REAL-TIME AND PRECISE DETECTION OF FIELD SOYBEAN RUST AND BACTERIAL SPOT BASED ON IMPROVED YOLOV11N

Abstract

To overcome YOLOv11’s limitations in complex field environments, this paper proposed SDD-YOLOv11n, a lightweight real-time detector for soybean diseases. The model reconstructed the backbone using GhostConv to minimize redundancy and integrates a C3k2_Star module to enhance small lesion detection against background noise. Additionally, a Detect Efficient (DE) head further compressed the architecture. Experimental results verified the model's efficiency, achieving a parameter count of 1.88 M and a weight size of 3.9 MB—reductions of 27.3% and 25% compared to YOLOv11n, respectively. Furthermore, the model maintained high detection performance with a Mean Average Precision (mAP50) of 75.6% and an F1-score of 69.3%, demonstrating its effectiveness in balancing architectural efficiency and accuracy in complex field environments.

Plant phenotyping relevance

圃場のダイズ病害病斑を画像から検出する軽量YOLOモデルの開発と性能評価が研究の中心であり、植物の病害状態を直接推定するフェノタイピング手法に該当する。

Code and data availability

The paper describes a self-constructed soybean disease image dataset (6,523 images from Jianshan Farm) and the SDD-YOLOv11n model, but no block contains any public deposit, availability statement, or URL for the dataset, images, code, or trained weights. The only URL is the article DOI itself.

No evidence-backed public reproduction asset is currently recorded.