An unsupervised deep learning model for dense velocity field reconstruction in particle image velocimetry (PIV) measurements

Abstract

Supervised deep learning methods reported recently have shown promising capability and efficiency in particle image velocimetry (PIV) processes compared to the traditional cross correlation and optical flow methods. However, the deep learning-based methods in previous reports require synthesized particle images and simulated flows for training prior to applications, conflicting with experimental scenarios. To address this crucial limitation, unsupervised deep learning methods have also been proposed for flow velocity reconstruction, but they are generally limited to rough flow reconstructions with low accuracy in velocity due to, for example, particle occlusion and out-of-boundary motions. This paper proposes a new unsupervised deep learning model named UnPWCNet-PIV (an unsupervised optical flow network using Pyramid, Warping, and Cost Volume). Such a pyramidical network with specific enhancements on flow reconstructions holds capabilities to manage particle occlusion and boundary motions. The new model showed comparable accuracy and robustness with the advanced supervised deep learning methods, which are based on synthesized images, together with superior performance on experimental images. This paper presents the details of the UnPWCNet-PIV architecture and the assessments of its accuracy and robustness on both synthesized and experimental images.