Tomato leaf disease detection based on attention mechanism and multi-scale feature fusion

• Published in: Frontiers in plant science Vol. 15; p. 1382802
• Main Authors: Wang, Yong, Zhang, Panxing, Tian, Shuang
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 09.04.2024
• Subjects: attention mechanism; disease detection; feature pyramid network; multi-scale feature fusion; Plant Science; YOLOv6; multi-scale feature fusion; disease detection; YOLOv6; attention mechanism; feature pyramid network
• ISSN: 1664-462X; 1664-462X
• DOI: 10.3389/fpls.2024.1382802

When detecting tomato leaf diseases in natural environments, factors such as changes in lighting, occlusion, and the small size of leaf lesions pose challenges to detection accuracy. Therefore, this study proposes a tomato leaf disease detection method based on attention mechanisms and multi-scale feature fusion. Firstly, the Convolutional Block Attention Module (CBAM) is introduced into the backbone feature extraction network to enhance the ability to extract lesion features and suppress the effects of environmental interference. Secondly, shallow feature maps are introduced into the re-parameterized generalized feature pyramid network (RepGFPN), constructing a new multi-scale re-parameterized generalized feature fusion module (BiRepGFPN) to enhance feature fusion expression and improve the localization ability for small lesion features. Finally, the BiRepGFPN replaces the Path Aggregation Feature Pyramid Network (PAFPN) in the YOLOv6 model to achieve effective fusion of deep semantic and shallow spatial information. Experimental results indicate that, when evaluated on the publicly available PlantDoc dataset, the model's mean average precision (mAP) showed improvements of 7.7%, 11.8%, 3.4%, 5.7%, 4.3%, and 2.6% compared to YOLOX, YOLOv5, YOLOv6, YOLOv6-s, YOLOv7, and YOLOv8, respectively. When evaluated on the tomato leaf disease dataset, the model demonstrated a precision of 92.9%, a recall rate of 95.2%, an F1 score of 94.0%, and a mean average precision (mAP) of 93.8%, showing improvements of 2.3%, 4.0%, 3.1%, and 2.7% respectively compared to the baseline model. These results indicate that the proposed detection method possesses significant detection performance and generalization capabilities.