Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Robust Optical Flow Detection Using 2D histogram with Variable Resolution

가변 분해능을 가진 2차원 히스토그램을 이용한 강건한 광류인식

  • Published : 2005.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

The proposed algorithm is to achieve the robust optical flow detection which is applicable for the case that the outlier rate is over $80\%$. If the outlier rate of optical flows is over $30\%$, the discrimination between the inliers and outlier with the conventional algorithm is very difficult. The proposed algorithm is to overcome such difficulty withthree steps of grouping algorithm; 1) constructing the 2 D histogram with two axies of the lengths and the directions of optical flows. 2) sorting the number of optical flows in each bin of the two-dimensional histogram in the descendingorder and removing some bins with lower number of optical flows than threshold 3) increasing the resolution of the two-dimensional histogram if the number of optical flows in a specific bin is over $20\%$ and decreasing theresolution if the number of optical flows is less than $10\%$. Such processing is repeated until the the number of optical flows falls into the range of $10\%-20\%$ in all the bins. The proposed algorithm works well on the different kinds of images with many of wrong optical flows. Experimental results are included.

두 영상에서 정확한 광류를 얻고자 할 경우, 잘못 정합된 광류의 수가 전체의 $80\%$이상일 경우에도, 정합이 잘된 광류만을 빠르고 안정적으로 추출하는 방법을 제안하였다. 제안한 방법은 다음과 같은 단계로 구성된 그룹화 알고리즘이다. 1)광류의 방향과 길이성분으로 구성된 2차원 히스토그램을 구성한 후, 2)2차원 히스토그램에서 광류수가 높은 그룹들부터 내림차 순으로 정리한 후 각 그룹에서 광류수가 적은 그룹은 제거한다. 또, 3)선택된 그룹들의 광류수가 $20\%$ 이상일때는 히스토그램의 분해율를 증가 시키고, $10\%$ 이하일 경우에는 히스토그램의 분해율을 감소시켜서 위 과정을 반복한다. 선택된 그룹들의 광류수가 $10\%$에서 $20\%$사이에 올 때 까지 이 반복을 계속한다. 제안한 알고리즘을 잘못된 광류가 많이 포함된 다양한 종류의 영상에 대해서 적용한 결과 강건하게 정합이 되어 잘못된 광류를 제거할 수 있었다. 이 논문은 이에 대한 실험결과를 포함하였다.

Keywords

References

  1. J. K Kearney, W. B. Thompson, and D. L. Boley, Optical flow estimation: An error analysis of Gradient-based methods with local optimization, IEEE Tr. on PAMI, Vol. PAMI-9, No.2, pp. 229-244, March 1987 https://doi.org/10.1109/TPAMI.1987.4767897
  2. E. H. Adelson and J. R. Bergen, Spatiotemporal energy models for the perception of motion, Journal of Optical Society of America, A, Vol. 2, No.2, pp. 284-299, Feb. 1985 https://doi.org/10.1364/JOSAA.2.000284
  3. S.M. Smith and J. M. Brady, Real-Time Motion Segmentation and Shape Tracking, IEEE Tr. on PAMI, Vol. 17, No. 8, 1995 https://doi.org/10.1109/34.400573
  4. B. K. P. Horn, B. B. Schunck, 'Determining optical flow,' Artificial Intelligence, Vol. 17, pp. 185-203, 1981 https://doi.org/10.1016/0004-3702(81)90024-2
  5. G. Harris, Determination of Ego-Motion From Matched Points,Proc. Alvey Vision Conf., Cambridge UK, 1987
  6. L. Kitchen, A. Rosenfeld, Gray Level Corner Detection, Pattern Recognition Letters, pp. 95-102, 1982 https://doi.org/10.1016/0167-8655(82)90020-4
  7. Farzin Mokhatarian and Riku Suomela,'Robust Image Corner Detection Through Curvature Scale Space,' , IEEE Tr. on PAMI, VOL. 12, December 1998 https://doi.org/10.1109/34.735812
  8. Smith, S.M., J.M. Brady, 1997. SUSAN - a new approach to low level image processing. International Journal of Computer Vision, 23(1), pp. 45-78, 1997 https://doi.org/10.1023/A:1007963824710
  9. R. M. Haralick et al. Pose estimation from corresponding point data. IEEE Tr. SMC, 19(6): 1426-1446,Nov. 1988 https://doi.org/10.1109/21.44063
  10. Rousseeuw, P. J. Least median of squares regression. Journal of American Statistics Association, 79: 871880, 1984 https://doi.org/10.2307/2288718