A Stereo Matching Algorithm with Projective Distortion of Variable Windows

가변 윈도우의 투영왜곡을 고려한 스테레오 정합 알고리듬

  • Published : 2001.03.01


Existing area-based stereo algorithms rely heavily on rectangular windows for computing correspondence. While the algorithms with the rectangular windows are efficient, they generate relatively large matching errors due to variations of disparity profiles near depth discontinuities and doesnt take into account local deformations of the windows due to projective distortion. In this paper, in order to deal with these problems, a new correlation function with 4 directional line masks, based on robust estimator, is proposed for the selection of potential matching points. These points is selected to consider depth discontinuities and reduce effects on outliers. The proposed matching method finds an arbitrarily-shaped variable window around a pixel in the 3d array which is constructed with the selected matching points. In addition, the method take into account the local deformation of the variable window with a constant disparity, and perform the estimation of sub-pixel disparities. Experiments with various synthetic images show that the proposed technique significantly reduces matching errors both in the vicinity of depth discontinuities and in continuously smooth areas, and also does not be affected drastically due to outlier and noise.


Depth Discontinuity;Local Deformation;Potential Matching Point;Robust Estimator;Stereo Matching;Variable Window


  1. Rodrigue, J. J. and Aggarwal, J. K., 1990, 'Stochastic Analysis of Stereo Quantization Error,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 12, No. 5, pp. 467-470
  2. Arora, J. S., 1989, Introduction to Optimum Design, McGraw-Hill
  3. Gonzalez, R. C., 1993, Digital Image Processing, Addison-Wesley
  4. 김경범, 김낙현, 정성종, 2000, '강건추정자와 직선마스크를 이용한 스테레오 정합,' 대한기계학회논문집(A), 제 24 권, 제 4 호, pp. 991-1000
  5. Kim, G. B. and Chung, S. C., 2000, 'A New Area-Based Stereo Algorithm for Measurement of 3D Shapes,' Trans. of NAMRI/SME, Vol. 28, pp. 383-388
  6. Faugeras, O., 1993, Three-Dimensional Computer Vision, MIT. Press
  7. Meer, P., Hintz, D., Rosenfeld, A. and Kim, D. Y., 1991, 'Robust Regression Methods for Computer Vision: A Review,' Int. J. Computer Vision, Vol. 6, No. 1 pp.59-70
  8. Faugeras, O., Hotz, B. and Mathieu, H. et al, 1993, 'Real Time Correlation-based Stereo: Algorithm, Implementations and Applications,' INRIA Tech. Rep. 2013
  9. Kanade, T. and Okutomi, M., 1994, 'A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 16, No. 9, pp. 920-923
  10. Dervernay, F. and Faugeras, O., 1994, 'Computing Differential Properties of 3D Shapes from Stereoscoptic Images without 3D Models,' Proc. of Computer Vision and Pattern Recog., pp. 208-213
  11. Wei, G. Q., Brauer, W. and Hirzinger, G., 1998, 'Intensity-and Gradient-based Stereo Matching Using Hierarchical Gaussian Basis Functions,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 20, No. 11 pp. 1143-1160
  12. Kanade, T., Yoshida, A., Oda, K., Kano, H. and Tanaka, M., 1996, 'A Stereo Machine for Vidio-rate Dense Depth Mapping and Its New Applications,' In Proc. of Computer Vision and Pattern Recog., pp. 196-202
  13. Igarashi, S., Shibukawa, K., and Kaneta, M., 1993, '3D Measurement of Shape Using Differential Stereo Vision Algorithm,' Int. Japan Soc. Prec. Eng., Vol. 27, No. 3, pp. 247-252
  14. Dhond, U. R. and Aggarwal, J. K., 1989, 'Structure from Stereo: A Review,' IEEE Trans. Syst. Man Cybernetics, Vol. 19, No. 6, pp. 1489-1510