GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural Environments
Effective fruit identification and maturity detection are important for harvesting and managing tomatoes. Current deep learning detection algorithms typically demand significant computational resources and memory. Detecting severely stacked and obscured tomatoes in unstructured natural environments...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/5/1502 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850222733490651136 |
|---|---|
| author | Yaolin Dong Jinwei Qiao Na Liu Yunze He Shuzan Li Xucai Hu Chengyan Yu Chengyu Zhang |
| author_facet | Yaolin Dong Jinwei Qiao Na Liu Yunze He Shuzan Li Xucai Hu Chengyan Yu Chengyu Zhang |
| author_sort | Yaolin Dong |
| collection | DOAJ |
| description | Effective fruit identification and maturity detection are important for harvesting and managing tomatoes. Current deep learning detection algorithms typically demand significant computational resources and memory. Detecting severely stacked and obscured tomatoes in unstructured natural environments is challenging because of target stacking, target occlusion, natural illumination, and background noise. The proposed method involves a new lightweight model called GPC-YOLO based on YOLOv8n for tomato identification and maturity detection. This study proposes a C2f-PC module based on partial convolution (PConv) for less computation, which replaced the original C2f feature extraction module of YOLOv8n. The regular convolution was replaced with the lightweight Grouped Spatial Convolution (GSConv) by downsampling to reduce the computational burden. The neck network was replaced with the convolutional neural network-based cross-scale feature fusion (CCFF) module to enhance the adaptability of the model to scale changes and to detect many small-scaled objects. Additionally, the integration of the simple attention mechanism (SimAM) and efficient intersection over union (EIoU) loss were implemented to further enhance the detection accuracy by leveraging these lightweight improvements. The GPC-YOLO model was trained and validated on a dataset of 1249 mobile phone images of tomatoes. Compared to the original YOLOv8n, GPC-YOLO achieved high-performance metrics, e.g., reducing the parameter number to 1.2 M (by 59.9%), compressing the model size to 2.7 M (by 57.1%), decreasing the floating point of operations to 4.5 G (by 45.1%), and improving the accuracy to 98.7% (by 0.3%), with a detection speed of 201 FPS. This study showed that GPC-YOLO could effectively identify tomato fruit and detect fruit maturity in unstructured natural environments. The model has immense potential for tomato ripeness detection and automated picking applications. |
| format | Article |
| id | doaj-art-09c5a593ec2c4c47b04187dd68b6fa02 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-09c5a593ec2c4c47b04187dd68b6fa022025-08-20T02:06:15ZengMDPI AGSensors1424-82202025-02-01255150210.3390/s25051502GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural EnvironmentsYaolin Dong0Jinwei Qiao1Na Liu2Yunze He3Shuzan Li4Xucai Hu5Chengyan Yu6Chengyu Zhang7School of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaSchool of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaEffective fruit identification and maturity detection are important for harvesting and managing tomatoes. Current deep learning detection algorithms typically demand significant computational resources and memory. Detecting severely stacked and obscured tomatoes in unstructured natural environments is challenging because of target stacking, target occlusion, natural illumination, and background noise. The proposed method involves a new lightweight model called GPC-YOLO based on YOLOv8n for tomato identification and maturity detection. This study proposes a C2f-PC module based on partial convolution (PConv) for less computation, which replaced the original C2f feature extraction module of YOLOv8n. The regular convolution was replaced with the lightweight Grouped Spatial Convolution (GSConv) by downsampling to reduce the computational burden. The neck network was replaced with the convolutional neural network-based cross-scale feature fusion (CCFF) module to enhance the adaptability of the model to scale changes and to detect many small-scaled objects. Additionally, the integration of the simple attention mechanism (SimAM) and efficient intersection over union (EIoU) loss were implemented to further enhance the detection accuracy by leveraging these lightweight improvements. The GPC-YOLO model was trained and validated on a dataset of 1249 mobile phone images of tomatoes. Compared to the original YOLOv8n, GPC-YOLO achieved high-performance metrics, e.g., reducing the parameter number to 1.2 M (by 59.9%), compressing the model size to 2.7 M (by 57.1%), decreasing the floating point of operations to 4.5 G (by 45.1%), and improving the accuracy to 98.7% (by 0.3%), with a detection speed of 201 FPS. This study showed that GPC-YOLO could effectively identify tomato fruit and detect fruit maturity in unstructured natural environments. The model has immense potential for tomato ripeness detection and automated picking applications.https://www.mdpi.com/1424-8220/25/5/1502YOLOv8lightweighttomatomaturityC2f-PC |
| spellingShingle | Yaolin Dong Jinwei Qiao Na Liu Yunze He Shuzan Li Xucai Hu Chengyan Yu Chengyu Zhang GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural Environments Sensors YOLOv8 lightweight tomato maturity C2f-PC |
| title | GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural Environments |
| title_full | GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural Environments |
| title_fullStr | GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural Environments |
| title_full_unstemmed | GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural Environments |
| title_short | GPC-YOLO: An Improved Lightweight YOLOv8n Network for the Detection of Tomato Maturity in Unstructured Natural Environments |
| title_sort | gpc yolo an improved lightweight yolov8n network for the detection of tomato maturity in unstructured natural environments |
| topic | YOLOv8 lightweight tomato maturity C2f-PC |
| url | https://www.mdpi.com/1424-8220/25/5/1502 |
| work_keys_str_mv | AT yaolindong gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments AT jinweiqiao gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments AT naliu gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments AT yunzehe gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments AT shuzanli gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments AT xucaihu gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments AT chengyanyu gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments AT chengyuzhang gpcyoloanimprovedlightweightyolov8nnetworkforthedetectionoftomatomaturityinunstructurednaturalenvironments |