Pedestrian Re-identification - Metric Learning using Symmetric Ensembles of Categories

Sateesh Pedagadi, James Orwell, Boghos Boghossian

2015

Abstract

This paper presents a method for pedestrian re-identification, with two novel contributions. Firstly, each element in the target population is classified into one of n categories, using the expected accuracy of the re-identification estimate for this element. A metric for each category is separately trained using a standard (Local Fisher) method. To process a test set, each element is classified into one of the categories, and the corresponding metric is selected and used. The second contribution is the proposal to use a symmetrised distance measure. A standard procedure is to learn a metric using one set as the probe and the other set as the gallery. This paper generalises that procedure by reversing the labels to learn a different metric, and uses a linear (symmetrised) combination of the two. This can be applied in cases for which there are two distinct sets of observations, i.e. from two cameras, e.g. VIPER. Using this publicly available dataset, it is demonstrated how these contributions result in improved re-identification performance.

References

  1. Aziz, K.-E., Merad, D., and Fertil, B. (2011). Person re-identification using appearance classification. In ICIAR (2), pages 170-179.
  2. Bak, S., Corvee, E., Bremond, F., and Thonnat, M. (2010). Person re-identification using haar-based and dcdbased signature. In Proc. Seventh IEEE Int Advanced Video and Signal Based Surveillance (AVSS) Conf, pages 1-8.
  3. Bauml, M. and Stiefelhagen, R. (2011). Evaluation of local features for person re-identification in image sequences. In Proc. 8th IEEE Int Advanced Video and Signal-Based Surveillance (AVSS) Conf, pages 291- 296.
  4. Bazzani, L., Cristani, M., Perina, A., Farenzena, M., and Murino, V. (2010). Multiple-shot person reidentification by hpe signature. In ICPR, pages 1413- 1416.
  5. Bazzani, L., Cristani, M., Perina, A., and Murino, V. (2012). Multiple-shot person re-identification by chromatic and epitomic analyses. Pattern Recognition Letters, 33(7):898-903.
  6. Bedagkar-Gala, A. and Shah, S. K. (2011). Multiple person re-identification using part based spatio-temporal color appearance model. In Proc. IEEE Int Computer Vision Workshops (ICCV Workshops) Conf, pages 1721-1728.
  7. Dikmen, M., Akbas, E., Huang, T., and Ahuja, N. (2011). Pedestrian recognition with a learned metric. Computer Vision-ACCV 2010, pages 501-512.
  8. Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., and Lin, C.-J. (2008). LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research, 9:1871-1874.
  9. Farenzena, M., Bazzani, L., Perina, A., Murino, V., and Cristani, M. (2010). Person re-identification by symmetry-driven accumulation of local features. In CVPR, pages 2360-2367.
  10. Gheissari, N., Sebastian, T., and Hartley, R. (2006). Person reidentification using spatiotemporal appearance. In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, volume 2, pages 1528-1535. IEEE.
  11. Gray, D., Brennan, S., and Tao, H. (2007). Evaluating appearance models for recognition, reacquisition, and tracking. In 10th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS).
  12. Gray, D. and Tao, H. (2008). Viewpoint invariant pedestrian recognition with an ensemble of localized features. Computer Vision-ECCV 2008, pages 262-275.
  13. Hamdoun, O., Moutarde, F., Stanciulescu, B., and Steux, B. (2008). Person re-identification in multi-camera system by signature based on interest point descriptors collected on short video sequences. In ICDSC, pages 1-6.
  14. Harandi, M. T., Sanderson, C., Wiliem, A., and Lovell, B. C. (2012). Kernel analysis over riemannian manifolds for visual recognition of actions, pedestrians and textures. In Proc. IEEE Workshop Applications of Computer Vision (WACV), pages 433-439.
  15. Javed, O., Shafique, K., and Shah, M. (2005). Appearance modeling for tracking in multiple non-overlapping cameras. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 2, pages 26-33. IEEE.
  16. Jungling, K. and Arens, M. (2011). View-invariant person re-identification with an implicit shape model. In Proc. 8th IEEE Int Advanced Video and Signal-Based Surveillance (AVSS) Conf, pages 197-202.
  17. Jungling, K., Bodensteiner, C., and Arens, M. (2011). Person re-identification in multi-camera networks. In Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition Workshops (CVPRW), pages 55-61.
  18. Kostinger, M., Hirzer, M., Wohlhart, P., Roth, P. M., and Bischof, H. (2012). Large scale metric learning from equivalence constraints. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pages 2288-2295.
  19. Kozakaya, T., Ito, S., and Kubota, S. (2011). Random ensemble metrics for object recognition. In ICCV'11, pages 1959-1966.
  20. Liu, C., Wang, G., Lin, X., and Li, L. (2012). Person reidentification by spatial pyramid color representation and local region matching. IEICE Transactions, 95- D(8):2154-2157.
  21. Ma, B., Su, Y., and Jurie, F. (2012). Local Descriptors Encoded by Fisher Vectors for Person Re-identification. In 12th European Conference on Computer Vision (ECCV) Workshops, pages 413-422, Italy.
  22. Mignon, A. and Jurie, F. (2012). Pcca: A new approach for distance learning from sparse pairwise constraints. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pages 2666-2672.
  23. Pedagadi, S., Orwell, J., Velastin, S. A., and Boghossian, B. A. (2013). Local fisher discriminant analysis for pedestrian re-identification. In CVPR, pages 3318- 3325.
  24. Prosser, B., Zheng, W.-S., Gong, S., and Xiang, T. (2010). Person re-identification by support vector ranking. In BMVC, pages 1-11.
  25. Swain, M. J. and Ballard, D. H. (1990). Indexing via color histograms. In ICCV'90, pages 390-393.
  26. Wu, Y., Mukunoki, M., Funatomi, T., Minoh, M., and Lao, S. (2011). Optimizing mean reciprocal rank for person re-identification. In Proc. 8th IEEE Int Advanced Video and Signal-Based Surveillance (AVSS) Conf, pages 408-413.
  27. Yang, J., Shi, Z., and Vela, P. A. (2011). Person reidentification by kernel pca based appearance learning. In CRV'11, pages 227-233.
  28. Zhang, Y. and Li, S. (2011). Gabor-lbp based region covariance descriptor for person re-identification. In Proc. Sixth Int Image and Graphics (ICIG) Conf, pages 368-371.
  29. Zhao, R., Ouyang, W., and Wang, X. (2013a). Person reidentification by salience matching. In IEEE International Conference on Computer Vision (ICCV), Sydney, Australia.
  30. Zhao, R., Ouyang, W., and Wang, X. (2013b). Unsupervised salience learning for person re-identification. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, USA.
  31. Zheng, W.-S., Gong, S., and Xiang, T. (2011). Person reidentification by probabilistic relative distance comparison. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pages 649-656.
  32. Zheng, W.-S., Gong, S., and Xiang, T. (2012). Transfer reidentification: From person to set-based verification. In CVPR, pages 2650-2657.
Download


Paper Citation


in Harvard Style

Pedagadi S., Orwell J. and Boghossian B. (2015). Pedestrian Re-identification - Metric Learning using Symmetric Ensembles of Categories . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 274-280. DOI: 10.5220/0005270602740280


in Bibtex Style

@conference{visapp15,
author={Sateesh Pedagadi and James Orwell and Boghos Boghossian},
title={Pedestrian Re-identification - Metric Learning using Symmetric Ensembles of Categories},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={274-280},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005270602740280},
isbn={978-989-758-090-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Pedestrian Re-identification - Metric Learning using Symmetric Ensembles of Categories
SN - 978-989-758-090-1
AU - Pedagadi S.
AU - Orwell J.
AU - Boghossian B.
PY - 2015
SP - 274
EP - 280
DO - 10.5220/0005270602740280