Cargando…

Tiller estimation method using deep neural networks

This paper describes a method based on a deep neural network (DNN) for estimating the number of tillers on a plant. A tiller is a branch on a grass plant, and the number of tillers is one of the most important determinants of yield. Traditionally, the tiller number is usually counted by hand, and so...

Descripción completa

Detalles Bibliográficos
Autores principales: Kinose, Rikuya, Utsumi, Yuzuko, Iwamura, Masakazu, Kise, Koichi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9880423/
https://www.ncbi.nlm.nih.gov/pubmed/36714728
http://dx.doi.org/10.3389/fpls.2022.1016507
_version_ 1784878907395145728
author Kinose, Rikuya
Utsumi, Yuzuko
Iwamura, Masakazu
Kise, Koichi
author_facet Kinose, Rikuya
Utsumi, Yuzuko
Iwamura, Masakazu
Kise, Koichi
author_sort Kinose, Rikuya
collection PubMed
description This paper describes a method based on a deep neural network (DNN) for estimating the number of tillers on a plant. A tiller is a branch on a grass plant, and the number of tillers is one of the most important determinants of yield. Traditionally, the tiller number is usually counted by hand, and so an automated approach is necessary for high-throughput phenotyping. Conventional methods use heuristic features to estimate the tiller number. Based on the successful application of DNNs in the field of computer vision, the use of DNN-based features instead of heuristic features is expected to improve the estimation accuracy. However, as DNNs generally require large volumes of data for training, it is difficult to apply them to estimation problems for which large training datasets are unavailable. In this paper, we use two strategies to overcome the problem of insufficient training data: the use of a pretrained DNN model and the use of pretext tasks for learning the feature representation. We extract features using the resulting DNNs and estimate the tiller numbers through a regression technique. We conducted experiments using side-view whole plant images taken with plan backgroud. The experimental results show that the proposed methods using a pretrained model and specific pretext tasks achieve better performance than the conventional method.
format Online
Article
Text
id pubmed-9880423
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-98804232023-01-28 Tiller estimation method using deep neural networks Kinose, Rikuya Utsumi, Yuzuko Iwamura, Masakazu Kise, Koichi Front Plant Sci Plant Science This paper describes a method based on a deep neural network (DNN) for estimating the number of tillers on a plant. A tiller is a branch on a grass plant, and the number of tillers is one of the most important determinants of yield. Traditionally, the tiller number is usually counted by hand, and so an automated approach is necessary for high-throughput phenotyping. Conventional methods use heuristic features to estimate the tiller number. Based on the successful application of DNNs in the field of computer vision, the use of DNN-based features instead of heuristic features is expected to improve the estimation accuracy. However, as DNNs generally require large volumes of data for training, it is difficult to apply them to estimation problems for which large training datasets are unavailable. In this paper, we use two strategies to overcome the problem of insufficient training data: the use of a pretrained DNN model and the use of pretext tasks for learning the feature representation. We extract features using the resulting DNNs and estimate the tiller numbers through a regression technique. We conducted experiments using side-view whole plant images taken with plan backgroud. The experimental results show that the proposed methods using a pretrained model and specific pretext tasks achieve better performance than the conventional method. Frontiers Media S.A. 2023-01-13 /pmc/articles/PMC9880423/ /pubmed/36714728 http://dx.doi.org/10.3389/fpls.2022.1016507 Text en Copyright © 2023 Kinose, Utsumi, Iwamura and Kise https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Kinose, Rikuya
Utsumi, Yuzuko
Iwamura, Masakazu
Kise, Koichi
Tiller estimation method using deep neural networks
title Tiller estimation method using deep neural networks
title_full Tiller estimation method using deep neural networks
title_fullStr Tiller estimation method using deep neural networks
title_full_unstemmed Tiller estimation method using deep neural networks
title_short Tiller estimation method using deep neural networks
title_sort tiller estimation method using deep neural networks
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9880423/
https://www.ncbi.nlm.nih.gov/pubmed/36714728
http://dx.doi.org/10.3389/fpls.2022.1016507
work_keys_str_mv AT kinoserikuya tillerestimationmethodusingdeepneuralnetworks
AT utsumiyuzuko tillerestimationmethodusingdeepneuralnetworks
AT iwamuramasakazu tillerestimationmethodusingdeepneuralnetworks
AT kisekoichi tillerestimationmethodusingdeepneuralnetworks