Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism
Maize diseases are reported to occur often, and are complicated and difficult to control, which seriously affects the yield and quality of maize. This paper proposes an improved YOLOv5n model incorporating a CA (Coordinate Attention) mechanism and STR (Swin Transformer) detection head, CTR_YOLOv5n,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/2/521 |
| _version_ | 1827759145251504128 |
|---|---|
| author | Li Ma Qiwen Yu Helong Yu Jian Zhang |
| author_facet | Li Ma Qiwen Yu Helong Yu Jian Zhang |
| author_sort | Li Ma |
| collection | DOAJ |
| description | Maize diseases are reported to occur often, and are complicated and difficult to control, which seriously affects the yield and quality of maize. This paper proposes an improved YOLOv5n model incorporating a CA (Coordinate Attention) mechanism and STR (Swin Transformer) detection head, CTR_YOLOv5n, to identify common maize leaf spot, gray spot, and rust diseases in mobile applications. Based on the lightweight model YOLOv5n, the accuracy of the model is improved by adding a CA attention module, and the global information acquisition capability is enhanced by using TR2 as the detection head. The average recognition accuracy of the algorithm model can reach 95.2%, which is 2.8 percent higher than the original model, and the memory size is reduced to 5.1MB compared to 92.9MB of YOLOv5l, which is 94.5% smaller and meets the requirement of being light weight. Compared with SE, CBAM, and ECA, which are the mainstream attention mechanisms, the recognition effect we used is better and the accuracy is higher, achieving fast and accurate recognition of maize leaf diseases with fewer computational resources, providing new ideas and methods for real-time recognition of maize and other crop spots in mobile applications. |
| first_indexed | 2024-03-11T09:16:55Z |
| format | Article |
| id | doaj.art-5c469d801f144c12a572b736893ab07c |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-11T09:16:55Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-5c469d801f144c12a572b736893ab07c2023-11-16T18:35:49ZengMDPI AGAgronomy2073-43952023-02-0113252110.3390/agronomy13020521Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention MechanismLi Ma0Qiwen Yu1Helong Yu2Jian Zhang3College of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaFaculty of Agronomy, Jilin Agricultural University, Changchun 130118, ChinaMaize diseases are reported to occur often, and are complicated and difficult to control, which seriously affects the yield and quality of maize. This paper proposes an improved YOLOv5n model incorporating a CA (Coordinate Attention) mechanism and STR (Swin Transformer) detection head, CTR_YOLOv5n, to identify common maize leaf spot, gray spot, and rust diseases in mobile applications. Based on the lightweight model YOLOv5n, the accuracy of the model is improved by adding a CA attention module, and the global information acquisition capability is enhanced by using TR2 as the detection head. The average recognition accuracy of the algorithm model can reach 95.2%, which is 2.8 percent higher than the original model, and the memory size is reduced to 5.1MB compared to 92.9MB of YOLOv5l, which is 94.5% smaller and meets the requirement of being light weight. Compared with SE, CBAM, and ECA, which are the mainstream attention mechanisms, the recognition effect we used is better and the accuracy is higher, achieving fast and accurate recognition of maize leaf diseases with fewer computational resources, providing new ideas and methods for real-time recognition of maize and other crop spots in mobile applications.https://www.mdpi.com/2073-4395/13/2/521deep learningattention mechanismmaize leaf diseasedigital agriculture |
| spellingShingle | Li Ma Qiwen Yu Helong Yu Jian Zhang Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism Agronomy deep learning attention mechanism maize leaf disease digital agriculture |
| title | Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism |
| title_full | Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism |
| title_fullStr | Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism |
| title_full_unstemmed | Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism |
| title_short | Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism |
| title_sort | maize leaf disease identification based on yolov5n algorithm incorporating attention mechanism |
| topic | deep learning attention mechanism maize leaf disease digital agriculture |
| url | https://www.mdpi.com/2073-4395/13/2/521 |
| work_keys_str_mv | AT lima maizeleafdiseaseidentificationbasedonyolov5nalgorithmincorporatingattentionmechanism AT qiwenyu maizeleafdiseaseidentificationbasedonyolov5nalgorithmincorporatingattentionmechanism AT helongyu maizeleafdiseaseidentificationbasedonyolov5nalgorithmincorporatingattentionmechanism AT jianzhang maizeleafdiseaseidentificationbasedonyolov5nalgorithmincorporatingattentionmechanism |