access icon free Person re-identification by multi-statistics on pyramid of covariance matrices

© The Institution of Engineering and Technology
Received 27/07/2013, Published

A novel and efficient covariance-based method for person re-identification is proposed. The approach exploits three colourspaces and intensity gradients as covariance features and extracts multiple statistical feature vectors from the pyramid of region covariance matrices. The distance measure of the covariance pyramid is designed to be the weighted combination of four vectorised statistical features by cascading on the covariance pyramid. The method is compared with the state-of-the-art methods using a benchmark dataset and is demonstrated to outperform other state-of-the-art methods.

Inspec keywords: feature extraction; video surveillance; statistical analysis; covariance matrices

Other keywords: intensity gradients; feature extraction; region covariance matrices; person re-identification; covariance-based method; covariance pyramid; multiple statistical feature vectors; video surveillance

Subjects: Other topics in statistics; Algebra; Image recognition; Algebra; Computer vision and image processing techniques; Other topics in statistics; Video signal processing

References

    1. 1)
      • 4. Bak, S., Corvee, E., Brémond, F., Thonnat, M.: ‘Person re-identification using spatial covariance regions of human body parts’. Int. Conf. Advanced Video and Signal Based Surveillance, Boston, MA, USA, 2010, pp. 435–440.
    2. 2)
      • 5. Hirzer, M., Beleznai, C., Roth, P.M.: ‘Person re-identification by descriptive and discriminative classification’. Scandinavian Conf. Image Analysis, Ystad, Sweden, 2010, pp. 91–102.
    3. 3)
      • 2. Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: ‘Person re-identification by symmetry-driven accumulation of local features’. IEEE Conf. Computer Vision and Pattern Recognition, San Francisco, CA, USA, 2010, pp. 2360–2367.
    4. 4)
      • 7. Ma, B.P., Yu, S., Frédéric, J.: ‘BiCov: a novel image representation for person re-identification and face verification’. Proc. British Machine Vision Conf., Guildford, UK, 2012, pp. 57.1–57.11.
    5. 5)
      • 1. Gray, D., Hai, T.: ‘Viewpoint invariant pedestrian recognition with an ensemble of localized features’. Proc. European Conf. Computer Vision, Marseille, France, 2008, pp. 262–275.
    6. 6)
      • 6. Hong, X., Chang, H., Shan, S., Chen, X.: ‘Sigma set: a small second order statistical region descriptor’. IEEE Conf. Computer Vision and Pattern Recognition, Miami, FL, USA, 2009, pp. 1802–1809.
    7. 7)
      • 3. Martinel, N., Foresti, G.L.: ‘Multi-signature based person re-identification’, Electron. Lett., 2012, 48, (13), pp. 765–767 (doi: 10.1049/el.2012.1607).
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2013.2442
Loading

Related content

content/journals/10.1049/el.2013.2442
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading