Probabilistic matching pair selection for SURF-based person re-identification - Archive ouverte HAL
Communication Dans Un Congrès BIOSIG '12 : IEEE International Conference of the Biometrics Special Interest Group Année : 2012

Probabilistic matching pair selection for SURF-based person re-identification

Résumé

The objective of this paper is to study the performance of human reidentification based on multi-shot SURF and to assess its degradation according to the angular difference between the test and reference video scene view angles. In this context, we propose a new automatic statistical method of acceptance and rejection of SURF correspondence based on the likelihood ratio of two GMMs learned on the reference set and modeling the distribution of distances resulting from matching sequences associated with the same person and with different persons respectively. The experimental results show that our approach compares favorably with the state of the art and achieves a good performance.
Fichier non déposé

Dates et versions

hal-00745762 , version 1 (26-10-2012)

Identifiants

  • HAL Id : hal-00745762 , version 1

Citer

Mohamed Ibn Khedher, Mounim El Yacoubi, Bernadette Dorizzi. Probabilistic matching pair selection for SURF-based person re-identification. BIOSIG '12 : IEEE International Conference of the Biometrics Special Interest Group, Sep 2012, Darmstadt, Germany. pp.1-6. ⟨hal-00745762⟩
116 Consultations
0 Téléchargements

Partager

More