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...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaolin Dong, Jinwei Qiao, Na Liu, Yunze He, Shuzan Li, Xucai Hu, Chengyan Yu, Chengyu Zhang
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