A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial Vehicle

Unexploded ordnance (UXO) presents a significant risk to both the natural environment and human safety. Current deep learning detection mechanisms are characterized by limited interpretability, resulting in a persistent absence of detection methods that are simultaneously efficient, secure, and prec...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongao Ling, Hui Zhao, Xu Zhao, Ziyu Liu, Wenbin Chen
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10858135/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228500657602560
author Zhongao Ling
Hui Zhao
Xu Zhao
Ziyu Liu
Wenbin Chen
author_facet Zhongao Ling
Hui Zhao
Xu Zhao
Ziyu Liu
Wenbin Chen
author_sort Zhongao Ling
collection DOAJ
description Unexploded ordnance (UXO) presents a significant risk to both the natural environment and human safety. Current deep learning detection mechanisms are characterized by limited interpretability, resulting in a persistent absence of detection methods that are simultaneously efficient, secure, and precise. To address these challenges, a dual-mode detection method based on interpretation-promoted YOLOv5 is proposed in this paper. A comprehensive dataset has been constructed to focus on the scarcity of low-altitude UXO target datasets, incorporating both visible light and infrared imagery. Dataset augmentation has been implemented through the application of generative adversarial networks for image super-resolution reconstruction, thereby enhancing the robustness of the dataset. To tackle issues of low detection accuracy and inadequate background discrimination associated with a single information source, an integration of visible light and infrared data has been proposed to enhance the interpretability of the YOLOv5 algorithm, leading to improved detection performance. Extensive low-altitude detection experiments were conducted in field environments using unmanned aerial vehicles (UAVs). Experimental results demonstrate that the proposed method achieves a remarkable detection accuracy of up to 97.1% and an impressive detection speed of up to 60.3 frames per second.
format Article
id doaj-art-75a56a68e2284a49becb92c9cd7fe523
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-75a56a68e2284a49becb92c9cd7fe5232025-08-20T02:04:30ZengIEEEIEEE Access2169-35362025-01-0113426344264910.1109/ACCESS.2025.353705810858135A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial VehicleZhongao Ling0https://orcid.org/0009-0002-7054-767XHui Zhao1https://orcid.org/0000-0002-5326-9930Xu Zhao2https://orcid.org/0000-0002-1712-6588Ziyu Liu3https://orcid.org/0009-0006-4401-713XWenbin Chen4Beijing Key Laboratory of High Dynamic Navigation Technology, Beijing Information Science and Technology University, Beijing, ChinaBeijing Key Laboratory of High Dynamic Navigation Technology, Beijing Information Science and Technology University, Beijing, ChinaBeijing Key Laboratory of High Dynamic Navigation Technology, Beijing Information Science and Technology University, Beijing, ChinaSchool of Environmental Science and Engineering, Beijing University of Technology, Beijing, ChinaChina Electronics Technology Group Corporation, Beijing, ChinaUnexploded ordnance (UXO) presents a significant risk to both the natural environment and human safety. Current deep learning detection mechanisms are characterized by limited interpretability, resulting in a persistent absence of detection methods that are simultaneously efficient, secure, and precise. To address these challenges, a dual-mode detection method based on interpretation-promoted YOLOv5 is proposed in this paper. A comprehensive dataset has been constructed to focus on the scarcity of low-altitude UXO target datasets, incorporating both visible light and infrared imagery. Dataset augmentation has been implemented through the application of generative adversarial networks for image super-resolution reconstruction, thereby enhancing the robustness of the dataset. To tackle issues of low detection accuracy and inadequate background discrimination associated with a single information source, an integration of visible light and infrared data has been proposed to enhance the interpretability of the YOLOv5 algorithm, leading to improved detection performance. Extensive low-altitude detection experiments were conducted in field environments using unmanned aerial vehicles (UAVs). Experimental results demonstrate that the proposed method achieves a remarkable detection accuracy of up to 97.1% and an impressive detection speed of up to 60.3 frames per second.https://ieeexplore.ieee.org/document/10858135/Unexploded ordnancelow-altitude detectionvisible lightinfrareddual-mode fusionYOLOv5
spellingShingle Zhongao Ling
Hui Zhao
Xu Zhao
Ziyu Liu
Wenbin Chen
A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial Vehicle
IEEE Access
Unexploded ordnance
low-altitude detection
visible light
infrared
dual-mode fusion
YOLOv5
title A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial Vehicle
title_full A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial Vehicle
title_fullStr A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial Vehicle
title_full_unstemmed A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial Vehicle
title_short A Dual Mode Detection Method for Unexploded Ordnance Based on YOLOv5 for Low Altitude Unmanned Aerial Vehicle
title_sort dual mode detection method for unexploded ordnance based on yolov5 for low altitude unmanned aerial vehicle
topic Unexploded ordnance
low-altitude detection
visible light
infrared
dual-mode fusion
YOLOv5
url https://ieeexplore.ieee.org/document/10858135/
work_keys_str_mv AT zhongaoling adualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT huizhao adualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT xuzhao adualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT ziyuliu adualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT wenbinchen adualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT zhongaoling dualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT huizhao dualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT xuzhao dualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT ziyuliu dualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle
AT wenbinchen dualmodedetectionmethodforunexplodedordnancebasedonyolov5forlowaltitudeunmannedaerialvehicle