Rice disease detection method based on multi-scale dynamic feature fusion

In order to enhance the accuracy of rice leaf disease detection in complex farmland environments, and facilitate the deployment of the deep learning model onto mobile terminals for rapid real-time inference, this paper introduces a disease detection network titled YOLOv11 Multi-scale Dynamic Feature...

Full description

Saved in:
Bibliographic Details
Main Authors: Qian Fan, Runhao Chen, Bin Li
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1543986/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850035515966881792
author Qian Fan
Runhao Chen
Bin Li
author_facet Qian Fan
Runhao Chen
Bin Li
author_sort Qian Fan
collection DOAJ
description In order to enhance the accuracy of rice leaf disease detection in complex farmland environments, and facilitate the deployment of the deep learning model onto mobile terminals for rapid real-time inference, this paper introduces a disease detection network titled YOLOv11 Multi-scale Dynamic Feature Fusion for Rice Disease Detection (YOLOv11-MSDFF-RiceD). The model adopts the concept of ParameterNet to design the FlexiC3k2Net module, which replaces the neck feature extraction network, thereby bolstering the model's feature learning capabilities without significantly increasing computational complexity. Additionally, an efficient multi-scale feature fusion module (EMFFM) is devised, improving both the computational efficiency and feature extraction capabilities of the model, while simultaneously reducing the number of parameters and memory footprint. The bounding box regression loss function, inner-WIoU, utilizes auxiliary bounding boxes and scale factors. Finally, the Dependency Graph (DepGraph) pruning model is employed to minimize the model's size, computational load, and parameter count, with only a moderate sacrifice in accuracy. Compared to the original YOLOv11n model, the optimized model achieves reductions in computational complexity, parameter scale, and memory usage by 50.7%, 49.6%, and 36.9%, respectively, with only a 1.7% improvement in mAP@0.5:0.9. These optimizations enable efficient deployment on resource-constrained mobile devices, making the model highly suitable for real-time disease detection in practical agricultural scenarios where hardware limitations are critical. Consequently, the improved model proposed in this paper effectively detects rice disease targets in complex environments, providing theoretical and technical support for the deployment and application of mobile terminal detection devices, such as rice disease detectors, in practical scenarios.
format Article
id doaj-art-eff87b4b0fc54d4d9a5cf1141cf9f0f0
institution DOAJ
issn 1664-462X
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-eff87b4b0fc54d4d9a5cf1141cf9f0f02025-08-20T02:57:28ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-05-011610.3389/fpls.2025.15439861543986Rice disease detection method based on multi-scale dynamic feature fusionQian FanRunhao ChenBin LiIn order to enhance the accuracy of rice leaf disease detection in complex farmland environments, and facilitate the deployment of the deep learning model onto mobile terminals for rapid real-time inference, this paper introduces a disease detection network titled YOLOv11 Multi-scale Dynamic Feature Fusion for Rice Disease Detection (YOLOv11-MSDFF-RiceD). The model adopts the concept of ParameterNet to design the FlexiC3k2Net module, which replaces the neck feature extraction network, thereby bolstering the model's feature learning capabilities without significantly increasing computational complexity. Additionally, an efficient multi-scale feature fusion module (EMFFM) is devised, improving both the computational efficiency and feature extraction capabilities of the model, while simultaneously reducing the number of parameters and memory footprint. The bounding box regression loss function, inner-WIoU, utilizes auxiliary bounding boxes and scale factors. Finally, the Dependency Graph (DepGraph) pruning model is employed to minimize the model's size, computational load, and parameter count, with only a moderate sacrifice in accuracy. Compared to the original YOLOv11n model, the optimized model achieves reductions in computational complexity, parameter scale, and memory usage by 50.7%, 49.6%, and 36.9%, respectively, with only a 1.7% improvement in mAP@0.5:0.9. These optimizations enable efficient deployment on resource-constrained mobile devices, making the model highly suitable for real-time disease detection in practical agricultural scenarios where hardware limitations are critical. Consequently, the improved model proposed in this paper effectively detects rice disease targets in complex environments, providing theoretical and technical support for the deployment and application of mobile terminal detection devices, such as rice disease detectors, in practical scenarios.https://www.frontiersin.org/articles/10.3389/fpls.2025.1543986/fullinner-WIoUrice disease detectionmulti-scale feature fusionflexiC3k2Netdeep learning
spellingShingle Qian Fan
Runhao Chen
Bin Li
Rice disease detection method based on multi-scale dynamic feature fusion
Frontiers in Plant Science
inner-WIoU
rice disease detection
multi-scale feature fusion
flexiC3k2Net
deep learning
title Rice disease detection method based on multi-scale dynamic feature fusion
title_full Rice disease detection method based on multi-scale dynamic feature fusion
title_fullStr Rice disease detection method based on multi-scale dynamic feature fusion
title_full_unstemmed Rice disease detection method based on multi-scale dynamic feature fusion
title_short Rice disease detection method based on multi-scale dynamic feature fusion
title_sort rice disease detection method based on multi scale dynamic feature fusion
topic inner-WIoU
rice disease detection
multi-scale feature fusion
flexiC3k2Net
deep learning
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1543986/full
work_keys_str_mv AT qianfan ricediseasedetectionmethodbasedonmultiscaledynamicfeaturefusion
AT runhaochen ricediseasedetectionmethodbasedonmultiscaledynamicfeaturefusion
AT binli ricediseasedetectionmethodbasedonmultiscaledynamicfeaturefusion