Impact of Video Source Coding on the Performance of Stereo Matching

  • Waqar Zia
  • Michel Sarkis
  • Klaus Diepold
Part of the Cognitive Systems Monographs book series (COSMOS, volume 6)


In several applications like Telepresence, multi-view video has to be source coded and transmitted to a location where stereo matching is performed. The effect of coding strategies on stereo matching techniques is, however, not thoroughly studied. In this paper, we present an analysis that demonstrates the impact of video source coding on the quality of stereo matching. We use MPEG-4 advanced simple profile to compress the transmitted video and examine the quantitative effect of lossy compression on several types of stereo algorithms. The results of the study are able to show us the relation between video coding compression parameters and the quality of the obtained disparity maps. These results can guide us to select suitable operating regions for both stereo matching and video compression. Thus, we are able to provide a better insight on how to trade between the compression parameters and the quality of dense matching to obtain an optimal performance.


Video Sequence Video Code Stereo Match Lossy Compression Match Cost 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Middlebury stereo evaluation,
  2. 2.
  3. 3.
    Xvid open-source research project,
  4. 4.
    Achtelik, M.: Vision-Based Pose Estimation for Autonomous Micro Aerial Vehicles. Master’s thesis, Technische Universität München, Munich, Germany (2009)Google Scholar
  5. 5.
    Birchfield, S., Tomasi, C.: Depth discontinuities by pixel-to-pixel stereo. Int. J. Computer Vision 35(3), 269–293 (1999)CrossRefGoogle Scholar
  6. 6.
    Ekmekcioglu, E., Worrall, S.T., Kondoz, A.M.: Bit-rate adaptive downsampling for the coding of multi-view video with depth information. In: 3DTV-Conf. (2008)Google Scholar
  7. 7.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. Int. J. Computer Vision 70(1), 41–54 (2006)CrossRefGoogle Scholar
  8. 8.
    ISO/IEC JTC1/SC29/WG11 N7327: Call for proposals on multi-view video coding (2005)Google Scholar
  9. 9.
    Karlsson, L.S., Sjöström, M.: Region-of-interest 3d video coding based on depth images. In: 3DTV-Conf. (2008)Google Scholar
  10. 10.
    Klaus, A., Sormann, M., Karner, K.: Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In: Int. Conf. Pattern Recog. (2006)Google Scholar
  11. 11.
    Kolmogorov, V., Zabih, R., Gortler, S.: Multi-camera scene reconstruction via graph cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  12. 12.
    Saponara, S., Blanch, C., Denolf, K., Bormans, J.: The jvt advanced video coding standard: Complexity and performance analysis. In: Packet Video Workshop (2003)Google Scholar
  13. 13.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Computer Vision 47(1), 7–42 (2002)zbMATHCrossRefGoogle Scholar
  14. 14.
    Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: IEEE Conf. Computer Vision and Pattern Recognition, pp. 195–202 (2003)Google Scholar
  15. 15.
    Vetro, A., McGuire, M., Matusik, W., Behrens, A., Lee, J., Pfister, H.: Multiview video test sequences from merl. ISO/IEC JTC1/SC29/WG11 Document m12077 (2005)Google Scholar
  16. 16.
    Wang, L., Liao, M., Gong, M., Yang, R., Nistér, D.: High quality real-time stereo using adaptive cost aggregation and dynamic programming. In: Int. Symp. 3D Data Processing, Visualization and Transmission, pp. 798–805 (2006)Google Scholar
  17. 17.
    Yang, Q., Wang, L., Yang, R., Wang, S., Liao, M., Nistér, D.: Real-time global stereo matching using hierarchical belief propagation. In: Br. Machine Vision Conf., pp. 989–998 (2006)Google Scholar
  18. 18.
    Yoon, K.J., Kweon, I.-S.: Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Analysis and Machine Intelligence 28(4), 650–656 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Waqar Zia
    • 1
  • Michel Sarkis
    • 1
  • Klaus Diepold
    • 1
  1. 1.Institute for Data ProcessingTechnische Universität München 

Personalised recommendations