Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework
Aiming at the problems of insufficient detection accuracy and high false detection rates of traditional pest detection models in the face of small targets and incomplete targets, this study proposes an improved target detection network, I-YOLOv10-SC. The network leverages Space-to-Depth Convolution...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/1/221 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589431007084544 |
|---|---|
| author | Wenxia Yuan Lingfang Lan Jiayi Xu Tingting Sun Xinghua Wang Qiaomei Wang Jingnan Hu Baijuan Wang |
| author_facet | Wenxia Yuan Lingfang Lan Jiayi Xu Tingting Sun Xinghua Wang Qiaomei Wang Jingnan Hu Baijuan Wang |
| author_sort | Wenxia Yuan |
| collection | DOAJ |
| description | Aiming at the problems of insufficient detection accuracy and high false detection rates of traditional pest detection models in the face of small targets and incomplete targets, this study proposes an improved target detection network, I-YOLOv10-SC. The network leverages Space-to-Depth Convolution to enhance its capability in detecting small insect targets. The Convolutional Block Attention Module is employed to improve feature representation and attention focus. Additionally, Shape Weights and Scale Adjustment Factors are introduced to optimize the loss function. The experimental results show that compared with the original YOLOv10, the model generated by the improved algorithm improves the accuracy by 5.88 percentage points, the recall rate by 6.67 percentage points, the balance score by 6.27 percentage points, the mAP value by 4.26 percentage points, the bounding box loss by 18.75%, the classification loss by 27.27%, and the feature point loss by 8%. The model oscillation has also been significantly improved. The enhanced I-YOLOv10-SC network effectively addresses the challenges of detecting small and incomplete insect targets in tea plantations, offering high precision and recall rates, thus providing a solid technical foundation for intelligent pest monitoring and precise prevention in smart tea gardens. |
| format | Article |
| id | doaj-art-d3494557b87f411294868bc61609b256 |
| institution | Kabale University |
| issn | 2073-4395 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-d3494557b87f411294868bc61609b2562025-01-24T13:17:14ZengMDPI AGAgronomy2073-43952025-01-0115122110.3390/agronomy15010221Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection FrameworkWenxia Yuan0Lingfang Lan1Jiayi Xu2Tingting Sun3Xinghua Wang4Qiaomei Wang5Jingnan Hu6Baijuan Wang7College of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaChina Tea (Yunnan) Co., Ltd., Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaAiming at the problems of insufficient detection accuracy and high false detection rates of traditional pest detection models in the face of small targets and incomplete targets, this study proposes an improved target detection network, I-YOLOv10-SC. The network leverages Space-to-Depth Convolution to enhance its capability in detecting small insect targets. The Convolutional Block Attention Module is employed to improve feature representation and attention focus. Additionally, Shape Weights and Scale Adjustment Factors are introduced to optimize the loss function. The experimental results show that compared with the original YOLOv10, the model generated by the improved algorithm improves the accuracy by 5.88 percentage points, the recall rate by 6.67 percentage points, the balance score by 6.27 percentage points, the mAP value by 4.26 percentage points, the bounding box loss by 18.75%, the classification loss by 27.27%, and the feature point loss by 8%. The model oscillation has also been significantly improved. The enhanced I-YOLOv10-SC network effectively addresses the challenges of detecting small and incomplete insect targets in tea plantations, offering high precision and recall rates, thus providing a solid technical foundation for intelligent pest monitoring and precise prevention in smart tea gardens.https://www.mdpi.com/2073-4395/15/1/221Space-to-Depth Convolutionshape weightsScale Adjustment Factorsintelligent pest monitoring |
| spellingShingle | Wenxia Yuan Lingfang Lan Jiayi Xu Tingting Sun Xinghua Wang Qiaomei Wang Jingnan Hu Baijuan Wang Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework Agronomy Space-to-Depth Convolution shape weights Scale Adjustment Factors intelligent pest monitoring |
| title | Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework |
| title_full | Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework |
| title_fullStr | Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework |
| title_full_unstemmed | Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework |
| title_short | Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework |
| title_sort | smart agricultural pest detection using i yolov10 sc an improved object detection framework |
| topic | Space-to-Depth Convolution shape weights Scale Adjustment Factors intelligent pest monitoring |
| url | https://www.mdpi.com/2073-4395/15/1/221 |
| work_keys_str_mv | AT wenxiayuan smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework AT lingfanglan smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework AT jiayixu smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework AT tingtingsun smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework AT xinghuawang smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework AT qiaomeiwang smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework AT jingnanhu smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework AT baijuanwang smartagriculturalpestdetectionusingiyolov10scanimprovedobjectdetectionframework |