Camera Extrinsic Parameter Estimation using 2D Homography and LM Method based on PPIV Recognition

PPIV 인식기반 2D 호모그래피와 LM방법을 이용한 카메라 외부인수 산출

  • 차정희 (숭실대학교 컴퓨터학부) ;
  • 전영민 (윈스로드주식회사 전략사업본부)
  • Published : 2006.03.01

Abstract

In this paper, we propose a method to estimate camera extrinsic parameter based on projective and permutation invariance point features. Because feature informations in previous research is variant to c.:men viewpoint, extraction of correspondent point is difficult. Therefore, in this paper, we propose the extracting method of invariant point features, and new matching method using similarity evaluation function and Graham search method for reducing time complexity and finding correspondent points accurately. In the calculation of camera extrinsic parameter stage, we also propose two-stage motion parameter estimation method for enhancing convergent degree of LM algorithm. In the experiment, we compare and analyse the proposed method with existing method by using various indoor images to demonstrate the superiority of the proposed algorithms.

본 논문에서는 사영과 치환불변 점 특징을 기반으로 카메라의 외부인수를 산출하는 방법을 제안한다. 기존 연구에서의 특징 정보들은 카메라의 뷰 포인트에 따라 변화하기 때문에 대응점 산출이 어렵다. 따라서 본 논문에서는 카메라 위치에 무관한 불변 점 특징을 추출하고 시간 복잡도 감소와 정확한 대응점 산출을 위해 유사도 평가함수와 Graham 탐색 방법을 이용한 새로운 정합방법을 제안한다. 또한 카메라 외부인수 산출단계에서는 LM 알고리즘의 수렴도를 향상시키기 위해 2단계 카메라 동작인수 산출방법을 제안한다. 실험에서는 다양한 실내영상을 이용하여 기존방법과 비교, 분석함으로써 제안한 알고리즘의 우수성을 입증하였다.

Keywords

References

  1. Christian Drewniok and Karl Rohr, 'High-Precision Localization of Circular Landmarks in Aerial Images', Proc. 17. Dagm-Symposium, Musterkennung 1995, pp. 594-601, Bielefeld, Germany, 13-15. September 1995
  2. Martin T.Hagan and Mohammad B.Menhaj, 'Training Feedback Networks with the Marquardt Algorithm', IEEE Transactions on Neural Networks, Vol. 5, No.6, November 1994 https://doi.org/10.1109/72.329697
  3. Reiner Lenz and Peter Meer, 'Point Configuration Invariants under Simultaneous Projective and Permutation Transformations,' Pattern Recognition, Vol. 27, No. 11, pp. 1523-1532, 1994 https://doi.org/10.1016/0031-3203(94)90130-9
  4. K. Sugihara, 'Some Location Problems for Robot navigation Using a Single Camera,' Computer Vision, Graphics and Image Processing 42, pp. 112-129, 1988 https://doi.org/10.1016/0734-189X(88)90145-4
  5. O. Faugeras and G. Toscani, 'The Calibration Problem for Stereo,' In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 15-20, Miami Beach, FL, June 1986
  6. P. C. Naval Jr., M.Mukunoki, M. Miinoh, and K. Ikeda. 'Estimation camera position and orientation from geographical map and mountain image', 38th Research Meeting of the Pattern Sensing Group, Society of Instrument and Control Engineers, pp. 9-16, 1997
  7. K. Kanatani, 'Computational Projective Geometry,' CVGIP: Image Understanding Workshop, Washington, DC, pp. 745-753, 1993
  8. S. Birchfield, 'KLT:An Implementation of the Kanade-Lucas-Tomasi Feature Tracker, http://vision.stanford.edu/~birch/klt/'
  9. Panos E. Trahanias, Savvas Velissaris and Thodoris Garavelos, 'Visual Landmark Extraction and Recognition for Autonomous Robot Navigation,' Proc. IROS 97, pp. 1036-1042, 1997
  10. V. Barnett, 'The Ordering of Multivariate Data,' Jornal of Royal Statistical Society A, Part 3 139 pp. 318-343, 1976 https://doi.org/10.2307/2344839
  11. Vicente, M.A., Gil, P., Reinoso., Torres, F, 'Object Recognition by Means of Projective Invariants Considering Corner-Points,' Proc. SPIE. Vol. 4570. pp. 105-112. 2002 https://doi.org/10.1117/12.454735
  12. J,L. Mundy, A. Zisserman, 'Geometric Invariance in Computer Vision,' MIT Press, Cambridge, MA, 1992
  13. Fishler, M.A. and Bolles, R.C., 'Random Sample Consensus: A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography,' Commumination ACM, vol. 24, no. 6, pp. 381 -395, 1981 https://doi.org/10.1145/358669.358692
  14. 장석우, '카메라의 동작을 보정한 장면 전환 검출', 숭실대학교 박사학위 청구논문, 2000
  15. Hartley, R. I, Zisserman, A, 'Multiple View Geometry in Computer Vision,' Cambridge University Press, 2000
  16. Michael A. Penna, 'Determining Camera Parameters From The Perspective Projection Of A Quadrilateral,' Pattern Recognition, Vol. 24. No.6, pp. 553-541, 1991 https://doi.org/10.1016/0031-3203(91)90019-2