Anisotropie diffusion-based texture preserving optical flow estimation using an incremental multi-resolution approach

@article{Lee2014AnisotropieDT,
  title={Anisotropie diffusion-based texture preserving optical flow estimation using an incremental multi-resolution approach},
  author={Ju Hwan Lee and Jong Seob Jeong and Byeong Cheol Choi and Ki Chang Nam and Sung-min Kim},
  journal={2014 International Conference on Information Science, Electronics and Electrical Engineering},
  year={2014},
  volume={1},
  pages={210-210}
}
The purpose of this study was to propose a texture preserving optical flow approach based on non-linear anisotropic diffusion filtering scheme to estimate the accurate motion fields. The proposed technique estimated the motion fields based on several fundamental techniques. Firstly, we recomposed the original image by using the structure-texture decomposition to remove the structure information from the input image. We then employed an anisotropic diffusion-based slightly non-convex TV-L1… CONTINUE READING