Improving Generalization of Synthetically Trained Sonar Image Descriptors for Underwater Place Recognition

TL;DR

This paper introduces a compact deep sonar descriptor pipeline trained solely on synthetic data that effectively generalizes to real underwater scenarios, improving place recognition despite challenging underwater conditions.

Contribution

A novel deep sonar descriptor architecture using synthetic training data and a specialized data generation process for robust underwater place recognition.

Findings

Effective generalization from synthetic to real sonar data

Outperforms state-of-the-art methods in underwater place recognition

Robustness to underwater environmental variability

Abstract

Autonomous navigation in underwater environments presents challenges due to factors such as light absorption and water turbidity, limiting the effectiveness of optical sensors. Sonar systems are commonly used for perception in underwater operations as they are unaffected by these limitations. Traditional computer vision algorithms are less effective when applied to sonar-generated acoustic images, while convolutional neural networks (CNNs) typically require large amounts of labeled training data that are often unavailable or difficult to acquire. To this end, we propose a novel compact deep sonar descriptor pipeline that can generalize to real scenarios while being trained exclusively on synthetic data. Our architecture is based on a ResNet18 back-end and a properly parameterized random Gaussian projection layer, whereas input sonar data is enhanced with standard ad-hoc normalization/prefiltering techniques. A customized synthetic data generation procedure is also presented. The proposed method has been evaluated extensively using both synthetic and publicly available real data, demonstrating its effectiveness compared to state-of-the-art methods.