Know Your Limits: Accuracy of Long Range Stereoscopic Object Measurements in Practice

  • Peter Pinggera
  • David Pfeiffer
  • Uwe Franke
  • Rudolf Mester
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8690)


Modern applications of stereo vision, such as advanced driver assistance systems and autonomous vehicles, require highest precision when determining the location and velocity of potential obstacles. Subpixel disparity accuracy in selected image regions is therefore essential. Evaluation benchmarks for stereo correspondence algorithms, such as the popular Middlebury and KITTI frameworks, provide important reference values regarding dense matching performance, but do not sufficiently treat local sub-pixel matching accuracy. In this paper, we explore this important aspect in detail. We present a comprehensive statistical evaluation of selected state-of-the-art stereo matching approaches on an extensive dataset and establish reference values for the precision limits actually achievable in practice. For a carefully calibrated camera setup under real-world imaging conditions, a consistent error limit of 1/10 pixel is determined. We present guidelines on algorithmic choices derived from theory which turn out to be relevant to achieving this limit in practice.


Stereo Vision Stereo Match Advanced Driver Assistance System Scene Flow Inverse Compositional 
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.


  1. 1.
    Alahari, K., Kohli, P., Torr, P.H.S.: Dynamic Hybrid Algorithms for MAP Inference in Discrete MRFs. TPAMI 32(10), 1846–1857 (2010)CrossRefGoogle Scholar
  2. 2.
    Baker, S., Matthews, I.: Lucas-Kanade 20 Years On: A Unifying Framework: Part 1. IJCV 56(3), 221–255 (2004)CrossRefGoogle Scholar
  3. 3.
    Elad, M., Teo, P., Hel-Or, Y.: On the Design of Filters for Gradient-Based Motion Estimation. Journal of Mathematical Imaging and Vision 23(3), 345–365 (2005)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Enzweiler, M., Hummel, M., Pfeiffer, D., Franke, U.: Efficient Stixel-Based Object Recognition. In: IV (2012)Google Scholar
  5. 5.
    Farid, H., Simoncelli, E.P.: Differentiation of Discrete Multidimensional Signals. TIP 13(4), 496–508 (2004)MathSciNetGoogle Scholar
  6. 6.
    Förstner, W.: Image Matching. In: Haralick, R.M., Shapiro, L.G. (eds.) Computer and Robot Vision, 2nd edn., ch. 16, pp. 289–372. Addison-Wesley (1993)Google Scholar
  7. 7.
    Franke, U., Pfeiffer, D., Rabe, C., Knoeppel, C., Enzweiler, M., Stein, F., Herrtwich, R.G.: Making Bertha See. In: ICCV Workshops (2013)Google Scholar
  8. 8.
    Gehrig, S.K., Eberli, F., Meyer, T.: A Real-Time Low-Power Stereo Vision Engine Using Semi-Global Matching. In: Fritz, M., Schiele, B., Piater, J.H. (eds.) ICVS 2009. LNCS, vol. 5815, pp. 134–143. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  9. 9.
    Gehrig, S.K., Franke, U.: Improving Stereo Sub-Pixel Accuracy for Long Range Stereo. In: ICCV 2007 Workshops (2007)Google Scholar
  10. 10.
    Geiger, A., Lenz, P., Urtasun, R.: Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In: CVPR, pp. 3354–3361 (2012)Google Scholar
  11. 11.
    Haller, I., Nedevschi, S.: Design of Interpolation Functions for Subpixel-Accuracy Stereo-Vision Systems. TIP 21(2), 889–898 (2012)MathSciNetGoogle Scholar
  12. 12.
    Hirschmüller, H.: Stereo Processing by Semiglobal Matching and Mutual Information. TPAMI 30(2), 328–341 (2008)CrossRefGoogle Scholar
  13. 13.
    Jähne, B.: Digital Image Processing - Concepts, Algorithms, and Scientific Applications, 3rd edn. Springer (1995)Google Scholar
  14. 14.
    Keys, R.G.: Cubic Convolution Interpolation for Digital Image Processing. ASSP 29(6), 1153–1160 (1981)CrossRefzbMATHMathSciNetGoogle Scholar
  15. 15.
    Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: Proc. Int. Joint Conf. on Artificial Intel. (1981)Google Scholar
  16. 16.
    Mester, R.: Motion Estimation Revisited: An Estimation-Theoretic Approach. In: SSIAI (2014)Google Scholar
  17. 17.
    Nehab, D., Rusinkiewiez, S., Davis, J.: Improved Sub-Pixel Stereo Correspondences Through Symmetric Refinement. In: ICCV, pp. 557–563 (2005)Google Scholar
  18. 18.
    Pfeiffer, D., Gehrig, S., Schneider, N.: Exploiting the Power of Stereo Confidences. In: CVPR, pp. 297–304 (2013)Google Scholar
  19. 19.
    Pinggera, P., Franke, U., Mester, R.: Highly Accurate Depth Estimation for Objects at Large Distances. In: Weickert, J., Hein, M., Schiele, B. (eds.) GCPR 2013. LNCS, vol. 8142, pp. 21–30. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  20. 20.
    Rabe, C.: Detection of Moving Objects by Spatio-Temporal Motion Analysis. Phd thesis, Christian-Albrechts-Universität zu Kiel (2011)Google Scholar
  21. 21.
    Ranftl, R., Gehrig, S., Pock, T., Bischof, H.: Pushing the Limits of Stereo Using Variational Stereo Estimation. In: IV (2012)Google Scholar
  22. 22.
    Robinson, D., Milanfar, P.: Fundamental Performance Limits in Image Registration. TIP 13(9), 1185–1199 (2004)Google Scholar
  23. 23.
    Rousseeuw, P.J., Croux, C.: Alternatives to the Median Absolute Deviation. Journal of the American Statistical Association 88(424) (1993)Google Scholar
  24. 24.
    Sabater, N., Morel, J.M., Almansa, A.: How Accurate Can Block Matches Be in Stereo Vision? SIAM Journal on Imaging Sciences 4(1), 472 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  25. 25.
    Sabater, N., Almansa, A., Morel, J.M.: Meaningful Matches in Stereovision. TPAMI 34(5), 930–942 (2012)CrossRefGoogle Scholar
  26. 26.
    Scharr, H.: Optimal Filters for Extended Optical Flow. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds.) IWCM 2004. LNCS, vol. 3417, pp. 14–29. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  27. 27.
    Scharstein, D., Szeliski, R.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. IJCV 47(1-3), 7–42 (2002)CrossRefzbMATHGoogle Scholar
  28. 28.
    Shimizu, M., Okutomi, M.: Precise Sub-pixel Estimation on Area-Based Matching. In: ICCV, pp. 90–97 (2001)Google Scholar
  29. 29.
    Sutton, M.A., Orteu, J.J., Schreier, H.W.: Image Correlation for Shape, Motion and Deformation Measurements. Springer (2009)Google Scholar
  30. 30.
    Szeliski, R., Scharstein, D.: Sampling the Disparity Space Image. TPAMI 26(3), 419–425 (2004)CrossRefGoogle Scholar
  31. 31.
    Thévenaz, P., Blu, T., Unser, M.: Interpolation Revisited. TMI 19(7) (2000)Google Scholar
  32. 32.
    Unser, M., Aldroubi, A., Eden, M.: B-Spline Signal Processing. TSP 41(2) (1993)Google Scholar
  33. 33.
    Vogel, C., Schindler, K., Roth, S.: Piecewise Rigid Scene Flow. In: ICCV (2013)Google Scholar
  34. 34.
    Wedel, A., Pock, T., Zach, C., Bischof, H., Cremers, D.: An Improved Algorithm for TV-L 1 Optical Flow. In: Cremers, D., Rosenhahn, B., Yuille, A.L., Schmidt, F.R. (eds.) Statistical and Geometrical Approaches to Visual Motion Analysis. LNCS, vol. 5604, pp. 23–45. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  35. 35.
    Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L1 Optical Flow. In: BMVC, pp. 108.1–108.11 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Peter Pinggera
    • 1
    • 2
  • David Pfeiffer
    • 1
  • Uwe Franke
    • 1
  • Rudolf Mester
    • 2
    • 3
  1. 1.Environment PerceptionDaimler R&DSindelfingenGermany
  2. 2.VSI Lab, Computer Science Dept.Goethe University FrankfurtGermany
  3. 3.Computer Vision Laboratory, Dept. EELinköping UniversitySweden

Personalised recommendations