SDALF+C: Augmenting the SDALF Descriptor by Relation-Based Information for Multi-shot Re-identification

  • Sylvie Jasmine Poletti
  • Vittorio Murino
  • Marco Cristani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8259)


We present a novel multi-shot re-identification method, that merges together two different pattern recognition paradigms for describing objects: feature-based and relation-based. The former aims at encoding visual properties that characterize the object per se. The latter gives a relational description of the object considering how the visual properties are interdependent. The method considers SDALF as feature-based description: SDALF segregates salient body parts, exploiting symmetry and asymmetry principles. Afterwards, the parts are described by color, texture and region-based features. As relation-based description we consider the covariance of features, recently employed for re-identification: in practice, the parts found by SDALF are additionally encoded as covariance matrices, capturing structural properties otherwise missed. The resulting descriptor, dubbed SDALF+C, is superior to SDALF by about 2% and to the covariance-based description by a 53%, both in terms of average rank1 probability, considering 5 different multi-shot benchmark datasets (i-LIDS, ETHZ1,2,3 and CAVIAR4REID).


re-identification SDALF covariance of features 


  1. 1.
    Bak, S., Corvee, E., Bremond, F., Thonnat, M.: Multiple-shot human re-identification by mean riemannian covariance grid. In: AVSS (2011)Google Scholar
  2. 2.
    Bazzani, L., Cristani, M., Murino, V.: Symmetry-driven accumulation of local features for human characterization and re-identification. CVIU 117(2), 130–144 (2013)Google Scholar
  3. 3.
    Bazzani, L., Cristani, M., Perina, A., Murino, V.: Multiple-shot person re-identification by chromatic and epitomic analyses. PRL 33(7), 898–903 (2012)CrossRefGoogle Scholar
  4. 4.
    Figueira, D., Bazzani, L., Quang, M.H., Cristani, M., Bernardino, A., Murino, V.: Semi-supervised multi-feature learning for person re-identification. In: AVSS (2013)Google Scholar
  5. 5.
    Figueiredo, M., Jain, A.K.: Unsupervised learning of finite mixture models. TPAMI 24(3), 381–396 (2002)CrossRefGoogle Scholar
  6. 6.
    Forssen, P.E.: Maximally stable colour regions for recognition and matching. In: CVPR (2007)Google Scholar
  7. 7.
    Hirzer, M., Roth, P.M., Kostinger, M., Bischof, H.: Relaxed pairwise learned metric for person re-identification. In: ECCV (2012)Google Scholar
  8. 8.
    Pennec, X., Fillard, P., Ayache, N.: A riemannian framework for tensor computing. IJCV 66(1), 41–66 (2006)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Perina, A., Jojic, N., Cristani, M., Murino, V.: Stel component analysis: Joint segmentation, modeling and recognition of objects classes. IJCV 100(3), 241–260 (2012)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Satta, R., Fumera, G., Roli, F., Cristani, M., Murino, V.: A multiple component matching framework for person re-identification. In: Maino, G., Foresti, G.L. (eds.) ICIAP 2011, Part II. LNCS, vol. 6979, pp. 140–149. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Zheng, W., Gong, S., Xiang, T.: Associating groups of people. In: BMVC (2009)Google Scholar
  12. 12.
    Zheng, W., Gong, S., Xiang, T.: Re-identification by relative distance comparison. TPAMI (99) (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sylvie Jasmine Poletti
    • 1
  • Vittorio Murino
    • 2
    • 1
  • Marco Cristani
    • 1
    • 2
  1. 1.Department of Computer ScienceUniversity of VeronaItaly
  2. 2.Pattern Analysis and Computer Vision Dept.Istituto Italiano di TecnologiaItaly

Personalised recommendations