Cotton Leaf Spot Detection Based on an Improved YOLOv11n Model.

Abstract

In cotton disease detection, the complex farmland environment and the varying scales of disease spots, especially the presence of small-target disease spots, limit the detection accuracy of lightweight models. To address this issue, an improved YOLOv11n detection algorithm is proposed. First, the backbone network is reconstructed using the GhostConv (G-conv) module, which generates redundant feature maps through linear operations, thereby reducing computational complexity. Second, an Adaptive Calibration and Feature Fusion Architecture Head (ACFFA) with prior calibration and cross-scale fusion capabilities is constructed in the detection stage to handle the problem of varying disease spot scales. Furthermore, the Adaptive Scale-aware Wise Intersection over Union (AS-WIoU) loss function, improved from WIoUv3, is introduced to enhance the stability of bounding box regression and improve detection accuracy for low-resolution, small-target lesions. Experimental results show that on the cotton disease dataset constructed based on the Mendeley Data database, the proposed model achieves mAP 50 and mAP 50-95 of 90.30% and 73.84%, respectively, with precision and recall of 92.33% and 87.68%, and a parameter count of 3.81 M. The algorithm significantly improves detection accuracy while maintaining efficient inference, making it suitable for real-time monitoring tasks on agricultural embedded terminals.

Plant phenotyping relevance

綿花葉の病斑を画像から検出・定量する改良YOLO手法が研究の中心であり、植物の病害状態を直接推定する画像ベースのフェノタイピングに該当する。

Code and data availability

The paper's cotton disease dataset was built from the public Mendeley Data repository (SAR-CLD-2024, doi:10.17632/B3JY2P6K8W), but no Mendeley URL is among the allowed_urls, so no directly actionable public URL can be cited. The authors state that raw data supporting the conclusions is available only on request, so the

No evidence-backed public reproduction asset is currently recorded.