nach oben

Erschienen in:

2016 | OriginalPaper | Buchkapitel

Person Re-Identification by Unsupervised \(\ell _1\) Graph Learning

verfasst von : Elyor Kodirov, Tao Xiang, Zhenyong Fu, Shaogang Gong

Erschienen in: Computer Vision – ECCV 2016

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Most existing person re-identification (Re-ID) methods are based on supervised learning of a discriminative distance metric. They thus require a large amount of labelled training image pairs which severely limits their scalability. In this work, we propose a novel unsupervised Re-ID approach which requires no labelled training data yet is able to capture discriminative information for cross-view identity matching. Our model is based on a new graph regularised dictionary learning algorithm. By introducing a \(\ell _1\)-norm graph Laplacian term, instead of the conventional squared \(\ell _2\)-norm, our model is robust against outliers caused by dramatic changes in background, pose, and occlusion typical in a Re-ID scenario. Importantly we propose to learn jointly the graph and representation resulting in further alleviation of the effects of data outliers. Experiments on four benchmark datasets demonstrate that the proposed model significantly outperforms the state-of-the-art unsupervised learning based alternatives whilst being extremely efficient to compute.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Towards Viewpoint Invariant 3D Human Pose Estimation

Nächstes Kapitel Deep Learning the City: Quantifying Urban Perception at a Global Scale

Nur mit Berechtigung zugänglich

In practice our model is not restricted by the number of camera views. We use two here purely for notational simplicity.

Empirically we found that adding an extra \(\Vert \mathbf Y\Vert _1\) term makes little difference to the Re-ID performance, but results in more complex solver and higher computational cost.

For example, deep learning based methods often perform stronger on the large datasets than the small ones due to the need for large training data.

The gap is much smaller if more powerful features are used - see supplementary material for details.

Aharon, M., Elad, M., Bruckstein, A.: K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Sig. Process. 54(11), 4311–4322 (2006)CrossRef

Ahmed, E., Jones, M., Marks, T.K.: An improved deep learning architecture for person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: application to face recognition. IEEE Trans. Pattern Anal. Mach, Intell (2006)MATH

Bartels, R.H., Stewart, G.W.: Solution of the matrix equation ax + xb = c [f4]. Commun. ACM 15(9), 820–826 (1972). http://doi.acm.org/10.1145/361573.361582 CrossRef

Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7, 2399–2434 (2006)MathSciNetMATH

Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1), 1–122 (2011)CrossRefMATH

Bryan, P., Wei-Shi, Z., Gong, S., Xiang, T.: Person re-identification by support vector ranking. In: Proceedings of BMVC (2010)

Cai, D., He, X., Han, J.: Semi-supervised discriminant analysis. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1–7. IEEE (2007)

Chen, D., Yuan, Z., Hua, G., Zheng, N., Wang, J.: Similarity learning on an explicit polynomial kernel feature map for person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

10.

Cheng, D.S., Cristani, M., Bazzani, L., Murino, V.: Custom pictorial structures for re-identification. In: Proceedings of BMVC (2011)

11.

Chung, F.R.: Spectral Graph Theory, vol. 92. American Mathematical Soc., Providence (1997)MATH

12.

Daitch, S.I., Kelner, J.A., Spielman, D.A.: Fitting a graph to vector data. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 201–208. ACM (2009)

13.

Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of CVPR (2005)

14.

Dikmen, M., Akbas, E., Huang, T.S., Ahuja, N.: Pedestrian recognition with a learned metric. In: Proceedings of ACCV (2011)

15.

Douglas, G., Shane, B., Hai, T.: Evaluating appearance models for recognition, reacquisition and tracking. In: PETS (2007)

16.

Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: Proceedings of CVPR (2010)

17.

Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRef

18.

Gao, S., Tsang, I., Chia, L., Zhao, P.: Local features are not lonely laplacian sparse coding for image classification. In: Proceedings of CVPR (2010)

19.

Giuseppe, L., Iacopo, M., Alberto, D.B.: Matching people across camera views using kernel canonical correlation analysis. In: Proceedings of ICDSC (2014)

20.

Gong, S., Cristani, M., Yan, S., Loy, C.C.: Person Re-Identification, vol. 1. Springer, London (2014)CrossRefMATH

21.

Guo, H., Jiang, Z., Davis, L.S.: Discriminative dictionary learning with pairwise constraints. In: Proceedings of ACCV (2014)

22.

Guo, X.: Robust subspace segmentation by simultaneously learning data representations and their affinity matrix. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI) (2015)

23.

Hirzer, M., Beleznai, C., Roth, M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Proceedings of SCIA (2011)

24.

Hirzer, M., Roth, M., Bischof, H.: Person re-identification by efficient impostor-based metric learning. In: Proceedings of AVSS (2012)

25.

Hirzer, M., Roth, M., Koestinger, M., Bischof, H.: Relaxed pairwise learned metric for person re-identification. In: Proceedings of ECCV (2012)

26.

Hirzer, M., Roth, P.M., Köstinger, M., Bischof, H.: Relaxed pairwise learned metric for person re-identification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 780–793. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33783-3_56

27.

James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning, vol. 112. Springer, New York (2013)CrossRefMATH

28.

Kenneth, K., Joseph, M., Bhaskar, R., Kjersti, E., Te-Won, L., Terrence, S.: Dictionary learning algorithms for sparse representation. Neural Comput. 15(2), 349–396 (2003)CrossRefMATH

29.

Kim, S.J., Koh, K., Boyd, S., Gorinevsky, D.: \(\backslash \)ell_1 trend filtering. SIAM Rev. 51(2), 339–360 (2009)MathSciNetCrossRefMATH

30.

Kodirov, E., Xiang, T., Gong, S.: Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification. In: Xianghua Xie, M.W.J., Tam, G.K.L. (eds.) Proceedings of the British Machine Vision Conference (BMVC), pp. 44.1–44.12. BMVA Press. https://dx.doi.org/10.5244/C.29.44

31.

Layne, R., Hospedales, T., Gong, S.: Re-id: hunting attributes in the wild. In: Proceedings of BMVC (2014)

32.

Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: Advances in Neural Information Processing Systems, pp. 801–808 (2006)

33.

Li, C.G., Lin, Z., Zhang, H., Guo, J.: Learning semi-supervised representation towards a unified optimization framework for semi-supervised learning. In: The IEEE International Conference on Computer Vision (ICCV), December 2015

34.

Li, C.G., Vidal, R.: Structured sparse subspace clustering: a unified optimization framework. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

35.

Li, W., Zhao, R., Wang, X.: Human reidentification with transferred metric learning. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 31–44. Springer, Heidelberg (2013). doi:10.1007/978-3-642-37331-2_3

36.

Li, W., Zhao, R., Xiao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 152–159 (2014)

37.

Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

38.

Liao, S., Li, S.Z.: Efficient psd constrained asymmetric metric learning for person re-identification. In: The IEEE International Conference on Computer Vision (ICCV), December 2015

39.

Lisanti, G., Masi, I., Bagdanov, A.D., Bimbo, A.D.: Person re-identification by iterative re-weighted sparse ranking. IEEE Trans. Pattern Anal. Mach. Intell. 37(8), 1629–1642 (2013)CrossRef

40.

Liu, C., Gong, S., Loy, C.C.: On-the-fly feature importance mining for person re-identification. Pattern Recogn. 47(4), 1602–1615 (2014)CrossRef

41.

Liu, X., Song, M., Tao, D., Zhou, X., Chen, C., Bu, J.: Semi-supervised coupled dictionary learning for person re-identification. In: Proceedings of CVPR (2014)

42.

Ma, B., Su, Y., Jurie, F.: Bicov: a novel image representation for person re-identification and face verification. In: Proceedings of BMVC (2012)

43.

Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online learning for matrix factorization and sparse coding. J. Mach. Learn. Res. 11, 19–60 (2010)MathSciNetMATH

44.

Nie, F., Wang, H., Huang, H., Ding, C.: Unsupervised and semi-supervised learning via \(l_1\)-norm graph. In: ICCV (2011)

45.

Nie, F., Wang, X., Huang, H.: Clustering and projected clustering with adaptive neighbors. In: Proceedings of the 20th ACM SIGKDD International Conference On Knowledge Discovery and Data Mining, pp. 977–986. ACM (2014)

46.

Paisitkriangkrai, S., Shen, C., van den Hengel, A.: Learning to rank in person re-identification with metric ensembles. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

47.

Pedagadi, S., Orwell, J., Velastin, S., Boghossian, B.: Local fisher discriminant analysis for pedestrian re-identification. In: Proceedings of CVPR (2013)

48.

Roth, P.M., Hirzer, M., Köstinger, M., Beleznai, C., Bischof, H.: Mahalanobis distance learning for person re-identification. In: Gong, S., Cristani, M., Yan, S., Loy, C.C. (eds.) Person Re-Identification, pp. 247–267. Springer, London (2014)CrossRef

49.

Shen, Y., Lin, W., Yan, J., Xu, M., Wu, J., Wang, J.: Person re-identification with correspondence structure learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3200–3208 (2015)

50.

Shi, H., Zhu, X., Liao, S., Lei, Z., Yang, Y., Li, S.Z.: Constrained deep metric learning for person re-identification. CoRR abs/1511.07545 (2015). http://arxiv.org/abs/1511.07545

51.

Su, C., Yang, F., Zhang, S., Tian, Q., Davis, L.S., Gao, W.: Multi-task learning with low rank attribute embedding for person re-identification. In: The IEEE International Conference on Computer Vision (ICCV), December 2015

52.

Ustinova, E., Ganin, Y., Lempitsky, V.S.: Multiregion bilinear convolutional neural networks for person re-identification. CoRR abs/1512.05300 (2015). http://arxiv.org/abs/1512.05300

53.

Vezzani, R., Baltieri, D., Cucchiara, R.: People reidentification in surveillance and forensics: a survey. ACM Comput. Surv. (CSUR) 46(2), 29 (2013)CrossRef

54.

Wang, H., Gong, S., Xiang, T.: Unsupervised learning of generative topic saliency for person re-identification. In: Proceedings of BMVC (2014)

55.

Xiong, F., Gou, M., Camps, O., Sznaier, M.: Person re-identification using kernel-based metric learning methods. In: Proceedings of ECCV (2014)

56.

Yang, Y., Yang, J., Yan, J., Liao, S., Yi, D., Li, S.Z.: Salient color names for person re-identification. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 536–551. Springer, Heidelberg (2014). doi:10.1007/978-3-319-10590-1_35

57.

Zhao, R., Ouyang, W., Wang, X.: Unsupervised salience learning for person re-identification. In: Proceedings of CVPR (2013)

58.

Zhao, R., Ouyang, W., Wang, X.: Learning mid-level filters for person re-identification. In: Proceedings of CVPR (2014)

59.

Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)

60.

Zheng, L., Wang, S., Tian, L., He, F., Liu, Z., Tian, Q.: Query-adaptive late fusion for image search and person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

61.

Zheng, M., Bu, J., Chen, C., Wang, C., Zhang, L., Qiu, G., Cai, D.: Graph regularized sparse coding for image representation. IEEE Trans. Image Process. 20(5), 1327–1336 (2011)MathSciNetCrossRef

Titel: Person Re-Identification by Unsupervised Graph Learning
verfasst von: Elyor Kodirov
Tao Xiang
Zhenyong Fu
Shaogang Gong
Verlag: Springer International Publishing
Buch: Computer Vision – ECCV 2016
Print ISBN: 978-3-319-46447-3

Electronic ISBN: 978-3-319-46448-0

Copyright-Jahr: 2016
DOI: https://doi.org/10.1007/978-3-319-46448-0_11

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner