Abstract | ||
---|---|---|
This paper addresses the problem of video registration for dense non-rigid structure from motion under suboptimal conditions, such as noise, self-occlusions, considerable external occlusions or specularities, i.e. the computation of optical flow between the reference image and each of the subsequent images in a video sequence when the camera observes a highly deformable object. We tackle this challenging task by improving previously proposed variational optimization techniques for multi-frame optical flow (MFOF) through detection, tracking and handling of uncertain flow field estimates. This is based on a novel Bayesian inference approach incorporated into the MFOF. At the same time, computational costs are significantly reduced through iterative pre-computation of the flow fields. As shown through experiments, the resulting method performs superior to other state-of-the-art (MF) OF methods on video sequences showing a highly non-rigidly deforming object with considerable occlusions. |
Year | Venue | Field |
---|---|---|
2016 | 2016 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2016) | Structure from motion,Computer vision,Occlusion,Bayesian inference,Pattern recognition,Computer science,Video tracking,Artificial intelligence,Optical flow,Trajectory,Adaptive optics,Computation |
DocType | ISSN | Citations |
Conference | 2472-6737 | 2 |
PageRank | References | Authors |
0.36 | 14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bertram Taetz | 1 | 97 | 11.15 |
Gabriele Bleser | 2 | 241 | 27.76 |
Vladislav Golyanik | 3 | 22 | 12.55 |
Didier Stricker | 4 | 1266 | 138.03 |