DOI QR코드

DOI QR Code

Development Robust Video Stabilization algorithm based Opticla Flow

Optical flow를 이용한 영상의 흔들림 보정 알고리듬 개발

  • Received : 2019.12.09
  • Accepted : 2019.12.30
  • Published : 2019.12.31

Abstract

An image compensating algorithm with high-vibration movement is proposed, using optical flow and the Kalman Filter. The temporal motion vector field is calculated by Optical flow and suspicious vectors are removed or adjusted by the Gaussian interpolation method. The high-vibrated vector filled is stabilized by the Kalman filter. Lastly, compensated images are obtained by affine transformation. This proposed algorithm gives good compensated video images on high-vibration situations.

Keywords

References

  1. Ko, S.J., Lee, S.H., Jeon, S.W. and Kang, E.S., 1999, "Fast digital image stabilizer based on gray-coded bit-plane matching." IEEE Trans. Consumer Electronics, Vol. 45, pp. 598-603 https://doi.org/10.1109/30.793546
  2. Paik, J.K., Park Y.G. and Kim, D.W., 1992, "An adaptive motion decision system for digital image stbilizer based on edge pattern matching.", IEEE, Trans. Consumer Electronics Vol. 38, pp. 607-615. https://doi.org/10.1109/30.156744
  3. Uomori K., Morimura, A., Ishii, H., Sakaguchi, T. and Kitamura, Y., 1990, "Automatic image stabilization system by full-digital signal processing," IEEE Trans. Consumer Electronics Vol. 36, pp.510-519. https://doi.org/10.1109/30.103167
  4. 김인철, 최은미, 오휘경, 2012, "연속 자유 공간에서 가우시안 보간법을 이용한 보행자 위치 추적", 정보처리학회논문지B 19권 3호, pp. 177-182.
  5. Kalman, R.E. 1960, "A new approach to linear filtering and prediction problems.", Transactions of the ASME-Journal of Basic Engineering, No. 82 (Series D), pp.35-45. https://doi.org/10.1115/1.3662552