PuSH - Publication Server of Helmholtz Zentrum München

Fast piecewise-affine motion estimation without segmentation.

IEEE Trans. Image Process. 27, 5612-5624 (2018)
Postprint DOI
Open Access Green
as soon as is submitted to ZB.
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
Additional Metrics?
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords Motion Estimation ; Optical Flow ; Optimization ; Piecewise Affine; Optical-flow Estimation; Variational-problems; Image Motion; Model; Time
Reviewing status