Advertisement

Motion Reconstruction of Swarm-Like Self-organized Motor Bike Traffic from Public Videos

  • Benjamin RehEmail author
  • Katja MombaurEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9882)

Abstract

The process of modeling swarm behaviour based on natural phenomena usually involves the comparison to real world motion data. Our research focuses on analyzing and reproducing realistic behavior of self-organized traffic of motorbikes as it can be observed in some Asian metropoles such as Hanoi or Ho Chi Minh City. We introduce a semi-automatic method to extract motion trajectories of motorbikes in dense traffic situations from public video material. This technique can also be applied to other scenarios with a high density of entities that are only partialally visible on the video frame. To reconstruct these motions as trajectories on the ground plane, the camera pose is estimated using hints found in the videos. In addition we introduce a geometrical model for the locomotion of bikes which enables us to reconstruct the steering angle from the trajectories which gives more insight to the decision making process of the driver. A controlled experiment presented in this paper verifies the validity of our methods.

Keywords

Motion reconstruction Image recognition Self-organizing traffic Crowd simulation 

References

  1. 1.
    Allround vision: Crazy Hanoi Traffic. https://www.youtube.com/watch?v=Gf8_lzCWvq4. Accessed 10 Nov 2014
  2. 2.
    Bouguet, J.Y.: Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm. Intel Corporation 5 (2001)Google Scholar
  3. 3.
    Branson, K., Robie, A.A., Bender, J., Perona, P., Dickinson, M.H.: High-throughput ethomics in large groups of drosophila. Nat. Methods 6(6), 451–457 (2009)CrossRefGoogle Scholar
  4. 4.
    Lochmatter, T., Roduit, P., Cianci, C., Correll, N., Jacot, J., Martinoli, A.: Swistrack - a flexible open source tracking software for multi-agent systems. In: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4004–4010, September 2008Google Scholar
  5. 5.
    Mor, J.: The levenberg-marquardt algorithm: implementation and theory. In: Watson, G. (ed.) Numerical Analysis. LNCS, vol. 630, pp. 105–116. Springer, Heidelberg (1978)CrossRefGoogle Scholar
  6. 6.
    Nelder, J.A., Mead, R.: A simplex method for function minimization. Comput. J. 7, 308–313 (1965)CrossRefzbMATHGoogle Scholar
  7. 7.
    Olivier, A.H., Marin, A., Crétual, A., Berthoz, A., Pettré, J.: Collision avoidance between two walkers: role-dependent strategies. Gait Posture 38(4), 751–756 (2013)CrossRefGoogle Scholar
  8. 8.
    Pettré, J., Ondřej, J., Olivier, A.H., Cretual, A., Donikian, S.: Experiment-based modeling, simulation and validation of interactions between virtual walkers. In: Proceedings of the 2009 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA 2009, New York, NY, USA, pp. 189–198 ACM (2009)Google Scholar
  9. 9.
    Shi, J., Tomasi, C.: Good features to track. In: 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Proceedings CVPR 1994, pp. 593–600. IEEE, June 1994Google Scholar
  10. 10.
    Whitworth, R.: Ho Chi Minh City (Saigon), Vietnam Rush Hour Traffic in Real Time. https://www.youtube.com/watch?v=Op1hdgzmhXM. Accessed 10 Nov 2014

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Optimization in Robotics and Biomechanics, Interdisciplinary Center for Scientific ComputingHeidelberg UniversityHeidelbergGermany

Personalised recommendations