Occlusion Detection and Motion Estimation with Convex Optimization
Abstract
We tackle the problem of simultaneously detecting occlusions and estimating optical flow. We show that, under standard assumptions of Lambertian reflection and static illumination, the task can be posed as a convex minimization problem. Therefore, the solution, computed using efficient algorithms, is guaranteed to be globally optimal, for any number of independently moving objects, and any number of occlusion layers. We test the proposed algorithm on benchmark datasets, expanded to enable evaluation of occlusion detection performance.
Cite
Text
Ayvaci et al. "Occlusion Detection and Motion Estimation with Convex Optimization." Neural Information Processing Systems, 2010.Markdown
[Ayvaci et al. "Occlusion Detection and Motion Estimation with Convex Optimization." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/ayvaci2010neurips-occlusion/)BibTeX
@inproceedings{ayvaci2010neurips-occlusion,
title = {{Occlusion Detection and Motion Estimation with Convex Optimization}},
author = {Ayvaci, Alper and Raptis, Michalis and Soatto, Stefano},
booktitle = {Neural Information Processing Systems},
year = {2010},
pages = {100-108},
url = {https://mlanthology.org/neurips/2010/ayvaci2010neurips-occlusion/}
}