International Journal of Computer Vision

, Volume 7, Issue 2, pp 143–162 | Cite as

A locally adaptive window for signal matching

  • Masatoshi Okutomi
  • Takeo Kanade


This article presents a signal matching algorithm that can select an appropriate window size adaptively so as to obtain both precise and stable estimation of correspondences.

Matching two signals by calculating the sum of squared differences (SSD) over a certain window is a basic technique in computer vision. Given the signals and a window, there are two factors that determine the difficulty of obtaining precise matching. The first is the variation of the signal within the window, which must be large enough, relative to noise, that the SSD values exhibit a clear and sharp minimum at the correct disparity. The second factor is the variation of disparity within the window, which must be small enough that signals of corresponding positions are duly compared. These two factors present conflicting requirements to the size of the matching window, since a larger window tends to increase the signal variation, but at the same time tends to include points of different disparity. A window size must be adaptively selected depending on local variations of signal and disparity in order to compute a most-certain estimate of disparity at each point.

There has been little work on a systematic method for automatic window-size selection. The major difficulty is that, while the signal variation is measurable from the input, the disparity variation is not, since disparities are what we wish to calculate. We introduce here a statistical model of disparity variation within a window, and employ it to establish a link between the window size and the uncertainty of the computed disparity. This allows us to choose the window size that minimizes uncertainty in the disparity computed at each point. This article presents a theory for the model and the resultant algorithm, together with analytical and experimental results that demonstrate their effectiveness.


Computer Vision Computer Image Window Size Match Algorithm Systematic Method 
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. Besl, P.J., Birch J.B., and Watson, Layne T. 1988. Robust window operators, Proc. 2nd Intern. Conf. Comput. Vision, pp. 591–600.Google Scholar
  2. Blake, A., and Zisserman, A. 1986. Invariant surface reconstruction using weak continuity constraint. Proc. Comput. Vision Patt. Recog. Miami Beach, pp. 62–68.Google Scholar
  3. Boult, T.E. 1986. Information Based Complecity in Non-Linear Equations and Computer Vision. Ph.D. thesis, Dept. of Computer Science, Columbia University.Google Scholar
  4. deCoulonF. 1986. Signal Theory and Processing. Artech House: Norwood, MA.Google Scholar
  5. ForstnerW., and PertlA. 1986. Photogrammetric Standard Methods and Digital Image Matching Techniques for High Precision Surface Measurements. Elsevier Science Publishers B.V.: New York, pp. 57–72.Google Scholar
  6. Kanade, T., and Okutomi, M. 1991. A stereo matching algorithm with an adaptive window: Theory and experiment. Proc. Intern. Conf. Robot. Autom., pp. 1088–1095, April. Also appeared in CMU Technical Report CMU-CS-90-120, 1990.Google Scholar
  7. LevineM.D., O'HandleyD.A., and YagiG.M. 1973. Computer determination of depth maps. Comput. Graph. Image Process., 2(4): 131–150.Google Scholar
  8. MandelbrotB.B., and VanNessB.J. 1968. Fractional Brownian motion, fractional noises and applications. SIAM, 10(4): 422–438.Google Scholar
  9. Marroquin, J.L. 1984. Surface reconstruction preserving discontinuities. Tech. Rept. A.I. Memo 792, MIT.Google Scholar
  10. Matthies, L., and Okutomi, M. 1989. A Bayesian foundation for active stereo vision. SPIE, Sensor Fusion II: Human and Machine Strategies, November.Google Scholar
  11. Matthies, L., Szeliski, R., and Kanade, T. 1988. Incremental estimation of dense depth maps from image sequences. Proc. Conf. Comput. Vision Patt. Recog., Ann Arbor, June, pp. 366–374.Google Scholar
  12. MoriK., KidodeM., and AsadaH. 1973. An iterative prediction and correction method for automatic stereo comparison. Comput. Graphics Image Process, 2:292–401.Google Scholar
  13. PrazdnyK. 1985. Detection of binocular disparities. Biological Cybernetics 52:93–99.Google Scholar
  14. RyanT.W., GrayR.T., and HuntB.R. 1980. Prediction of correlation errors in stereo-pair images. Optical Engineering 19(3): 312–322.Google Scholar

Copyright information

© Kluwer Academic Publishers 1992

Authors and Affiliations

  • Masatoshi Okutomi
    • 1
  • Takeo Kanade
    • 1
  1. 1.School of Computer ScienceCarnegie Mellon UniversityPittsburgh

Personalised recommendations