Journal of Korea Game Society (한국게임학회 논문지)

Korea Game Society (한국게임학회)
권호 표지
DOI QR코드

DOI QR Code

Camera Tracking Method based on Model with Multiple Planes

다수의 평면을 가지는 모델기반 카메라 추적방법

  • Lee, In-Pyo (Dept. of Imaging Science and Arts, GSAIM, Chung-Ang University) ;
  • Nam, Bo-Dam (Dept. of Imaging Science and Arts, GSAIM, Chung-Ang University) ;
  • Hong, Hyun-Ki (Dept. of Imaging Science and Arts, GSAIM, Chung-Ang University)
  • 이인표 (중앙대학교 첨단영상대학원 영상학과) ;
  • 남보담 (중앙대학교 첨단영상대학원 영상학과) ;
  • 홍현기 (중앙대학교 첨단영상대학원 영상학과)
  • Received : 2011.05.23
  • Accepted : 2011.07.04
  • Published : 2011.08.20
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a novel camera tracking method based on model with multiple planes. The proposed algorithm detects QR code that is one of the most popular types of two-dimensional barcodes. A 3D model is imported from the detected QR code for augmented reality application. Based on the geometric property of the model, the vertices are detected and tracked using optical flow. A clipping algorithm is applied to identify each plane from model surfaces. The proposed method estimates the homography from coplanar feature correspondences, which is used to obtain the initial camera motion parameters. After deriving a linear equation from many feature points on the model and their 3D information, we employ DLT(Direct Linear Transform) to compute camera information. In the final step, the error of camera poses in every frame are minimized with local Bundle Adjustment algorithm in real-time.

본 논문에서는 다수의 평면을 가지는 모델기반 카메라 추적 시스템이 제안된다. 상품의 정보를 표기하기 위한 2차원 바코드(barcode)로 널리 사용되는 QR(Quick Response) 코드를 인식하여 해당 물체의 3차원 모델을 임포팅한다. 그리고 관련 기하정보를 이용하여 모델의 주요 정점(vertex)을 추출하고 옵티컬 플로우(optical flow)를 이용하여 추적한다. 클리핑 알고리즘으로 다수의 평면을 가지는 물체의 평면 영역을 구별하고 매칭된 특징으로부터 호모그래피를 계산하여 초기 단계의 대략적인 카메라 움직임 파라미터를 추정한다. 이후 카메라의 움직임에 따라 다양한 평면에 존재하는 특징점과 해당 3차원 정보를 선형 방정식으로 구성하고 DLT(Direct Linear Transform) 방법을 적용한다. 최종 단계에서 번들 조정(Bundle Adjustment) 알고리즘을 이용해 카메라의 움직임 파라미터에 포함된 에러를 최소화 한다.

Keywords

References

  1. T.W. Kan, C.H. Teng and W.S. Chou, "Applying QR code in augmented reality applications," in Proc. of Int. Conf. on Virtual Reality Continuum and its Applications in Industry, 2009.
  2. G. Simon, A. W. Fitzgibbon and A. Zisserman, "Markerless tracking using planar structures in the scene," in Proc. Int. Symposium on Augmented Reality, 2000.
  3. G. Klein and D. Murray, "Parallel tracking and mapping for small AR workspaces," in Proc. of the Conf. on Computer Vision and Augmented Reality, 2007.
  4. Z. Zhang, "A flexible new technique for camera calibration," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1330-1334, 2000.
  5. E. Trucco and A. Verri, "Introductory Techniques for 3-D Computer Vision". Prentice Hall, 1998.
  6. K. Kim, V. Lepetit and W. Woo, "Keyframe-based modeling and tracking of multiple 3D objects," Int. Symposium of Mixed and Augmented Reality, 2010.
  7. L. Vacchetti, V. Lepetit, and P. Fua, "Stable real-time 3d tracking using online and offline information," IEEE Trans. on PAMI, vol. 26, pp. 1385-1391, 2004. https://doi.org/10.1109/TPAMI.2004.92
  8. R. Freeman and A, "Steed, interactive modelling and tracking for mixed and augmented reality," in Proc. of the ACM symposium on Virtual Reality Software and Technology, 2006.
  9. V. Lepetit, P. Lagger and P. Fua, "Randomized trees for real-time keypoint recognition," IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2005.
  10. J. Y. Bouguet, "Pyramidal implementation of the lucas-kanade feature tracker description of the algorithm," Intel Corporation Microprocessor Research Labs, 2000.
  11. F. Dornaika and C. Garcia, "Robust camera calibration using 2D to 3D feature correspondences," Optical Science Engineering and Instrumentation, Videometrics V, Volume 3174, 1999.
  12. 김기백, 이석한, 최종수, "히스토그램 명세화와 칼만 필터를 이용한 급격한 밝기 변화에 강건한 증강현실 시스템," 전자공학회논문지, 제 48권 제 2호, 1-148쪽, 2011년 3월