Fast 3D particle reconstruction using a convolutional neural network: application to dusty plasmas

Abstract We present an algorithm to reconstruct the three-dimensional positions of particles in a dense cloud dusty plasma using convolutional neural network. The approach is found be very fast and yields relatively high accuracy. In this paper, we describe examine regarding particle number reconstruction accuracy synthetic data experimental data. To show applicability 3D dust under weightlessness are reconstructed from stereoscopic camera images prescribed