YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection
Fusarium head blight (FHB) is a destructive disease that affects wheat production. Detecting FHB accurately and rapidly is crucial for improving wheat yield. Traditional models are difficult to apply to mobile devices due to large parameters, high computation, and resource requirements. Therefore, t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2024-03-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1948.pdf |
| _version_ | 1797234681615220736 |
|---|---|
| author | Chengkai Yang Xiaoyun Sun Jian Wang Haiyan Lv Ping Dong Lei Xi Lei Shi |
| author_facet | Chengkai Yang Xiaoyun Sun Jian Wang Haiyan Lv Ping Dong Lei Xi Lei Shi |
| author_sort | Chengkai Yang |
| collection | DOAJ |
| description | Fusarium head blight (FHB) is a destructive disease that affects wheat production. Detecting FHB accurately and rapidly is crucial for improving wheat yield. Traditional models are difficult to apply to mobile devices due to large parameters, high computation, and resource requirements. Therefore, this article proposes a lightweight detection method based on an improved YOLOv8s to facilitate the rapid deployment of the model on mobile terminals and improve the detection efficiency of wheat FHB. The proposed method introduced a C-FasterNet module, which replaced the C2f module in the backbone network. It helps reduce the number of parameters and the computational volume of the model. Additionally, the Conv in the backbone network is replaced with GhostConv, further reducing parameters and computation without significantly affecting detection accuracy. Thirdly, the introduction of the Focal CIoU loss function reduces the impact of sample imbalance on the detection results and accelerates the model convergence. Lastly, the large target detection head was removed from the model for lightweight. The experimental results show that the size of the improved model (YOLOv8s-CGF) is only 11.7 M, which accounts for 52.0% of the original model (YOLOv8s). The number of parameters is only 5.7 × 106 M, equivalent to 51.4% of the original model. The computational volume is only 21.1 GFLOPs, representing 74.3% of the original model. Moreover, the mean average precision (mAP@0.5) of the model is 99.492%, which is 0.003% higher than the original model, and the mAP@0.5:0.95 is 0.269% higher than the original model. Compared to other YOLO models, the improved lightweight model not only achieved the highest detection precision but also significantly reduced the number of parameters and model size. This provides a valuable reference for FHB detection in wheat ears and deployment on mobile terminals in field environments. |
| first_indexed | 2024-04-24T16:35:56Z |
| format | Article |
| id | doaj.art-55106347320642598bcd15761af220a5 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-04-24T16:35:56Z |
| publishDate | 2024-03-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-55106347320642598bcd15761af220a52024-03-29T15:05:16ZengPeerJ Inc.PeerJ Computer Science2376-59922024-03-0110e194810.7717/peerj-cs.1948YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detectionChengkai Yang0Xiaoyun Sun1Jian Wang2Haiyan Lv3Ping Dong4Lei Xi5Lei Shi6College of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan, ChinaFusarium head blight (FHB) is a destructive disease that affects wheat production. Detecting FHB accurately and rapidly is crucial for improving wheat yield. Traditional models are difficult to apply to mobile devices due to large parameters, high computation, and resource requirements. Therefore, this article proposes a lightweight detection method based on an improved YOLOv8s to facilitate the rapid deployment of the model on mobile terminals and improve the detection efficiency of wheat FHB. The proposed method introduced a C-FasterNet module, which replaced the C2f module in the backbone network. It helps reduce the number of parameters and the computational volume of the model. Additionally, the Conv in the backbone network is replaced with GhostConv, further reducing parameters and computation without significantly affecting detection accuracy. Thirdly, the introduction of the Focal CIoU loss function reduces the impact of sample imbalance on the detection results and accelerates the model convergence. Lastly, the large target detection head was removed from the model for lightweight. The experimental results show that the size of the improved model (YOLOv8s-CGF) is only 11.7 M, which accounts for 52.0% of the original model (YOLOv8s). The number of parameters is only 5.7 × 106 M, equivalent to 51.4% of the original model. The computational volume is only 21.1 GFLOPs, representing 74.3% of the original model. Moreover, the mean average precision (mAP@0.5) of the model is 99.492%, which is 0.003% higher than the original model, and the mAP@0.5:0.95 is 0.269% higher than the original model. Compared to other YOLO models, the improved lightweight model not only achieved the highest detection precision but also significantly reduced the number of parameters and model size. This provides a valuable reference for FHB detection in wheat ears and deployment on mobile terminals in field environments.https://peerj.com/articles/cs-1948.pdfFusarium head blightYOLOv8sImage recognitionLightweight modelLoss function |
| spellingShingle | Chengkai Yang Xiaoyun Sun Jian Wang Haiyan Lv Ping Dong Lei Xi Lei Shi YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection PeerJ Computer Science Fusarium head blight YOLOv8s Image recognition Lightweight model Loss function |
| title | YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection |
| title_full | YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection |
| title_fullStr | YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection |
| title_full_unstemmed | YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection |
| title_short | YOLOv8s-CGF: a lightweight model for wheat ear Fusarium head blight detection |
| title_sort | yolov8s cgf a lightweight model for wheat ear fusarium head blight detection |
| topic | Fusarium head blight YOLOv8s Image recognition Lightweight model Loss function |
| url | https://peerj.com/articles/cs-1948.pdf |
| work_keys_str_mv | AT chengkaiyang yolov8scgfalightweightmodelforwheatearfusariumheadblightdetection AT xiaoyunsun yolov8scgfalightweightmodelforwheatearfusariumheadblightdetection AT jianwang yolov8scgfalightweightmodelforwheatearfusariumheadblightdetection AT haiyanlv yolov8scgfalightweightmodelforwheatearfusariumheadblightdetection AT pingdong yolov8scgfalightweightmodelforwheatearfusariumheadblightdetection AT leixi yolov8scgfalightweightmodelforwheatearfusariumheadblightdetection AT leishi yolov8scgfalightweightmodelforwheatearfusariumheadblightdetection |