Name
Abstract | ||
|---|---|---|
Despite the fact that temporal coherence is undeniably one of the key aspects when processing video data, this concept has hardly been exploited in recent optical flow methods. In this paper, we will present a novel parametrization for multi-frame optical flow computation that naturally enables us to embed the assumption of a temporally coherent spatial flow structure, as well as the assumption that the optical flow is smooth along motion trajectories. While the first assumption is realized by expanding spatial regularization over multiple frames, the second assumption is imposed by two novel first- and second-order trajectorial smoothness terms. With respect to the latter, we investigate an adaptive decision scheme that makes a local (per pixel) or global (per sequence) selection of the most appropriate model possible. Experiments show the clear superiority of our approach when compared to existing strategies for imposing temporal coherence. Moreover, we demonstrate the state-of-the-art performance of our method by achieving Top 3 results at the widely used Middlebury benchmark. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICCV.2011.6126359 | Computer Vision |
Keywords | Field | DocType |
image motion analysis,image sequences,video signal processing,Middlebury benchmark,adaptive decision scheme,global selection,local selection,motion trajectory,multiframe optical flow computation,optical flow methods,spatial regularization,state-of-the-art performance,temporal coherence modeling,temporally coherent spatial flow structure,trajectorial smoothness terms,video data processing | Computer vision,Parametrization,Computer science,Robustness (computer science),Coherence (physics),Regularization (mathematics),Artificial intelligence,Pixel,Smoothness,Optical flow,Trajectory | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
ISBN | Citations | PageRank |
978-1-4577-1101-5 | 37 | 1.08 |
References | Authors | |
22 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sebastian Volz | 1 | 60 | 4.31 |
| Andrés Bruhn | 2 | 1558 | 82.42 |
| Levi Valgaerts | 3 | 470 | 15.88 |
| Henning Zimmer | 4 | 530 | 21.88 |