Hydroponic lettuce defective leaves identification based on improved YOLOv5s
Achieving intelligent detection of defective leaves of hydroponic lettuce after harvesting is of great significance for ensuring the quality and value of hydroponic lettuce. In order to improve the detection accuracy and efficiency of hydroponic lettuce defective leaves, firstly, an image acquisitio...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1242337/full |
| _version_ | 1797648562316640256 |
|---|---|
| author | Xin Jin Xin Jin Haowei Jiao Chao Zhang Mingyong Li Bo Zhao Guowei Liu Jiangtao Ji |
| author_facet | Xin Jin Xin Jin Haowei Jiao Chao Zhang Mingyong Li Bo Zhao Guowei Liu Jiangtao Ji |
| author_sort | Xin Jin |
| collection | DOAJ |
| description | Achieving intelligent detection of defective leaves of hydroponic lettuce after harvesting is of great significance for ensuring the quality and value of hydroponic lettuce. In order to improve the detection accuracy and efficiency of hydroponic lettuce defective leaves, firstly, an image acquisition system is designed and used to complete image acquisition for defective leaves of hydroponic lettuce. Secondly, this study proposed EBG_YOLOv5 model which optimized the YOLOv5 model by integrating the attention mechanism ECA in the backbone and introducing bidirectional feature pyramid and GSConv modules in the neck. Finally, the performance of the improved model was verified by ablation experiments and comparison experiments. The experimental results proved that, the Precision, Recall rate and mAP0.5 of the EBG_YOLOv5 were 0.1%, 2.0% and 2.6% higher than those of YOLOv5s, respectively, while the model size, GFLOPs and Parameters are reduced by 15.3%, 18.9% and 16.3%. Meanwhile, the accuracy and model size of EBG_YOLOv5 were higher and smaller compared with other detection algorithms. This indicates that the EBG_YOLOv5 being applied to hydroponic lettuce defective leaves detection can achieve better performance. It can provide technical support for the subsequent research of lettuce intelligent nondestructive classification equipment. |
| first_indexed | 2024-03-11T15:33:55Z |
| format | Article |
| id | doaj.art-3912c8e176494ba286c7b0c691cb4b36 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-11T15:33:55Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-3912c8e176494ba286c7b0c691cb4b362023-10-27T00:23:51ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-10-011410.3389/fpls.2023.12423371242337Hydroponic lettuce defective leaves identification based on improved YOLOv5sXin Jin0Xin Jin1Haowei Jiao2Chao Zhang3Mingyong Li4Bo Zhao5Guowei Liu6Jiangtao Ji7College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, ChinaScience and Technology Innovation Center for Completed Set Equipment, Longmen Laboratory, Luoyang, ChinaCollege of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, ChinaCollege of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, ChinaState Key Laboratory of Soil - Plant - Machine System Technology, Chinese Academy of Agricultural Mechanization Sciences, Beijing, ChinaEponic Agriculture Co., Ltd, Zhuhai, ChinaCollege of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, ChinaAchieving intelligent detection of defective leaves of hydroponic lettuce after harvesting is of great significance for ensuring the quality and value of hydroponic lettuce. In order to improve the detection accuracy and efficiency of hydroponic lettuce defective leaves, firstly, an image acquisition system is designed and used to complete image acquisition for defective leaves of hydroponic lettuce. Secondly, this study proposed EBG_YOLOv5 model which optimized the YOLOv5 model by integrating the attention mechanism ECA in the backbone and introducing bidirectional feature pyramid and GSConv modules in the neck. Finally, the performance of the improved model was verified by ablation experiments and comparison experiments. The experimental results proved that, the Precision, Recall rate and mAP0.5 of the EBG_YOLOv5 were 0.1%, 2.0% and 2.6% higher than those of YOLOv5s, respectively, while the model size, GFLOPs and Parameters are reduced by 15.3%, 18.9% and 16.3%. Meanwhile, the accuracy and model size of EBG_YOLOv5 were higher and smaller compared with other detection algorithms. This indicates that the EBG_YOLOv5 being applied to hydroponic lettuce defective leaves detection can achieve better performance. It can provide technical support for the subsequent research of lettuce intelligent nondestructive classification equipment.https://www.frontiersin.org/articles/10.3389/fpls.2023.1242337/fulldefect detectionEBG_YOLOv5ECABiFPNGSConv |
| spellingShingle | Xin Jin Xin Jin Haowei Jiao Chao Zhang Mingyong Li Bo Zhao Guowei Liu Jiangtao Ji Hydroponic lettuce defective leaves identification based on improved YOLOv5s Frontiers in Plant Science defect detection EBG_YOLOv5 ECA BiFPN GSConv |
| title | Hydroponic lettuce defective leaves identification based on improved YOLOv5s |
| title_full | Hydroponic lettuce defective leaves identification based on improved YOLOv5s |
| title_fullStr | Hydroponic lettuce defective leaves identification based on improved YOLOv5s |
| title_full_unstemmed | Hydroponic lettuce defective leaves identification based on improved YOLOv5s |
| title_short | Hydroponic lettuce defective leaves identification based on improved YOLOv5s |
| title_sort | hydroponic lettuce defective leaves identification based on improved yolov5s |
| topic | defect detection EBG_YOLOv5 ECA BiFPN GSConv |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1242337/full |
| work_keys_str_mv | AT xinjin hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s AT xinjin hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s AT haoweijiao hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s AT chaozhang hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s AT mingyongli hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s AT bozhao hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s AT guoweiliu hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s AT jiangtaoji hydroponiclettucedefectiveleavesidentificationbasedonimprovedyolov5s |