Evaluation of a New Coarse-to-Fine Strategy for Fast Semi-Global Stereo Matching

  • Simon Hermann
  • Reinhard Klette
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7087)

Abstract

The paper considers semi-global stereo matching in the context of vision-based driver assistance systems. The need for real-time performance in this field requires a design change of the originally proposed method to run on current hardware. This paper proposes such a new design; the novel strategy first generates a disparity map from half-resolution input images. The result is then used as prior to restrict the disparity search space for full-resolution computation. This approach is compared to an SGM strategy as employed currently in a state-of-the-art real-time FPGA solution. Furthermore, trinocular stereo evaluation is performed on ten real-world traffic sequences with a total of 4,000 trinocular frames. An extension to the original evaluation methodology is proposed to resolve ambiguities and to incorporate disparity density in a statistically meaningful way. Evaluation results indicate that the novel SGM method is up to 40% faster when compared to the previous strategy. It returns denser disparity maps, and is also more accurate on evaluated traffic scenes.

Keywords

Semi-global matching driver assistance systems coarse-to-fine stereo 

References

  1. 1.
    Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High Accuracy Optical Flow Estimation Based on a Theory for Warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    .enpeda.. image sequence analysis test site, http://www.mi.auckland.ac.nz/EISATS
  3. 3.
    Ernst, I., Hirschmüller, H.: Mutual information based semi-global stereo matching on the GPU. In: Int. Symp. on Advances Visual Computing, pp. 228–239 (2008)Google Scholar
  4. 4.
    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
  5. 5.
    Haller, I., Pantillie, C., Oniga, F., Nedevschi, S.: Real-time semi-global dense stereo solution with improved sub-pixel accuracy. In: Intelligent Vehicles Symp., pp. 369–376 (2010)Google Scholar
  6. 6.
    Hermann, S., Morales, S., Vaudrey, T., Klette, R.: Illumination Invariant Cost Functions in Semi-Global Matching. In: Koch, R., Huang, F. (eds.) ACCV Workshops 2010, Part II. LNCS, vol. 6469, pp. 245–254. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  7. 7.
    Hirschmüller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: Computer Vision Pattern Recognition, vol. 2, pp. 807–814 (2005)Google Scholar
  8. 8.
    Hirschmüller, H., Scharstein, D.: Evaluation of stereo matching costs on images with radiometric differences. IEEE Trans. Pattern Analysis Machine Intelligence 31, 1582–1599 (2009)CrossRefGoogle Scholar
  9. 9.
    Morales, S., Klette, R.: A Third Eye for Performance Evaluation in Stereo Sequence Analysis. In: Jiang, X., Petkov, N. (eds.) CAIP 2009. LNCS, vol. 5702, pp. 1078–1086. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  10. 10.
    Ohta, Y., Kanade, T.: Stereo by two-level dynamic programming. In: Proc. of Int. Joint Conf. on Artificial Intelligence, pp. 1120–1126 (1985)Google Scholar
  11. 11.
    Rabe, C., Müller, T., Wedel, A., Franke, U.: Dense, Robust, and Accurate Motion Field Estimation from Stereo Image Sequences in Real-Time. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 582–595. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Saito, T., Toriwaki, J.: New algorithms for n-dimensional Euclidean distance transformation. Pattern Recognition 27, 1551–1565 (1994)CrossRefGoogle Scholar
  13. 13.
    Shimizu, M., Okutomi, M.: An analysis of subpixel estimation error on area-based image matching. Digital Signal Processing 2, 1239–1242 (2002)Google Scholar
  14. 14.
    Sizintsev, M., Wildes, R.P.: Coarse-to-fine stereo vision with accurate 3D boundaries. Image and Vision Computing 28(3), 352–366 (2010)CrossRefGoogle Scholar
  15. 15.
    Wegener, P.: A technique for counting ones in a binary computer. Comm. ACM 3, 322 (1960)CrossRefGoogle Scholar
  16. 16.
    Zabih, R., Woodfill, J.: Non-Parametric Local Transform for Computing Visual Correspondence. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 800, pp. 151–158. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  17. 17.
    Vaudrey, T., Rabe, C., Klette, R., Milburn, J.: Differences between stereo and motion behaviour on synthetic and real-world stereo sequences. In: Image Vision Computing, New Zealand, pp. 1–6 (2008)Google Scholar
  18. 18.
    Zach, C., Pock, T., Bischof, H.: A Duality Based Approach for Realtime TV-L 1 Optical Flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Simon Hermann
    • 1
  • Reinhard Klette
    • 1
  1. 1.The .enpeda.. project, Department of Computer ScienceThe University of AucklandNew Zealand

Personalised recommendations