PuSH - Publikationsserver des Helmholtz Zentrums München

Fortun, D.* ; Storath, M.* ; Rickert, D. ; Weinmann, A. ; Unser, M.*

Fast piecewise-affine motion estimation without segmentation.

IEEE Trans. Image Process. 27, 5612-5624 (2018)
Verlagsversion Postprint DOI
Open Access Green
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.
Altmetric
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Motion Estimation ; Optical Flow ; Optimization ; Piecewise Affine; Optical-flow Estimation; Variational-problems; Image Motion; Model; Time
ISSN (print) / ISBN 1057-7149
e-ISSN 1941-0042
Quellenangaben Band: 27, Heft: 11, Seiten: 5612-5624 Artikelnummer: , Supplement: ,
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Verlagsort 445 Hoes Lane, Piscataway, Nj 08855-4141 Usa
Begutachtungsstatus