Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural Network

The next generation of United States Navy uncrewed aerial systems (UASs) is expected to operate in global positioning system and radio frequency-denied maritime environments. In these challenging conditions, these UASs must accurately identify specific surface vessels among multiple similar vessels...

Full description

Saved in:
Bibliographic Details
Main Authors: Sean McCormick, Adrien Richez, Violet Mwaffo, Donald H. Costello
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10720770/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846150362918027264
author Sean McCormick
Adrien Richez
Violet Mwaffo
Donald H. Costello
author_facet Sean McCormick
Adrien Richez
Violet Mwaffo
Donald H. Costello
author_sort Sean McCormick
collection DOAJ
description The next generation of United States Navy uncrewed aerial systems (UASs) is expected to operate in global positioning system and radio frequency-denied maritime environments. In these challenging conditions, these UASs must accurately identify specific surface vessels among multiple similar vessels using passive onboard sensors. This study explores the potential of a deep neural network (DNN) to differentiate between three similar surface vessel classes using actual footage of the vessels underway within their operational environments. The DNN’s effectiveness is evaluated using data collected under diverse environmental conditions, including different times of the day and various sky conditions, which imply varying levels of light and visibility. The trained DNN model demonstrated outstanding performance on real-world maritime datasets, achieving a mean Average Precision of 94.2% at an intersection over union of 0.5, effectively distinguishing vessels with minimal false positives. Our findings demonstrate that, with proper training, a DNN model can accurately differentiate between vessels despite their similarity and under challenging conditions.
format Article
id doaj-art-00efe5369a434783889a3e526c90a52f
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-00efe5369a434783889a3e526c90a52f2024-11-29T00:01:21ZengIEEEIEEE Access2169-35362024-01-011217479617480710.1109/ACCESS.2024.348301410720770Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural NetworkSean McCormick0https://orcid.org/0009-0002-7073-546XAdrien Richez1https://orcid.org/0009-0001-4099-9328Violet Mwaffo2https://orcid.org/0000-0001-7867-5305Donald H. Costello3Weapons, Robotics, and Control Engineering Department, United States Naval Academy, Annapolis, MD, USAAerospace Engineering Department, United States Naval Academy, Annapolis, MD, USAWeapons, Robotics, and Control Engineering Department, United States Naval Academy, Annapolis, MD, USAMATRIX Laboratory, Clark School of Engineering, University of Maryland, College Park, MD, USAThe next generation of United States Navy uncrewed aerial systems (UASs) is expected to operate in global positioning system and radio frequency-denied maritime environments. In these challenging conditions, these UASs must accurately identify specific surface vessels among multiple similar vessels using passive onboard sensors. This study explores the potential of a deep neural network (DNN) to differentiate between three similar surface vessel classes using actual footage of the vessels underway within their operational environments. The DNN’s effectiveness is evaluated using data collected under diverse environmental conditions, including different times of the day and various sky conditions, which imply varying levels of light and visibility. The trained DNN model demonstrated outstanding performance on real-world maritime datasets, achieving a mean Average Precision of 94.2% at an intersection over union of 0.5, effectively distinguishing vessels with minimal false positives. Our findings demonstrate that, with proper training, a DNN model can accurately differentiate between vessels despite their similarity and under challenging conditions.https://ieeexplore.ieee.org/document/10720770/Deep neural networks (DNN)military operationsGPS/RF-denied environmentsmaritime operationssurface vessel identificationuncrewed aerial systems (UASs)
spellingShingle Sean McCormick
Adrien Richez
Violet Mwaffo
Donald H. Costello
Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural Network
IEEE Access
Deep neural networks (DNN)
military operations
GPS/RF-denied environments
maritime operations
surface vessel identification
uncrewed aerial systems (UASs)
title Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural Network
title_full Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural Network
title_fullStr Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural Network
title_full_unstemmed Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural Network
title_short Discriminating Similar Naval Vessels Using YOLOv8 Deep Neural Network
title_sort discriminating similar naval vessels using yolov8 deep neural network
topic Deep neural networks (DNN)
military operations
GPS/RF-denied environments
maritime operations
surface vessel identification
uncrewed aerial systems (UASs)
url https://ieeexplore.ieee.org/document/10720770/
work_keys_str_mv AT seanmccormick discriminatingsimilarnavalvesselsusingyolov8deepneuralnetwork
AT adrienrichez discriminatingsimilarnavalvesselsusingyolov8deepneuralnetwork
AT violetmwaffo discriminatingsimilarnavalvesselsusingyolov8deepneuralnetwork
AT donaldhcostello discriminatingsimilarnavalvesselsusingyolov8deepneuralnetwork