| Online-Ressource |
Verfasst von: | Fortun, Denis [VerfasserIn]  |
| Storath, Martin [VerfasserIn]  |
| Rickert, Dennis [VerfasserIn]  |
| Weinmann, Andreas [VerfasserIn]  |
| Unser, Michael [VerfasserIn]  |
Titel: | Fast piecewise-affine motion estimation without segmentation |
Verf.angabe: | Denis Fortun, Martin Storath, Dennis Rickert, Andreas Weinmann, and Michael Unser, Fellow, IEEE |
E-Jahr: | 2018 |
Jahr: | 23 July 2018 |
Umfang: | 13 S. |
Fussnoten: | Gesehen am 08.04.2020 |
Titel Quelle: | Enthalten in: Institute of Electrical and Electronics EngineersIEEE transactions on image processing |
Ort Quelle: | New York, NY : IEEE, 1992 |
Jahr Quelle: | 2018 |
Band/Heft Quelle: | 27(2018), 11, Seite 5612-5624 |
ISSN Quelle: | 1941-0042 |
Abstract: | Current algorithmic approaches for piecewise affine motion estimation are based on alternating motion segmentation and estimation. We propose a new method to estimate piecewise affine motion fields directly without intermediate segmentation. To this end, we reformulate the problem by imposing piecewise constancy of the parameter field, and derive a specific proximal splitting optimization scheme. A key component of our framework is an efficient 1D piecewise-affine estimator for vector-valued signals. The first advantage of our approach over segmentation-based methods is its absence of initialization. The second advantage is its lower computational cost, which is independent of the complexity of the motion field. In addition to these features, we demonstrate competitive accuracy with other piecewise-parametric methods on standard evaluation benchmarks. Our new regularization scheme also outperforms the more standard use of total variation and total generalized variation. |
DOI: | doi:10.1109/TIP.2018.2856399 |
URL: | Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.
Volltext ; Verlag: https://doi.org/10.1109/TIP.2018.2856399 |
| Volltext: https://ieeexplore.ieee.org/document/8417969 |
| DOI: https://doi.org/10.1109/TIP.2018.2856399 |
Datenträger: | Online-Ressource |
Sprache: | eng |
Sach-SW: | current algorithmic approaches |
| Estimation |
| fast piecewise-affine motion estimation |
| Image segmentation |
| image sequences |
| intermediate segmentation |
| motion estimation |
| Motion estimation |
| motion segmentation |
| Motion segmentation |
| optical flow |
| optimisation |
| optimization |
| Optimization |
| parameter field |
| piecewise affine |
| piecewise affine motion estimation |
| piecewise affine motion fields |
| piecewise constancy |
| piecewise constant techniques |
| piecewise-affine estimator |
| piecewise-parametric methods |
| segmentation-based methods |
| specific proximal splitting optimization scheme |
| Standards |
| total generalized variation |
| TV |
K10plus-PPN: | 1694288633 |
Verknüpfungen: | → Zeitschrift |
Fast piecewise-affine motion estimation without segmentation / Fortun, Denis [VerfasserIn]; 23 July 2018 (Online-Ressource)