A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images
Litchi flowering management is an important link in litchi orchard management. Statistical litchi flowering rate data can provide an important reference for regulating the number of litchi flowers and directly determining the quality and yield of litchi fruit. At present, the statistical work regard...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-08-01
|
Series: | Frontiers in Plant Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.966639/full |
_version_ | 1811286867293765632 |
---|---|
author | Peiyi Lin Denghui Li Yuhang Jia Yingyi Chen Guangwen Huang Hamza Elkhouchlaa Zhongwei Yao Zhengqi Zhou Haobo Zhou Jun Li Jun Li Huazhong Lu |
author_facet | Peiyi Lin Denghui Li Yuhang Jia Yingyi Chen Guangwen Huang Hamza Elkhouchlaa Zhongwei Yao Zhengqi Zhou Haobo Zhou Jun Li Jun Li Huazhong Lu |
author_sort | Peiyi Lin |
collection | DOAJ |
description | Litchi flowering management is an important link in litchi orchard management. Statistical litchi flowering rate data can provide an important reference for regulating the number of litchi flowers and directly determining the quality and yield of litchi fruit. At present, the statistical work regarding litchi flowering rates requires considerable labour costs. Therefore, this study aims at the statistical litchi flowering rate task, and a combination of unmanned aerial vehicle (UAV) images and computer vision technology is proposed to count the numbers of litchi flower clusters and flushes in a complex natural environment to improve the efficiency of litchi flowering rate estimation. First, RGB images of litchi canopies at the flowering stage are collected by a UAV. After performing image preprocessing, a dataset is established, and two types of objects in the images, namely, flower clusters and flushes, are manually labelled. Second, by comparing the pretraining and testing results obtained when setting different training parameters for the YOLOv4 model, the optimal parameter combination is determined. The YOLOv4 model trained with the optimal combination of parameters tests best on the test set, at which time the mean average precision (mAP) is 87.87%. The detection time required for a single image is 0.043 s. Finally, aiming at the two kinds of targets (flower clusters and flushes) on 8 litchi trees in a real orchard, a model for estimating the numbers of flower clusters and flushes on a single litchi tree is constructed by matching the identified number of targets with the actual number of targets via equation fitting. Then, the data obtained from the manual counting process and the estimation model for the other five litchi trees in the real orchard are statistically analysed. The average error rate for the number of flower clusters is 4.20%, the average error rate for the number of flushes is 2.85%, and the average error for the flowering rate is 1.135%. The experimental results show that the proposed method is effective for estimating the litchi flowering rate and can provide guidance regarding the management of the flowering periods of litchi orchards. |
first_indexed | 2024-04-13T03:07:22Z |
format | Article |
id | doaj.art-56affffaa5a9426cbad1930600d51312 |
institution | Directory Open Access Journal |
issn | 1664-462X |
language | English |
last_indexed | 2024-04-13T03:07:22Z |
publishDate | 2022-08-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Plant Science |
spelling | doaj.art-56affffaa5a9426cbad1930600d513122022-12-22T03:05:11ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-08-011310.3389/fpls.2022.966639966639A novel approach for estimating the flowering rate of litchi based on deep learning and UAV imagesPeiyi Lin0Denghui Li1Yuhang Jia2Yingyi Chen3Guangwen Huang4Hamza Elkhouchlaa5Zhongwei Yao6Zhengqi Zhou7Haobo Zhou8Jun Li9Jun Li10Huazhong Lu11College of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, Guangzhou, ChinaGuangdong Academy of Agricultural Sciences, Guangzhou, ChinaLitchi flowering management is an important link in litchi orchard management. Statistical litchi flowering rate data can provide an important reference for regulating the number of litchi flowers and directly determining the quality and yield of litchi fruit. At present, the statistical work regarding litchi flowering rates requires considerable labour costs. Therefore, this study aims at the statistical litchi flowering rate task, and a combination of unmanned aerial vehicle (UAV) images and computer vision technology is proposed to count the numbers of litchi flower clusters and flushes in a complex natural environment to improve the efficiency of litchi flowering rate estimation. First, RGB images of litchi canopies at the flowering stage are collected by a UAV. After performing image preprocessing, a dataset is established, and two types of objects in the images, namely, flower clusters and flushes, are manually labelled. Second, by comparing the pretraining and testing results obtained when setting different training parameters for the YOLOv4 model, the optimal parameter combination is determined. The YOLOv4 model trained with the optimal combination of parameters tests best on the test set, at which time the mean average precision (mAP) is 87.87%. The detection time required for a single image is 0.043 s. Finally, aiming at the two kinds of targets (flower clusters and flushes) on 8 litchi trees in a real orchard, a model for estimating the numbers of flower clusters and flushes on a single litchi tree is constructed by matching the identified number of targets with the actual number of targets via equation fitting. Then, the data obtained from the manual counting process and the estimation model for the other five litchi trees in the real orchard are statistically analysed. The average error rate for the number of flower clusters is 4.20%, the average error rate for the number of flushes is 2.85%, and the average error for the flowering rate is 1.135%. The experimental results show that the proposed method is effective for estimating the litchi flowering rate and can provide guidance regarding the management of the flowering periods of litchi orchards.https://www.frontiersin.org/articles/10.3389/fpls.2022.966639/fulllitchi flowering rateconvolutional neural networkobject detectionUAV imagesimage analysis |
spellingShingle | Peiyi Lin Denghui Li Yuhang Jia Yingyi Chen Guangwen Huang Hamza Elkhouchlaa Zhongwei Yao Zhengqi Zhou Haobo Zhou Jun Li Jun Li Huazhong Lu A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images Frontiers in Plant Science litchi flowering rate convolutional neural network object detection UAV images image analysis |
title | A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images |
title_full | A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images |
title_fullStr | A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images |
title_full_unstemmed | A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images |
title_short | A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images |
title_sort | novel approach for estimating the flowering rate of litchi based on deep learning and uav images |
topic | litchi flowering rate convolutional neural network object detection UAV images image analysis |
url | https://www.frontiersin.org/articles/10.3389/fpls.2022.966639/full |
work_keys_str_mv | AT peiyilin anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT denghuili anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT yuhangjia anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT yingyichen anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT guangwenhuang anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT hamzaelkhouchlaa anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT zhongweiyao anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT zhengqizhou anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT haobozhou anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT junli anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT junli anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT huazhonglu anovelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT peiyilin novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT denghuili novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT yuhangjia novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT yingyichen novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT guangwenhuang novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT hamzaelkhouchlaa novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT zhongweiyao novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT zhengqizhou novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT haobozhou novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT junli novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT junli novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages AT huazhonglu novelapproachforestimatingthefloweringrateoflitchibasedondeeplearninganduavimages |