Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model

In seedling cultivation of hybrid rice, fast estimation of seedling density is of great significance for classifying seedling cultivation. This research presents an improved YOLOv8 model for estimating seedling density at the needle leaf stage. Firstly, the auxiliary frame technology was used to add...

Full description

Saved in:
Bibliographic Details
Main Authors: Zehua Li, Yongjun Lin, Yihui Pan, Xu Ma, Xiaola Wu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/14/12/3066
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850042332302278656
author Zehua Li
Yongjun Lin
Yihui Pan
Xu Ma
Xiaola Wu
author_facet Zehua Li
Yongjun Lin
Yihui Pan
Xu Ma
Xiaola Wu
author_sort Zehua Li
collection DOAJ
description In seedling cultivation of hybrid rice, fast estimation of seedling density is of great significance for classifying seedling cultivation. This research presents an improved YOLOv8 model for estimating seedling density at the needle leaf stage. Firstly, the auxiliary frame technology was used to address the problem of locating the detection area of seedlings. Secondly, the Standard Convolution (SConv) layers in the neck network were replaced by the Group Shuffle Convolution (GSConv) layer to lightweight the model. A dynamic head module was added to the head network to enhance the capability of the model to identify seedlings. The CIoU loss function was replaced by the EIoU loss function, enhancing the convergence speed of the model. The results showed that the improved model achieved an average precision of 96.4%; the parameters and floating-point computations (FLOPs) were 7.2 M and 2.4 G. In contrast with the original model, the parameters and FLOPs were reduced by 0.9 M and 0.6 G, and the average precision was improved by 1.9%. Compared with state-of-the-art models such as YOLOv7 et al., the improved YOLOv8 achieved preferred comprehensive performance. Finally, a fast estimation system for hybrid rice seedling density was developed using a smartphone and the improved YOLOv8. The average inference time for each image was 8.5 ms, and the average relative error of detection was 4.98%. The fast estimation system realized portable real-time detection of seedling density, providing technical support for classifying seedling cultivation of hybrid rice.
format Article
id doaj-art-d945866f0f584fc1900ec41aed24e811
institution DOAJ
issn 2073-4395
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-d945866f0f584fc1900ec41aed24e8112025-08-20T02:55:35ZengMDPI AGAgronomy2073-43952024-12-011412306610.3390/agronomy14123066Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 ModelZehua Li0Yongjun Lin1Yihui Pan2Xu Ma3Xiaola Wu4College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, ChinaSchool of Engineering, South China Agricultural University, Guangzhou 510642, ChinaSchool of Artificial Intelligence, Zhujiang College, South China Agricultural University, Guangzhou 510900, ChinaIn seedling cultivation of hybrid rice, fast estimation of seedling density is of great significance for classifying seedling cultivation. This research presents an improved YOLOv8 model for estimating seedling density at the needle leaf stage. Firstly, the auxiliary frame technology was used to address the problem of locating the detection area of seedlings. Secondly, the Standard Convolution (SConv) layers in the neck network were replaced by the Group Shuffle Convolution (GSConv) layer to lightweight the model. A dynamic head module was added to the head network to enhance the capability of the model to identify seedlings. The CIoU loss function was replaced by the EIoU loss function, enhancing the convergence speed of the model. The results showed that the improved model achieved an average precision of 96.4%; the parameters and floating-point computations (FLOPs) were 7.2 M and 2.4 G. In contrast with the original model, the parameters and FLOPs were reduced by 0.9 M and 0.6 G, and the average precision was improved by 1.9%. Compared with state-of-the-art models such as YOLOv7 et al., the improved YOLOv8 achieved preferred comprehensive performance. Finally, a fast estimation system for hybrid rice seedling density was developed using a smartphone and the improved YOLOv8. The average inference time for each image was 8.5 ms, and the average relative error of detection was 4.98%. The fast estimation system realized portable real-time detection of seedling density, providing technical support for classifying seedling cultivation of hybrid rice.https://www.mdpi.com/2073-4395/14/12/3066seedling density estimationdeep learningobject detectionclassification of seedlingsmechanized seedling cultivation
spellingShingle Zehua Li
Yongjun Lin
Yihui Pan
Xu Ma
Xiaola Wu
Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model
Agronomy
seedling density estimation
deep learning
object detection
classification of seedlings
mechanized seedling cultivation
title Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model
title_full Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model
title_fullStr Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model
title_full_unstemmed Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model
title_short Fast and Accurate Density Estimation of Hybrid Rice Seedlings Using a Smartphone and an Improved YOLOv8 Model
title_sort fast and accurate density estimation of hybrid rice seedlings using a smartphone and an improved yolov8 model
topic seedling density estimation
deep learning
object detection
classification of seedlings
mechanized seedling cultivation
url https://www.mdpi.com/2073-4395/14/12/3066
work_keys_str_mv AT zehuali fastandaccuratedensityestimationofhybridriceseedlingsusingasmartphoneandanimprovedyolov8model
AT yongjunlin fastandaccuratedensityestimationofhybridriceseedlingsusingasmartphoneandanimprovedyolov8model
AT yihuipan fastandaccuratedensityestimationofhybridriceseedlingsusingasmartphoneandanimprovedyolov8model
AT xuma fastandaccuratedensityestimationofhybridriceseedlingsusingasmartphoneandanimprovedyolov8model
AT xiaolawu fastandaccuratedensityestimationofhybridriceseedlingsusingasmartphoneandanimprovedyolov8model