Integrated Learning-Based Pest and Disease Detection Method for Tea Leaves
Currently, the detection of tea pests and diseases remains a challenging task due to the complex background and the diverse spot patterns of tea leaves. Traditional methods of tea pest detection mainly rely on the experience of tea farmers and experts in specific fields, which is complex and ineffic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/14/5/1012 |
| _version_ | 1797600089644990464 |
|---|---|
| author | Yinkai Wang Renjie Xu Di Bai Haifeng Lin |
| author_facet | Yinkai Wang Renjie Xu Di Bai Haifeng Lin |
| author_sort | Yinkai Wang |
| collection | DOAJ |
| description | Currently, the detection of tea pests and diseases remains a challenging task due to the complex background and the diverse spot patterns of tea leaves. Traditional methods of tea pest detection mainly rely on the experience of tea farmers and experts in specific fields, which is complex and inefficient and can easily lead to misclassification and omission of diseases. Currently, a single detection model is often used for tea pest and disease identification; however, its learning and perception capabilities are insufficient to complete target detection of pests and diseases in complex tea garden environments. To address the problem that existing target detection algorithms are difficult to identify in the complex environment of tea plantations, an integrated learning-based pest detection method is proposed to detect one disease (<i>Leaf blight</i>) and one pest (<i>Apolygus lucorμm</i>), and to perform adaptive learning and extraction of tea pests and diseases. In this paper, the YOLOv5 weakly supervised model is selected, and it is found through experiments that the GAM attention mechanism’s introduction on the basis of YOLOv5’s network can better identify the <i>Apolygus lucorμm</i>; the introduction of CBAM attention mechanism significantly enhances the effect of identifying <i>Leaf blight</i>. After integrating the two modified YOLOv5 models, the prediction results were processed using the weighted box fusion (WBF) algorithm. The integrated model made full use of the complementary advantages among the models, improved the feature extraction ability of the model and enhanced the detection capability of the model. The experimental findings demonstrate that the tea pest detection algorithm effectively enhances the detection ability of tea pests and diseases with an average accuracy of 79.3%. Compared with the individual models, the average accuracy improvement was 8.7% and 9.6%, respectively. The integrated algorithm, which may serve as a guide for tea disease diagnosis in field environments, has improved feature extraction capabilities, can extract more disease feature information, and better balances the model’s recognition accuracy and model complexity. |
| first_indexed | 2024-03-11T03:43:37Z |
| format | Article |
| id | doaj.art-66c298dbc6f94763aaef9421e3066ecb |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-11T03:43:37Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-66c298dbc6f94763aaef9421e3066ecb2023-11-18T01:24:58ZengMDPI AGForests1999-49072023-05-01145101210.3390/f14051012Integrated Learning-Based Pest and Disease Detection Method for Tea LeavesYinkai Wang0Renjie Xu1Di Bai2Haifeng Lin3The College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Management, Nanjing Agricultural University, Nanjing 210095, ChinaDepartment of Computing and Software, McMaster University, Hamilton, ON L8S 4L8, CanadaThe College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaCurrently, the detection of tea pests and diseases remains a challenging task due to the complex background and the diverse spot patterns of tea leaves. Traditional methods of tea pest detection mainly rely on the experience of tea farmers and experts in specific fields, which is complex and inefficient and can easily lead to misclassification and omission of diseases. Currently, a single detection model is often used for tea pest and disease identification; however, its learning and perception capabilities are insufficient to complete target detection of pests and diseases in complex tea garden environments. To address the problem that existing target detection algorithms are difficult to identify in the complex environment of tea plantations, an integrated learning-based pest detection method is proposed to detect one disease (<i>Leaf blight</i>) and one pest (<i>Apolygus lucorμm</i>), and to perform adaptive learning and extraction of tea pests and diseases. In this paper, the YOLOv5 weakly supervised model is selected, and it is found through experiments that the GAM attention mechanism’s introduction on the basis of YOLOv5’s network can better identify the <i>Apolygus lucorμm</i>; the introduction of CBAM attention mechanism significantly enhances the effect of identifying <i>Leaf blight</i>. After integrating the two modified YOLOv5 models, the prediction results were processed using the weighted box fusion (WBF) algorithm. The integrated model made full use of the complementary advantages among the models, improved the feature extraction ability of the model and enhanced the detection capability of the model. The experimental findings demonstrate that the tea pest detection algorithm effectively enhances the detection ability of tea pests and diseases with an average accuracy of 79.3%. Compared with the individual models, the average accuracy improvement was 8.7% and 9.6%, respectively. The integrated algorithm, which may serve as a guide for tea disease diagnosis in field environments, has improved feature extraction capabilities, can extract more disease feature information, and better balances the model’s recognition accuracy and model complexity.https://www.mdpi.com/1999-4907/14/5/1012tea diseasefeature extractionintegrated learningmachine learning |
| spellingShingle | Yinkai Wang Renjie Xu Di Bai Haifeng Lin Integrated Learning-Based Pest and Disease Detection Method for Tea Leaves Forests tea disease feature extraction integrated learning machine learning |
| title | Integrated Learning-Based Pest and Disease Detection Method for Tea Leaves |
| title_full | Integrated Learning-Based Pest and Disease Detection Method for Tea Leaves |
| title_fullStr | Integrated Learning-Based Pest and Disease Detection Method for Tea Leaves |
| title_full_unstemmed | Integrated Learning-Based Pest and Disease Detection Method for Tea Leaves |
| title_short | Integrated Learning-Based Pest and Disease Detection Method for Tea Leaves |
| title_sort | integrated learning based pest and disease detection method for tea leaves |
| topic | tea disease feature extraction integrated learning machine learning |
| url | https://www.mdpi.com/1999-4907/14/5/1012 |
| work_keys_str_mv | AT yinkaiwang integratedlearningbasedpestanddiseasedetectionmethodfortealeaves AT renjiexu integratedlearningbasedpestanddiseasedetectionmethodfortealeaves AT dibai integratedlearningbasedpestanddiseasedetectionmethodfortealeaves AT haifenglin integratedlearningbasedpestanddiseasedetectionmethodfortealeaves |