Generalization of deep recurrent optical flow estimation for particle-image velocimetry data

Measurement Science and Technology, vol. 33, pp. 094003

Abstract

Abstract Particle-image velocimetry (PIV) is one of the key techniques in modern experimental fluid mechanics to determine the velocity components of flow fields in a wide range of complex engineering problems. Current PIV processing tools are mainly handcrafted models based on cross-correlations computed across interrogation windows. Although widely used, these existing tools have a number of well-known shortcomings, including limited spatial output resolution and peak-locking biases. Recently, new approaches for PIV processing leveraging a novel neural network architecture for optical flow estimation called recurrent all-pairs field transforms (RAFT) have been developed. These have matched or exceeded the performance of classical, handcrafted models. While the RAFT-PIV method is a promising approach, it is important for the broader fluids community to more completely understand its empirical behavior and performance. To this end, in this study, we thoroughly investigate the performance of RAFT-PIV under varying image and lighting conditions. We consider applications spanning synthetic and experimental data, with a breadth and depth going far beyond currently available empirical results. The results for the wide variation of experiments shed new light on the capabilities of deep learning for PIV processing.

Authors 4

1. Christian Lagemann corresponding Aachen Institute of Aerodynamics Aachen

   RWTH Aachen University

   Affiliation as printed

   Institute of Aerodynamics Aachen, RWTH Aachen University, Aachen, Germany

2. Kai Lagemann corresponding

   University of Bonn · German Center for Neurodegenerative Diseases

   Affiliation as printed

   Statistics and Machine Learning, DZNE, Bonn, Germany

3. Sach Mukherjee corresponding

   University of Bonn · University of Cambridge · German Center for Neurodegenerative Diseases

   Affiliation as printed

   Statistics and Machine Learning, DZNE, Bonn, Germany

   University of Cambridge, Cambridge, United Kingdom

4. Wolfgang Schröder corresponding Aachen Institute of Aerodynamics Aachen JARA Center for Simulation and Data Science

   RWTH Aachen University

   Affiliation as printed

   Institute of Aerodynamics Aachen, RWTH Aachen University, Aachen, Germany

   JARA Center for Simulation and Data Science, RWTH Aachen University, Aachen, Germany