Fast estimation of plant growth dynamics using deep neural networks

Gall, Gabriella; Pereira, Talmo D.; Jordan, Alex; Meroz, Yasmine

Fast estimation of plant growth dynamics using deep neural networks

Dateien

Gall_2-10lm48gzxqu7c2.pdfGröße: 3.97 MBDownloads: 139

Datum

2022

Autor:innen

Gall, Gabriella

Pereira, Talmo D.

Jordan, Alex

Meroz, Yasmine

Angaben zur Forschungsförderung

European Union (EU): 824074

Open Access-Veröffentlichung

Open Access Gold

Sammlungen

Biologie
Exzellenzcluster "Centre for the Advanced Study of Collective Behaviour"

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

Plant Methods. BioMed Central. 2022, 18, 21. eISSN 1746-4811. Available under: doi: 10.1186/s13007-022-00851-9

Zusammenfassung

Background
In recent years, there has been an increase of interest in plant behaviour as represented by growth-driven responses. These are generally classified into nastic (internally driven) and tropic (environmentally driven) movements. Nastic movements include circumnutations, a circular movement of plant organs commonly associated with search and exploration, while tropisms refer to the directed growth of plant organs toward or away from environmental stimuli, such as light and gravity. Tracking these movements is therefore fundamental for the study of plant behaviour. Convolutional neural networks, as used for human and animal pose estimation, offer an interesting avenue for plant tracking. Here we adopted the Social LEAP Estimates Animal Poses (SLEAP) framework for plant tracking. We evaluated it on time-lapse videos of cases spanning a variety of parameters, such as: (i) organ types and imaging angles (e.g., top-view crown leaves vs. side-view shoots and roots), (ii) lighting conditions (full spectrum vs. IR), (iii) plant morphologies and scales (100 μm-scale Arabidopsis seedlings vs. cm-scale sunflowers and beans), and (iv) movement types (circumnutations, tropisms and twining).

Results
Overall, we found SLEAP to be accurate in tracking side views of shoots and roots, requiring only a low number of user-labelled frames for training. Top views of plant crowns made up of multiple leaves were found to be more challenging, due to the changing 2D morphology of leaves, and the occlusions of overlapping leaves. This required a larger number of labelled frames, and the choice of labelling “skeleton” had great impact on prediction accuracy, i.e., a more complex skeleton with fewer individuals (tracking individual plants) provided better results than a simpler skeleton with more individuals (tracking individual leaves).

Conclusions
In all, these results suggest SLEAP is a robust and versatile tool for high-throughput automated tracking of plants, presenting a new avenue for research focusing on plant dynamics.

Fachgebiet (DDC)

570 Biowissenschaften, Biologie

Zitieren

ISO 690

GALL, Gabriella, Talmo D. PEREIRA, Alex JORDAN, Yasmine MEROZ, 2022. Fast estimation of plant growth dynamics using deep neural networks. In: Plant Methods. BioMed Central. 2022, 18, 21. eISSN 1746-4811. Available under: doi: 10.1186/s13007-022-00851-9

BibTex

@article{Gall2022-02-20estim-56692,
  year={2022},
  doi={10.1186/s13007-022-00851-9},
  title={Fast estimation of plant growth dynamics using deep neural networks},
  volume={18},
  journal={Plant Methods},
  author={Gall, Gabriella and Pereira, Talmo D. and Jordan, Alex and Meroz, Yasmine},
  note={Article Number: 21}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/56692">
    <dc:language>eng</dc:language>
    <dc:creator>Pereira, Talmo D.</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/>
    <dcterms:abstract xml:lang="eng">Background&lt;br /&gt;In recent years, there has been an increase of interest in plant behaviour as represented by growth-driven responses. These are generally classified into nastic (internally driven) and tropic (environmentally driven) movements. Nastic movements include circumnutations, a circular movement of plant organs commonly associated with search and exploration, while tropisms refer to the directed growth of plant organs toward or away from environmental stimuli, such as light and gravity. Tracking these movements is therefore fundamental for the study of plant behaviour. Convolutional neural networks, as used for human and animal pose estimation, offer an interesting avenue for plant tracking. Here we adopted the Social LEAP Estimates Animal Poses (SLEAP) framework for plant tracking. We evaluated it on time-lapse videos of cases spanning a variety of parameters, such as: (i) organ types and imaging angles (e.g., top-view crown leaves vs. side-view shoots and roots), (ii) lighting conditions (full spectrum vs. IR), (iii) plant morphologies and scales (100 μm-scale Arabidopsis seedlings vs. cm-scale sunflowers and beans), and (iv) movement types (circumnutations, tropisms and twining).&lt;br /&gt;&lt;br /&gt;Results&lt;br /&gt;Overall, we found SLEAP to be accurate in tracking side views of shoots and roots, requiring only a low number of user-labelled frames for training. Top views of plant crowns made up of multiple leaves were found to be more challenging, due to the changing 2D morphology of leaves, and the occlusions of overlapping leaves. This required a larger number of labelled frames, and the choice of labelling “skeleton” had great impact on prediction accuracy, i.e., a more complex skeleton with fewer individuals (tracking individual plants) provided better results than a simpler skeleton with more individuals (tracking individual leaves).&lt;br /&gt;&lt;br /&gt;Conclusions&lt;br /&gt;In all, these results suggest SLEAP is a robust and versatile tool for high-throughput automated tracking of plants, presenting a new avenue for research focusing on plant dynamics.</dcterms:abstract>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/56692/1/Gall_2-10lm48gzxqu7c2.pdf"/>
    <dc:contributor>Gall, Gabriella</dc:contributor>
    <dc:contributor>Pereira, Talmo D.</dc:contributor>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/>
    <dc:creator>Gall, Gabriella</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/>
    <dcterms:title>Fast estimation of plant growth dynamics using deep neural networks</dcterms:title>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-02-28T07:06:43Z</dcterms:available>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-02-28T07:06:43Z</dc:date>
    <dc:creator>Meroz, Yasmine</dc:creator>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/56692"/>
    <dc:rights>Attribution 4.0 International</dc:rights>
    <dcterms:issued>2022-02-20</dcterms:issued>
    <dc:contributor>Meroz, Yasmine</dc:contributor>
    <dc:creator>Jordan, Alex</dc:creator>
    <dc:contributor>Jordan, Alex</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/56692/1/Gall_2-10lm48gzxqu7c2.pdf"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja