Determination of Wheat Growth Stages Using Image Sequences and Deep Learning

The growth stage of wheat is key information for critical decision-making related to cultivar screening of wheat and farming activities. In order to solve the problem that it is difficult to determine the growth stages of a large number of wheat breeding materials grown in an artificial climate room...

Full description

Saved in:
Bibliographic Details
Main Authors: Chunying Wang, Xubin Song, Weiting Pan, Haixia Yu, Xiang Li, Ping Liu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/1/13
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589488022355968
author Chunying Wang
Xubin Song
Weiting Pan
Haixia Yu
Xiang Li
Ping Liu
author_facet Chunying Wang
Xubin Song
Weiting Pan
Haixia Yu
Xiang Li
Ping Liu
author_sort Chunying Wang
collection DOAJ
description The growth stage of wheat is key information for critical decision-making related to cultivar screening of wheat and farming activities. In order to solve the problem that it is difficult to determine the growth stages of a large number of wheat breeding materials grown in an artificial climate room accurately and quickly, the first attempt was made to determine the growth stages of wheat using image sequences of growth and development. A hybrid model (DenseNet–BiLSTM) based on the DenseNet and Bidirectional Long Short-Term Memory was proposed for determining the growth stage of wheat. The spatiotemporal characteristics of wheat growth and development were modeled by DenseNet–BiLSTM synthetically to classify the growth stage of each wheat image in the sequence. The determination accuracy of the growth stages obtained by the proposed DenseNet–BiLSTM model was 98.43%. Of these, the determination precisions of the tillering, re-greening, jointing, booting, and heading period were 100%, 97.80%, 97.80%, 85.71%, and 95.65%, respectively. In addition, the accurate determination of the growth stages and further analysis of its relationship with meteorological conditions will help biologists, geneticists, and breeders to breed, screen, and evaluate wheat varieties with ecological adaptability.
format Article
id doaj-art-9ba7a435fd05456d941dee6ca479f749
institution Kabale University
issn 2073-4395
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-9ba7a435fd05456d941dee6ca479f7492025-01-24T13:16:21ZengMDPI AGAgronomy2073-43952024-12-011511310.3390/agronomy15010013Determination of Wheat Growth Stages Using Image Sequences and Deep LearningChunying Wang0Xubin Song1Weiting Pan2Haixia Yu3Xiang Li4Ping Liu5State Key Laboratory of Wheat Improvement, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Tai’an 271000, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Tai’an 271000, ChinaState Key Laboratory of Wheat Improvement, Shandong Agricultural University, Tai’an 271018, ChinaState Key Laboratory of Wheat Improvement, Shandong Agricultural University, Tai’an 271018, ChinaState Key Laboratory of Wheat Improvement, Shandong Agricultural University, Tai’an 271018, ChinaThe growth stage of wheat is key information for critical decision-making related to cultivar screening of wheat and farming activities. In order to solve the problem that it is difficult to determine the growth stages of a large number of wheat breeding materials grown in an artificial climate room accurately and quickly, the first attempt was made to determine the growth stages of wheat using image sequences of growth and development. A hybrid model (DenseNet–BiLSTM) based on the DenseNet and Bidirectional Long Short-Term Memory was proposed for determining the growth stage of wheat. The spatiotemporal characteristics of wheat growth and development were modeled by DenseNet–BiLSTM synthetically to classify the growth stage of each wheat image in the sequence. The determination accuracy of the growth stages obtained by the proposed DenseNet–BiLSTM model was 98.43%. Of these, the determination precisions of the tillering, re-greening, jointing, booting, and heading period were 100%, 97.80%, 97.80%, 85.71%, and 95.65%, respectively. In addition, the accurate determination of the growth stages and further analysis of its relationship with meteorological conditions will help biologists, geneticists, and breeders to breed, screen, and evaluate wheat varieties with ecological adaptability.https://www.mdpi.com/2073-4395/15/1/13wheatgrowth stage determinationdeep learningspatiotemporal informationimage sequences
spellingShingle Chunying Wang
Xubin Song
Weiting Pan
Haixia Yu
Xiang Li
Ping Liu
Determination of Wheat Growth Stages Using Image Sequences and Deep Learning
Agronomy
wheat
growth stage determination
deep learning
spatiotemporal information
image sequences
title Determination of Wheat Growth Stages Using Image Sequences and Deep Learning
title_full Determination of Wheat Growth Stages Using Image Sequences and Deep Learning
title_fullStr Determination of Wheat Growth Stages Using Image Sequences and Deep Learning
title_full_unstemmed Determination of Wheat Growth Stages Using Image Sequences and Deep Learning
title_short Determination of Wheat Growth Stages Using Image Sequences and Deep Learning
title_sort determination of wheat growth stages using image sequences and deep learning
topic wheat
growth stage determination
deep learning
spatiotemporal information
image sequences
url https://www.mdpi.com/2073-4395/15/1/13
work_keys_str_mv AT chunyingwang determinationofwheatgrowthstagesusingimagesequencesanddeeplearning
AT xubinsong determinationofwheatgrowthstagesusingimagesequencesanddeeplearning
AT weitingpan determinationofwheatgrowthstagesusingimagesequencesanddeeplearning
AT haixiayu determinationofwheatgrowthstagesusingimagesequencesanddeeplearning
AT xiangli determinationofwheatgrowthstagesusingimagesequencesanddeeplearning
AT pingliu determinationofwheatgrowthstagesusingimagesequencesanddeeplearning