Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7
Traditional maize seedling detection mainly relies on manual observation and experience, which is time-consuming and prone to errors. With the rapid development of deep learning and object-detection technology, we propose a lightweight model LW-YOLOv7 to address the above issues. The new model can b...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/13/7731 |
| _version_ | 1797592109487751168 |
|---|---|
| author | Kai Zhao Lulu Zhao Yanan Zhao Hanbing Deng |
| author_facet | Kai Zhao Lulu Zhao Yanan Zhao Hanbing Deng |
| author_sort | Kai Zhao |
| collection | DOAJ |
| description | Traditional maize seedling detection mainly relies on manual observation and experience, which is time-consuming and prone to errors. With the rapid development of deep learning and object-detection technology, we propose a lightweight model LW-YOLOv7 to address the above issues. The new model can be deployed on mobile devices with limited memory and real-time detection of maize seedlings in the field. LW-YOLOv7 is based on YOLOv7 but incorporates GhostNet as the backbone network to reduce parameters. The Convolutional Block Attention Module (CBAM) enhances the network’s attention to the target region. In the head of the model, the Path Aggregation Network (PANet) is replaced with a Bi-Directional Feature Pyramid Network (BiFPN) to improve semantic and location information. The SIoU loss function is used during training to enhance bounding box regression speed and detection accuracy. Experimental results reveal that LW-YOLOv7 outperforms YOLOv7 in terms of accuracy and parameter reduction. Compared to other object-detection models like Faster RCNN, YOLOv3, YOLOv4, and YOLOv5l, LW-YOLOv7 demonstrates increased accuracy, reduced parameters, and improved detection speed. The results indicate that LW-YOLOv7 is suitable for real-time object detection of maize seedlings in field environments and provides a practical solution for efficiently counting the number of seedling maize plants. |
| first_indexed | 2024-03-11T01:46:48Z |
| format | Article |
| id | doaj.art-18c36867720b4fa0927f93901a881798 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T01:46:48Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-18c36867720b4fa0927f93901a8817982023-11-18T16:10:35ZengMDPI AGApplied Sciences2076-34172023-06-011313773110.3390/app13137731Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7Kai Zhao0Lulu Zhao1Yanan Zhao2Hanbing Deng3College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, ChinaCollege of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, ChinaCollege of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, ChinaCollege of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, ChinaTraditional maize seedling detection mainly relies on manual observation and experience, which is time-consuming and prone to errors. With the rapid development of deep learning and object-detection technology, we propose a lightweight model LW-YOLOv7 to address the above issues. The new model can be deployed on mobile devices with limited memory and real-time detection of maize seedlings in the field. LW-YOLOv7 is based on YOLOv7 but incorporates GhostNet as the backbone network to reduce parameters. The Convolutional Block Attention Module (CBAM) enhances the network’s attention to the target region. In the head of the model, the Path Aggregation Network (PANet) is replaced with a Bi-Directional Feature Pyramid Network (BiFPN) to improve semantic and location information. The SIoU loss function is used during training to enhance bounding box regression speed and detection accuracy. Experimental results reveal that LW-YOLOv7 outperforms YOLOv7 in terms of accuracy and parameter reduction. Compared to other object-detection models like Faster RCNN, YOLOv3, YOLOv4, and YOLOv5l, LW-YOLOv7 demonstrates increased accuracy, reduced parameters, and improved detection speed. The results indicate that LW-YOLOv7 is suitable for real-time object detection of maize seedlings in field environments and provides a practical solution for efficiently counting the number of seedling maize plants.https://www.mdpi.com/2076-3417/13/13/7731YOLOv7seedling maizedetection modellightweightattention models |
| spellingShingle | Kai Zhao Lulu Zhao Yanan Zhao Hanbing Deng Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7 Applied Sciences YOLOv7 seedling maize detection model lightweight attention models |
| title | Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7 |
| title_full | Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7 |
| title_fullStr | Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7 |
| title_full_unstemmed | Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7 |
| title_short | Study on Lightweight Model of Maize Seedling Object Detection Based on YOLOv7 |
| title_sort | study on lightweight model of maize seedling object detection based on yolov7 |
| topic | YOLOv7 seedling maize detection model lightweight attention models |
| url | https://www.mdpi.com/2076-3417/13/13/7731 |
| work_keys_str_mv | AT kaizhao studyonlightweightmodelofmaizeseedlingobjectdetectionbasedonyolov7 AT luluzhao studyonlightweightmodelofmaizeseedlingobjectdetectionbasedonyolov7 AT yananzhao studyonlightweightmodelofmaizeseedlingobjectdetectionbasedonyolov7 AT hanbingdeng studyonlightweightmodelofmaizeseedlingobjectdetectionbasedonyolov7 |