Advertisement

View-Adaptive Metric Learning for Multi-view Person Re-identification

  • Canxiang Yan
  • Shiguang ShanEmail author
  • Dan Wang
  • Hao Li
  • Xilin Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9004)

Abstract

Person re-identification is a challenging problem due to drastic variations in viewpoint, illumination and pose. Most previous works on metric learning learn a global distance metric to handle those variations. Different from them, we propose a view-adaptive metric learning (VAML) method, which adopts different metrics adaptively for different image pairs under varying views. Specifically, given a pair of images (or features extracted), VAML firstly estimates their view vectors (consisting of probabilities belonging to each view) respectively, and then adaptively generates a specific metric for these two images. To better achieve this goal, we elaborately encode the automatically estimated view vector into an augmented representation of the input feature, with which the distance can be analytically learned and simply computed. Furthermore, we also contribute a new large-scale multi-view pedestrian dataset containing 1000 subjects and 8 kinds of view-angles. Extensive experiments show that the proposed method achieves state-of-the-art performance on the public VIPeR dataset and the new dataset.

Keywords

Image Pair Viewpoint Change Fisher Discriminant Analysis Cumulative Match Characteristic Generalize Eigenvalue Decomposition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgement

The work is partially supported by Natural Science Foundation of China(NSFC) under contracts Nos. 61222211, 61272321, 61402430 and 61025010; and the China Postdoctoral Science Foundation 133366.

References

  1. 1.
    Gheissari, N., Sebastian, T., Hartley, R.: Person reidentification using spatiotemporal appearance. In: CVPR, pp. 1528–1535 (2006)Google Scholar
  2. 2.
    Wang, X., Doretto, G., Sebastian, T., Rittscher, J., Tu, P.: Shape and appearance context modeling. In: ICCV, pp. 1–8 (2007)Google Scholar
  3. 3.
    Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: CVPR, pp. 2360–2367 (2010)Google Scholar
  4. 4.
    Bak, S., Corvee, E., Bremond, F., Thonnat, M.: Multiple-shot human re-identification by mean riemannian covariance grid. In: AVSS, pp. 179–184 (2011)Google Scholar
  5. 5.
    Bazzani, L., Cristani, M., Perina, A., Farenzena, M., Murino, V.: Multiple-shot person re-identification by HPE signature. In: ICPR, pp. 1413–1416 (2010)Google Scholar
  6. 6.
    Cheng, D., Cristani, M., Stoppa, M., Bazzani, L., Murino, V.: Custom pictorial structures for re-identification. In: BMVC (2011)Google Scholar
  7. 7.
    Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 262–275. Springer, Heidelberg (2008) CrossRefGoogle Scholar
  8. 8.
    Prosser, B., Zheng, W.S., Gong, S., Xiang, T.: Person re-identification by support vector ranking. In: BMVC (2010)Google Scholar
  9. 9.
    Ma, B., Su, Y., Jurie, F.: Bicov: a novel image representation for person re-identification and face verification. In: BMVC (2012)Google Scholar
  10. 10.
    Schwartz, W., Davis, L.: Learning discriminative appearance-based models using partial least squares. In: SIBGRAPI, pp. 322–329 (2009)Google Scholar
  11. 11.
    Zhao, R., Ouyang, W., Wang, X.: Person re-identification by salience matching. In: ICCV, pp. 2528–2535 (2013)Google Scholar
  12. 12.
    Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. In: NIPS (2006)Google Scholar
  13. 13.
    Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML, pp. 209–216 (2007)Google Scholar
  14. 14.
    Zheng, W.S., Gong, S., Xiang, T.: Re-identification by relative distance comparison. PAMI 35, 653–668 (2013)CrossRefGoogle Scholar
  15. 15.
    Köstinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: CVPR (2012)Google Scholar
  16. 16.
    Pedagadi, S., Orwell, J., Velastin, S., Boghossian, B.: Local fisher discriminant analysis for pedestrian re-identification. In: CVPR, pp. 3318–3325 (2013)Google Scholar
  17. 17.
    Li, Z., Chang, S., Liang, F., Huang, T., Cao, L., Smith, J.: Learning locally-adaptive decision functions for person verification. In: CVPR, pp. 3610–3617 (2013)Google Scholar
  18. 18.
    Rupnik, J., Shawe-Taylor, J.: Multi-view canonical correlation analysis. In: SiKDD, pp. 1–4 (2010)Google Scholar
  19. 19.
    Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: PETS (2007)Google Scholar
  20. 20.
    Zheng, W.S., Gong, S., Xiang, T.: Person re-identification by probabilistic relative distance comparison. In: CVPR (2011)Google Scholar
  21. 21.
    Haralick, R., Shanmugam, K., Dinstein, I.: Textural features for image classification. SMC 3, 610–621 (1973)Google Scholar
  22. 22.
    Howarth, P., Rüger, S.: Evaluation of texture features for content-based image retrieval. In: IVR, pp. 326–334 (2004)Google Scholar
  23. 23.
    Zivkovic, Z.: Improved adaptive gaussian mixture model for background subtraction. In: ICPR, pp. 28–31 (2004)Google Scholar
  24. 24.
    Lin, Z., Davis, L.: Learning pairwise dissimilarity profiles for appearance recognition in visual surveillance. In: AVC, pp. 23–24 (2008)Google Scholar
  25. 25.
    Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 91–102. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  26. 26.
    Belhumeur, P., Hespanha, J., Kriegman, D.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. PAMI 19, 711–720 (1997)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Canxiang Yan
    • 1
    • 2
  • Shiguang Shan
    • 1
    Email author
  • Dan Wang
    • 1
    • 2
  • Hao Li
    • 1
    • 2
  • Xilin Chen
    • 1
  1. 1.Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS)Institute of Computing Technology, CASBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations