Vision-Based Autonomous Navigation for Unmanned Surface Vessel in Extreme Marine Conditions

TL;DR

This paper introduces a vision-based navigation system for unmanned surface vessels that effectively operates in extreme marine conditions by using GANs for noise removal and YOLOv5 for target detection, validated through simulation.

Contribution

It presents a novel integrated perception framework combining GAN-based noise reduction with YOLOv5 detection for USV navigation in extreme conditions, outperforming existing methods.

Findings

Outperforms state-of-the-art de-hazing methods in simulations

Effective target tracking under sandstorm and fog conditions

Validated on MBZIRC benchmark dataset

Abstract

Visual perception is an important component for autonomous navigation of unmanned surface vessels (USV), particularly for the tasks related to autonomous inspection and tracking. These tasks involve vision-based navigation techniques to identify the target for navigation. Reduced visibility under extreme weather conditions in marine environments makes it difficult for vision-based approaches to work properly. To overcome these issues, this paper presents an autonomous vision-based navigation framework for tracking target objects in extreme marine conditions. The proposed framework consists of an integrated perception pipeline that uses a generative adversarial network (GAN) to remove noise and highlight the object features before passing them to the object detector (i.e., YOLOv5). The detected visual features are then used by the USV to track the target. The proposed framework has been thoroughly tested in simulation under extremely reduced visibility due to sandstorms and fog. The results are compared with state-of-the-art de-hazing methods across the benchmarked MBZIRC simulation dataset, on which the proposed scheme has outperformed the existing methods across various metrics.