Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework

Citrus Huanglongbing (HLB) is one of the most devastating diseases in the global citrus industry, but its early detection under complex field conditions remains a major challenge. Existing methods often suffer from insufficient dataset diversity and poor generalization, and struggle to accurately de...

Full description

Saved in:
Bibliographic Details
Main Authors: Liang Cao, Wei Xiao, Zeng Hu, Xiangli Li, Zhongzhen Wu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/14/2223
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418328011964416
author Liang Cao
Wei Xiao
Zeng Hu
Xiangli Li
Zhongzhen Wu
author_facet Liang Cao
Wei Xiao
Zeng Hu
Xiangli Li
Zhongzhen Wu
author_sort Liang Cao
collection DOAJ
description Citrus Huanglongbing (HLB) is one of the most devastating diseases in the global citrus industry, but its early detection under complex field conditions remains a major challenge. Existing methods often suffer from insufficient dataset diversity and poor generalization, and struggle to accurately detect subtle early-stage lesions and multiple HLB symptoms in natural backgrounds. To address these issues, we propose an enhanced YOLO11-based framework, DCH-YOLO11. We constructed a multi-symptom HLB leaf dataset (MS-HLBD) containing 9219 annotated images across five classes: Healthy (1862), HLB blotchy mottling (2040), HLB Zinc deficiency (1988), HLB yellowing (1768), and Canker (1561), collected under diverse field conditions. To improve detection performance, the DCH-YOLO11 framework incorporates three novel modules: the C3k2 Dynamic Feature Fusion (C3k2_DFF) module, which enhances early and subtle lesion detection through dynamic feature fusion; the C2PSA Context Anchor Attention (C2PSA_CAA) module, which leverages context anchor attention to strengthen feature extraction in complex vein regions; and the High-efficiency Dynamic Feature Pyramid Network (HDFPN) module, which optimizes multi-scale feature interaction to boost detection accuracy across different object sizes. On the MS-HLBD dataset, DCH-YOLO11 achieved a precision of 91.6%, recall of 87.1%, F1-score of 89.3, and mAP50 of 93.1%, surpassing Faster R-CNN, SSD, RT-DETR, YOLOv7-tiny, YOLOv8n, YOLOv9-tiny, YOLOv10n, YOLO11n, and YOLOv12n by 13.6%, 8.8%, 5.3%, 3.2%, 2.0%, 1.6%, 2.6%, 1.8%, and 1.6% in mAP50, respectively. On a publicly available citrus HLB dataset, DCH-YOLO11 achieved a precision of 82.7%, recall of 81.8%, F1-score of 82.2, and mAP50 of 89.4%, with mAP50 improvements of 8.9%, 4.0%, 3.8%, 3.2%, 4.7%, 3.2%, and 3.4% over RT-DETR, YOLOv7-tiny, YOLOv8n, YOLOv9-tiny, YOLOv10n, YOLO11n, and YOLOv12n, respectively. These results demonstrate that DCH-YOLO11 achieves both state-of-the-art accuracy and excellent generalization, highlighting its strong potential for robust and practical citrus HLB detection in real-world applications.
format Article
id doaj-art-d9e7dbc8e6684b7d87e2897434793af6
institution Kabale University
issn 2227-7390
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-d9e7dbc8e6684b7d87e2897434793af62025-08-20T03:32:27ZengMDPI AGMathematics2227-73902025-07-011314222310.3390/math13142223Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 FrameworkLiang Cao0Wei Xiao1Zeng Hu2Xiangli Li3Zhongzhen Wu4College of Artificial Intelligence, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Artificial Intelligence, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Artificial Intelligence, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Artificial Intelligence, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Agriculture & Biology, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCitrus Huanglongbing (HLB) is one of the most devastating diseases in the global citrus industry, but its early detection under complex field conditions remains a major challenge. Existing methods often suffer from insufficient dataset diversity and poor generalization, and struggle to accurately detect subtle early-stage lesions and multiple HLB symptoms in natural backgrounds. To address these issues, we propose an enhanced YOLO11-based framework, DCH-YOLO11. We constructed a multi-symptom HLB leaf dataset (MS-HLBD) containing 9219 annotated images across five classes: Healthy (1862), HLB blotchy mottling (2040), HLB Zinc deficiency (1988), HLB yellowing (1768), and Canker (1561), collected under diverse field conditions. To improve detection performance, the DCH-YOLO11 framework incorporates three novel modules: the C3k2 Dynamic Feature Fusion (C3k2_DFF) module, which enhances early and subtle lesion detection through dynamic feature fusion; the C2PSA Context Anchor Attention (C2PSA_CAA) module, which leverages context anchor attention to strengthen feature extraction in complex vein regions; and the High-efficiency Dynamic Feature Pyramid Network (HDFPN) module, which optimizes multi-scale feature interaction to boost detection accuracy across different object sizes. On the MS-HLBD dataset, DCH-YOLO11 achieved a precision of 91.6%, recall of 87.1%, F1-score of 89.3, and mAP50 of 93.1%, surpassing Faster R-CNN, SSD, RT-DETR, YOLOv7-tiny, YOLOv8n, YOLOv9-tiny, YOLOv10n, YOLO11n, and YOLOv12n by 13.6%, 8.8%, 5.3%, 3.2%, 2.0%, 1.6%, 2.6%, 1.8%, and 1.6% in mAP50, respectively. On a publicly available citrus HLB dataset, DCH-YOLO11 achieved a precision of 82.7%, recall of 81.8%, F1-score of 82.2, and mAP50 of 89.4%, with mAP50 improvements of 8.9%, 4.0%, 3.8%, 3.2%, 4.7%, 3.2%, and 3.4% over RT-DETR, YOLOv7-tiny, YOLOv8n, YOLOv9-tiny, YOLOv10n, YOLO11n, and YOLOv12n, respectively. These results demonstrate that DCH-YOLO11 achieves both state-of-the-art accuracy and excellent generalization, highlighting its strong potential for robust and practical citrus HLB detection in real-world applications.https://www.mdpi.com/2227-7390/13/14/2223YOLOnatural environmentHLBfeature fusionattention mechanism
spellingShingle Liang Cao
Wei Xiao
Zeng Hu
Xiangli Li
Zhongzhen Wu
Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework
Mathematics
YOLO
natural environment
HLB
feature fusion
attention mechanism
title Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework
title_full Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework
title_fullStr Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework
title_full_unstemmed Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework
title_short Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework
title_sort detection of citrus huanglongbing in natural field conditions using an enhanced yolo11 framework
topic YOLO
natural environment
HLB
feature fusion
attention mechanism
url https://www.mdpi.com/2227-7390/13/14/2223
work_keys_str_mv AT liangcao detectionofcitrushuanglongbinginnaturalfieldconditionsusinganenhancedyolo11framework
AT weixiao detectionofcitrushuanglongbinginnaturalfieldconditionsusinganenhancedyolo11framework
AT zenghu detectionofcitrushuanglongbinginnaturalfieldconditionsusinganenhancedyolo11framework
AT xianglili detectionofcitrushuanglongbinginnaturalfieldconditionsusinganenhancedyolo11framework
AT zhongzhenwu detectionofcitrushuanglongbinginnaturalfieldconditionsusinganenhancedyolo11framework