Proposal of Depth Estimation Method Using Deep Learning for Droplet Visualization

Abstract

In the Urea-SCR system, two-dimensional visualization images of spray droplet taken by a high-speed camera are used for verification of atomization and measurement of droplet diameter. This paper describes the method for predicting the droplet diameter from visualization image with depth of field using deep learning to improve accuracy of measuring droplet size distribution. As a result from trained model, this method showed applicability to measure droplet within various depths.