Statistical Modelling of Object Detection in Stereo Vision-Based Driver Assistance

  • Jan Erik Stellet
  • Jan Schumacher
  • Oliver Lange
  • Wolfgang Branz
  • Frank Niewels
  • J. Marius Zöllner
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 302)


In this work, a statistical analysis of object detection for stereo vision-based driver assistance systems is presented. Analytic modelling has not been attempted previously due to the complexity of dense disparity maps and state-of-the-art algorithms. To approach this problem, a simplified algorithm for object detection in stereo images which allows studying error propagation is considered. In order to model the input densities, vehicle contours are approximated by Gaussian Mixture Models and distance dependent measurement noise is taken into account. Theoretical results are verified with Monte Carlo methods and real-world image sequences. Using the proposed model, a prediction on the uncertainty in object location and optimal threshold selection can be obtained.


Driver assistance Stereo vision Object detection  Statistical modelling Error propagation 


  1. 1.
    Badino, H.: Binocular Ego-Motion Estimation for Automotive Applications. Ph.D. thesis, Goethe Universitaet Frankfurt am Main (2008)Google Scholar
  2. 2.
    Barth, A.: Vehicle Tracking and Motion Estimation Based on Stereo Vision Sequences. Ph.D. thesis, Friedrich-Wilhelms-Universitaet zu Bonn (2010)Google Scholar
  3. 3.
    Chang, P., Hirvonen, D., Camus, T., Southall, B.: Stereo-based object detection, classification, and quantitative evaluation with automotive applications. In: Computer Vision and Pattern Recognition - Workshops, 2005. CVPR Workshops. IEEE Computer Society Conference on. pp. 62–62 (2005)Google Scholar
  4. 4.
    DasGupta, A.: Asymptotic theory of statistics and probability. Springer (2008)Google Scholar
  5. 5.
    Fessler, J.: Mean and variance of implicitly defined biased estimators (such as penalized maximum likelihood): applications to tomography. Image Processing, IEEE Transactions on 5(3), 493–506 (1996)Google Scholar
  6. 6.
    Hillenbrand, J., Kroschel, K.: A study on the performance of uncooperative collision mitigation systems at intersection-like traffic situations. In: Cybernetics and Intelligent Systems, 2006 IEEE Conference on. pp. 1–6 (2006)Google Scholar
  7. 7.
    Labayrade, R., Aubert, D., Tarel, J.P.: Real time obstacle detection in stereovision on non flat road geometry through “v-disparity” representation. In: Intelligent Vehicle Symposium, 2002. IEEE. vol. 2, pp. 646–651 vol. 2 (2002)Google Scholar
  8. 8.
    Matthies, L., Grandjean, P.: Stochastic performance, modeling and evaluation of obstacle detectability with imaging range sensors. Robotics and Automation, IEEE Transactions on 10(6), 783–792 (1994)Google Scholar
  9. 9.
    Nilsson, J.: Handbook of Augmented Reality, chap. Using Augmentation Techniques for Performance Evaluation in Automotive Safety, pp. 631–649. Springer (2011)Google Scholar
  10. 10.
    Pfeiffer, D.: The Stixel World. Ph.D. thesis, Humboldt-Universitaet zu Berlin (2012)Google Scholar
  11. 11.
    Pfeiffer, D., Morales, S., Barth, A., Franke, U.: Ground truth evaluation of the stixel representation using laser scanners. In: Intelligent Transportation Systems (ITSC), 2010 13th International IEEE Conference on. pp. 1091–1097 (2010)Google Scholar
  12. 12.
    Schneider, N., Gehrig, S., Pfeiffer, D., Banitsas, K.: An evaluation framework for stereo-based driver assistance. In: Real-World Scene Analysis 2011, LNCS. p. 2751 (2012)Google Scholar
  13. 13.
    Terejanu, G., Singla, P., Singh, T., Scott, P.D.: Uncertainty propagation for nonlinear dynamical systems using Gaussian mixture models. Journal of Guidance, Control, and Dynamics 31(6), 1622–1633 (2008)Google Scholar
  14. 14.
    Zhang, T., Boult, T.: Realistic stereo error models and finite optimal stereo baselines. In: Applications of Computer Vision (WACV), 2011 IEEE Workshop on. pp. 426–433 (2011)Google Scholar
  15. 15.
    Zheng, P., McDonald, M.: The effect of sensor errors on the performance of collision warning systems. In: Proceedings of the Intelligent Transportation Systems. pp. 469–474 (2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Jan Erik Stellet
    • 1
  • Jan Schumacher
    • 1
  • Oliver Lange
    • 2
  • Wolfgang Branz
    • 1
  • Frank Niewels
    • 1
  • J. Marius Zöllner
    • 3
  1. 1.Robert Bosch GmbHCorporate Research, Vehicle Safety and Assistance SystemsRenningenGermany
  2. 2.Robert Bosch GmbHCorporate Research, Automotive Video SystemsHildesheimGermany
  3. 3.FZI Forschungszentrum InformatikKarlsruheGermany

Personalised recommendations