Matches in SemOpenAlex for { <https://semopenalex.org/work/W3116155102> ?p ?o ?g. }
- W3116155102 endingPage "227372" @default.
- W3116155102 startingPage "227360" @default.
- W3116155102 abstract "Recently, the interpolation of correspondences method has been widely used in optical flow estimation, because it produces an accurate flow field and costs little runtimes. However, most of the existing matching-based optical flow methods are usually susceptible to non-rigid motion and large displacements. We propose in this article a large displacement optical flow estimation method based on robust interpolation of sparse correspondences, named Riscflow. First, we utilize the deep matching model to achieve an initial matching result of two consecutive frames, and then we exploit a grid-based motion statistics optimization scheme to remove the outliers from the initial matching field. Second, we propose a random forest-based motion boundary extraction model and construct a sparse-to-dense interpolation method by using the boundary information to prevent the dense matching field from edge-blurring. Third, we design a global optical flow estimation method by using an energy function to optimize the dense matching field. Finally, we respectively run the proposed method on the MPI-Sintel and UCF101 databases to conduct a comprehensive comparison with some state-of-the-art optical flow approaches including the variational methods, the matching-based methods, and the deep learning-based methods. The comparison results demonstrate that the proposed method has high accuracy and good robustness of optical flow estimation, and especially gains the benefit of edge-preserving under non-rigid motion and large displacements." @default.
- W3116155102 created "2021-01-05" @default.
- W3116155102 creator A5004258931 @default.
- W3116155102 creator A5035561676 @default.
- W3116155102 creator A5064386450 @default.
- W3116155102 creator A5064925158 @default.
- W3116155102 creator A5087555148 @default.
- W3116155102 creator A5088671036 @default.
- W3116155102 date "2020-01-01" @default.
- W3116155102 modified "2023-10-17" @default.
- W3116155102 title "Large Displacement Optical Flow Estimation Based on Robust Interpolation of Sparse Correspondences" @default.
- W3116155102 cites W1578285471 @default.
- W3116155102 cites W1762798876 @default.
- W3116155102 cites W1763426478 @default.
- W3116155102 cites W1867429401 @default.
- W3116155102 cites W1909538523 @default.
- W3116155102 cites W1951289974 @default.
- W3116155102 cites W1991171799 @default.
- W3116155102 cites W1997409415 @default.
- W3116155102 cites W2011811831 @default.
- W3116155102 cites W2033040413 @default.
- W3116155102 cites W2033959528 @default.
- W3116155102 cites W2100315781 @default.
- W3116155102 cites W2113221323 @default.
- W3116155102 cites W2129587342 @default.
- W3116155102 cites W2131747574 @default.
- W3116155102 cites W2150066425 @default.
- W3116155102 cites W2155302366 @default.
- W3116155102 cites W2156956645 @default.
- W3116155102 cites W2157394577 @default.
- W3116155102 cites W2158919891 @default.
- W3116155102 cites W2168874984 @default.
- W3116155102 cites W2278648135 @default.
- W3116155102 cites W2302395601 @default.
- W3116155102 cites W2517490240 @default.
- W3116155102 cites W2548527721 @default.
- W3116155102 cites W2560335610 @default.
- W3116155102 cites W2560474170 @default.
- W3116155102 cites W2604987967 @default.
- W3116155102 cites W2623012233 @default.
- W3116155102 cites W2738028674 @default.
- W3116155102 cites W2754925132 @default.
- W3116155102 cites W2755343736 @default.
- W3116155102 cites W2768201706 @default.
- W3116155102 cites W2793114969 @default.
- W3116155102 cites W2793872863 @default.
- W3116155102 cites W2800114522 @default.
- W3116155102 cites W2893765796 @default.
- W3116155102 cites W2901940963 @default.
- W3116155102 cites W2904071629 @default.
- W3116155102 cites W2905310541 @default.
- W3116155102 cites W2962864875 @default.
- W3116155102 cites W2963219046 @default.
- W3116155102 cites W2963548592 @default.
- W3116155102 cites W2963686433 @default.
- W3116155102 cites W2963782415 @default.
- W3116155102 cites W2964002255 @default.
- W3116155102 cites W2964156315 @default.
- W3116155102 cites W2964748237 @default.
- W3116155102 cites W2977536039 @default.
- W3116155102 cites W2980116241 @default.
- W3116155102 cites W2990026522 @default.
- W3116155102 cites W3000966067 @default.
- W3116155102 cites W3007471652 @default.
- W3116155102 cites W3010749748 @default.
- W3116155102 cites W3100280854 @default.
- W3116155102 cites W3109379931 @default.
- W3116155102 cites W3109908659 @default.
- W3116155102 cites W4249022109 @default.
- W3116155102 cites W764651262 @default.
- W3116155102 doi "https://doi.org/10.1109/access.2020.3045764" @default.
- W3116155102 hasPublicationYear "2020" @default.
- W3116155102 type Work @default.
- W3116155102 sameAs 3116155102 @default.
- W3116155102 citedByCount "2" @default.
- W3116155102 countsByYear W31161551022021 @default.
- W3116155102 countsByYear W31161551022023 @default.
- W3116155102 crossrefType "journal-article" @default.
- W3116155102 hasAuthorship W3116155102A5004258931 @default.
- W3116155102 hasAuthorship W3116155102A5035561676 @default.
- W3116155102 hasAuthorship W3116155102A5064386450 @default.
- W3116155102 hasAuthorship W3116155102A5064925158 @default.
- W3116155102 hasAuthorship W3116155102A5087555148 @default.
- W3116155102 hasAuthorship W3116155102A5088671036 @default.
- W3116155102 hasBestOaLocation W31161551021 @default.
- W3116155102 hasConcept C107551265 @default.
- W3116155102 hasConcept C11413529 @default.
- W3116155102 hasConcept C115961682 @default.
- W3116155102 hasConcept C137800194 @default.
- W3116155102 hasConcept C154945302 @default.
- W3116155102 hasConcept C155542232 @default.
- W3116155102 hasConcept C15744967 @default.
- W3116155102 hasConcept C31972630 @default.
- W3116155102 hasConcept C33923547 @default.
- W3116155102 hasConcept C41008148 @default.
- W3116155102 hasConcept C542102704 @default.
- W3116155102 hasConceptScore W3116155102C107551265 @default.
- W3116155102 hasConceptScore W3116155102C11413529 @default.