Browse > Article

Fast Disparity Estimation Method Considering Temporal and Spatial Redundancy Based on a Dynamic Programming  

Yun, Jung-Hwan (광운대학교 전자공학과 디지털 미디어 연구실)
Bae, Byung-Kyu (광운대학교 전자공학과 디지털 미디어 연구실)
Park, Se-Hwan (광운대학교 전자공학과 디지털 미디어 연구실)
Song, Hyok (전자부품연구원)
Kim, Dong-Wook (광운대학교 전자재료공학과 Digital Design & Test Lab.)
Yoo, Ji-Sang (광운대학교 전자공학과 디지털 미디어 연구실)
Abstract
In this paper, we propose a fast disparity estimation method considering temporal and spatial redundancy based on a dynamic programming for stereo matching. For the first step, the dynamic programming is performed to estimate disparity vectors with correlation between neighboring pixels in an image. Next, we efficiently compensate regions, which disparity vectors are not allocated, with neighboring disparity vectors assuming that disparity vectors in same object are quite similar. Moreover, in case of video sequence, we can decrease a complexity with temporal redundancy between neighboring frames. For performance comparison, we generate an intermediate-view image using the estimated disparity vector. Test results show that the proposed algorithm gives $0.8{\sim}2.4dB$-increased PSNR(peak signal to noise ratio) compared to a conventional block matching algorithm, and the proposed algorithm also gives approximately 0.1dB-increased PSNR and $48{\sim}68%$-lower complexity compared to the disparity estimation method based on general dynamic programming.
Keywords
Disparity estimation; Dynamic programming; Temporal and spatial redundancies;
Citations & Related Records
연도 인용수 순위
  • Reference
1 김봉겸, 임재권, "신뢰확산 알고리듬을 이용한 선 그룹화 기반 스테레오 정합," 전자공학회 논문지 제42권 SP 제3호, 2005.
2 Zitnick, C. L., S. B. Kang, M. Uyttendaele, S.Winder and R. Szeliski, "High-quality video view interpolation using a layered representation," Proceedings of SIGGRAPH (ACM Transactions on Graphics), pp.600-608, 2004.
3 R_Szeliski. "Prediction error as a quality metric for motion and stereo," ICCV, pp.781-788, 1999.
4 http://vision.middlebury.edu/stereo
5 Myron Z. Brown, Darius Burschka and Gregory D. Hager, "Advances in Computational Stereo," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.25, No.8, pp.993-1008, August 2003.   DOI   ScienceOn
6 P.H.S Torr and A. Criminisi, "Dense Stereo Using Pivoted Dynamic Programming," Microsoft Research, MSR-TR-2002-51, 2002.
7 Scharstein, D. and R. Szeliski, "A taxonomy and evaluation of dense two-frame stereo correspondence algorithms," IJCV 47(1), pp.7-42, 2002.   DOI
8 Ingemar J. Cox L. Hingorani, Satish B.Rao "A Maximum Likelihood Stereo Algorithm," CVIU, 63:3, pp.542-567, 1996.   DOI   ScienceOn
9 김미현, 강문기, 이철희, 최윤식, 손광훈, "경계-보 존 방향성 평활화를 이용한 양안 영상의 변이 추 정과 중간시점 영상의 재구성," 방송공학회논문 지, 제4권 제1호 pp.59-67, 1999.