Viewpoint Invariant Person Re-identification with Pose and Weighted Local Features

  • Chun-Huei Chen
  • Ju-Chin ChenEmail author
  • Kawuu W. Lin
Part of the Studies in Computational Intelligence book series (SCI, volume 769)


In this study, we propose a viewpoint-invariant person re-identification scheme with pose priors and weighted local features. We divide the pose angle into three classes: (0°, 180°), (45°, 135°), and 90°. Each of the classes has a weighted map. In addition, the texture-based feature, histogram of oriented gradients, is extracted to predict pose angle using support vector machine. Moreover, two additional features, salient color names and local binary patterns (LBP), are extracted. The former feature is computed using a weighted map with Gaussian distribution. The latter feature is computed using a weighted map based on the predicted pose angle. Then, the image representation is concatenated with salient color names and LBP. Finally, we adopt cross-view quadratic discriminant analysis for person re-identification.


Person re-identification Pose angle estimation Color names 


  1. 1.
    Tu, P., Doretto, G., Krahnstoever, N., Perera, A.G.A., Wheeler, F., Liu, X., Rittscher, J., Sebastian, T., Yu, T., Harding, K.: An intelligent video framework for homeland protection. In: SPIE Defense and Security Symposium (2007)Google Scholar
  2. 2.
    Wang, S., Lewandowski, M., Annesley, J., Orwell, J.: Re-identification of pedestrians with variable occlusion and scale. In: ICCV, pp. 1876–1882 (2011)Google Scholar
  3. 3.
    Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: ECCV, vol. 5302, pp. 262–275 (2008)Google Scholar
  4. 4.
    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
  5. 5.
    Liu, C., Gong, S., Loy, C.C., Lin, X.: Person re-identification: what features are important? In: ECCV, vol. 7583, pp. 391–401 (2012)Google Scholar
  6. 6.
    Zha, R., Ouyang, W., Wang, X.: Unsupervised salience learning for person re-identification. In: CVPR, pp. 3586–3593 (2013)Google Scholar
  7. 7.
    Kuo, C.H., Khamis, S., Shet, V.: Person re-identification using semantic color names and RankBoost. In: WACV, pp. 281–287 (2013)Google Scholar
  8. 8.
    Simonnet, D., Lewandowski, M., Velastin, S.A., Orwell, J., Turkbeyler, E.: Re-identification of pedestrians in crowds using dynamic time warping. In: ECCV, vol. 7583, pp. 423–432 (2012)Google Scholar
  9. 9.
    Prosser, B., Zheng, W., Gong, S., Xiang, T.: Person re-identification by support vector ranking. In: BMVC, pp. 1–11 (2010)Google Scholar
  10. 10.
    Cheng, D.S., Cristani, M., Stoppa, M., Bazzani, L., Murino, V.: Custom pictorial structures for re-identification. In: BMVC (2011)Google Scholar
  11. 11.
    Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: SCIA, pp. 91–102 (2011)Google Scholar
  12. 12.
    Kviatkovsky, I., Adam, A., Rivlin, E.: Color invariants for person re-identification. TPAMI 35, 1622–1634 (2013)Google Scholar
  13. 13.
    Zheng, W.S., Gong, S., Xiang, T.: Re-identification by relative distance comparison. TPAMI 35, 653–668 (2013)CrossRefGoogle Scholar
  14. 14.
    Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. In: Advances NIPS (2005)Google Scholar
  15. 15.
    Weinberger, K.Q., Saul, L.K.: Fast solvers and efficient implementations for distance metric learning. In: ICML, pp. 1160–1167 (2008)Google Scholar
  16. 16.
    Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML, pp. 209–216 (2007)Google Scholar
  17. 17.
    Koestinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: CVPR, pp. 2288–2295 (2012)Google Scholar
  18. 18.
    Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: CVPR, pp. 2197–2206 (2015)Google Scholar
  19. 19.
    Roth, P.M., Hirzer, M., Koestinger, M., Beleznai, C., Bischof, H.: Mahalanobis distance learning for person re-identification. In: Person Re-identification, pp. 247–267 (2014)Google Scholar
  20. 20.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. TIST 2(27) (2011). Software available at
  21. 21.
    Navneet, D., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886–893 (2005)Google Scholar
  22. 22.
    Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: PETS (2007)Google Scholar
  23. 23.
    van de Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. Image Process. 1512–1523 (2009)Google Scholar
  24. 24.
    van de Weijer, J., Schmid, C.: Applying color names to image description. In: ICIP, vol. 3, pp. III-493–III-496 (2007)Google Scholar
  25. 25.
    Yang, Y., Yang, J., Yan, J., Liao, S., Yi, D., Li, S.Z.: Salient color names for person re-identification. In: ECCV, vol. 8689, pp. 536–551 (2014)Google Scholar
  26. 26.
    Liu, Y., Zhang, D., Lu, G., Ma, W.Y.: Region-based image retrieval with high-level semantic color names. In: Proceedings of the 11th International Multimedia Modelling Conference, pp. 180–187 (2005)Google Scholar
  27. 27.
    Ojala, T., Pietikäinen, M., Harwood, D.: Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. In: ICPR, vol. 1, pp. 582–585 (1994)Google Scholar
  28. 28.
    Mäenpää, T., Pietikäinen, M.: Texture analysis with local binary patterns. In: Handbook of Pattern Recognition and Computer Vision, pp. 197–216 (2005)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.National Kaohsiung University of Applied SciencesKaohsiungTaiwan, ROC

Personalised recommendations