TNT logo LUH TNT

Multiple People Tracking

TNT members involved in this project:
Dipl.-Math. Roberto Henschel
Prof. Dr.-Ing. Bodo Rosenhahn
Dr.-Ing. Laura Leal-Taixé
Show active Staff only

Multiple people tracking is a challenging task of the computer vision domain, with applications in surveillance, action recognition and for example human-computer interaction systems.

Whereas single object tracking can be considered as almost solved, multiple people tracking still remains a difficult problem with ongoing research, due to the complex interaction between persons, that needs to be modeled in order to obtain good results.

We are interested in finding the global optimal solution to the data association problem. In order to do so, we propose to solve the tracking problem by using knowledge from graph theory:

  • We model the association problem as a hierarchical tracking problem in a DAG, which reduces wrong decisions in each step compared to other hierarchical approaches and we solve the association problem by efficiently computing a minimum cost arborescence.
  • We model the association problem in a network flow graph, include social and grouping behavior between objects and solve it by applying the simplex algorithm.

Show all publications
  • Roberto Henschel, Laura Leal-Taixé, Bodo Rosenhahn, Konrad Schindler
    Tracking with multi-level features
    arXiv, July 2016
  • Roberto Henschel, Laura Leal-Taixé, Rosenhahn Bodo
    Solving Multiple People Tracking In A Minimum Cost Arborescence
    IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW), 1st Workshop on Benchmarking Multi-target Tracking (BMTT), Waikoloa Beach, Hawaii, USA, January 2015
  • Roberto Henschel, Laura Leal-Taixé, Bodo Rosenhahn
    Efficient Multiple People Tracking Using Minimum Cost Arborescences
    German Conference on Pattern Recognition (GCPR), accepted as oral presentation, Münster, Germany, September 2014