The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Image-based Modeling by Minimizing Projection Error of Primitive Edges

정형체의 투사 선분의 오차 최소화에 의한 영상기반 모델링

  • Published : 2005.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes an image-based modeling method which recovers 3D models using projected line segments in multiple images. Using the method, a user obtains accurate 3D model data via several steps of simple manual works. The embedded nonlinear minimization technique in the model parameter estimation stage is based on the distances between the user provided image line segments and the projected line segments of primitives. We define an error using a finite line segment and thus increase accuracy in the model parameter estimation. The error is defined as the sum of differences between the observed image line segments provided by the user and the predicted image line segments which are computed using the current model parameters and camera parameters. The method is robust in a sense that it recovers 3D structures even from partially occluded objects and it does not be seriously affected by small measurement errors in the reconstruction process. This paper also describesexperimental results from real images and difficulties and tricks that are found while implementing the image-based modeler.

다중영상으로부터 투사 선분을 이용하여 3D 모델을 생성하고 각 면의 텍스쳐를 획득하는 구조 복원 기법을 제안한다 사용자는 매우 단순한 절차를 통해 정확한 3D 모델 데이터를 획득할 수 있다. 모델 파라메터 추정을 위해 내재된 비선형 최적화 방법은 사용자 지정 영상 선분과 모델의 투사 선분의 거리를 최소화하는 방법에 기반하고 있다. 모델링 기법의 기능적 주요 목표는 형상이 포함된 다중 영상으로부터 그 형상의 3차원 구조를 복원하고 각 면의 텍스쳐를 생성하는 것이다. 본 연구에서는 3D 정형체를 사용하여 사용의 편리성을 증대시킬 수 있고 정형체의 파라메터의 오차를 최소화하여 복원된 구조의 정확성을 높이는 방법을 제시한다. 제안된 방법은 유한 선분에 기반한 오차 함수를 도입하여 무한 직선에 기반한 방법보다 정확한 모델링이 가능하다. 제안된 방법을 다양한 실제 영상에 적용한 실험 결과를 제시하고 다중 영상기반 모델링 도구의 개발 과정에서의 기술적인 문제점과 해결책을 기술한다.

Keywords

References

  1. M. Wilczkowiak, E. Boyer, P. Sturm, 'Camera Calibration and 3D Reconstruction from Single Images Using Parallelepipeds,' 8th International Conference on Computer Vision, pp.142-148, 2001
  2. A. Criminisi, I. Reid, A. Zisserman, 'Single View Metrology,' International journal of Computer Vision, Vol.40, No.2, pp. 123-148, 2000 https://doi.org/10.1023/A:1026598000963
  3. A. Fusiello, 'Uncalibrated Euclidean reconstruction: A review,' Image and Vision Computing, Vol.18, No.67, pp. 555-563, 2000 https://doi.org/10.1016/S0262-8856(99)00065-7
  4. R. I. Hartley and A. Zisserman, 'Multiple View Geometry in Computer Vision', 2nd Ed., Cambridge University Press, 2004
  5. E. Debevec, Camillo J. Taylor, and Jitendra Malik, 'Modeling and Rendering Architecture from Photographs: A Hybrid Geometry- and Image-Based Approach,' Proceedings of SIGGRAPH 96, pp.11-20, 1996
  6. Adrien Bartoli and Peter Sturm, 'Multiple- View Structure and Motion from Line Correspondences,' Proceedings of the IEEE International Conference on Computer Vision, Nice, France, IEEE CSP, pp.207-212, 2003 https://doi.org/10.1109/ICCV.2003.1238342
  7. Adrien Bartoli, Richard Hartley, and Fredrik Kahl, 'Motion from 3D Line Correspondences: Linear and Non-Linear Solutions,' IEEE International Conference on Computer Vision and Pattern Recognition, IEEE CSP, pp.477-484, 2003 https://doi.org/10.1109/CVPR.2003.1211392
  8. L. Quan, and T. Kanade, 'Affine Structure from Line Correspondences With Uncalibrated Affine Cameras,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.19, pp.834-845, 1997 https://doi.org/10.1109/34.608285
  9. Camillo J Taylor and David J Kriegman, 'Structure and Motion from Line Segments in Multiple Images,' IEEE Trans. PAMI, Vol.17, No.11, pp.1021-1032, 1995 https://doi.org/10.1109/34.473228
  10. Zhengyou Zhang, 'Estimating Motion and Structure from Correspondences of Line Segments between Two Perspective Images,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.17, No.12, pp.1129-1139, 1995 https://doi.org/10.1109/34.476506
  11. J. Oliensis and Mike Werman, 'Structure from Motion using Points, Lines, and Intensities,' IEEE International Conference on Computer Vision and Pattern Recognition, IEEE CSP, pp. 599-606, 2000 https://doi.org/10.1109/CVPR.2000.854927
  12. 조동욱, 김지영, 배영래, 고일석, '복잡한 물체의 기술을 위한 원뿔 표면의 분류 및 임계치 선정', 정보처리학회논문지 제 11-B권, 제3호, pp.297-302, 2004 https://doi.org/10.3745/KIPSTB.2004.11B.3.297
  13. John Oliensis, 'A Critique of Structure-from-Motion Algorithms,' Computer Vision and Image Understanding: CVIU, Vol.80, No.2, pp.172-214, 2000 https://doi.org/10.1006/cviu.2000.0869
  14. S. El-Hakim, J-A. Beraldin, and J-F. Lapointe, 'Towards Automatic Modeling of Monuments and Towers,' IEEE Proceedings of the International Symposium on 3D Data Processing Visualization and Transmission, pp.526-531, 2002 https://doi.org/10.1109/TDPVT.2002.1024111
  15. Canoma. http://www.canoma.com/
  16. Realviz ImageModeler, http://www.realviz.com/
  17. W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, 'Numerical Recipes in C', 2nd Ed, Cambridge University Press, 1992
  18. S. Jacoby, J. Kowalik, and J. Pizzo, 'Iterative Methods for Nonlinear Optimization Problems', Prentice-Hall, 1972