Robust Estimation of Camera Motion Using A Local Phase Based Affine Model

국소적 위상기반 어파인 모델을 이용한 강인한 카메라 움직임 추정

  • Jang, Suk-Yoon (ICS Lab, Dept. of Electrical and Electronic Eng., Yonsei University) ;
  • Yoon, Chang-Yong (ICS Lab, Dept. of Electrical and Electronic Eng., Yonsei University) ;
  • Park, Mig-Non (ICS Lab, Dept. of Electrical and Electronic Eng., Yonsei University)
  • 장석윤 (연세대학교 전기전자공학과 지능제어시스템연구실) ;
  • 윤창용 (연세대학교 전기전자공학과 지능제어시스템연구실) ;
  • 박민용 (연세대학교 전기전자공학과 지능제어시스템연구실)
  • Published : 2009.01.25

Abstract

Techniques for tracking the same region of physical space with the temporal sequences of images by matching the contours of constant phase show robust and stable performance in relative to the tracking techniques using or assuming the constant intensity. Using this property, we describe an algorithm for obtaining the robust motion parameters caused by the global camera motion. First, we obtain the optical flow based on the phase of spacially filtered sequential images on the region in a direction orthogonal to orientation of each component of gabor filter bank. And then, we apply the least squares method to the optical flow to determine the affine motion parameters. We demonstrate hat proposed method can be applied to the vision based pointing device which estimate its motion using the image including the display device which cause lighting condition varieties and noise.

동영상에서 시공간상 일정한 위상을 갖는 윤곽선을 정합시켜 물리적 공간에서의 동일한 위치를 추적하는 방법은 명암이 일정한 윤곽선을 정합시키거나 일정한 명암을 전제로 추적하는 방법에 비해 정확성이 높고 조명조건에 대해 안정된 특성이 있다. 본 논문에서는 이러한 성질을 이용하여 조명변화와 노이즈에 강인하게 카메라의 움직임을 추정하는 기법을 소개한다. 우선, 가버 필터뱅크를 사용하여 공간적으로 여과된 연속영상으로부터 계산된 위상의 크기를 기반으로 필터의 방향과 수직인 곳의 광류를 구한 후, 최소제곱법을 적용하여 어파인 모델에 상응하는 카메라의 움직임 파라미터를 구한다. 실험을 통하여 이러한 방법은 조명조건의 변화를 야기하는 디스플레이 기기를 피사체로 하여 카메라의 위치변화를 추정하는 방식의 영상기반 포인팅 디바이스에도 적용될 수 있음을 보인다.

Keywords

References

  1. H. Cantzler and C. Hoile, 'A novel form of a pointing device,' Proc. Vision, Video and Graphics, pp.57–62, 2003
  2. J. Wang, S. Zhai, and J. Canny, 'Camera phone based motion sensing: Interaction, techniques, applications and performance study,' UIST'06, Montreux, Switzerland, pp.101-110, Oct. 2006
  3. C. Hand, 'A Survey of 3D Interaction Techniques,' Computer Graphics Forum, pp.269-281, December 1997 https://doi.org/10.1111/1467-8659.00194
  4. http://www.gyration.com
  5. http://wii.nintendo.com
  6. S. Jang, M. Pomplun, G. Kim, and H. Choi, 'Adaptive robust estimation of affine parameters from block motion vectors,' Image Vision Computing. Vol.23(14), pp. 1250-1263, 2005 https://doi.org/10.1016/j.imavis.2005.09.003
  7. Y.R. Huang, C.M. Kuo, and C.L. Kuo, 'Efficient global motion estimation algorithm using recursive least squares,' Optical Engineering, Vol.45(5), May 2006 https://doi.org/10.1117/1.2205201
  8. F. Comby and O. Strauss, 'Using quasi-continuous histograms for fuzzy main motion estimation in video sequence,' Fuzzy Sets and Systems, Vol.158(5), pp. 475-495, March 2007 https://doi.org/10.1016/j.fss.2006.09.011
  9. B.Lucas and T.Kanade, 'An iterative image registration technique with an application to stereo vision,' Proceedings of DARPA Image Understanding Workshop, pp.121-130, 1981
  10. E .Memin and P. Perez, 'Hierarchical Estimation and Segmentation of Dense Motion Fields,' IJCV(46), No. 2, February 2002, pp. 129-155 https://doi.org/10.1023/A:1013539930159
  11. D. J. Fleet and A. D. Jepson, 'Stability of Phase Information,' IEEE Trans. PAMI, Vol. 15, No. 12, pp. 1253-1268, 1993 https://doi.org/10.1109/34.250844
  12. D. Fleet and A. Jepson, 'Computation of component image velocity from local phase information,' International Journal of Computer Vision, Vol. 5(1), pp. 77-104, 1990 https://doi.org/10.1007/BF00056772
  13. T. Gautama and M. M. Van Hulle, 'A phase-based approach to the estimation of the optical flow field using spatial filtering,' IEEE Trans. Neural Net., Vol.13, No.5, pp.1127-1136, 2002 https://doi.org/10.1109/TNN.2002.1031944
  14. M. V. Srinivasan, S. Venkatesh, and R. Hosie, 'Qualitative Estimation of Camera Motion Parameters from Video Sequences,' Pattern Recognition, Vol.30, No. 4, pp.593-606, April 1997 https://doi.org/10.1016/S0031-3203(96)00106-9
  15. Jahne and H. Hauβecker, Computer Vision and Applications: A Guide for Students and Practitioners, Academic Press, pp.382-388, 2000