A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11n

Existing methods for detecting cotton boll diseases frequently exhibit high rates of <b>both</b> false negatives and false positives under complex field conditions (e.g., lighting variations, shadows, and occlusions) and struggle to achieve real-time performance on edge devices. To addre...

Full description

Saved in:
Bibliographic Details
Main Authors: Lei Yang, Wenhao Cui, Jingqian Li, Guotao Han, Qi Zhou, Yubin Lan, Jing Zhao, Yongliang Qiao
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/8085
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078470788349952
author Lei Yang
Wenhao Cui
Jingqian Li
Guotao Han
Qi Zhou
Yubin Lan
Jing Zhao
Yongliang Qiao
author_facet Lei Yang
Wenhao Cui
Jingqian Li
Guotao Han
Qi Zhou
Yubin Lan
Jing Zhao
Yongliang Qiao
author_sort Lei Yang
collection DOAJ
description Existing methods for detecting cotton boll diseases frequently exhibit high rates of <b>both</b> false negatives and false positives under complex field conditions (e.g., lighting variations, shadows, and occlusions) and struggle to achieve real-time performance on edge devices. To address these limitations, this study proposes an enhanced YOLOv11n model (YOLOv11n-ECS) for improved detection accuracy. A dataset of cotton boll diseases under different lighting conditions and shooting angles in the field was constructed. To mitigate false negatives and false positives encountered by the original YOLOv11n model during detection, the EMA (efficient multi-scale attention) mechanism is introduced to enhance the weights of important features and suppress irrelevant regions, thereby improving the detection accuracy of the model. Partial Convolution (PConv) is incorporated into the C3k2 module to reduce computational redundancy and lower the model’s computational complexity while maintaining high recognition accuracy. Furthermore, to enhance the localization accuracy of diseased bolls, the original CIoU loss is replaced with Shape-IoU. The improved model achieves floating point operations (FLOPs), parameter count, and model size at 96.8%, 96%, and 96.3% of the original YOLOv11n model, respectively. The improved model achieves an mAP@0.5 of 85.6% and an mAP@0.5:0.95 of 62.7%, representing improvements of 2.3 and 1.9 percentage points, respectively, over the baseline YOLOv11n model. Compared with CenterNet, Faster R-CNN, YOLOv8-LSW, MSA-DETR, DMN-YOLO, and YOLOv11n, the improved model shows mAP@0.5 improvements of 25.7, 21.2, 5.5, 4.0, 4.5, and 2.3 percentage points, respectively, along with corresponding mAP@0.5:0.95 increases of 25.6, 25.3, 8.3, 2.8, 1.8, and 1.9 percentage points. Deployed on a Jetson TX2 development board, the model achieves a recognition speed of 56 frames per second (FPS) and an mAP of 84.2%, confirming its suitability for real-time detection. Furthermore, the improved model effectively reduces instances of both false negatives and false positives for diseased cotton bolls while yielding higher detection confidence, thus providing robust technical support for intelligent cotton boll disease detection.
format Article
id doaj-art-af536cc8f41f4ded97acf6048b523f6c
institution DOAJ
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-af536cc8f41f4ded97acf6048b523f6c2025-08-20T02:45:33ZengMDPI AGApplied Sciences2076-34172025-07-011514808510.3390/app15148085A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11nLei Yang0Wenhao Cui1Jingqian Li2Guotao Han3Qi Zhou4Yubin Lan5Jing Zhao6Yongliang Qiao7School of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaSchool of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaSchool of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaSchool of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaSchool of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaSchool of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaSchool of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaAustralian Institute for Machine Learning (AIML), University of Adelaide, Adelaide, SA 5000, AustraliaExisting methods for detecting cotton boll diseases frequently exhibit high rates of <b>both</b> false negatives and false positives under complex field conditions (e.g., lighting variations, shadows, and occlusions) and struggle to achieve real-time performance on edge devices. To address these limitations, this study proposes an enhanced YOLOv11n model (YOLOv11n-ECS) for improved detection accuracy. A dataset of cotton boll diseases under different lighting conditions and shooting angles in the field was constructed. To mitigate false negatives and false positives encountered by the original YOLOv11n model during detection, the EMA (efficient multi-scale attention) mechanism is introduced to enhance the weights of important features and suppress irrelevant regions, thereby improving the detection accuracy of the model. Partial Convolution (PConv) is incorporated into the C3k2 module to reduce computational redundancy and lower the model’s computational complexity while maintaining high recognition accuracy. Furthermore, to enhance the localization accuracy of diseased bolls, the original CIoU loss is replaced with Shape-IoU. The improved model achieves floating point operations (FLOPs), parameter count, and model size at 96.8%, 96%, and 96.3% of the original YOLOv11n model, respectively. The improved model achieves an mAP@0.5 of 85.6% and an mAP@0.5:0.95 of 62.7%, representing improvements of 2.3 and 1.9 percentage points, respectively, over the baseline YOLOv11n model. Compared with CenterNet, Faster R-CNN, YOLOv8-LSW, MSA-DETR, DMN-YOLO, and YOLOv11n, the improved model shows mAP@0.5 improvements of 25.7, 21.2, 5.5, 4.0, 4.5, and 2.3 percentage points, respectively, along with corresponding mAP@0.5:0.95 increases of 25.6, 25.3, 8.3, 2.8, 1.8, and 1.9 percentage points. Deployed on a Jetson TX2 development board, the model achieves a recognition speed of 56 frames per second (FPS) and an mAP of 84.2%, confirming its suitability for real-time detection. Furthermore, the improved model effectively reduces instances of both false negatives and false positives for diseased cotton bolls while yielding higher detection confidence, thus providing robust technical support for intelligent cotton boll disease detection.https://www.mdpi.com/2076-3417/15/14/8085detection of cotton boll diseasesYOLOv11EMA mechanismpartial convolutionloss function
spellingShingle Lei Yang
Wenhao Cui
Jingqian Li
Guotao Han
Qi Zhou
Yubin Lan
Jing Zhao
Yongliang Qiao
A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11n
Applied Sciences
detection of cotton boll diseases
YOLOv11
EMA mechanism
partial convolution
loss function
title A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11n
title_full A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11n
title_fullStr A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11n
title_full_unstemmed A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11n
title_short A Real-Time Cotton Boll Disease Detection Model Based on Enhanced YOLOv11n
title_sort real time cotton boll disease detection model based on enhanced yolov11n
topic detection of cotton boll diseases
YOLOv11
EMA mechanism
partial convolution
loss function
url https://www.mdpi.com/2076-3417/15/14/8085
work_keys_str_mv AT leiyang arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT wenhaocui arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT jingqianli arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT guotaohan arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT qizhou arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT yubinlan arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT jingzhao arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT yongliangqiao arealtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT leiyang realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT wenhaocui realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT jingqianli realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT guotaohan realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT qizhou realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT yubinlan realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT jingzhao realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n
AT yongliangqiao realtimecottonbolldiseasedetectionmodelbasedonenhancedyolov11n