YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV Imagery
Pine Wilt Disease (PWD) is a highly infectious and lethal disease that severely threatens global pine forest ecosystems and forestry economies. Early and accurate detection of infected trees is crucial to prevent large-scale outbreaks and support timely forest management. However, existing remote se...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/11/3315 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849722239460573184 |
|---|---|
| author | Hua Shi Yonghang Wang Xiaozhou Feng Yufen Xie Zhenhui Zhu Hui Guo Guofeng Jin |
| author_facet | Hua Shi Yonghang Wang Xiaozhou Feng Yufen Xie Zhenhui Zhu Hui Guo Guofeng Jin |
| author_sort | Hua Shi |
| collection | DOAJ |
| description | Pine Wilt Disease (PWD) is a highly infectious and lethal disease that severely threatens global pine forest ecosystems and forestry economies. Early and accurate detection of infected trees is crucial to prevent large-scale outbreaks and support timely forest management. However, existing remote sensing-based detection models often struggle with performance degradation in complex environments, as well as a trade-off between detection accuracy and real-time efficiency. To address these challenges, we propose an improved object detection model, YOLOv8-MFD, designed for accurate and efficient detection of PWD-infected trees from UAV imagery. The model incorporates a MobileViT-based backbone that fuses convolutional neural networks with Transformer-based global modeling to enhance feature representation under complex forest backgrounds. To further improve robustness and precision, we integrate a Focal Modulation mechanism to suppress environmental interference and adopt a Dynamic Head to strengthen multi-scale object perception and adaptive feature fusion. Experimental results on a UAV-based forest dataset demonstrate that YOLOv8-MFD achieves a precision of 92.5%, a recall of 84.7%, an F1-score of 88.4%, and a mAP@0.5 of 88.2%. Compared to baseline models such as YOLOv8 and YOLOv10, our method achieves higher accuracy while maintaining acceptable computational cost (11.8 GFLOPs) and a compact model size (10.2 MB). Its inference speed is moderate and still suitable for real-time deployment. Overall, the proposed method offers a reliable solution for early-stage PWD monitoring across large forested areas, enabling more timely disease intervention and resource protection. Furthermore, its generalizable architecture holds promise for broader applications in forest health monitoring and agricultural disease detection. |
| format | Article |
| id | doaj-art-5e0e0b02ae3748dfab7e27b91dc50d61 |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-5e0e0b02ae3748dfab7e27b91dc50d612025-08-20T03:11:24ZengMDPI AGSensors1424-82202025-05-012511331510.3390/s25113315YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV ImageryHua Shi0Yonghang Wang1Xiaozhou Feng2Yufen Xie3Zhenhui Zhu4Hui Guo5Guofeng Jin6College of Sciences, Xi’an Technological University, Xi’an 710021, ChinaCollege of Sciences, Xi’an Technological University, Xi’an 710021, ChinaCollege of Sciences, Xi’an Technological University, Xi’an 710021, ChinaShaanxi Academy of Forestry, Xi’an 710016, ChinaCollege of Sciences, Xi’an Technological University, Xi’an 710021, ChinaShaanxi Academy of Forestry, Xi’an 710016, ChinaXi’an New Aomei Information Technology, Co., Ltd., Xi’an 710100, ChinaPine Wilt Disease (PWD) is a highly infectious and lethal disease that severely threatens global pine forest ecosystems and forestry economies. Early and accurate detection of infected trees is crucial to prevent large-scale outbreaks and support timely forest management. However, existing remote sensing-based detection models often struggle with performance degradation in complex environments, as well as a trade-off between detection accuracy and real-time efficiency. To address these challenges, we propose an improved object detection model, YOLOv8-MFD, designed for accurate and efficient detection of PWD-infected trees from UAV imagery. The model incorporates a MobileViT-based backbone that fuses convolutional neural networks with Transformer-based global modeling to enhance feature representation under complex forest backgrounds. To further improve robustness and precision, we integrate a Focal Modulation mechanism to suppress environmental interference and adopt a Dynamic Head to strengthen multi-scale object perception and adaptive feature fusion. Experimental results on a UAV-based forest dataset demonstrate that YOLOv8-MFD achieves a precision of 92.5%, a recall of 84.7%, an F1-score of 88.4%, and a mAP@0.5 of 88.2%. Compared to baseline models such as YOLOv8 and YOLOv10, our method achieves higher accuracy while maintaining acceptable computational cost (11.8 GFLOPs) and a compact model size (10.2 MB). Its inference speed is moderate and still suitable for real-time deployment. Overall, the proposed method offers a reliable solution for early-stage PWD monitoring across large forested areas, enabling more timely disease intervention and resource protection. Furthermore, its generalizable architecture holds promise for broader applications in forest health monitoring and agricultural disease detection.https://www.mdpi.com/1424-8220/25/11/3315pine wilt diseaseUAV remote sensingYOLOv8MobileViTfocal modulationdynamic head |
| spellingShingle | Hua Shi Yonghang Wang Xiaozhou Feng Yufen Xie Zhenhui Zhu Hui Guo Guofeng Jin YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV Imagery Sensors pine wilt disease UAV remote sensing YOLOv8 MobileViT focal modulation dynamic head |
| title | YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV Imagery |
| title_full | YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV Imagery |
| title_fullStr | YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV Imagery |
| title_full_unstemmed | YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV Imagery |
| title_short | YOLOv8-MFD: An Enhanced Detection Model for Pine Wilt Diseased Trees Using UAV Imagery |
| title_sort | yolov8 mfd an enhanced detection model for pine wilt diseased trees using uav imagery |
| topic | pine wilt disease UAV remote sensing YOLOv8 MobileViT focal modulation dynamic head |
| url | https://www.mdpi.com/1424-8220/25/11/3315 |
| work_keys_str_mv | AT huashi yolov8mfdanenhanceddetectionmodelforpinewiltdiseasedtreesusinguavimagery AT yonghangwang yolov8mfdanenhanceddetectionmodelforpinewiltdiseasedtreesusinguavimagery AT xiaozhoufeng yolov8mfdanenhanceddetectionmodelforpinewiltdiseasedtreesusinguavimagery AT yufenxie yolov8mfdanenhanceddetectionmodelforpinewiltdiseasedtreesusinguavimagery AT zhenhuizhu yolov8mfdanenhanceddetectionmodelforpinewiltdiseasedtreesusinguavimagery AT huiguo yolov8mfdanenhanceddetectionmodelforpinewiltdiseasedtreesusinguavimagery AT guofengjin yolov8mfdanenhanceddetectionmodelforpinewiltdiseasedtreesusinguavimagery |