DOI QR코드

DOI QR Code

가우시안 잡음과 계산량을 고려한 하이브리드 센서스 변환

Hybrid census transform considering gaussian noise and computational complexity

  • 정성환 (한국기술교육대학교 전기전자통신공학과) ;
  • 강성진 (한국기술교육대학교 전기전자통신공학과)
  • Jeong, Seong-Hwan (Department of Electronics and Communication Engineering, Korea University of Technology and Education) ;
  • Kang, Sung-Jin (Department of Electronics and Communication Engineering, Korea University of Technology and Education)
  • 투고 : 2013.05.20
  • 심사 : 2013.08.07
  • 발행 : 2013.08.31

초록

스테레오 매칭 중 센서스 변환은 방사 왜곡과 밝기 변화에 강한 특징이 있다. 본 논문은 미니 센서스 변환과 일반화된 센서스 변환을 동시에 이용한 하이브리드 센서스 변환을 제안하였다. 제안한 하이브리드 센서스 변환 방법은 미니 센서스 변환의 적은 계산량과 일반화된 센서스 변환의 잡음에 강인한 특성을 반영하여 설계되었다. 성능을 평가하기 위하여 후처리 과정까지 포함하여 스테레오 매칭을 수행하였다. 그 결과 하이브리드 센서스 변환은 일반화된 센서스 변환과 성능이 비슷하였고, 계산량은 미니 센서스 변환과 일반화된 센서스의 중간값을 갖는다.

Census transform is one of the stereo vision methods which is robust to radiometric distortion and illuminance change. This paper proposes a hybrid census transform using the mini census transform and the generalized census transform concurrently. This method uses simplicity of mini census transform and noise feature of generalized census transform together. This paper performed stereo matching containing post processing to evaluate each methods. The result shows that hybrid census transform has similar performance to generalized census transform and mean value of calculation complexity between mini census transform and generalized census transform.

키워드

참고문헌

  1. H. Hirschmuller and D. Scharstein, "Evaluation of Stereo Matching Costs on Images with Radiometric Differences," IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(9), pp.1582-1599, 2009. DOI: http://dx.doi.org/10.1109/TPAMI.2008.221
  2. R. Zabih and J. Woodfill, "Non-parametric Local Transforms for Computing Visual Correspondence," European Conference on Computer Vision, pp.151-158, 1994 DOI: http://dx.doi.org.10.1007/BFb0028345
  3. N. Chang, T. Tsai, B. Hsu, Y. Chen, and T. Chang, "Algorithm and Architecture of Disparity Estimation With Mini-Census Adaptive Support Weight," IEEE Transactions on Circuits and Systems for Video Technology, 20(6), pp.792-805, 2010. DOI: http://dx.doi.org/10.1109/TCSVT.2010.2045814
  4. W. Fire and J. Archibald, "Improved Census Transforms for Resource-Optimized Stereo Vision," IEEE Transactions on Circuits and Systems for Video Technology, PP(99), pp.1, 2012. DOI: http://dx.doi.org/10.1109/TCSVT.2012.2203197
  5. K. Zhang, J. Lu, and G. Lafruit, "Cross-Based Local Stereo Matching Using Orthogonal Integral Images," IEEE Transactions on Circuits and Systems for Video Technology, 19(7), pp.1073-1079, 2009. DOI: http://dx.doi.org/10.1109/TCSVT.2009.2020478
  6. L. Zhang, K. Chang, T. Chang, G. Lafruit, G. Kuzmanov, and D. Verkest, "Real-time high-definition stereo matching on FPGA," Field Programmable Gate Arrays, pp.55-64, 2011.
  7. Lu Zhang, "Design and Implementation of Real-Time High-Definition Stereo Matching SoC on FPGA," M.Sc. Thesis, Delft University of Technology, 2010
  8. D. Scharstein and R. Szeliski, http://vision.middlebury.edu/stereo/