Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification

Vito Renò, Angelo Cardellicchio, Tiziano Politi, Cataldo Guaragnella, Tiziana D'Orazio

2016

Abstract

In this paper, a method to find, exploit and classify ambiguities in the results of a person re-identification (PRID) algorithm is presented. We start from the assumption that ambiguity is implicit in the classical formulation of the re-identification problem, as a specific individual may resemble one or more subjects by the color of dresses or the shape of the body. Therefore, we propose the introduction of the AMbiguity rAte in REidentification (AMARE) approach, which relates the results of a classical PRID pipeline on a specific dataset with their effectiveness in re-identification terms, exploiting the ambiguity rate (AR). As a consequence, the cumulative matching curves (CMC) used to show the results of a PRID algorithm will be filtered according to the AR. The proposed method gives a different interpretation of the output of PRID algorithms, because the CMC curves are processed, split and studied separately. Real experiments demonstrate that the separation of the results is really helpful in order to better understand the capabilities of a PRID algorithm.

References

  1. Bauml, M. and Stiefelhagen, R. (2011). Evaluation of local features for person re-identification in image sequences. In Adv. Video and Signal-Based Surveill.
  2. Bedagkar-Gala, A. and Shah, S. K. (2014). A survey of approaches and trends in person re-identification. Image and Vis. Comput., 32(4):270-286.
  3. Cardellicchio, A., D'Orazio, T., Politi, T., and Renò, V. (2015). An human perceptive model for person reidentification. In VISAPP-Int. Conf. on Comput. Vis. Theory and Appl.-2015.
  4. Corvee, E., Bak, S., Bremond, F., et al. (2012). People detection and re-identification for multi surveillance cameras. In VISAPP-Int. Conf. on Comput. Vis. Theory and Appl.-2012.
  5. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Comput. Vis. and Pattern Recognit., 2005. CVPR 2005. IEEE Comput. Soc. Conf. on, volume 1, pages 886-893. IEEE.
  6. D'Orazio, T. and Cicirelli, G. (2012). People reidentification and tracking from multiple cameras: A review. In Image Process. (ICIP), 2012 19th IEEE Int. Conf. on, pages 1601-1604.
  7. D'Orazio, T. and Guaragnella, C. (2012). A graph-based signature generation for people re-identification in a multi-camera surveillance system. In VISAPP, volume 1, pages 414-417.
  8. D'Orazio, T., Mazzeo, P., and Spagnolo, P. (2009). Color brightness transfer function evaluation for non overlapping multi camera tracking. In Distrib. Smart Cameras, 2009. ICDSC 2009. Third ACM/IEEE Int. Conf. on, pages 1-6. IEEE.
  9. Farenzena, M., Bazzani, L., Perina, A., Murino, V., and Cristani, M. (2010). Person re-identification by symmetry-driven accumulation of local features. In Comput. Vis. and Pattern Recognit. (CVPR), 2010 IEEE Conf. on, pages 2360-2367. IEEE.
  10. Gheissari, N., Sebastian, T. B., and Hartley, R. (2006). Person reidentification using spatiotemporal appearance. In Comput. Vis. and Pattern Recognit., 2006 IEEE Comput. Soc. Conf. 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 Proc. IEEE Int. Workshop on Perform. Eval. for Track. and Surveill. (PETS), volume 3. Citeseer.
  12. Gray, D. and Tao, H. (2008). Viewpoint invariant pedestrian recognition with an ensemble of localized features. In Comput. Vis.-ECCV 2008 , pages 262-275. Springer.
  13. Javed, O., Shafique, K., Rasheed, Z., and Shah, M. (2008). Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views. Comput. Vis. and Image Understanding, 109(2):146- 162.
  14. Jojic, N., Perina, A., Cristani, M., Murino, V., and Frey, B. (2009). Stel component analysis: Modeling spatial correlations in image class structure. In Comput. Vis. and Pattern Recognit., 2009. CVPR 2009. IEEE Conf. on, pages 2044-2051. IEEE.
  15. Lantagne, M., Parizeau, M., and Bergevin, R. (2003). Vip: Vision tool for comparing images of people. In Vis. Interface, volume 2.
  16. Lu, J. and Zhang, E. (2007). Gait recognition for human identification based on ica and fuzzy svm through multiple views fusion. Pattern Recognit. Lett., 28(16):2401-2411.
  17. Renò, V., Marani, R., D'Orazio, T., Stella, E., and Nitti, M. (2014). An adaptive parallel background model for high-throughput video appl. and smart cameras embedding. In Proc. of the Int. Conf. on Distrib. Smart Cameras, ICDSC 7814, pages 30:1-30:6, New York, NY, USA. ACM.
  18. Roy, A., Sural, S., and Mukherjee, J. (2012). A hierarchical method combining gait and phase of motion with spatiotemporal model for person re-identification. Pattern Recognit. Lett., 33(14):1891-1901.
  19. Saghafi, M. A., Hussain, A., Zaman, H. B., and Saad, M. H. M. (2014). Review of person re-identification techniques. IET Comput. Vis., 8(6):455-474.
  20. Spagnolo, P., Leo, M., D'Orazio, T., and Distante, A. (2004). Robust moving objects segmentation by background subtraction. In The International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS).
  21. Stauffer, C. and Grimson, W. E. L. (1999). Adaptive background mixture models for real-time tracking. In Comput. Vis. and Pattern Recognit., 1999. IEEE Comput. Soc. Conf. on., volume 2. IEEE.
  22. Wang, X., Doretto, G., Sebastian, T., Rittscher, J., and Tu, P. (2007). Shape and appearance context modeling. In Comput. Vis., 2007. ICCV 2007. IEEE 11th Int. Conf. on, pages 1-8. IEEE.
  23. Yang, L. and Jin, R. (2006). Distance metric learning: A comprehensive survey. Michigan State Universiy, 2.
  24. Zheng, W.-S., Gong, S., and Xiang, T. (2009). Associating groups of people. In Proc. of the British Machine Vis. Conf., pages 23.1-23.11. BMVA Press. doi:10.5244/C.23.23.
  25. Zivkovic, Z. (2004). Improved adaptive gaussian mixture model for background subtraction. In Pattern Recognit., 2004. ICPR 2004. Proc. of the 17th Int. Conf. on, volume 2, pages 28-31 Vol.2.
Download


Paper Citation


in Harvard Style

Renò V., Cardellicchio A., Politi T., Guaragnella C. and D'Orazio T. (2016). Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 484-494. DOI: 10.5220/0005822104840494


in Bibtex Style

@conference{icpram16,
author={Vito Renò and Angelo Cardellicchio and Tiziano Politi and Cataldo Guaragnella and Tiziana D'Orazio},
title={Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={484-494},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005822104840494},
isbn={978-989-758-173-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification
SN - 978-989-758-173-1
AU - Renò V.
AU - Cardellicchio A.
AU - Politi T.
AU - Guaragnella C.
AU - D'Orazio T.
PY - 2016
SP - 484
EP - 494
DO - 10.5220/0005822104840494