Advertisement

Safety Quantification of Intersections Using Computer Vision Techniques

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9474)

Abstract

Vision-based safety analysis is a difficult task since traditional motion-based techniques work poorly when pedestrians and vehicles stop due to traffic signals. This work presents a tracking method in order to provide a robust tracking of pedestrians and vehicles, and quantify safety through investigating the tracks. Surrogate safety measurements are estimated including TTC and DTI values for a highly cluttered video of Las Vegas intersection and the performance of the tracking system is evaluated at detection and tracking steps separately.

Keywords

Bipartite Graph Optical Flow Gaussian Mixture Model Local Binary Pattern Traffic Signal 
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.

Notes

Acknowledgement

The authors acknowledge the Nevada Department of Transportation for their support of this research.

References

  1. 1.
    Liu, Y., Ozguner, U., Ekici, E.: Performance evaluation of intersection warning system using a vehicle traffic and wireless simulator. In: Proceedings of IEEE Intelligent Vehicles Symposium, pp. 171–176 (2005)Google Scholar
  2. 2.
    Shirazi, M., Morris, B.: Observing behaviors at intersections: a review of recent studies and developments. In: 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 1258–1263 (2015)Google Scholar
  3. 3.
    Chin, H.C., Quek, S.T.: Measurement of traffic conflicts. J. Comput. Sci. 26(3), 169–185 (1997)CrossRefGoogle Scholar
  4. 4.
    Shirazi, M.S., Morris, B.: A typical video-based framework for counting, behavior and safety analysis at intersections. In: 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 1264–1269 (2015)Google Scholar
  5. 5.
    Sayed, T., Zaki, M.H., Autey, J.: A novel approach for diagnosing cycling safety issues using automated computer vision techniques. Transportation Research Board Annual Meeting Compendium of Papers (2013)Google Scholar
  6. 6.
    Zaki, M.H., Tarek, S., Tageldin, A., Hussein, M.: Application of computer vision to diagnosis of pedestrian safety issues. Transp. Res. Rec. J. Transp. Res. Board 2393, 75–84 (2013)CrossRefGoogle Scholar
  7. 7.
    Shirazi, M.S., Morris, B.: Contextual combination of appearance and motion for intersection videos with vehicles and pedestrians. In: Bebis, G., et al. (eds.) ISVC 2014, Part I. LNCS, vol. 8887, pp. 708–717. Springer, Heidelberg (2014) Google Scholar
  8. 8.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking, pp. 246–252 (1999)Google Scholar
  9. 9.
    Ojala, T., Pietikainen, M., Harwood, D.: A comparative study of texture measures with classification based on feature distributions. Trans. Pattern Recogn. 29, 51–59 (1996)CrossRefGoogle Scholar
  10. 10.
    Shirazi, M.S., Morris, B.: Vision-based turning movement counting at intersections by cooperating zone and trajectory comparison modules. In: Proceedings of 17th International IEEE Conference on Intelligent Transportation Systems, Qingdao, China, pp. 3100–3105 (2014)Google Scholar
  11. 11.
    Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors. Intern. J. Comput. Vis. 75, 247–266 (2007)CrossRefGoogle Scholar
  12. 12.
    Saunier, N., Sayed, T.: A feature-based tracking algorithm for vehicles in intersections. Proceedings of 3rd Canadian Conference on Computer and Robot Vision, Quebec, Canada, p. 59 (2006)Google Scholar
  13. 13.
    Ismail, K., Sayed, T., Saunier, N.: Automated analysis of pedestrian-vehicle: conflicts context for before-and-after studies. Transp. Res. Rec. J. Trans. Res. Board 2198, 52–64 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.University of Nevada, Las VegasLas VegasUSA

Personalised recommendations