Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage
Crop seedlings are similar in appearance to weeds, making crop detection extremely difficult. To solve the problem of detecting crop seedlings in complex field environments, a seedling dataset with four crops was constructed in this study. The single leaf labeling method was proposed as an alternati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Sprog: | English |
| Udgivet: |
MDPI AG
2023-05-01
|
| Serier: | Agronomy |
| Fag: | |
| Online adgang: | https://www.mdpi.com/2073-4395/13/6/1503 |
| _version_ | 1827739007385075712 |
|---|---|
| author | Shuolin Kong Jian Li Yuting Zhai Zhiyuan Gao Yang Zhou Yanlei Xu |
| author_facet | Shuolin Kong Jian Li Yuting Zhai Zhiyuan Gao Yang Zhou Yanlei Xu |
| author_sort | Shuolin Kong |
| collection | DOAJ |
| description | Crop seedlings are similar in appearance to weeds, making crop detection extremely difficult. To solve the problem of detecting crop seedlings in complex field environments, a seedling dataset with four crops was constructed in this study. The single leaf labeling method was proposed as an alternative to conventional labeling approaches to improve the detection accuracy for dense planting crops. Second, a seedling detection network based on YOLOv5 and a transformer mechanism was proposed, and the effects of three features (query, key and value) in the transformer mechanism on the detection accuracy were explored in detail. Finally, the seedling detection network was optimized into a lightweight network. The experimental results show that application of the single leaf labeling method could improve the mAP0.5 of the model by 1.2% and effectively solve the problem of missed detection. By adding the transformer mechanism module, the mAP0.5 was improved by 1.5%, enhancing the detection capability of the model for dense and obscured targets. In the end, this study found that query features had the least impact on the transformer mechanism, and the optimized model improved the computation speed by 23 ms·frame<sup>−1</sup> on the intelligent computing platform Jetson TX2, providing a theoretical basis and technical support for real-time seedling management. |
| first_indexed | 2024-03-11T02:52:01Z |
| format | Article |
| id | doaj.art-a9a5934cb15140d5a40cf2a63e8d9f9c |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-11T02:52:01Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-a9a5934cb15140d5a40cf2a63e8d9f9c2023-11-18T08:54:08ZengMDPI AGAgronomy2073-43952023-05-01136150310.3390/agronomy13061503Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling StageShuolin Kong0Jian Li1Yuting Zhai2Zhiyuan Gao3Yang Zhou4Yanlei Xu5College of Information and Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information and Technology, Jilin Agricultural University, Changchun 130118, ChinaCrop seedlings are similar in appearance to weeds, making crop detection extremely difficult. To solve the problem of detecting crop seedlings in complex field environments, a seedling dataset with four crops was constructed in this study. The single leaf labeling method was proposed as an alternative to conventional labeling approaches to improve the detection accuracy for dense planting crops. Second, a seedling detection network based on YOLOv5 and a transformer mechanism was proposed, and the effects of three features (query, key and value) in the transformer mechanism on the detection accuracy were explored in detail. Finally, the seedling detection network was optimized into a lightweight network. The experimental results show that application of the single leaf labeling method could improve the mAP0.5 of the model by 1.2% and effectively solve the problem of missed detection. By adding the transformer mechanism module, the mAP0.5 was improved by 1.5%, enhancing the detection capability of the model for dense and obscured targets. In the end, this study found that query features had the least impact on the transformer mechanism, and the optimized model improved the computation speed by 23 ms·frame<sup>−1</sup> on the intelligent computing platform Jetson TX2, providing a theoretical basis and technical support for real-time seedling management.https://www.mdpi.com/2073-4395/13/6/1503crop seedling detectiondense target detectionlightweight transformerYOLOv5 |
| spellingShingle | Shuolin Kong Jian Li Yuting Zhai Zhiyuan Gao Yang Zhou Yanlei Xu Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage Agronomy crop seedling detection dense target detection lightweight transformer YOLOv5 |
| title | Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage |
| title_full | Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage |
| title_fullStr | Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage |
| title_full_unstemmed | Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage |
| title_short | Real-Time Detection of Crops with Dense Planting Using Deep Learning at Seedling Stage |
| title_sort | real time detection of crops with dense planting using deep learning at seedling stage |
| topic | crop seedling detection dense target detection lightweight transformer YOLOv5 |
| url | https://www.mdpi.com/2073-4395/13/6/1503 |
| work_keys_str_mv | AT shuolinkong realtimedetectionofcropswithdenseplantingusingdeeplearningatseedlingstage AT jianli realtimedetectionofcropswithdenseplantingusingdeeplearningatseedlingstage AT yutingzhai realtimedetectionofcropswithdenseplantingusingdeeplearningatseedlingstage AT zhiyuangao realtimedetectionofcropswithdenseplantingusingdeeplearningatseedlingstage AT yangzhou realtimedetectionofcropswithdenseplantingusingdeeplearningatseedlingstage AT yanleixu realtimedetectionofcropswithdenseplantingusingdeeplearningatseedlingstage |