A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques
With the widespread application of drone technology, the demand for pest detection and identification from low-resolution and noisy images captured with drones has been steadily increasing. In this study, a lightweight pest identification model based on Transformer and super-resolution sampling tech...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/13/9/1812 |
| _version_ | 1827727695114403840 |
|---|---|
| author | Yuzhe Bai Fengjun Hou Xinyuan Fan Weifan Lin Jinghan Lu Junyu Zhou Dongchen Fan Lin Li |
| author_facet | Yuzhe Bai Fengjun Hou Xinyuan Fan Weifan Lin Jinghan Lu Junyu Zhou Dongchen Fan Lin Li |
| author_sort | Yuzhe Bai |
| collection | DOAJ |
| description | With the widespread application of drone technology, the demand for pest detection and identification from low-resolution and noisy images captured with drones has been steadily increasing. In this study, a lightweight pest identification model based on Transformer and super-resolution sampling techniques is introduced, aiming to enhance identification accuracy under challenging conditions. The Transformer model was found to effectively capture spatial dependencies in images, while the super-resolution sampling technique was employed to restore image details for subsequent identification processes. The experimental results demonstrated that this approach exhibited significant advantages across various pest image datasets, achieving Precision, Recall, mAP, and FPS scores of 0.97, 0.95, 0.95, and 57, respectively. Especially in the presence of low resolution and noise, this method was capable of performing pest identification with high accuracy. Furthermore, an adaptive optimizer was incorporated to enhance model convergence and performance. Overall, this study offers an efficient and accurate method for pest detection and identification in practical applications, holding significant practical value. |
| first_indexed | 2024-03-10T23:08:59Z |
| format | Article |
| id | doaj.art-e69da25030c04120a0051e05e71a091e |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-10T23:08:59Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-e69da25030c04120a0051e05e71a091e2023-11-19T09:07:38ZengMDPI AGAgriculture2077-04722023-09-01139181210.3390/agriculture13091812A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling TechniquesYuzhe Bai0Fengjun Hou1Xinyuan Fan2Weifan Lin3Jinghan Lu4Junyu Zhou5Dongchen Fan6Lin Li7China Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaSchool of Computer Science and Engineering, Beihang University, Beijing 100191, ChinaChina Agricultural University, Beijing 100083, ChinaWith the widespread application of drone technology, the demand for pest detection and identification from low-resolution and noisy images captured with drones has been steadily increasing. In this study, a lightweight pest identification model based on Transformer and super-resolution sampling techniques is introduced, aiming to enhance identification accuracy under challenging conditions. The Transformer model was found to effectively capture spatial dependencies in images, while the super-resolution sampling technique was employed to restore image details for subsequent identification processes. The experimental results demonstrated that this approach exhibited significant advantages across various pest image datasets, achieving Precision, Recall, mAP, and FPS scores of 0.97, 0.95, 0.95, and 57, respectively. Especially in the presence of low resolution and noise, this method was capable of performing pest identification with high accuracy. Furthermore, an adaptive optimizer was incorporated to enhance model convergence and performance. Overall, this study offers an efficient and accurate method for pest detection and identification in practical applications, holding significant practical value.https://www.mdpi.com/2077-0472/13/9/1812smart agriculturepest detectionTransformersuper resolution |
| spellingShingle | Yuzhe Bai Fengjun Hou Xinyuan Fan Weifan Lin Jinghan Lu Junyu Zhou Dongchen Fan Lin Li A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques Agriculture smart agriculture pest detection Transformer super resolution |
| title | A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques |
| title_full | A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques |
| title_fullStr | A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques |
| title_full_unstemmed | A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques |
| title_short | A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques |
| title_sort | lightweight pest detection model for drones based on transformer and super resolution sampling techniques |
| topic | smart agriculture pest detection Transformer super resolution |
| url | https://www.mdpi.com/2077-0472/13/9/1812 |
| work_keys_str_mv | AT yuzhebai alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT fengjunhou alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT xinyuanfan alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT weifanlin alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT jinghanlu alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT junyuzhou alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT dongchenfan alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT linli alightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT yuzhebai lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT fengjunhou lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT xinyuanfan lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT weifanlin lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT jinghanlu lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT junyuzhou lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT dongchenfan lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques AT linli lightweightpestdetectionmodelfordronesbasedontransformerandsuperresolutionsamplingtechniques |