$\require{mediawiki-texvc}$

연합인증

연합인증 가입 기관의 연구자들은 소속기관의 인증정보(ID와 암호)를 이용해 다른 대학, 연구기관, 서비스 공급자의 다양한 온라인 자원과 연구 데이터를 이용할 수 있습니다.

이는 여행자가 자국에서 발행 받은 여권으로 세계 각국을 자유롭게 여행할 수 있는 것과 같습니다.

연합인증으로 이용이 가능한 서비스는 NTIS, DataON, Edison, Kafe, Webinar 등이 있습니다.

한번의 인증절차만으로 연합인증 가입 서비스에 추가 로그인 없이 이용이 가능합니다.

다만, 연합인증을 위해서는 최초 1회만 인증 절차가 필요합니다. (회원이 아닐 경우 회원 가입이 필요합니다.)

연합인증 절차는 다음과 같습니다.

최초이용시에는
ScienceON에 로그인 → 연합인증 서비스 접속 → 로그인 (본인 확인 또는 회원가입) → 서비스 이용

그 이후에는
ScienceON 로그인 → 연합인증 서비스 접속 → 서비스 이용

연합인증을 활용하시면 KISTI가 제공하는 다양한 서비스를 편리하게 이용하실 수 있습니다.

Terrain Geometry from Monocular Image Sequences 원문보기

Journal of computing science and engineering, v.2 no.1, 2008년, pp.98 - 108  

McKenzie, Alexander (Caltech) ,  Vendrovsky, Eugene (Rhythm+Hues Studios) ,  Noh, Jun-Yong (KAIST)

Abstract AI-Helper 아이콘AI-Helper

Terrain reconstruction from images is an ill-posed, yet commonly desired Structure from Motion task when compositing visual effects into live-action photography. These surfaces are required for choreography of a scene, casting physically accurate shadows of CG elements, and occlusions. We present a ...

주제어

AI 본문요약
AI-Helper 아이콘 AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

  • 5. Additional terrain geometry created with our system for "The Lion, the Witch, and the Wardrobe";. Landscape meshes arc created from the original plates (Left) and used to composite characters and shadows into the scene (Right).
  • The GMM was also used for automated clustering of points. The resulting "clean" point samples were used in a geometry reconstruction step to obtain a final three-dimensional representation of the photographed terrain. Our approach was successfully employed in several feature films, most notably "The Chronicles of Narnia\ and the recent film "The Kingdom'.
  • Our approach was successfully employed in several feature films, most notably "The Chronicles of Narnia\ and the recent film "The Kingdom'. Future work includes extending the approach to handle fully 3-dimensional terrain, complete with overhangs and other complicated geometries. Such an improvement requires modification to our quantification of errors, reminiscent of [Hoppe et al.
  • This is achieved by locally fitting a radial basis function to the neighborhood of a point to predict its error likelihood, and a Gaussian mixture model to automatically determine the appropriate error cutoff threshold. The final step is to use this cleaned dataset in a surface generation method that captures the many benefits of using RBFs as a scattered data interpolant for the remaining irregularly sampled dataset.

이론/모형

  • Figure 3 demonstrates how this outher rejection improves the reconstruction quality. Surface Alignment: A high resolution quad mesh is created, with principle axes aligned with the principle axes of the dataset P (expressed as a matrix X) through use of Principle Component Analysis (PCA). We compute the covariance matrix C =(X - X)(X - X) where X denotes the mean position, and apply an eigen decomposition D = VCV to extract the principle direction vectors V.
  • obtained via optical flow of an input image sequence. The algorithm used locally fit radial basis functions to estimate errors, and a Gaussian mixture model mechanism to determine an appropriate cutoff threshold. The GMM was also used for automated clustering of points.
본문요약 정보가 도움이 되었나요?

참고문헌 (18)

  1. 2D3. Boujou 4. http://www.2d3.com. 

  2. AMENTA, N., CHOI, S., AND KOLLURI, R. 2001. The Power Crust, Unions of Balls, and the Medial Axis Transform. In Computational Geometry: Theory and Applications. 127-153. 

  3. BARRON, J. L., FLEET, D. J., AND BEAUCHEMIN, S. 1994. Performance of optical flow techniques. In International Journal of Computer Vision. 43-77. 

  4. BOUMAN, C. A. 2005. Cluster: An Unsupervised Algorithm for Modeling Gaussian Mixtures. Tech. rep., Purdue. 

  5. CARR, J. C., BEATSON, R. K., CHERRIE, J. B., MITCHELL, T. J., FRIGHT, W. R., MCCALLUM, B. C., AND EVANS, T. R. 2001. Reconstruction and Representation of 3D Objects with Radial Basis Functions. In ACM Siggraph. 67-76. 

  6. CAZALS, F. AND GIESEN, J. 2004. Delaunay Triangulation Based Surface Reconstruction: Ideas and Algorithms. Tech. rep., INRIA Sophia-Antipoles. 

  7. Fitzgibbon, A. W. and ZISSERMAN, A. 1998. Automatic Camera Recovery for Closed or Open Image Sequences. In European Conference on Computer Vision. 311-326. 

  8. FORSYTH, D. A. AND PONCE, J. 2003. Computer Vision, a modern approach. Prentice Hall. 

  9. HARTLEY, R. I. AND ZISSERMAN, A. 2004. Multiple View Geometry in Computer Vision. Cambridge University Press. 

  10. HOPPE, H., DEROSE, T., DUCHAMP, T., MCDONALD, J., AND STUETZLE, W. 1992. Surface Reconstruction from Unorganized Points, Computer Graphics 26. 

  11. HORNUNG, A. AND KOBBELT, L. 2006. Robust Reconstruction of Watertight 3D Models from Non-uniformly Sampled Point Clouds Without Normal Information. In Symposium on Geometry Processing. 41-50. 

  12. ISENBURG, M., LIU, Y., SHEWCHUK, J., AND SNOEYINK, J. 2006. Streaming Computation of Delaunay Triangulations. In ACM Siggraph. 1049-1056. 

  13. KAZHDAN, M., BOLITHO, M., AND HOPPE, H. 2006. Poisson Surface Reconstruction. In Symposium on Geometry Processing. 61-70. 

  14. KOLLURI, R., SHEWCHUK, J., AND O'BRIEN, J. 2004. Spectral Surface Reconstruction from Noisy Point Clouds. In Symposium on Geometry Processing. 11-21. 

  15. LINDSTROM, P. AND PASCUCCI, V. 2002. Terrain Simplification Simplified: A General Framework for View-Dependent Out-of-Core Visualization. IEEE TVCG 8, 3, 239-254. 

  16. OHTAKE, Y., BELYAEV, A., ALEXA, M., TURK, G., AND SEIDEL, H. 2003. Multi-level Partition of Unity Implicits. In ACM Siggraph. 463-470. 

  17. SAMOZINO, M., ALEXA, M., ALLIEZ, P., AND YVINEC, M. 2006. Reconstruction with Voronoi Centered Radial Basis Functions. In Symposium on Geometry Processing. 51-60. 

  18. SCHALL, O., BELYAEV, A., AND SEIDEL, H.-P. 2005. Robust filtering of noisy scattered point data. In IEEE/Eurographics Symposium on Point-Based Graphics. 71-77. 

저자의 다른 논문 :

관련 콘텐츠

오픈액세스(OA) 유형

BRONZE

출판사/학술단체 등이 한시적으로 특별한 프로모션 또는 일정기간 경과 후 접근을 허용하여, 출판사/학술단체 등의 사이트에서 이용 가능한 논문

저작권 관리 안내
섹션별 컨텐츠 바로가기

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

AI-Helper 아이콘
AI-Helper
안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

선택된 텍스트

맨위로