Name
Abstract | ||
|---|---|---|
The brightness constancy assumption is the base of estimating the flow fields in most differential optical flow approaches. However, the brightness constancy constraint easily violates with any variation in the lighting conditions in the scene. Thus, this work proposes a robust data term against illumination changes based on a rich descriptor. This descriptor extracts the textures features for each image in the two consecutive images using local edge responses. In addition, a weighted non-local term depending on the intensity similarity, the spatial distance and the occlusion state of pixels is integrated within the adapted duality total variational optical flow algorithm in order to obtain accurate flow fields. The proposed model yields state-of-the-art results on the the KITTI optical flow database and benchmark. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1145/2510650.2510660 | ARTEMIS@ACM Multimedia |
Keywords | Field | DocType |
rich descriptor,flow field,kitti optical flow database,illumination change,weighted non-local term,robust data term,differential optical flow approach,accurate flow field,brightness constancy constraint,total variational optical flow,brightness constancy assumption,motion estimation,optical flow | Computer vision,Computer science,Flow (psychology),Robustness (computer science),Robust statistics,Duality (optimization),Artificial intelligence,Pixel,Motion estimation,Optical flow,Brightness | Conference |
Citations | PageRank | References |
2 | 0.39 | 9 |
Authors | ||
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 Angel Garcia | 4 | 154 | 12.86 |
| Domenec Puig | 5 | 332 | 54.33 |