Occlusion Detection and Motion Estimation with Convex Optimization

Occlusion Detection and Motion Estimation with Convex Optimization

Conference

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.

Details

PUBLISHED IN
Advances in Neural Information Processing Systems (NIPS)
PUBLICATION DATE
15 十二月 2010
AUTHORS
A. Ayvaci, M. Raptis, S. Soatto