Automatic estimation of asymmetry for gradient-based alignment of noisy images on Lie group

Many parametric image alignment approaches assume equality of the images to register up to motion compensation. In presence of noise this assumption does not hold. In particular, for gradient-based approaches, which rely on the optimization of an error functional with gradient descent methods, the performances depend on the amount of noise in each image. We propose in this paper to use the Asymmetric Composition on Lie groups (ACL) formulation of the alignment problem to improve the robustness in presence of asymmetric levels of noise. The ACL formulation, generalizing state-of-the-art gradient-based image alignment, introduces a parameter to weight the influence of the images during the optimization. Three new methods are presented to estimate this asymmetry parameter: one supervised (MVACL) and two fully automatic (AACL and GACL). Theoretical results and experimental validation show how the new algorithms improve robustness in presence of noise. Finally, we illustrate the interest of the new approaches for object tracking under low-light conditions.

► We model the image alignment problem as the minimization of an asymmetric error.
► We study the influence of additive noise on the alignment performance.
► The optimization involves a deterministic structural term and a random noise term.
► A trade-off has to be done to minimize the influence of both terms.
► New algorithms are introduced to achieve this trade-off automatically.