From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection
Head (panicle) density is a major component in understanding crop yield, especially in crops that produce variable numbers of tillers such as sorghum and wheat. Use of panicle density both in plant breeding and in the agronomy scouting of commercial crops typically relies on manual counts observation, which is an inefficient and tedious process. Because of the easy availability of red–green–blue images, machine learning approaches have been applied to replacing manual counting. However, much of this research focuses on detection per se in limited testing conditions and does not provide a general protocol to utilize deep-learning-based counting. In this paper, we provide a comprehensive pipeline from data collection to model deployment in deep-learning-assisted panicle yield estimation for sorghum. This pipeline provides a basis from data collection and model training, to model validation and model deployment in commercial fields. Accurate model training is the foundation of the pipeline. However, in natural environments, the deployment dataset is frequently different from the training data (domain shift) causing the model to fail, so a robust model is essential to build a reliable solution. Although we demonstrate our pipeline in a sorghum field, the pipeline can be generalized to other grain species. Our pipeline provides a high-resolution head density map that can be utilized for diagnosis of agronomic variability within a field, in a pipeline built without commercial software.
Main Authors: | , , , , , , , , |
---|---|
Format: | article biblioteca |
Language: | eng |
Subjects: | F01 - Culture des plantes, U30 - Méthodes de recherche, U10 - Informatique, mathématiques et statistiques, Sorghum, analyse d'image, analyse de données, collecte de données, modélisation des cultures, panicule, http://aims.fao.org/aos/agrovoc/c_7244, http://aims.fao.org/aos/agrovoc/c_36762, http://aims.fao.org/aos/agrovoc/c_15962, http://aims.fao.org/aos/agrovoc/c_2128, http://aims.fao.org/aos/agrovoc/c_9000024, http://aims.fao.org/aos/agrovoc/c_24557, |
Online Access: | http://agritrop.cirad.fr/603956/ http://agritrop.cirad.fr/603956/1/plantphenomics.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-cirad-fr-603956 |
---|---|
record_format |
koha |
spelling |
dig-cirad-fr-6039562024-01-29T04:31:59Z http://agritrop.cirad.fr/603956/ http://agritrop.cirad.fr/603956/ From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection. James Chrisbin, Gu Yanyang, Potgieter Andries, David Etienne, Madec Simon, Guo Wei, Baret Frédéric, Eriksson Anders, Chapman Scott. 2023. Plant Phenomics, 5:0017, 16 p.https://doi.org/10.34133/plantphenomics.0017 <https://doi.org/10.34133/plantphenomics.0017> From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection James, Chrisbin Gu, Yanyang Potgieter, Andries David, Etienne Madec, Simon Guo, Wei Baret, Frédéric Eriksson, Anders Chapman, Scott eng 2023 Plant Phenomics F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques Sorghum analyse d'image analyse de données collecte de données modélisation des cultures panicule http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_36762 http://aims.fao.org/aos/agrovoc/c_15962 http://aims.fao.org/aos/agrovoc/c_2128 http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_24557 Head (panicle) density is a major component in understanding crop yield, especially in crops that produce variable numbers of tillers such as sorghum and wheat. Use of panicle density both in plant breeding and in the agronomy scouting of commercial crops typically relies on manual counts observation, which is an inefficient and tedious process. Because of the easy availability of red–green–blue images, machine learning approaches have been applied to replacing manual counting. However, much of this research focuses on detection per se in limited testing conditions and does not provide a general protocol to utilize deep-learning-based counting. In this paper, we provide a comprehensive pipeline from data collection to model deployment in deep-learning-assisted panicle yield estimation for sorghum. This pipeline provides a basis from data collection and model training, to model validation and model deployment in commercial fields. Accurate model training is the foundation of the pipeline. However, in natural environments, the deployment dataset is frequently different from the training data (domain shift) causing the model to fail, so a robust model is essential to build a reliable solution. Although we demonstrate our pipeline in a sorghum field, the pipeline can be generalized to other grain species. Our pipeline provides a high-resolution head density map that can be utilized for diagnosis of agronomic variability within a field, in a pipeline built without commercial software. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/acceptedVersion http://agritrop.cirad.fr/603956/1/plantphenomics.pdf text cc_by info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/ https://doi.org/10.34133/plantphenomics.0017 10.34133/plantphenomics.0017 info:eu-repo/semantics/altIdentifier/doi/10.34133/plantphenomics.0017 info:eu-repo/semantics/altIdentifier/purl/https://doi.org/10.34133/plantphenomics.0017 |
institution |
CIRAD FR |
collection |
DSpace |
country |
Francia |
countrycode |
FR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-cirad-fr |
tag |
biblioteca |
region |
Europa del Oeste |
libraryname |
Biblioteca del CIRAD Francia |
language |
eng |
topic |
F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques Sorghum analyse d'image analyse de données collecte de données modélisation des cultures panicule http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_36762 http://aims.fao.org/aos/agrovoc/c_15962 http://aims.fao.org/aos/agrovoc/c_2128 http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_24557 F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques Sorghum analyse d'image analyse de données collecte de données modélisation des cultures panicule http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_36762 http://aims.fao.org/aos/agrovoc/c_15962 http://aims.fao.org/aos/agrovoc/c_2128 http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_24557 |
spellingShingle |
F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques Sorghum analyse d'image analyse de données collecte de données modélisation des cultures panicule http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_36762 http://aims.fao.org/aos/agrovoc/c_15962 http://aims.fao.org/aos/agrovoc/c_2128 http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_24557 F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques Sorghum analyse d'image analyse de données collecte de données modélisation des cultures panicule http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_36762 http://aims.fao.org/aos/agrovoc/c_15962 http://aims.fao.org/aos/agrovoc/c_2128 http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_24557 James, Chrisbin Gu, Yanyang Potgieter, Andries David, Etienne Madec, Simon Guo, Wei Baret, Frédéric Eriksson, Anders Chapman, Scott From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection |
description |
Head (panicle) density is a major component in understanding crop yield, especially in crops that produce variable numbers of tillers such as sorghum and wheat. Use of panicle density both in plant breeding and in the agronomy scouting of commercial crops typically relies on manual counts observation, which is an inefficient and tedious process. Because of the easy availability of red–green–blue images, machine learning approaches have been applied to replacing manual counting. However, much of this research focuses on detection per se in limited testing conditions and does not provide a general protocol to utilize deep-learning-based counting. In this paper, we provide a comprehensive pipeline from data collection to model deployment in deep-learning-assisted panicle yield estimation for sorghum. This pipeline provides a basis from data collection and model training, to model validation and model deployment in commercial fields. Accurate model training is the foundation of the pipeline. However, in natural environments, the deployment dataset is frequently different from the training data (domain shift) causing the model to fail, so a robust model is essential to build a reliable solution. Although we demonstrate our pipeline in a sorghum field, the pipeline can be generalized to other grain species. Our pipeline provides a high-resolution head density map that can be utilized for diagnosis of agronomic variability within a field, in a pipeline built without commercial software. |
format |
article |
topic_facet |
F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques Sorghum analyse d'image analyse de données collecte de données modélisation des cultures panicule http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_36762 http://aims.fao.org/aos/agrovoc/c_15962 http://aims.fao.org/aos/agrovoc/c_2128 http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_24557 |
author |
James, Chrisbin Gu, Yanyang Potgieter, Andries David, Etienne Madec, Simon Guo, Wei Baret, Frédéric Eriksson, Anders Chapman, Scott |
author_facet |
James, Chrisbin Gu, Yanyang Potgieter, Andries David, Etienne Madec, Simon Guo, Wei Baret, Frédéric Eriksson, Anders Chapman, Scott |
author_sort |
James, Chrisbin |
title |
From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection |
title_short |
From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection |
title_full |
From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection |
title_fullStr |
From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection |
title_full_unstemmed |
From prototype to inference: A pipeline to apply deep learning in sorghum panicle detection |
title_sort |
from prototype to inference: a pipeline to apply deep learning in sorghum panicle detection |
url |
http://agritrop.cirad.fr/603956/ http://agritrop.cirad.fr/603956/1/plantphenomics.pdf |
work_keys_str_mv |
AT jameschrisbin fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT guyanyang fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT potgieterandries fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT davidetienne fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT madecsimon fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT guowei fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT baretfrederic fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT erikssonanders fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection AT chapmanscott fromprototypetoinferenceapipelinetoapplydeeplearninginsorghumpanicledetection |
_version_ |
1792500505888423936 |