HSSNet: A End-to-End Network for Detecting Tiny Targets of Apple Leaf Diseases in Complex Backgrounds.

Abstract

Apple leaf diseases are one of the most important factors that reduce apple quality and yield. The object detection technology based on deep learning can detect diseases in a timely manner and help automate disease control, thereby reducing economic losses. In the natural environment, tiny apple leaf disease targets (a resolution is less than 32 × 32 pixel 2 ) are easily overlooked. To address the problems of complex background interference, difficult detection of tiny targets and biased detection of prediction boxes that exist in standard detectors, in this paper, we constructed a tiny target dataset TTALDD-4 containing four types of diseases, which include Alternaria leaf spot, Frogeye leaf spot, Grey spot and Rust, and proposed the HSSNet detector based on the YOLOv7-tiny benchmark for professional detection of apple leaf disease tiny targets. Firstly, the H-SimAM attention mechanism is proposed to focus on the foreground lesions in the complex background of the image. Secondly, SP-BiFormer Block is proposed to enhance the ability of the model to perceive tiny targets of leaf diseases. Finally, we use the SIOU loss to improve the case of prediction box bias. The experimental results show that HSSNet achieves 85.04% mAP (mean average precision), 67.53% AR (average recall), and 83 FPS (frames per second). Compared with other standard detectors, HSSNet maintains high real-time detection speed with higher detection accuracy. This provides a reference for the automated control of apple leaf diseases.

Plant phenotyping relevance

リンゴ葉の病斑という植物の病害状態を画像から検出する専用データセットと深層学習検出器を開発し、精度・再現率・速度で評価しており、表現型取得手法が研究の中心である。

Code and data availability

The paper introduces the TTALDD-4 apple leaf disease dataset and the HSSNet detector, but no block contains any public deposit, availability statement, or authors' URL for the dataset, images, annotations, code, or trained models. The only URLs present are citations to prior work (e.g., Ultralytics YOLO, AppleLeaf9), a

No evidence-backed public reproduction asset is currently recorded.