What question did this study set out to answer?

The aim is to enhance pest and disease detection in flax while balancing accuracy and computational resources.

March 29, 2026Agriculture0 citationsOpen Access

Improved YOLOv11 for Lightweight and Accurate Detection of Flax Diseases and Pests in Complex Field Environments

PWPengyan WangGansu Agricultural University CLChengshuai LiGansu Agricultural University LWLinjing WeiGansu Agricultural University

Key Points

The aim is to enhance pest and disease detection in flax while balancing accuracy and computational resources.
Developed a lightweight YOLOv11 optimization framework.
Created a dedicated dataset for seven flax pest and disease categories.
Employed instance-level data augmentation to address class imbalance.
Incorporated ADown and C3K2-STAR modules for better feature representation.
Introduced auxiliary detection heads for improved training supervision.
Achieved higher mAP@50 scores than various existing models, with improvements ranging from 2.2 to 7.3 percentage points.
Showed strong results on mAP@50:95 metric, outperforming several models.
Achieved significant model compression with up to 94.8% fewer parameters than competing models.
Reduced computational costs by up to 95.6%.

Abstract

Timely and accurate detection of flax (Linum usitatissimum L.) pests and diseases is essential for ensuring stable yield and product quality. Nevertheless, practical field deployment remains challenging due to complex backgrounds, large variations in target scale, and limited computational resources. To tackle these issues, a lightweight optimization framework based on YOLOv11 is developed for flax pest and disease recognition. A dedicated dataset comprising seven common flax pest and disease categories is established, and an instance-level data augmentation strategy is employed to enhance data diversity and mitigate class imbalance. Building upon the YOLOv11 baseline, ADown and C3K2-STAR modules are incorporated to strengthen multi-scale feature representation while reducing computational redundancy, and auxiliary detection heads are introduced to provide additional supervision during training. Experimental results show that the proposed approach achieves better performance than Faster R-CNN, RT-DETR-ResNet50, YOLOv3-tiny, YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n by 4.4, 7.3, 4.1, 2.4, 2.6, 2.2, and 2.8 percentage points in mAP@50, respectively. For the more stringent mAP@50:95 metric, the proposed model also outperforms Faster R-CNN, RT-DETR-ResNet50, YOLOv3-tiny, YOLOv5n, YOLOv11n, and YOLOv12n by 2.9, 3.6, 4.3, 2.8, 2.0, and 0.5 percentage points, respectively, while achieving performance comparable to YOLOv8n. Meanwhile, it achieves substantial model compression, with 55.1%, 94.8%, 77.0%, 18.6%, 15.1%, and 14.5% fewer parameters than Faster R-CNN, RT-DETR-ResNet50, YOLOv3-tiny, YOLOv8n, YOLOv11n, and YOLOv12n, respectively, and it reduces computational cost (GFLOPS) by 31.5%, 95.6%, 61.5%, 19.1%, 12.7%, and 12.7%. These results indicate that the proposed method achieves a favorable balance between detection accuracy and computational efficiency, suggesting its potential suitability for practical flax pest and disease monitoring as well as deployment on resource-constrained edge devices, although further validation in more diverse scenarios is still needed.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper