JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE B

Accepted manuscript available online (unedited version)

Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases

Author(s): Jinxian TAO¹, Xiaoli LI¹, Jingfei ZHANG³, Muhammad SHOAIB¹, Muhammad adnan ISLAM¹, Ibrar AHMAD¹, Yong HE¹, Sitan YE¹, Yujie WANG¹, Binhui LIAO³, Mostafa GOUDA^1, ²
Affiliation(s): ¹College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China ²Department of Nutrition & Food Science, National Research Centre, Dokki, 12622, Giza, Egypt ³Liandu Agriculture and Rural Bureau, Lishui 323000, China
Corresponding email(s): Xiaoli LI, xiaolili@zju.edu.cn Jingfei ZHANG, 13857077928@163.com
Key Words: Tea disease detection; YOLO11n; Convolutional module; Attention mechanism; Loss function.

Share this article to： More <<< Previous Paper \|Next Paper >>>

Jinxian TAO¹, Xiaoli LI¹, Jingfei ZHANG³, Muhammad SHOAIB¹, Muhammad adnan ISLAM¹, Ibrar AHMAD¹, Yong HE¹, Sitan YE¹, Yujie WANG¹, Binhui LIAO³, Mostafa GOUDA^1,². Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases[J]. Journal of Zhejiang University Science B,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.B2500693

@article{title="Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases",
author="Jinxian TAO¹, Xiaoli LI¹, Jingfei ZHANG³, Muhammad SHOAIB¹, Muhammad adnan ISLAM¹, Ibrar AHMAD¹, Yong HE¹, Sitan YE¹, Yujie WANG¹, Binhui LIAO³, Mostafa GOUDA^1,²",
journal="Journal of Zhejiang University Science B",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.B2500693"
}

%0 Journal Article
%T Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases
%A Jinxian TAO¹
%A Xiaoli LI¹
%A Jingfei ZHANG³
%A Muhammad SHOAIB¹
%A Muhammad adnan ISLAM¹
%A Ibrar AHMAD¹
%A Yong HE¹
%A Sitan YE¹
%A Yujie WANG¹
%A Binhui LIAO³
%A Mostafa GOUDA^1
%A²
%J Journal of Zhejiang University SCIENCE B
%P
%@ 1673-1581
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.B2500693"

TY - JOUR
T1 - Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases
A1 - Jinxian TAO¹
A1 - Xiaoli LI¹
A1 - Jingfei ZHANG³
A1 - Muhammad SHOAIB¹
A1 - Muhammad adnan ISLAM¹
A1 - Ibrar AHMAD¹
A1 - Yong HE¹
A1 - Sitan YE¹
A1 - Yujie WANG¹
A1 - Binhui LIAO³
A1 - Mostafa GOUDA^{1
A1 -}²
J0 - Journal of Zhejiang University Science B
SP -
EP -
%@ 1673-1581
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.B2500693"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Tea diseases, including brown and grey blight, result in significant yield and quality losses, especially in Longjing tea production. Traditional detection methods are prone to errors, while existing deep learning models often struggle to be robust in natural field conditions. To address these challenges, an improved lightweight detection model, Asymmetric Multi-level mechanism, Dynamic Snake convolution, SIoU loss function-YOLO (ADS-YOLO), was developed and validated. In the method, a dataset comprising 5694 smartphone-captured images of tea leaves was established under natural lighting. Enhancements were implemented in the YOLO11n baseline algorithm through the incorporation of the SIoU loss function for better bounding box regression, dynamic snake convolution (DSC), which realizes adaptive feature extraction based on the dynamic spatial context, and an Asymmetric Multi-level (AML) mechanism, which achieves lightweight feature fusion via adaptive multi-scale design. The results showed that ADS-YOLO achieved a precision of 0.935 and a recall of 0.870, compared to 0.894 and 0.818, respectively, using the baseline YOLO11n. Importantly, ADS-YOLO demonstrated a real-time performance of 137.1 FPS, coupled with reduced computational costs. ADS-YOLO improved mAP@0.5 by 6.4% compared with YOLOv5n and achieved up to 44.6% higher accuracy than YOLOv7t. In conclusion, ADS-YOLO achieved high accuracy, providing a scalable solution for real-time crop health monitoring and sustainable, precision agriculture for tea prodution.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference