Name
Abstract | ||
|---|---|---|
Most of the variational optical flow methods are based on the well-known brightness constancy assumption or high-order constancy assumptions to implement the data term in the optimization energy function. Unfortunately, any variation in the lighting within the scene violates the brightness constancy constraint; in turn, the gradient constancy assumption does not work properly with large illumination changes. This paper proposes an illumination-robust constancy based on a robust texture descriptor rather than the brightness constancy. Thus, the similarity function used as a data term was obtained from extracting texture features through the local directional pattern descriptor for two consecutive frames within the duality total variational optical flow algorithm. In addition, a weighted nonlocal term that depends on both the color similarity and the occlusion state of pixels is integrated during the optimization process to increase the accuracy of the resulting flow field. The experimental results show a qualitative comparison with the proposed approach and yield state-of-the-art results on the KITTI, Midleburry, and MPI-sintel data sets. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TCSVT.2014.2308628 | Circuits and Systems for Video Technology, IEEE Transactions |
Keywords | DocType | Volume |
feature extraction,image sequences,image texture,KITTI data sets,MPI-sintel data sets,Midleburry data sets,brightness constancy assumption,brightness constancy constraint,color similarity,consecutive frames,data term,duality total variational optical flow algorithm,gradient constancy assumption,high-order constancy assumptions,illumination-robust constancy,illumination-robust optical flow,lighting,local directional pattern descriptor,optimization energy function,optimization process,pixel occlusion state,robust texture descriptor,similarity function,texture feature extraction,variational optical flow methods,weighted nonlocal term,Features descriptors,local directional pattern (LDP),optical flow,similarity measure,total variation,weighted nonlocal term | Journal | 24 |
Issue | ISSN | Citations |
9 | 1051-8215 | 5 |
PageRank | References | Authors |
0.46 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mahmoud A. Mohamed | 1 | 13 | 4.05 |
| Hatem A. Rashwan | 2 | 68 | 16.88 |
| Bärbel Mertsching | 3 | 261 | 49.17 |
| Miguel Ángel Garcia | 4 | 220 | 24.41 |
| Domènec Puig | 5 | 84 | 7.98 |