Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective

Keiichi Mochida, Satoru Koda, Komaki Inoue, Takashi Hirayama, Shojiro Tanaka, Ryuei Nishii, Farid Melgani

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.

Original languageEnglish
JournalGigaScience
Volume8
Issue number1
DOIs
Publication statusPublished - Jan 1 2019

Fingerprint

Computer vision
Learning systems
Productivity
Unmanned vehicles
Agriculture
Image analysis
Crops
Remote sensing
Genes
Throughput
Neural networks
Sensors
Breeding
Machine Learning
Genotype
Phenotype

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications

Cite this

Computer vision-based phenotyping for improvement of plant productivity : a machine learning perspective. / Mochida, Keiichi; Koda, Satoru; Inoue, Komaki; Hirayama, Takashi; Tanaka, Shojiro; Nishii, Ryuei; Melgani, Farid.

In: GigaScience, Vol. 8, No. 1, 01.01.2019.

Research output: Contribution to journalArticle

Mochida, Keiichi ; Koda, Satoru ; Inoue, Komaki ; Hirayama, Takashi ; Tanaka, Shojiro ; Nishii, Ryuei ; Melgani, Farid. / Computer vision-based phenotyping for improvement of plant productivity : a machine learning perspective. In: GigaScience. 2019 ; Vol. 8, No. 1.
@article{ec909a78ebb8444a98a21c8a9e125048,
title = "Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective",
abstract = "Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.",
author = "Keiichi Mochida and Satoru Koda and Komaki Inoue and Takashi Hirayama and Shojiro Tanaka and Ryuei Nishii and Farid Melgani",
year = "2019",
month = "1",
day = "1",
doi = "10.1093/gigascience/giy153",
language = "English",
volume = "8",
journal = "GigaScience",
issn = "2047-217X",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Computer vision-based phenotyping for improvement of plant productivity

T2 - a machine learning perspective

AU - Mochida, Keiichi

AU - Koda, Satoru

AU - Inoue, Komaki

AU - Hirayama, Takashi

AU - Tanaka, Shojiro

AU - Nishii, Ryuei

AU - Melgani, Farid

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.

AB - Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.

UR - http://www.scopus.com/inward/record.url?scp=85059494625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059494625&partnerID=8YFLogxK

U2 - 10.1093/gigascience/giy153

DO - 10.1093/gigascience/giy153

M3 - Article

C2 - 30520975

AN - SCOPUS:85059494625

VL - 8

JO - GigaScience

JF - GigaScience

SN - 2047-217X

IS - 1

ER -