TY  - JOUR
AU  - Fei Yang
AU  - Yongmei Cheng
AU  - Joost Van de Weijer
AU  - Mikhail Mozerov
PY  - 2020//
TI  - Improved Discrete Optical Flow Estimation With Triple Image Matching Cost
T2  - ACCESS
JO  - IEEE Access
SP  - 17093
EP  - 17102
VL  - 8
N2  - Approaches that use more than two consecutive video frames in the optical flow estimation have a long research history. However, almost all such methods utilize extra information for a pre-processing flow prediction or for a post-processing flow correction and filtering. In contrast, this paper differs from previously developed techniques. We propose a new algorithm for the likelihood function calculation (alternatively the matching cost volume) that is used in the maximum a posteriori estimation. We exploit the fact that in general, optical flow is locally constant in the sense of time and the likelihood function depends on both the previous and the future frame. Implementation of our idea increases the robustness of optical flow estimation. As a result, our method outperforms 9% over the DCFlow technique, which we use as prototype for our CNN based computation architecture, on the most challenging MPI-Sintel dataset for the non-occluded mask metric. Furthermore, our approach considerably increases the accuracy of the flow estimation for the matching cost processing, consequently outperforming the original DCFlow algorithm results up to 50% in occluded regions and up to 9% in non-occluded regions on the MPI-Sintel dataset. The experimental section shows that the proposed method achieves state-of-the-arts results especially on the MPI-Sintel dataset.
UR  - https://ieeexplore.ieee.org/abstract/document/8963946
UR  - http://dx.doi.org/10.1109/ACCESS.2020.2968180
N1  - LAMP; 600.120
ID  - Fei Yang2020
ER  -