DOI QR코드

DOI QR Code

고차 통계 초점 척도를 이용한 3D 모델 복원 알고리즘

3D Model Reconstruction Algorithm Using a Focus Measure Based on Higher Order Statistics

  • 이주현 (금오공과대학교 컴퓨터공학과) ;
  • 윤현주 (금오공과대학교 컴퓨터공학과) ;
  • 한규필 (금오공과대학교 컴퓨터공학과)
  • 투고 : 2012.03.06
  • 심사 : 2012.10.30
  • 발행 : 2013.01.31

초록

본 논문에서는 정확한 깊이를 추출하기 위해 고차 통계기반 초점 척도를 이용한 SFF(shape from focus) 알고리즘을 제시한다. 기존의 SFF기반 3차원 깊이 복원 기법들은 초점 척도로 SML(sum of modified Laplacian)을 사용하기 때문에, 성능이 영상의 특성에 크게 의존하여 초점이 정밀하거나 질감이 풍부한 영상에서만 효율적이다. 그러므로, 본 논문에서는 비교적 질감과 초점이 빈약한 영상에서도 초점 값을 추출할 수 있도록 고차 통계(HOS:higher order statistics)를 이용한 알고리즘을 제안한다. 이 초점 척도에 의해 초점 영역 맵이 생성되고 국부적으로 최적의 초점 값을 갖는 화소를 추출하기 위해 영역개선, 세선화, 모서리 검출과정이 순서적으로 적용된다. 최종적으로 추출된 점에 대해서 Delaunay 삼각화를 사용하여 3차원 모델정보를 생성한다.

This paper presents a SFF(shape from focus) algorithm using a new focus measure based on higher order statistics for the exact depth estimation. Since conventional SFF-based 3D depth reconstruction algorithms used SML(sum of modified Laplacian) as the focus measure, their performance is strongly depended on the image characteristics. These are efficient only for the rich texture and well focused images. Therefore, this paper adopts a new focus measure using HOS(higher order statistics), in order to extract the focus value for relatively poor texture and focused images. The initial best focus area map is generated by the measure. Thereafter, the area refinement, thinning, and corner detection methods are successively applied for the extraction of the locally best focus points. Finally, a 3D model from the carefully selected points is reconstructed by Delaunay triangulation.

키워드

참고문헌

  1. 이광엽, 3차원 그래픽 프로세서 기술 동향, http://kidbs.itfind.or.kr/WZIN/jugidong/1172/117203.htm, 2004.
  2. A.C. Kak, Handbook of Industrial Robotics, Ch. on Depth Perception for Robots, New York: John Wiley, 1985.
  3. U. R. Dhond and J. K. Aggarwal, "Structure from Stereo : A Review," IEEE Trans. Syst. Man Cybern., Vol. 19, No. 6, pp. 1489-1510, 1989. https://doi.org/10.1109/21.44067
  4. S.K. Nayar and Y. Nakagawa, "Shape from Focus," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 8, pp. 824-831, 1994. https://doi.org/10.1109/34.308479
  5. A.S. Malik and T.S. Choi, "Consideration of Illumination effects and Optimization of Window Size for Accurate Calculation of Depth Map for 3D Shape Recovery," Pattern Recognition, Vol. 40, No. 1, pp. 154-170, 2007. https://doi.org/10.1016/j.patcog.2006.05.032
  6. G. Gelle, M. Colas, and G. Delaunay, "Higher Order Statistics for Detection and Classification of Faulty Fanbelts using Acoustical Analysis," Proc. of IEEE Signal Processing Workshop on Higher-Order Statistics (SPW-HOS'97), pp. 43-46, 1997.
  7. J.M. Mendel, "Tutorial on Higher-Order Statistics (Spectra) in Signal Processing and System Theory : Theoretical Results and Some Applications," Proc. of IEEE, Vol. 79, Issue. 3, pp. 278-305, 1991. https://doi.org/10.1109/5.75086
  8. C. Kim, "Segmenting a Low Depth-of-Field Image using Morphological Filters and Region Merging," IEEE Trans. on Image Processing, Vol. 14, issue 10, pp. 1503-1511, 2005. https://doi.org/10.1109/TIP.2005.846030
  9. 박정우, 김창익, "낮은 피사계 심도의 동영상에서 포커스 된 비디오 객체의 자동 검출," 정보과학회논문지 : 소프트웨어 및 응용, 제33권, 제10호, pp. 823-924, 2006.
  10. Y.T. Zhang and C. Suen, "A Fast Parallel Algorithm for Thinning Digital Patterns," Comm. ACM, Vol. 27, No. 3, pp. 236-239, 1984. https://doi.org/10.1145/357994.358023
  11. C. Harris and M.J. Stephens, "A Combined Corner and Edge Detector," Proc. of Alvey Vision Conference, pp. 147-152, 1988.
  12. D.F. Watson, "Computing the N-Dimensional Delaunay Tessellation with Application to Voronoi Poytopes," Comput. J., Vol 24, No. 2, pp. 167-172, 1981. https://doi.org/10.1093/comjnl/24.2.167
  13. M.T. Mahmood, and Tae-Sun Choi, "A Feature Analysis Approach to Estimate 3D Shape from Image Focus," 15th IEEE Int'l Conference on Image Processing (ICIP 2008), pp. 3216-3219, 2008.