Marker Detection by Using Affine-SIFT Matching Points for Marker Occlusion of Augmented Reality

증강현실에서 가려진 마커를 위한 Affine-SIFT 정합 점들을 이용한 마커 검출 기법

  • Kim, Yong-Min (Dept. of Comp. Sci. and Eng., Hanyang University) ;
  • Park, Chan-Woo (Dept. of Comp. Sci. and Eng., Hanyang University) ;
  • Park, Ki-Tae (Ambient Intelligence Software Team, Institute of Hanyang BK21, Hanyang University) ;
  • Moon, Young-Shik (Dept. of Comp. Sci. and Eng., Hanyang University)
  • 김용민 (한양대학교 컴퓨터공학과) ;
  • 박찬우 (한양대학교 컴퓨터공학과) ;
  • 박기태 (한양대학교 BK21 엠비언트인텔리전스소프트웨어팀) ;
  • 문영식 (한양대학교 컴퓨터공학과)
  • Received : 2010.11.23
  • Accepted : 2010.02.24
  • Published : 2011.03.25

Abstract

In this paper, a novel method of marker detection robust against marker occlusion in augmented reality is proposed. the proposed method consists of four steps. In the first step, in order to effectively detect an occluded marker, we first utilize the Affine-SIFT (ASIFT, Affine-Scale Invariant Features Transform) for detecting matching points between an enrolled marker and an input images with an occluded marker. In the second step, we apply the Principal Component Analysis (PCA) for eliminating outlier of the matching points in the enrolled marker. And then matching points are projected to the first and second axis for longest value and the shortest value of an ellipse are determined by average distance between the projected points and a center of the points. In the third step, Convex-hull vertices including matching points are considered as polygon vertices for estimating a geometric affine transformation. In the final step, by estimating the geometric affine transformation of the points, a marker robust against a marker occlusion is detected. Experimental results have shown that the proposed method effectively detects occlude markers.

본 논문은 증강현실 시스템에서 마커가 가려진 상황에서도 강건한 마커 검출을 위하여 지역적인 특징 점들을 이용하는 방법을 제안한다. 가려진 마커를 효율적으로 검출하기 위하여, 첫 번째 단계로 등록된 마커와 가려진 마커가 포함된 입력 영상을 Affine-SIFT (ASIFT, Affine-Scale Invariant Features Transform) 방법을 이용해 정합된 특징 점들을 검출한다. 두 번째 단계로 정합된 특징 점들의 이상치(Outlier)를 제거하기 위하여, 등록된 마커의 특징 점들에 주성분 분석(Principal Component Analysis)을 적용하고 제 1 주축과 제 2 주축으로 사영한 후 중심으로 부터의 거리에 대한 평균값을 타원의 장축과 단축으로 지정한다. 세 번째 단계로 마커의 기하학적인 왜곡을 추정하기 위하여 특징 점들이 이루는 Convex-hull 지점들을 다각형의 꼭짓점으로 정한다. 마지막 단계로, 입력영상에 정합된 특징 점들의 기하적인 왜곡의 변화를 추정함으로써 마커의 가려진 환경에 서도 강건한 마커 검출 결과를 얻을 수 있다.

Keywords

References

  1. T. P. Caudell and D. W. Mizell, "Augmented reality: an application of heads-up display technology to manual manufacturing processess," Proc. IEEE Hawaii Int. Conf. on Systems Sciences, vol. 2, pp. 659-669, 1992.
  2. H. Kato and M. Billinghurst, "Marker tracking and HMD calibration for a video-based augmented reality conferencing system," Proc. 2nd IEEE and ACM Int. Workshop Augmented Reality, vol. 85, pp. 20-21, Oct. 1999.
  3. M. Fiala, "ARTag, a fiducial marker system using digital techniques," Proc. of IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 590-596, Jun. 2005.
  4. D. Wagner and D. Schmalstieg, "ARToolKitPlus for pose tracking on mobile devices," Proc. 12th Computer Vision Winter Workshop, pp. 139-146, Feb. 2007.
  5. D. G. Lowe, "Object recognition from local scale-invariant features," Proc. 7th International Conf. on Computer Vision, vol. 2,, pp. 1150-1157, Sep. 1999.
  6. M. Brown and D. G. Lowe, "Invariant features from interest point groups," Proc. 13th British Machine Vision Conf., pp. 656-665, Sep. 2002.
  7. Y. Ke and R. Sukthankar, "PCA-SIFT: A more distinctive representation for local image descriptors," Proc. of the Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 506-513, Jun. 2004.
  8. H. Bay and T. Tuytelaars, L. Van Gool, "SURF: Speeded up robust features," Proc. of Computer Vision and Image Understanding, vol. 110, issue 3, pp. 404-417, Jun. 2006.
  9. J. M. Morel, "ASIFT: A new framework for fully affine invariant image comparison," SIAM Journal on Image Science, vol. 2, issue 2, pp. 438-469, 2009. https://doi.org/10.1137/080732730
  10. P. H. S. Torr and D. W. Murray, "The development and comparison of robust methods for estimating the fundamental matrix," International Journal of Computer Vision, vol. 24, issue. 3, pp. 271-300, 1997. https://doi.org/10.1023/A:1007927408552
  11. L. Moisan and B. Stival. "A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix," International Journal of Computer Vision, vol. 57, issue. 3, pp. 201-218, 2004. https://doi.org/10.1023/B:VISI.0000013094.38752.54