Abstract

An important tool for experimental fluid mechanics research is Particle Image Velocimetry (PIV). Several robust methodologies have been proposed to perform the estimation of the velocity field from the images, however, alternative methods are still needed to increase the spatial resolution of the results. This work presents a novel approach for estimating fluid flow fields using neural networks and the optical flow equation to predict displacement vectors between sequential images. The result is a continuous representation of the displacement that can be evaluated at the full spatial resolution of the image. The methodology was validated on synthetic and experimental images. Accurate results were obtained in terms of the estimation of instantaneous velocity fields, and of the determined time average turbulence quantities and power spectral density. Comparisons against OpenPIV and RAFT256-PIV are included, with accuracy and runtime reported across synthetic and experimental sequences. The methodology proposed differs from previous attempts of using machine learning for this task: it does not require any previous training, and could be directly used in any pair of images.