Time to Collision and Collision Risk Estimation from Local Scale and Motion

  • Shrinivas Pundlik
  • Eli Peli
  • Gang Luo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6938)


Computer-vision based collision risk assessment is important in collision detection and obstacle avoidance tasks. We present an approach to determine both time to collision (TTC) and collision risk for semi-rigid obstacles from videos obtained with an uncalibrated camera. TTC for a body moving relative to the camera can be calculated using the ratio of its image size and its time derivative. In order to compute this ratio, we utilize the local scale change and motion information obtained from detection and tracking of feature points, wherein lies the chief novelty of our approach. Using the same local scale change and motion information, we also propose a measure of collision risk for obstacles moving along different trajectories relative to the camera optical axis. Using videos of pedestrians captured in a controlled experimental setup, in which ground truth can be established, we demonstrate the accuracy of our TTC and collision risk estimation approach for different walking trajectories.


Ground Truth Feature Point Motion Information Collision Risk Affine Motion 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lee, D.N.: A theory of the visual control of braking based on information about time-to-collision Perception 5, 437–459 (1976)Google Scholar
  2. 2.
    Tresilian, J.R.: Visually timed action: time-out for ’tau’? Trends in Cognitive Sciences 3, 301–310 (1999)CrossRefGoogle Scholar
  3. 3.
    Luo, G., Woods, R., Peli, E.: Collision judgment when using an augmented vision head mounted display device. Investigative Ophthalmology and Visual Science 50, 4509–4515 (2009)CrossRefGoogle Scholar
  4. 4.
    Cipolla, R., Blake, A.: Surface orientation and time to contact from divergence and deformation. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 187–202. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  5. 5.
    Ancona, N., Poggio, T.: Optical flow from 1d correlation: Application to a simple time to crash detector. International Journal of Computer Vision 14, 131–146 (1995)CrossRefGoogle Scholar
  6. 6.
    Alenya, G., Negre, A., Crowley, J.L.: A Comparison of Three Methods for Measure of Time to Contact. In: IEEE/RSJ Conference on Intelligent Robots and Systems, pp. 1–6 (2009)Google Scholar
  7. 7.
    Meyer, F.G.: Time-to-collision from first order models of the motion field. IEEE Transactions on Robotics and Automation 10, 792–798 (1994)CrossRefGoogle Scholar
  8. 8.
    Camus, T.A.: Calculating time-to-contact using real time quantized optical flow. Max-Planck-Institut fur Biologische Kybernetik Technical Report (1995)Google Scholar
  9. 9.
    Horn, B.K.P., Fang, Y., Masaki, I.: Time to Contact Relative to a Planar Surface. In: IEEE Intelligent Vehicle Symposium, pp. 68–74 (2007)Google Scholar
  10. 10.
    Horn, B.K.P., Fang, Y., Masaki, I.: Hierarchical framework for direct gradient-based time-to-contact estimation. In: IEEE Intelligent Vehicle Symposium, pp. 1394–1400 (2009)Google Scholar
  11. 11.
    Lourakis, M., Orphanoudakis, S.: Using planar parallax to estimate the time-to-contact. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 640–645 (1999)Google Scholar
  12. 12.
    Colombo, C., DelBimbo, A.: Generalized bounds for time to collision from first order image motion. In: IEEE International Conference on Computer Vision, pp. 220–226 (1999)Google Scholar
  13. 13.
    Negre, A., Braillon, C., Crowley, J.L., Laugier, C.: Real time time to collision from variation of intrinsic scale. In: Proceedings of the International Symposium on Experimental Robotics, pp. 75–84 (2006)Google Scholar
  14. 14.
    Muller, D., Pauli, J., Nunn, C., Gormer, S., Muller-Schneiders, S.: Time to Contact Estimation Using Interest Points. In: IEEE Conference on Intelligent Transportation Systems, pp. 1–6 (2009)Google Scholar
  15. 15.
    Shi, J., Tomasi, C.: Good Features to Track. In: IEEE Conference On Computer Vision And Pattern Recognition, pp. 593–600 (1994)Google Scholar
  16. 16.
    Lowe, D.: Distinctive image features from scale invariant keypoints. International Journal of Computer Vision 60, 75–84 (2004)CrossRefGoogle Scholar
  17. 17.
    Bouguet, J.Y.: Pyramidal implementation of the lucas-kanade feature tracker (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Shrinivas Pundlik
    • 1
  • Eli Peli
    • 1
  • Gang Luo
    • 1
  1. 1.Schepens Eye Research InstituteHarvard Medical SchoolBostonUSA

Personalised recommendations