Stereo-based Pedestrian Detection in Crosswalks for Pedestrian Behavioural Modelling Assessment

D. F. Llorca, I. Parra, R. Quintero, C. Fernández, R. Izquierdo, M. A. Sotelo

2014

Abstract

In this paper, a stereo- and infrastructure-based pedestrian detection system is presented to deal with infrastructure-based pedestrian safety measurements as well as to assess pedestrian behaviour modelling methods. Pedestrian detection is performed by region growing over temporal 3D density maps, which are obtained by means of stereo reconstruction and background modelling. 3D tracking allows to correlate the pedestrian position with the different pedestrian crossing regions (waiting and crossing areas). As an example of an infrastructure safety system, a blinking luminous traffic sign is switched on to warn the drivers about the presence of pedestrians in the waiting and the crossing regions. The detection system provides accurate results even for nighttime conditions: an overall detection rate of 97.43% with one false alarm per each 10 minutes. In addition, the proposed approach is validated for being used in pedestrian behaviour modelling, applying logistic regression to model the probability of a pedestrian to cross or wait. Some of the predictor variables are automatically obtained by using the pedestrian detection system. Other variables are still needed to be labelled using manual supervision. A sequential feature selection method showed that time-to-collision and pedestrian waiting time (both variables automatically collected) are the most significant parameters when predicting the pedestrian intent. An overall predictive accuracy of 93.10% is obtained, which clearly validates the proposed methodology.

References

  1. Í lvarez, S., Llorca, D. F., and Sotelo, M. A. (2014). Hierarchical camera auto-calibration for traffic surveillance systems. Expert Systems with Applications, 41:1532- 1542.
  2. Í lvarez, S., Sotelo, M. A., Llorca, D. F., Quintero, R., and Marcos, O. (2012). Monocular vision-based target detection on dynamic transport infrastructures. Lecture Notes in Computer Science, 6927:576-583.
  3. Das, S., Manski, C. F., and Manuszak, M. D. (2005). Walk or wait? an empirical analysis of street crossing decisions. Journal of Applied Econometrics, 20(4):529- 548.
  4. EC (2012). Basic fact sheets 2012. mobility and transport, road safety. site: http://ec.europa.eu/transport/ road safety/specialist/statistics/index en.htm.
  5. Favoreel, W. (2011). Pedestrian sensing for increased traffic safety and efficiency at signalized intersections. In 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance.
  6. Gerónimo, D. and L ópez, A. M. (2014). Vision-based Pedestrian Protection Systems for Intelligent Vehicles. Springer.
  7. Kadali, B. R. and Vedagiri, P. (2013). Modelling pedestrian road crossing behaviour under mixed traffic condition. European Transport, 15(3).
  8. Keller, C. G., Enzweiler, M., Rohrbach, M., D. F. Llorca, C. S., and Gavrila, D. M. (2011). The benefits of dense stereo for pedestrian detection. IEEE Transactions on Intelligent Transportation Systems, 12(4):1096-1106.
  9. Keller, C. G. and Gavrila, D. M. (2014). Will the pedestrian cross? a study on pedestrian path prediction. IEEE Transactions on Intelligent Transportation Systems. In press.
  10. Koh, P. P. and Wong, Y. D. (2014). Gap acceptance of violators at signalised pedestrian crossings. Accident Analysis and Prevention, 62:178-185.
  11. Kohler, S., Goldhammer, M., Bauer, S., Zecha, S., Doll, K., Brunsmann, U., and Dietmayer, K. (2013). Stationary detection of the pedestrian's intention at intersections. IEEE Intelligent Transportation Systems Magazine, 5(4):87-99.
  12. Llorca, D. F., Milanés, V., Parra, I., Gavilán, M., Daza, I. G., Pérez, J., and Sotelo, M. A. (2011). Autonomous pedestrian collision avoidance using a fuzzy steering controller. IEEE Transactions on Intelligent Transportation Systems, 12(2):390-401.
  13. Llorca, D. F., Sotelo, M. A., Hellín, A. M., Gavilán, M., Daza, I. G., and Lorente, A. G. (2012). Stereo regionsof-interest selection for pedestrian protection: a survey. Transportation Research Part C, 25:226-237.
  14. Milanes, V., Llorca, D. F., Villagrá, J., Pérez, J., Parra, I., González, C., and Sotelo, M. A. (2012). Vision-based active safety system for automatic stopping. Expert Systems with Applications, 39(12):11234-11242.
  15. Nedevschi, S., Bota, S., and Tomiuc, C. (2009). Stereobased pedestrian detection for collision-avoidance applications. IEEE Transactions on Intelligent Transportation Systems, 10(3):380-391.
  16. Parra, I., Llorca, D. F., Sotelo, M. A., Bergasa, L. M., de Toro, P. R., Nuevo, J., Ocana, M., and GarcíaGarrido., M. A. (2007). Combination of feature extraction methods for svm pedestrian detection. IEEE Transactions on Intelligent Transportation Systems, 8(2):292-307.
  17. Quintero, R., Almeida, J., Llorca, D. F., and Sotelo, M. A. (2014). Pedestrian path prediction using body language traits. In IV2014, IEEE Intelligent Vehicle Symposium.
  18. Schmidt, S. and Farber, B. (2009). Pedestrians at the kerb - recognising the action intentions of humans. Transportation Research Part F, 12(4):300-310.
  19. Weimer, D., Kohler, S., Hellert, C., Doll, K., Brunsmann, U., and Krzikalla, R. (2011). Gpu architecture for stationary multisensor pedestrian detection at smart intersections. In IV2011, IEEE Intelligent Vehicle Symposium.
Download


Paper Citation


in Harvard Style

F. Llorca D., Parra I., Quintero R., Fernández C., Izquierdo R. and A. Sotelo M. (2014). Stereo-based Pedestrian Detection in Crosswalks for Pedestrian Behavioural Modelling Assessment . In Proceedings of the 11th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-758-040-6, pages 102-109. DOI: 10.5220/0005055401020109


in Bibtex Style

@conference{icinco14,
author={D. F. Llorca and I. Parra and R. Quintero and C. Fernández and R. Izquierdo and M. A. Sotelo},
title={Stereo-based Pedestrian Detection in Crosswalks for Pedestrian Behavioural Modelling Assessment},
booktitle={Proceedings of the 11th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2014},
pages={102-109},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005055401020109},
isbn={978-989-758-040-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Stereo-based Pedestrian Detection in Crosswalks for Pedestrian Behavioural Modelling Assessment
SN - 978-989-758-040-6
AU - F. Llorca D.
AU - Parra I.
AU - Quintero R.
AU - Fernández C.
AU - Izquierdo R.
AU - A. Sotelo M.
PY - 2014
SP - 102
EP - 109
DO - 10.5220/0005055401020109