A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields
To address the issue of the computational intensity and deployment difficulties associated with weed detection models, a lightweight target detection model for weeds based on YOLOv8s in maize fields was proposed in this study. Firstly, a lightweight network, designated as Dualconv High Performance G...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/12/3062 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850239877938937856 |
|---|---|
| author | Jinyong Huang Xu Xia Zhihua Diao Xingyi Li Suna Zhao Jingcheng Zhang Baohua Zhang Guoqiang Li |
| author_facet | Jinyong Huang Xu Xia Zhihua Diao Xingyi Li Suna Zhao Jingcheng Zhang Baohua Zhang Guoqiang Li |
| author_sort | Jinyong Huang |
| collection | DOAJ |
| description | To address the issue of the computational intensity and deployment difficulties associated with weed detection models, a lightweight target detection model for weeds based on YOLOv8s in maize fields was proposed in this study. Firstly, a lightweight network, designated as Dualconv High Performance GPU Net (D-PP-HGNet), was constructed on the foundation of the High Performance GPU Net (PP-HGNet) framework. Dualconv was introduced to reduce the computation required to achieve a lightweight design. Furthermore, Adaptive Feature Aggregation Module (AFAM) and Global Max Pooling were incorporated to augment the extraction of salient features in complex scenarios. Then, the newly created network was used to reconstruct the YOLOv8s backbone. Secondly, a four-stage inverted residual moving block (iRMB) was employed to construct a lightweight iDEMA module, which was used to replace the original C2f feature extraction module in the Neck to improve model performance and accuracy. Finally, Dualconv was employed instead of the conventional convolution for downsampling, further diminishing the network load. The new model was fully verified using the established field weed dataset. The test results showed that the modified model exhibited a notable improvement in detection performance compared with YOLOv8s. Accuracy improved from 91.2% to 95.8%, recall from 87.9% to 93.2%, and mAP@0.5 from 90.8% to 94.5%. Furthermore, the number of GFLOPs and the model size were reduced to 12.7 G and 9.1 MB, respectively, representing a decrease of 57.4% and 59.2% compared to the original model. Compared with the prevalent target detection models, such as Faster R-CNN, YOLOv5s, and YOLOv8l, the new model showed superior performance in accuracy and lightweight. The new model proposed in this paper effectively reduces the cost of the required hardware to achieve accurate weed identification in maize fields with limited resources. |
| format | Article |
| id | doaj-art-c80c3e44e28a41febcb2f796c45d8d90 |
| institution | OA Journals |
| issn | 2073-4395 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-c80c3e44e28a41febcb2f796c45d8d902025-08-20T02:01:01ZengMDPI AGAgronomy2073-43952024-12-011412306210.3390/agronomy14123062A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize FieldsJinyong Huang0Xu Xia1Zhihua Diao2Xingyi Li3Suna Zhao4Jingcheng Zhang5Baohua Zhang6Guoqiang Li7School of Agricultural Sciences, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Agricultural Sciences, Zhengzhou University, Zhengzhou 450001, ChinaCollege of Electrical Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaCollege of Electrical Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaCollege of Electrical Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaCollege of Artificial Intelligence, Nanjing Agricultural University, Nanjing 211800, ChinaKey Laboratory of Huang-Huai-Hai Smart Agricultural Technology, Ministry of Agriculture and Rural Affairs, Zhengzhou 450002, ChinaTo address the issue of the computational intensity and deployment difficulties associated with weed detection models, a lightweight target detection model for weeds based on YOLOv8s in maize fields was proposed in this study. Firstly, a lightweight network, designated as Dualconv High Performance GPU Net (D-PP-HGNet), was constructed on the foundation of the High Performance GPU Net (PP-HGNet) framework. Dualconv was introduced to reduce the computation required to achieve a lightweight design. Furthermore, Adaptive Feature Aggregation Module (AFAM) and Global Max Pooling were incorporated to augment the extraction of salient features in complex scenarios. Then, the newly created network was used to reconstruct the YOLOv8s backbone. Secondly, a four-stage inverted residual moving block (iRMB) was employed to construct a lightweight iDEMA module, which was used to replace the original C2f feature extraction module in the Neck to improve model performance and accuracy. Finally, Dualconv was employed instead of the conventional convolution for downsampling, further diminishing the network load. The new model was fully verified using the established field weed dataset. The test results showed that the modified model exhibited a notable improvement in detection performance compared with YOLOv8s. Accuracy improved from 91.2% to 95.8%, recall from 87.9% to 93.2%, and mAP@0.5 from 90.8% to 94.5%. Furthermore, the number of GFLOPs and the model size were reduced to 12.7 G and 9.1 MB, respectively, representing a decrease of 57.4% and 59.2% compared to the original model. Compared with the prevalent target detection models, such as Faster R-CNN, YOLOv5s, and YOLOv8l, the new model showed superior performance in accuracy and lightweight. The new model proposed in this paper effectively reduces the cost of the required hardware to achieve accurate weed identification in maize fields with limited resources.https://www.mdpi.com/2073-4395/14/12/3062weed detectionYOLOv8sattention mechanismlightweight modeltarget detection |
| spellingShingle | Jinyong Huang Xu Xia Zhihua Diao Xingyi Li Suna Zhao Jingcheng Zhang Baohua Zhang Guoqiang Li A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields Agronomy weed detection YOLOv8s attention mechanism lightweight model target detection |
| title | A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields |
| title_full | A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields |
| title_fullStr | A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields |
| title_full_unstemmed | A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields |
| title_short | A Lightweight Model for Weed Detection Based on the Improved YOLOv8s Network in Maize Fields |
| title_sort | lightweight model for weed detection based on the improved yolov8s network in maize fields |
| topic | weed detection YOLOv8s attention mechanism lightweight model target detection |
| url | https://www.mdpi.com/2073-4395/14/12/3062 |
| work_keys_str_mv | AT jinyonghuang alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT xuxia alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT zhihuadiao alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT xingyili alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT sunazhao alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT jingchengzhang alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT baohuazhang alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT guoqiangli alightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT jinyonghuang lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT xuxia lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT zhihuadiao lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT xingyili lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT sunazhao lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT jingchengzhang lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT baohuazhang lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields AT guoqiangli lightweightmodelforweeddetectionbasedontheimprovedyolov8snetworkinmaizefields |