Predictive 3D Sonar Mapping of Underwater Environments via Object-specific Bayesian Inference

TL;DR

This paper presents a Bayesian inference framework for large-scale 3D underwater mapping using stereo sonar data, exploiting semantic class repetition to infer unknown structures and improve reconstruction efficiency.

Contribution

It introduces a novel object-specific Bayesian inference approach that leverages semantic segmentation and orthogonal sonar fusion for enhanced 3D underwater mapping.

Findings

Validated in simulation and real outdoor environments.

Effectively infers unknown 3D structures from partial sonar data.

Improves large-scale underwater 3D reconstruction efficiency.

Abstract

Recent work has achieved dense 3D reconstruction with wide-aperture imaging sonar using a stereo pair of orthogonally oriented sonars. This allows each sonar to observe a spatial dimension that the other is missing, without requiring any prior assumptions about scene geometry. However, this is achieved only in a small region with overlapping fields-of-view, leaving large regions of sonar image observations with an unknown elevation angle. Our work aims to achieve large-scale 3D reconstruction more efficiently using this sensor arrangement. We propose dividing the world into semantic classes to exploit the presence of repeating structures in the subsea environment. We use a Bayesian inference framework to build an understanding of each object class's geometry when 3D information is available from the orthogonal sonar fusion system, and when the elevation angle of our returns is unknown, our framework is used to infer unknown 3D structure. We quantitatively validate our method in a simulation and use data collected from a real outdoor littoral environment to demonstrate the efficacy of our framework in the field. Video attachment: https://www.youtube.com/watch?v=WouCrY9eK4o&t=75s