Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseases

Abstract Detecting rice leaf diseases is essential for agricultural stability and crop health. However, the diversity of these diseases, their uneven distribution, and complex field environments create challenges for precise, multi-scale detection. While YOLO object detection algorithms show strong...

Full description

Saved in:
Bibliographic Details
Main Authors: Bo Gan, Guolin Pu, Weiyin Xing, Lianfang Wang, Shu Liang
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-06843-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849768849350590464
author Bo Gan
Guolin Pu
Weiyin Xing
Lianfang Wang
Shu Liang
author_facet Bo Gan
Guolin Pu
Weiyin Xing
Lianfang Wang
Shu Liang
author_sort Bo Gan
collection DOAJ
description Abstract Detecting rice leaf diseases is essential for agricultural stability and crop health. However, the diversity of these diseases, their uneven distribution, and complex field environments create challenges for precise, multi-scale detection. While YOLO object detection algorithms show strong performance in automated detection, their feature extraction capabilities remain limited in complex agricultural settings. Moreover, their high computational demands hinder deployment on resource-constrained devices, necessitating further optimization.To overcome these issues, This paper presents G-YOLO, a novel architecture that combines a Lightweight and Efficient Detection Head (LEDH) with Multi-scale Spatial Pyramid Pooling Fast (MSPPF). The LEDH enhances detection speed by simplifying the network structure while maintaining accuracy, reducing computational demands. The MSPPF improves the model’s ability to capture intricate details of rice leaf diseases at various scales by fusing multi-level feature maps. On the RiceDisease dataset, G-YOLO surpasses YOLOv8n with 4.4% higher mAP@0.5, 3.9% higher mAP@0.75, and a 13.1% increase in FPS, making it well-suited for resource-constrained devices due to its efficient design.
format Article
id doaj-art-d9e2e5834ff840ee95aa8d412b696391
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d9e2e5834ff840ee95aa8d412b6963912025-08-20T03:03:40ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-06843-8Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseasesBo Gan0Guolin Pu1Weiyin Xing2Lianfang Wang3Shu Liang4Dazhou Vocational and Technical CollegeDazhou Vocational and Technical CollegeMianyang PolytechnicDazhou Vocational and Technical CollegeDazhou Vocational and Technical CollegeAbstract Detecting rice leaf diseases is essential for agricultural stability and crop health. However, the diversity of these diseases, their uneven distribution, and complex field environments create challenges for precise, multi-scale detection. While YOLO object detection algorithms show strong performance in automated detection, their feature extraction capabilities remain limited in complex agricultural settings. Moreover, their high computational demands hinder deployment on resource-constrained devices, necessitating further optimization.To overcome these issues, This paper presents G-YOLO, a novel architecture that combines a Lightweight and Efficient Detection Head (LEDH) with Multi-scale Spatial Pyramid Pooling Fast (MSPPF). The LEDH enhances detection speed by simplifying the network structure while maintaining accuracy, reducing computational demands. The MSPPF improves the model’s ability to capture intricate details of rice leaf diseases at various scales by fusing multi-level feature maps. On the RiceDisease dataset, G-YOLO surpasses YOLOv8n with 4.4% higher mAP@0.5, 3.9% higher mAP@0.75, and a 13.1% increase in FPS, making it well-suited for resource-constrained devices due to its efficient design.https://doi.org/10.1038/s41598-025-06843-8Rice leaf disease detectionAgricultural stabilityCrop healthLightweight
spellingShingle Bo Gan
Guolin Pu
Weiyin Xing
Lianfang Wang
Shu Liang
Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseases
Scientific Reports
Rice leaf disease detection
Agricultural stability
Crop health
Lightweight
title Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseases
title_full Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseases
title_fullStr Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseases
title_full_unstemmed Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseases
title_short Enhanced YOLOv8 with lightweight and efficient detection head for for detecting rice leaf diseases
title_sort enhanced yolov8 with lightweight and efficient detection head for for detecting rice leaf diseases
topic Rice leaf disease detection
Agricultural stability
Crop health
Lightweight
url https://doi.org/10.1038/s41598-025-06843-8
work_keys_str_mv AT bogan enhancedyolov8withlightweightandefficientdetectionheadforfordetectingriceleafdiseases
AT guolinpu enhancedyolov8withlightweightandefficientdetectionheadforfordetectingriceleafdiseases
AT weiyinxing enhancedyolov8withlightweightandefficientdetectionheadforfordetectingriceleafdiseases
AT lianfangwang enhancedyolov8withlightweightandefficientdetectionheadforfordetectingriceleafdiseases
AT shuliang enhancedyolov8withlightweightandefficientdetectionheadforfordetectingriceleafdiseases