Sparse coding with cross-view invariant dictionaries for person re-identification

Article

Abstract

The task of matching observations of the same person in disjoint views captured by non-overlapping cameras is known as the person re-identification problem. It is challenging owing to low-quality images, inter-object occlusions, and variations in illumination, viewpoints and poses. Unlike previous approaches that learn Mahalanobis-like distance metrics, we propose a novel approach based on dictionary learning that takes the advances of sparse coding of discriminatingly and cross-view invariantly encoding features representing different people. Firstly, we propose a robust and discriminative feature extraction method of different feature levels. The feature representations are projected to a lower computation common subspace. Secondly, we learn a single cross-view invariant dictionary for each feature level for different camera views and a fusion strategy is utilized to generate the final matching results. Experimental statistics show the superior performance of our approach by comparing with state-of-the-art methods on two publicly available benchmark datasets VIPeR and PRID 2011.

Keywords

Dictionary learning Sparse coding Person re-identification Intelligent surveillance 

Notes

Acknowledgements

This work has been supported by New Century Excellent Talents in University of Ministry of Education under Grant NCET-12-0358, and Program of Shanghai Technology Research Leader under Grant 16XD1424400.

References

  1. 1.
    Aharon M, Elad M, Bruckstein A (2006) K-svd: an algorithm for designing overcomplete dictionaries for sparse representation. Proc IEEE Trans Signal Process 54 (11):4311–4322CrossRefGoogle Scholar
  2. 2.
    Ahmed E, Jones M, Marks T K (2015) An improved deep learning architecture for person re-identification. In: Proceedings IEEE computer vision and pattern recognition, pp 3908–3916Google Scholar
  3. 3.
    Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imag Sci 2(1):183–202MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Dong S C, Cristani M, Stoppa M, Bazzani L, Murino V (2011) Custom pictorial structures for re-identification. In: Proceedings brit mach vis conf, BMVC, pp 68.1–68.11Google Scholar
  5. 5.
    Engel C, Baumgartner P, Holzmann M, Nutzel J F (2010) Person re-identification by support vector ranking. In: Proceedings brit mach vis conf, BMVC, pp 21.1–21.11Google Scholar
  6. 6.
    Farenzena M, Bazzani L, Perina A, Murino V (2010) Person re-identification by symmetry-driven accumulation of local features. In: Proceedings IEEE conference on computer vision and pattern recognition, pp 2360–2367Google Scholar
  7. 7.
    Fisher B R (2012) The use of multiple measurements in taxonomic problems. Ann Eugen 7(2):179–188CrossRefGoogle Scholar
  8. 8.
    Gong S, Cristani M, Yan S et al (2014) Person re-identification, 1st ednGoogle Scholar
  9. 9.
    Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Proceedings eur conf computer vision, pp 262–275. ECCVGoogle Scholar
  10. 10.
    Gu S, Zhang L, Zuo W, Feng X (2014) Projective dictionary pair learning for pattern classification. In: Proceedings advances in neural information processing systems, pp 793–801Google Scholar
  11. 11.
    Hirzer M, Beleznai C, Roth PM, Bischof H (2011) Person re-identification by descriptive and discriminative classification. In: Proceedings Scandinavian conference on image analysis, vol 6688, pp 91–102Google Scholar
  12. 12.
    Hirzer M, Roth P M, Stinger M, Bischof H (2012) Relaxed pairwise learned metric for person re-identification. In: Proceedings ECCV, vol 7577, pp 780–793Google Scholar
  13. 13.
    Jiang Z, Lin Z, Davis LS (2003) Label consistent K-SVD: learning a discriminative dictionary for recognition. Proc IEEE Trans Pattern Anal Mach Intell 35(11):2651–2664CrossRefGoogle Scholar
  14. 14.
    Jing XY, Zhu X, Wu F, You X, Liu Q et al (2015) Super-resolution person re-identification with semi-coupled low-rank discriminant dictionary learning. In: Proceedings computer vision and pattern recognition, pp 695–704Google Scholar
  15. 15.
    Jurie F, Mignon A (2012) PCCA: a new approach for distance learning from sparse pairwise constraints. In: Proceedings IEEE conf comput vis pattern recog, pp 2666–2672Google Scholar
  16. 16.
    Karanam S, Li Y, Radke RJ (2015) Person re-identification with discriminatively trained viewpoint invariant dictionaries. In: Proceedings IEEE international conference on computer vision, pp 4516–4524Google Scholar
  17. 17.
    Karanam S, Gou M, Wu Z, Rates-Borras A, Camps O, Radke RJ (2016) A comprehensive evaluation and benchmark for person re-identification: features, metrics, and datasetsGoogle Scholar
  18. 18.
    Kodirov E, Xiang T, Gong S (2015) Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification. In: Proceedings British machine vision conference, pp 44.1–44.12Google Scholar
  19. 19.
    Kostinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. In: Proceedings IEEE Conference on computer vision and pattern recognition, pp 2288–2295Google Scholar
  20. 20.
    Layne R, Hospedales T M, Gong S (2014) Attributes-Based Re-identification. In: Proceedings advances in computer vision & pattern recognition, pp 93–117Google Scholar
  21. 21.
    Li Y, Lu H, Li J et al (2016) Underwater image de-scattering and classification by deep neural network. In: Computers and electrical engineering, pp 68–77Google Scholar
  22. 22.
    Liao S, Zhao G, Kellokumpu V, Pietikainen M, Li SZ (2010) Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes. In: Proceedings IEEE computer society conference on computer vision and pattern recognition, pp 1301–1306Google Scholar
  23. 23.
    Liao S, Hu Y, Zhu X, Li S Z (2015) Person re-identification by local maximal occurrence representation and metric learning. Proc IEEE Conf Comput Vis Pattern Recog 8(4):2197–2206Google Scholar
  24. 24.
    Lisanti G, Masi I, Bagdanov A D, Bimbo A D (2013) Person re-identification by iterative re-weighted sparse ranking. Proc IEEE Trans Pattern Anal Mach Intell 37 (8):1629–42CrossRefGoogle Scholar
  25. 25.
    Lisanti G, Masi I, Bimbo A D (2014) Matching people across camera views using kernel canonical correlation analysis Proceedings of the international conference on distributed smart cameras, ICDSC ’14. ACM, New York, pp 10:1–10:6Google Scholar
  26. 26.
    Liu X, Song M, Tao D, Zhou X et al (2014) Semi-supervised coupled dictionary learning for person re- identification. In: Proceedings IEEE conference computer vision and pattern recognition, pp 3550–3557Google Scholar
  27. 27.
    Liu X, Wang H, Wu Y et al (2015) An ensemble color model for human re-identification. In: Applications of computer vision, pp 868–875Google Scholar
  28. 28.
    Lu H, Li B, Zhu J et al (2016) Wound intensity correction and segmentation with convolutional neural networks. In: Concurrency and computation practice and experienceGoogle Scholar
  29. 29.
    Lu HM, Li YJ, Uemura T, Ge ZY, Xu X, He L, Serikawa S, Kim H (2017) FDCNet: filtering deep convolutional network for marine organism classification. In: Multimedia tools and applications, pp 1–14Google Scholar
  30. 30.
    Lu H M, Li Y J, Zhang Y D, Chen M, Serikawa S, Kim H (2017) Underwater optical image processing: a comprehensive review. In: Mobile networks and applications, pp 1–12Google Scholar
  31. 31.
    Ma B, Yu S, Jurie F (2012) BiCov: a novel image representation for person re-identification and face verification. In: Proceedings brit. mach. vis. conf., BMVC, pp 57.1–57.11Google Scholar
  32. 32.
    Moghaddam B, Jebara T, Pentland A (2000) Bayesian face recognition. Pattern Recogn 33(11):1771–1782CrossRefGoogle Scholar
  33. 33.
    Paisitkriangkrai S, Shen C, Anton VDH (2015) Learning to rank in person re-identification with metric ensembles. In: Proceedings computer vision and pattern recognition, pp 1846–1855Google Scholar
  34. 34.
    Pedagadi S, Orwell J, Velastin S, Boghossian B (2013) Local fisher discriminant analysis for pedestrian re-identification. In: Proceedings IEEE conf. comput. vis. pattern recog., pp 3318–3325Google Scholar
  35. 35.
    Peng P, Xiang T, Wang Y, Pontil M, Gong S, Huang T et al (2016) Unsupervised cross-dataset transfer learning for person re-identification. In: Proceedings IEEE conference on computer vision and pattern recognition, pp 1306–1315Google Scholar
  36. 36.
    Roth PM, Hirzer M, Koestinger M, Beleznai C, Bischof H (2014) Mahalanobis distance learning for person re-identification. In Person re-identification. Springer, pp 247–267Google Scholar
  37. 37.
    Sheng L, Ming S, Yun F (2015) Cross-view projective dictionary learning for person re-identification. In: Proceedings international joint conference on artificial intelligence. IJCAIGoogle Scholar
  38. 38.
    Shi Z, Hospedales TM, Xiang T (2015) Transferring a semantic representation for person re-identification and search. In: Proceedings computer vision and pattern recognition, pp 4184–4193Google Scholar
  39. 39.
    Tibshirani R (2011) Regression shrinkage and selection via the lasso. J R Stat Soc 73(3):273–282MathSciNetCrossRefGoogle Scholar
  40. 40.
    Wang T, Gong S, Zhu X, Wang S (2014) Person re-identification by video ranking. Proc Eur Conf Comput Vis 8692:688–703Google Scholar
  41. 41.
    Wu L, Shen C, Hengel A V D (2016) PersonNet: person Re-identification with deep convolutional neural networksGoogle Scholar
  42. 42.
    Xiong F, Gou M, Camps O, Sznaier M (2014) Person re-identification using kernel-based metric learning methods. In: Proceedings ECCA, vol 8695, pp 1–16Google Scholar
  43. 43.
    Xu X, He L, Shimada A, Taniguchi RI, Lu H (2016) Learning unified binary codes for cross-modal retrieval via latent semantic hashing. In: Neurocomputing, pp 191–203Google Scholar
  44. 44.
    Yang Y, Yang J, Yan J et al (2014) Salient color names for person re-identification. In: Proceedings European conference on computer vision, pp 536–551Google Scholar
  45. 45.
    Zeng M, Wu Z, Tian C, Hu L (2015) Efficient person re-identification by hybrid spatiogram and covariance descriptor. In: Proceedings IEEE conference computer vision and pattern recognition, pp 48–56Google Scholar
  46. 46.
    Zhang Q, Li B (2010) Discriminative k-svd for dictionary learning in face recognition. In: Proceedings IEEE conference computer vision and pattern recognition, pp 2691–2698Google Scholar
  47. 47.
    Zhang L, Xiang T, Gong S (2016) Learning a discriminative null space for person re-identification, pp 1239–1248Google Scholar
  48. 48.
    Zhang Y, Li B, Lu H, Irie A, Ruan X (2016) Sample-specific svm learning for person re-identification. In: Proceedings IEEE conference on computer vision and pattern recognition, pp 1278–1287Google Scholar
  49. 49.
    Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: Proceedings IEEE conference on computer vision and pattern recognition, vol 9. IEEE Computer Society, pp 3586–3593Google Scholar
  50. 50.
    Zheng W S, Gong S, Xiang T (2013) Re-identification by relative distance comparison. Proc IEEE Trans Pattern Anal Mach Intell 35(3):653–668CrossRefGoogle Scholar
  51. 51.
    Zheng L, Wang S, Tian L, He F, Liu Z, Tian Q (2015) Query-adaptive late fusion for image search and person re-identification. In: Proceedings IEEE conference on computer vision and pattern recognition, CVPR, pp 1741–1750Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.Department of Information Security EngineeringShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations