Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7
In response to the poor detection performance of grapes in orchards caused by issues such as leaf occlusion and fruit overlap, this study proposes an improved grape detection method named YOLOv7-MCSF based on the You Only Look Once v7 (YOLOv7) framework. Firstly, the original backbone network is rep...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/1/42 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589487110094848 |
|---|---|
| author | Fuchun Sun Qiurong Lv Yuechao Bian Renwei He Dong Lv Leina Gao Haorong Wu Xiaoxiao Li |
| author_facet | Fuchun Sun Qiurong Lv Yuechao Bian Renwei He Dong Lv Leina Gao Haorong Wu Xiaoxiao Li |
| author_sort | Fuchun Sun |
| collection | DOAJ |
| description | In response to the poor detection performance of grapes in orchards caused by issues such as leaf occlusion and fruit overlap, this study proposes an improved grape detection method named YOLOv7-MCSF based on the You Only Look Once v7 (YOLOv7) framework. Firstly, the original backbone network is replaced with MobileOne to achieve a lightweight improvement of the model, thereby reducing the number of parameters. In addition, a Channel Attention (CA) module was added to the neck network to reduce interference from the orchard background and to accelerate the inference speed. Secondly, the SPPFCSPC pyramid pooling is embedded to enhance the speed of image feature fusion while maintaining a consistent receptive field. Finally, the Focal-EIoU loss function is employed to optimize the regression prediction boxes, accelerating their convergence and improving regression accuracy. The experimental results indicate that, compared to the original YOLOv7 model, the YOLOv7-MCSF model achieves a 26.9% reduction in weight, an increase in frame rate of 21.57 f/s, and improvements in precision, recall, and mAP of 2.4%, 1.8%, and 3.5%, respectively. The improved model can efficiently and in real-time identify grape clusters, providing technical support for the deployment of mobile devices and embedded grape detection systems in orchard environments. |
| format | Article |
| id | doaj-art-9925da98a33d48679ef0833bc10df26c |
| institution | Kabale University |
| issn | 2073-4395 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-9925da98a33d48679ef0833bc10df26c2025-01-24T13:16:28ZengMDPI AGAgronomy2073-43952024-12-011514210.3390/agronomy15010042Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7Fuchun Sun0Qiurong Lv1Yuechao Bian2Renwei He3Dong Lv4Leina Gao5Haorong Wu6Xiaoxiao Li7Entrepreneurship College, Chengdu University, Chengdu 610106, ChinaEntrepreneurship College, Chengdu University, Chengdu 610106, ChinaSchool of Mechanical Engineering, Chengdu University, Chengdu 610106, ChinaEngineering & Technical College, Chengdu University of Technology, Chengdu 610059, ChinaChengdu Institute of Metrology Verification and Testing, Chengdu 610000, ChinaEntrepreneurship College, Chengdu University, Chengdu 610106, ChinaSchool of Electronic Information and Electrical Engineering, Chengdu University, Chengdu 610106, ChinaSchool of Mechanical Engineering, Chengdu University, Chengdu 610106, ChinaIn response to the poor detection performance of grapes in orchards caused by issues such as leaf occlusion and fruit overlap, this study proposes an improved grape detection method named YOLOv7-MCSF based on the You Only Look Once v7 (YOLOv7) framework. Firstly, the original backbone network is replaced with MobileOne to achieve a lightweight improvement of the model, thereby reducing the number of parameters. In addition, a Channel Attention (CA) module was added to the neck network to reduce interference from the orchard background and to accelerate the inference speed. Secondly, the SPPFCSPC pyramid pooling is embedded to enhance the speed of image feature fusion while maintaining a consistent receptive field. Finally, the Focal-EIoU loss function is employed to optimize the regression prediction boxes, accelerating their convergence and improving regression accuracy. The experimental results indicate that, compared to the original YOLOv7 model, the YOLOv7-MCSF model achieves a 26.9% reduction in weight, an increase in frame rate of 21.57 f/s, and improvements in precision, recall, and mAP of 2.4%, 1.8%, and 3.5%, respectively. The improved model can efficiently and in real-time identify grape clusters, providing technical support for the deployment of mobile devices and embedded grape detection systems in orchard environments.https://www.mdpi.com/2073-4395/15/1/42image processinggrape target detectionYOLOv7lightweight network |
| spellingShingle | Fuchun Sun Qiurong Lv Yuechao Bian Renwei He Dong Lv Leina Gao Haorong Wu Xiaoxiao Li Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7 Agronomy image processing grape target detection YOLOv7 lightweight network |
| title | Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7 |
| title_full | Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7 |
| title_fullStr | Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7 |
| title_full_unstemmed | Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7 |
| title_short | Grape Target Detection Method in Orchard Environment Based on Improved YOLOv7 |
| title_sort | grape target detection method in orchard environment based on improved yolov7 |
| topic | image processing grape target detection YOLOv7 lightweight network |
| url | https://www.mdpi.com/2073-4395/15/1/42 |
| work_keys_str_mv | AT fuchunsun grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 AT qiuronglv grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 AT yuechaobian grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 AT renweihe grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 AT donglv grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 AT leinagao grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 AT haorongwu grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 AT xiaoxiaoli grapetargetdetectionmethodinorchardenvironmentbasedonimprovedyolov7 |