International Journal of Social Robotics

, Volume 2, Issue 1, pp 19–30 | Cite as

Multi-model Hypothesis Group Tracking and Group Size Estimation

  • Boris LauEmail author
  • Kai O. Arras
  • Wolfram Burgard


People tracking is essential for robots that are supposed to interact with people. The majority of approaches track humans in the vicinity of the robot independently. However, people typically form groups that split and merge. These group formation processes reflect social relations and interactions that we seek to recognize in this paper. To this end, we pose the group tracking problem as a recursive multi-hypothesis model selection problem in which we hypothesize over both, the partitioning of tracks into groups (models) and the association of observations to tracks (assignments). Model hypotheses that include split, merge, and continuation events are first generated in a data-driven manner and then validated by means of the assignment probabilities conditioned on the respective model. Observations are found by clustering points from a laser range finder and associated to existing group tracks using the minimum average Hausdorff distance. We further propose a method to estimate the number of people in the individual groups. Experiments with a mobile robot demonstrate that the approach is able to accurately recover social grouping of people with respect to the ground truth. The results also show that tracking groups is clearly more efficient than tracking people separately. Our system runs in real-time on a typical desktop computer.

Group tracking People tracking Laser-based tracking Mobile robot Multi-hypothesis tracking Proxemics theory Interaction Social relations 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kluge B, Köhler C, Prassler E (2001) Fast and robust tracking of multiple moving objects with a laser range finder. In: Proceedings of the IEEE int. conf. on robotics and automation Google Scholar
  2. 2.
    Fod A, Howard A, Mataric MJ (2002) Laser-based people tracking. In: IEEE intl. conf. on robotics and automation (ICRA), Washington DC, May 2002, pp 3024–3029 Google Scholar
  3. 3.
    Schulz D, Burgard W, Fox D, Cremers A (2003) People tracking with a mobile robot using sample-based joint probabilistic data association filters. Intl J Robotics Res. 22(2) Google Scholar
  4. 4.
    Cui J, Zha H, Zhao H, Shibasaki R (2005) Tracking multiple people using laser and vision. In: IEEE/RSJ international conference on intelligent robots and systems, Alberta, Canada Google Scholar
  5. 5.
    Zajdel W, Zivkovic Z, Kröse B (2005) Keeping track of humans: Have I seen this person before? In: IEEE international conference on robotics and automation, Barcelona, Spain Google Scholar
  6. 6.
    Taylor G, Kleeman L (2004) A multiple hypothesis walking person tracker with switched dynamic model. In: Proc. of the Australasian conference on robotics and automation, Canberra, Australia Google Scholar
  7. 7.
    Arras KO, Grzonka S, Luber M, Burgard W (2008) Efficient people tracking in laser range data using a multi-hypothesis leg-tracker with adaptive occlusion probabilities. In IEEE international conference on robotics and automation (ICRA), Pasadena, CA, USA, May 2008 Google Scholar
  8. 8.
    Khan Z, Balch T, Dellaert F (2006) MCMC data association and sparse factorization updating for real time multitarget tracking with merged and multiple measurements. IEEE Trans. Pattern Analysis Mach Intell 28(12) Google Scholar
  9. 9.
    Mucientes M, Burgard W (2006) Multiple hypothesis tracking of clusters of people. In: IEEE/RSJ international conference on intelligent robots and systems, October 2006, pp 692–697 Google Scholar
  10. 10.
    McKenna S, Jabri S, Duric Z, Rosenfeld A, Wechsler H (2000) Tracking groups of people. Comput Vis Image Underst 80(1):42–56 zbMATHCrossRefGoogle Scholar
  11. 11.
    Gennari G, Hager GD (2004) Probabilistic data association methods in visual tracking of groups. In: IEEE conference on computer vision pattern recognition (CVPR) Google Scholar
  12. 12.
    Bose B, Wang X, Grimson E (2007) Multi-class object tracking algorithm that handles fragmentation and grouping. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1–8 Google Scholar
  13. 13.
    Reid DB (1979) An algorithm for tracking multiple targets. IEEE Trans Autom Control AC-24(6):843–854 CrossRefGoogle Scholar
  14. 14.
    Cox I, Hingorani S (1996) An efficient implementation of Reid’s multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Trans Pattern Analysis Mach Intell 18(2):138–150 CrossRefGoogle Scholar
  15. 15.
    Joo S-W, Chellappa R (2007) A multiple-hypothesis approach for multiobject visual tracking. IEEE Trans Image Process 16(11):2849–2854 CrossRefMathSciNetGoogle Scholar
  16. 16.
    Murty K (1968) An algorithm for ranking all the assignments in order of increasing cost. Oper Res 16:682–687 zbMATHCrossRefGoogle Scholar
  17. 17.
    Lau B, Arras KO, Burgard W (2009) Tracking groups of people with a multi-model hypothesis tracker. In: International conference on robotics and automation (ICRA), Kobe, Japan Google Scholar
  18. 18.
    Hall E (1974) Handbook of proxemics research. Society for the Anthropology of Visual Communications Google Scholar
  19. 19.
    Arras KO, Martínez Mozos Ó, Burgard W (2007) Using boosted features for the detection of people in 2d range data. In: Proc. IEEE intl. conf. on robotics and automation (ICRA’07), Rome, Italy Google Scholar
  20. 20.
    Hartigan J (1975) Clustering algorithms. Wiley, New York zbMATHGoogle Scholar
  21. 21.
    Dubuisson MP, Jain AK (1994) A modified Hausdorff distance for object matching. In: Intl. conference on pattern recognition, vol 1, Jerusalem, Israel, pp A:566–568 Google Scholar
  22. 22.
    Cox I, Miller M (1995) On finding ranked assignments with application to multi-target tracking and motion correspondence. IEEE Trans Aerosp Electron Syst 31(1):486–489 CrossRefGoogle Scholar

Copyright information

© Springer Science & Business Media BV 2009

Authors and Affiliations

  1. 1.Autonomous Intelligent Systems Group, Department of Computer ScienceUniversity of FreiburgFreiburgGermany
  2. 2.Social Robotics Laboratory, Department of Computer ScienceUniversity of FreiburgFreiburgGermany

Personalised recommendations