Prediction of Object Geometry from Acoustic Scattering Using Convolutional Neural Networks
This work addresses a domain-specific problem in acoustic imaging, but it is incremental as it applies existing CNN methods to new simulated data without introducing novel paradigms.
The paper tackles the problem of predicting object geometry from acoustic scattering features by training convolutional neural networks on simulated data, achieving high accuracy with robustness to data degradation such as fewer channels or lower resolutions.
Acoustic scattering is strongly influenced by boundary geometry of objects over which sound scatters. The present work proposes a method to infer object geometry from scattering features by training convolutional neural networks. The training data is generated from a fast numerical solver developed on CUDA. The complete set of simulations is sampled to generate multiple datasets containing different amounts of channels and diverse image resolutions. The robustness of our approach in response to data degradation is evaluated by comparing the performance of networks trained using the datasets with varying levels of data degradation. The present work has found that the predictions made from our models match ground truth with high accuracy. In addition, accuracy does not degrade when fewer data channels or lower resolutions are used.