http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
다중 국부최소 해결을 위한 강력한 다중 베이스라인 스테레오 알고리즘 연구
전정희,김하석,전윤재 대불대학교 2001 論文集 Vol.7 No.1
Correspondence problem is one of the most difficult problems in stereo vision. To find the true matching points in stereo image pair is difficult. In this paper, a new matching algorithm, RMBS(Robust Multiple-Baseline Stereo) has been proposed. The proposed algorithm is based on the principle that the distances from each camera to a point in the scene have to be equal. RMBS computes disparity (ζ= F/Z= d/B) by averaging ζ_(i) obtained from each stereo image pair. In a region with regular pattern RMBS solve the multiple local minima problem using adaptive window. RMBS increases the adaptive window size until the multiple local minima vanish. From the results it is found that RMBS is faster than the conventional MBS and solve the multiple local minima problem.