Towards View-point Invariant Person Re-identification via Fusion of Anthropometric and Gait Features from Kinect Measurements

Athira Nambiar, Alexandre Bernardino, Jacinto C. Nascimento, Ana Fred

Abstract

In this work, we present view-point invariant person re-identification (Re-ID) by multi-modal feature fusion of 3D soft biometric cues. We exploit the MS Kinect sensor v.2, to collect the skeleton points from the walking subjects and leverage both the anthropometric features and the gait features associated with the person. The key proposals of the paper are two fold: First, we conduct an extensive study of the influence of various features both individually and jointly (by fusion technique), on the person Re-ID. Second, we present an actual demonstration of the view-point invariant Re-ID paradigm, by analysing the subject data collected in different walking directions. Focusing the latter, we further analyse three different categories which we term as pseudo, quasi and full view-point invariant scenarios, and evaluate our system performance under these various scenarios. Initial pilot studies were conducted on a new set of 20 people, collected at the host laboratory. We illustrate, for the first time, gait-based person re-identification with truly view-point invariant behaviour, i.e. the walking direction of the probe sample being not represented in the gallery samples.

References

  1. Aarai, K. and Andrie, R. (2013). 3d skeleton model derived from kinect depth sensor camera and its application to walking style quality evaluations. In International Journal of Advanced Research in Artificial Intelligence 2.
  2. Andersson, V. O. and Araujo, R. M. (2015). Person identification using anthropometric and gait data from kinect sensor. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence.
  3. Ariyanto, G. and Nixon, M. S. (2011). Model-based 3d gait biometrics. In In International Joint Conference on Biometrics (IJCB).
  4. Barbosa, I. B., Cristani, M., Alessio, D. B., Bazzani, L., and Murino, V. (2012). Re-identification with rgb-d sensors. In Computer VisionECCV 2012. Workshops and Demonstrations.
  5. Dantcheva, A., Velardo, C., D'angelo, A., and Dugelay, J. (2010). Bag of soft biometrics for person identification : New trends and challenges. In Mutimedia Tools and Applications, Springer.
  6. Doretto, G., Sebastian, T., Tu, P., and Rittscher, J. (2011). Appearance-based person reidentification in camera networks: Problem overview and current approaches. In Journal of Ambient Intelligence and Humanized Computing, 2.
  7. Fernandez, D., Madrid-Cuevas, F., Carmona-Poyato, A., Muoz-Salinas, R., and Medina-Carnicer, R. (2016). A new approach for multi-view gait recognition on unconstrained paths. In Journal of Visual Communication and Image Representation 38.
  8. Gabel, M., Gilad-Bachrach, R., Renshaw, E., and Schuste, A. (2012). Full body gait analysis with kinect. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).
  9. Gianaria, E., Grangetto, M., Lucenteforte, M., and Balossino, N. (2014). Human classification using gait features. In Biometric Authentication 8897.
  10. Grother, P. and Phillips, P. J. (2004). Models of large population recognition performance. In Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
  11. Iwashita, Y., Baba, R., Ogawara, K., and Kurazume, R. (2010). Person identification from spatio-temporal 3d gait. In Proceedings of the International Conference on Emerging Security Technologies.
  12. Iwashita, Y., Ogawarab, K., and Kurazume, R. (2014). Identification of people walking along curved trajectories. In Pattern Recognition Letters 48.
  13. Lee, L. and Grimson, W. (2002). Gait analysis for recognition and classification. In Proc. IEEE International Conference on Automatic Face and Gesture Recognition.
  14. Nixon, M. S., Correia, P. L., Nasrollahi, K., Moeslund, T. B., Hadidd, A., and Tistarelli, M. (2015). On soft biometrics. In Pattern Recognition Letters 68.
  15. Riccio, D., Marsico, M., Distasi, R., and Ricciardi, S. (2014). A comparison of approaches for person reidentification. In International Conference on Pattern Recognition Applications and Methods.
  16. Seely, R. D., Samangooei, S., Middleton, L., Carter, J. N., and Nixon, M. S. (2008). The university of southampton multi-biometric tunnel and introducing a novel 3d gait dataset. In 2nd IEEE International Conference on Biometrics: Theory, Applications and Systems BTAS.
  17. Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A., Finocchio, M., Blake, A., Cook, M., and Moore, R. (2013). Real-time human pose recognition in parts from single depth images. In Communications of the ACM (CACM), 56(1).
  18. Sivapalan, S., Chen, D., Denman, S., Sridharan, S., and Fookes, C. (2011). 3d ellipsoid fitting for multiview gait recognition. In In Proceedings of 8th IEEE International Conference on Advanced Video and SignalBased Surveillance (AVSS).
  19. Zhao, G., Liu, G., Li, H., and Pietikinen, M. (2006). 3d gait recognition using multiple cameras. In 7th International Conference on Automatic Face and Gesture Recognition.
Download


Paper Citation


in Harvard Style

Nambiar A., Bernardino A., Nascimento J. and Fred A. (2017). Towards View-point Invariant Person Re-identification via Fusion of Anthropometric and Gait Features from Kinect Measurements . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 108-119. DOI: 10.5220/0006165301080119


in Bibtex Style

@conference{visapp17,
author={Athira Nambiar and Alexandre Bernardino and Jacinto C. Nascimento and Ana Fred},
title={Towards View-point Invariant Person Re-identification via Fusion of Anthropometric and Gait Features from Kinect Measurements},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={108-119},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006165301080119},
isbn={978-989-758-226-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Towards View-point Invariant Person Re-identification via Fusion of Anthropometric and Gait Features from Kinect Measurements
SN - 978-989-758-226-4
AU - Nambiar A.
AU - Bernardino A.
AU - Nascimento J.
AU - Fred A.
PY - 2017
SP - 108
EP - 119
DO - 10.5220/0006165301080119