YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8

Pine wilt disease (PWD) poses a severe threat to the health of pine trees and has resulted in substantial losses to global pine forest resources. Due to the minute size of the pathogens and the concealed symptoms of PWD, early detection through remote sensing image technology is essential. However,...

Full description

Saved in:
Bibliographic Details
Main Authors: Junchao Yuan, Lina Wang, Tingting Wang, Ali Kashif Bashir, Maryam M. Al Dabel, Jiaxing Wang, Hailin Feng, Kai Fang, Wei Wang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10750037/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846150408188198912
author Junchao Yuan
Lina Wang
Tingting Wang
Ali Kashif Bashir
Maryam M. Al Dabel
Jiaxing Wang
Hailin Feng
Kai Fang
Wei Wang
author_facet Junchao Yuan
Lina Wang
Tingting Wang
Ali Kashif Bashir
Maryam M. Al Dabel
Jiaxing Wang
Hailin Feng
Kai Fang
Wei Wang
author_sort Junchao Yuan
collection DOAJ
description Pine wilt disease (PWD) poses a severe threat to the health of pine trees and has resulted in substantial losses to global pine forest resources. Due to the minute size of the pathogens and the concealed symptoms of PWD, early detection through remote sensing image technology is essential. However, in practical applications, remote sensing images are easily affected by factors, such as cloud cover and changes in illumination, resulting in significant noise and blurriness in the images. These interference factors significantly reduce the accuracy of existing object detection models. Therefore, this article presents a novel and highly robust methodology for detecting PWD, termed YOLOv8-RD. We synthesized the benefits of residual learning and fuzzy deep neural networks to develop a residual fuzzy module (ResFuzzy), which adeptly filters image noise and refines background features with enhanced smoothness. Simultaneously, we integrated a detail processing module into the ResFuzzy module to enhance the low-frequency detail features transmitted in residual learning. Furthermore, by incorporating the dynamic upsampling operator, our model can dynamically adjust the sampling step size based on the variations in the input feature map during the upsampling process, thereby effectively recovering detail from the feature map. Our model exhibited exceptional robustness to severe noise. When evaluated on a PWD dataset with 100% interference samples at an intensity of 0.07, our model achieved an average precision improvement of 4.9%, 6.3%, 7.3%, and 3.0% compared to four most representative models, making it well suited for PWD detection in interfering environments.
format Article
id doaj-art-9ffdd527606b4bcd99c5ec8cd96fd00c
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-9ffdd527606b4bcd99c5ec8cd96fd00c2024-11-29T00:00:52ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-011838539710.1109/JSTARS.2024.349483810750037YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8Junchao Yuan0https://orcid.org/0009-0009-9368-6606Lina Wang1https://orcid.org/0009-0009-7601-2917Tingting Wang2https://orcid.org/0000-0002-2666-7159Ali Kashif Bashir3https://orcid.org/0000-0003-2601-9327Maryam M. Al Dabel4https://orcid.org/0000-0003-4371-8939Jiaxing Wang5https://orcid.org/0000-0002-7672-6911Hailin Feng6https://orcid.org/0000-0003-2734-480XKai Fang7https://orcid.org/0000-0003-0419-1468Wei Wang8https://orcid.org/0000-0002-1717-5785College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaCollege of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, ChinaDepartment of Computing and Mathematics, Manchester Metropolitan University, Manchester, U.K.Department of Computer Science and Engineering, University of Hafr AlBatin, Hafar Al Batin, Saudi ArabiaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaGuangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, ChinaPine wilt disease (PWD) poses a severe threat to the health of pine trees and has resulted in substantial losses to global pine forest resources. Due to the minute size of the pathogens and the concealed symptoms of PWD, early detection through remote sensing image technology is essential. However, in practical applications, remote sensing images are easily affected by factors, such as cloud cover and changes in illumination, resulting in significant noise and blurriness in the images. These interference factors significantly reduce the accuracy of existing object detection models. Therefore, this article presents a novel and highly robust methodology for detecting PWD, termed YOLOv8-RD. We synthesized the benefits of residual learning and fuzzy deep neural networks to develop a residual fuzzy module (ResFuzzy), which adeptly filters image noise and refines background features with enhanced smoothness. Simultaneously, we integrated a detail processing module into the ResFuzzy module to enhance the low-frequency detail features transmitted in residual learning. Furthermore, by incorporating the dynamic upsampling operator, our model can dynamically adjust the sampling step size based on the variations in the input feature map during the upsampling process, thereby effectively recovering detail from the feature map. Our model exhibited exceptional robustness to severe noise. When evaluated on a PWD dataset with 100% interference samples at an intensity of 0.07, our model achieved an average precision improvement of 4.9%, 6.3%, 7.3%, and 3.0% compared to four most representative models, making it well suited for PWD detection in interfering environments.https://ieeexplore.ieee.org/document/10750037/Fuzzy deep neural networks (FDNNs)interference environmentsremote sensingresidual learningupsampling process
spellingShingle Junchao Yuan
Lina Wang
Tingting Wang
Ali Kashif Bashir
Maryam M. Al Dabel
Jiaxing Wang
Hailin Feng
Kai Fang
Wei Wang
YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Fuzzy deep neural networks (FDNNs)
interference environments
remote sensing
residual learning
upsampling process
title YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8
title_full YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8
title_fullStr YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8
title_full_unstemmed YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8
title_short YOLOv8-RD: High-Robust Pine Wilt Disease Detection Method Based on Residual Fuzzy YOLOv8
title_sort yolov8 rd high robust pine wilt disease detection method based on residual fuzzy yolov8
topic Fuzzy deep neural networks (FDNNs)
interference environments
remote sensing
residual learning
upsampling process
url https://ieeexplore.ieee.org/document/10750037/
work_keys_str_mv AT junchaoyuan yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT linawang yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT tingtingwang yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT alikashifbashir yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT maryammaldabel yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT jiaxingwang yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT hailinfeng yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT kaifang yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8
AT weiwang yolov8rdhighrobustpinewiltdiseasedetectionmethodbasedonresidualfuzzyyolov8