Platform motion estimation in multiple-input multiple-output synthetic aperture sonar with coupled variational autoencoders

Abstract

Synthetic aperture sonar (SAS) utilizes the motion of the platform carrying the sonar system to synthesize an aperture that is much longer than thephysical antenna by coherently combining data from several pings. Coherent processing in SAS requires platform motion estimation and compensation with sub-wavelength accuracy for high-resolution imaging. Micronavigation, i.e., through-the-sensor platform motion estimation from spatio-temporal coherence measurements of diffuse backscatter on overlapping recordings between successive pings, is essential when positioning information from navigational instruments is absent or inadequately accurate. Representation learning with a variational autoencoder (VAE) offers an unsupervised data-driven micronavigation solution. In this study, we introduce a hierarchical variational model implemented with coupled VAEs to relate the common latent features between datasets of coherence measurements in broadband multiple-input multiple-output SAS systems. We show that self-supervising the training process of independently parameterized but coupled VAEs improves significantly the accuracy of the micronavigation estimates.