Deep Learning from Shallow Dives: Sonar Image Generation and Training for Underwater Object Detection

TL;DR

This paper introduces a novel image synthesis method using underwater sonar simulation to generate training data, enabling effective deep learning-based underwater object detection despite limited real-world sonar data.

Contribution

The paper presents a new end-to-end sonar image synthesis approach based on underwater simulation models to address data scarcity in training deep learning models.

Findings

Synthetic images improve training effectiveness

Models trained on simulated data perform well on real sonar images

The approach enhances underwater object detection capabilities

Abstract

Among underwater perceptual sensors, imaging sonar has been highlighted for its perceptual robustness underwater. The major challenge of imaging sonar, however, arises from the difficulty in defining visual features despite limited resolution and high noise levels. Recent developments in deep learning provide a powerful solution for computer-vision researches using optical images. Unfortunately, deep learning-based approaches are not well established for imaging sonars, mainly due to the scant data in the training phase. Unlike the abundant publically available terrestrial images, obtaining underwater images is often costly, and securing enough underwater images for training is not straightforward. To tackle this issue, this paper presents a solution to this field's lack of data by introducing a novel end-to-end image-synthesizing method in the training image preparation phase. The proposed method present image synthesizing scheme to the images captured by an underwater simulator. Our synthetic images are based on the sonar imaging models and noisy characteristics to represent the real data obtained from the sea. We validate the proposed scheme by training using a simulator and by testing the simulated images with real underwater sonar images obtained from a water tank and the sea.