identification. In: CVPRGoogle Scholar
  57. 57.
    Zheng WS, Gong S, Xiang T (2009) Associating groups of people. In: BMVCGoogle Scholar
  58. 58.
    Zheng M, Bu J, Chen C, Wang C, Zhang L, Qiu G, Cai D (2011) Graph regularized sparse coding for image representation. IEEE Trans Image Process 20(5):1327–1336MathSciNetCrossRefMATHGoogle Scholar
  59. 59.
    Zheng WS, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: CVPRGoogle Scholar
  60. 60.
    Zheng WS, Gong S, Xiang T (2013) Reidentification by relative distance comparison. IEEE Trans Pattern Anal Mach Intell 35(3):653–668CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • Caixia Yan
    • 1
  • Minnan Luo
    • 1
  • Wenhe Liu
    • 2
  • Qinghua Zheng
    • 1
  1. 1.SPKLSTN Lab, Department of Computer Science and TechnologyXi’an Jiaotong UniversityXi’anChina
  2. 2.CAI, University of Technology SydneySydneyAustralia

Personalised recommendations