YOLO-BSMamba: A YOLOv8s-Based Model for Tomato Leaf Disease Detection in Complex Backgrounds DOI Creative Commons
Zhihong Liu, Xiangyun Guo, Tian Zhao

и другие.

Agronomy, Год журнала: 2025, Номер 15(4), С. 870 - 870

Опубликована: Март 30, 2025

The precise identification of diseases in tomato leaves is great importance for target pesticide application a complex background scenario. Existing models often have difficulty capturing long-range dependencies and fine-grained features images, leading to poor recognition where there are backgrounds. To tackle this challenge, study proposed using YOLO-BSMamba detection mode. We that Hybrid Convolutional Mamba module (HCMamba) integrated within the neck network, with aim improving feature representation by leveraging capture global contextual capabilities State Space Model (SSM) discerning localized spatial convolution. Furthermore, we introduced Similarity-Based Attention Mechanism into C2f improve model’s extraction focusing on disease-indicative leaf areas reducing noise. weighted bidirectional pyramid network (BiFPN) was utilized replace feature-fusion component thereby enhancing performance lesions exhibiting heterogeneous symptomatic gradations enabling model effectively integrate from different scales. Research results showed achieved an F1 score, [email protected], [email protected]:0.95 81.9%, 86.7%, 72.0%, respectively, which represents improvement 3.0%, 4.8%, 4.3%, compared YOLOv8s. Compared other YOLO series models, it achieves best [email protected] score. This provides robust reliable method disease recognition, expected efficiency, further enhance crop monitoring management precision agriculture.

Язык: Английский

YOLO-BSMamba: A YOLOv8s-Based Model for Tomato Leaf Disease Detection in Complex Backgrounds DOI Creative Commons
Zhihong Liu, Xiangyun Guo, Tian Zhao

и другие.

Agronomy, Год журнала: 2025, Номер 15(4), С. 870 - 870

Опубликована: Март 30, 2025

The precise identification of diseases in tomato leaves is great importance for target pesticide application a complex background scenario. Existing models often have difficulty capturing long-range dependencies and fine-grained features images, leading to poor recognition where there are backgrounds. To tackle this challenge, study proposed using YOLO-BSMamba detection mode. We that Hybrid Convolutional Mamba module (HCMamba) integrated within the neck network, with aim improving feature representation by leveraging capture global contextual capabilities State Space Model (SSM) discerning localized spatial convolution. Furthermore, we introduced Similarity-Based Attention Mechanism into C2f improve model’s extraction focusing on disease-indicative leaf areas reducing noise. weighted bidirectional pyramid network (BiFPN) was utilized replace feature-fusion component thereby enhancing performance lesions exhibiting heterogeneous symptomatic gradations enabling model effectively integrate from different scales. Research results showed achieved an F1 score, [email protected], [email protected]:0.95 81.9%, 86.7%, 72.0%, respectively, which represents improvement 3.0%, 4.8%, 4.3%, compared YOLOv8s. Compared other YOLO series models, it achieves best [email protected] score. This provides robust reliable method disease recognition, expected efficiency, further enhance crop monitoring management precision agriculture.

Язык: Английский

Процитировано

0