Introducing Context Awareness in Multi-Target Tracking using Re-Identification Methodologies

Abstract:


In this paper, re-identification techniques are exploited to add context awareness to a multi-target tracker and enhance its tracking performance, in an online manner. To achieve that, targets are labeled as independent, occluders or occluded ones, based on the completeness of their appearance information. For each category, a different tracking strategy is employed to achieve the optimal results. In cases of tracking failure, an online automated re-identification technique is proposed, to alleviate multiple identity assignments to the same target. Experimental evaluation conducted on the CAVIAR and PETS 2009 datasets shows that the proposed mechanism enhances tracking performance compared to a baseline tracker and achieves competitive performance with state of the art methods.


  • V. Lovatsis, A. Dimou, P. Daras, "Introducing Context Awareness in Multi-Target Tracking using Re-Identification Methodologies", 5th International Conference on Imaging for Crime Detection and Prevention (ICDP-13), London, 16th-17th December, 2013.

  • Full document available here.
    Contact Information

    Dr. Petros Daras, Principal Researcher Grade Α
    1st km Thermi – Panorama, 57001, Thessaloniki, Greece
    P.O.Box: 60361
    Tel.: +30 2310 464160 (ext. 156)
    Fax: +30 2310 464164
    Email: daras@iti.gr