A New Stereo Matching Algorithm

새로운 스테레오 정합 알고리즘

  • 김충원 (조선대학교 전자정보공과대학 컴퓨터공학부)
  • Published : 2006.10.31

Abstract

In this raper in order to recover sharp object boundaries we propose a new efficient stereo matching algorithm in which window size is varied to the distance from the boundaries of object. To this end, the processing region is divided into small subregions with a same area and the disparities of the center pixels in the subregions are calculated using a area-based algorithm with multiple windows. From the this disparity map we can find the edges of the contracted objects. The disparities of original image are obtained using the gradient constraint that means the disparity of the center pixel is similar to the ones of the remaining pixels in the subregion. from the experimental results it is found that the proposed algorithm is very good for recovering sharp object boundaries compared to the similar different algorithm.

물체의 경계로부터 거리에 따라 다른 크기의 창을 사용함으로써 물체의 경계를 정확히 찾는 새로운 스테레오정합 알고리즘을 제안한다. 원 영상을 같은 크기의 작은 부분으로 나누고, 이 작은 영역들의 중앙 화소들의 시차를 구한 표본 시차 지도로부터 축소된 물체의 경계를 찾는다. 경계로부터의 거리에 따라 크기가 다른 창을 원 영상에 적용하여 시차를 구한다. 원 영상의 시차를 구할 때 작은 영역 내에 있는 화소들의 시차는 이미 구한 중앙화소의 시차와 유사하다는 기울기 제한 조건을 이용하였다. 실험결과로부터 제안한 알고리즘이 다른 알고리즘 보다 우수함을 확인하였다.

Keywords

References

  1. J. Jeon, C. Kim, and Y. S. Ho, 'Stereo for recovering sharp object boundaries,' EurAsia-ICT 2002, LNCS 2510, pp. 248-255, Springer-Verlag, 2002
  2. J. Jeon, C. Kim, and Y. S. Ho, 'Sharp and dense disparity maps using multiple windows,' PCM 2002, LNCS 2532, pp. 1057-1064, Springer-Verlag, 2002
  3. D. G. Jones and J. Malik, 'A computational framework for determining stereo correspondence from a set of linear spatial filters,' Second European Conference on Computer Vision(ECCV'92), LNCS 588, pp. 395-410, Springer-Verlag, 1992
  4. T. Kanade and M. Okutomi, 'A stereo matching algorithm with an adaptive window: theory and experiment,' IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 16, No. 9, pp. 920-932, September 1999 https://doi.org/10.1109/34.310690
  5. A. Fusiello, V. Roberto, and E. Trucco, 'Symmetric stereo with multiple windowing,' International Journal of Pattern Recognition and Artificial Intelligence, Vol. 14, No. 8, pp. 1053-1066, 2000 https://doi.org/10.1142/S0218001400000696
  6. S. Changming, 'A fast stereo matching method,' Digital Imaging Computing: Techniques and Applications, pp. 95-100, Auckland, November 1997
  7. M. Z. Brown, 'Advances in computational stereo,' IEEE Trans, Pattern Recognition and Machine Intelligence, Vol. 25, No.8, pp. 993-1008, 2003 https://doi.org/10.1109/TPAMI.2003.1217603
  8. D. Scharstein and R. Szeliski, 'A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,' Microsoft Research Technical Report MSR-TR-2001-81, 2001