Neural Shape-From-Shading for Survey-Scale Self-Consistent Bathymetry From Sidescan

Abstract

Sidescan sonar is a small and cost-effective sensing solution that can be easily mounted on most vessels. Historically, it has been used to produce high-definition acoustical images that experts may use to identify targets on the seafloor or in the water column. While solutions have been proposed to produce bathymetry solely from sidescan, or in conjunction with multibeam, they have had limited impact. This is partly a result of mostly being limited to single survey lines. In this article, we propose a modern, scalable solution to create high quality survey-scale bathymetry from many sidescan survey lines. By incorporating multiple observations of the same place, results can be improved as the estimates reinforce each other. Our method is based on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sinusoidal representation networks</i> , a recent advance in neural representation learning. We demonstrate the scalability of the approach by producing bathymetry from a large sidescan survey. The resulting quality is demonstrated by comparing to data collected with a high-precision multibeam sensor.