Deep Learning Based Greenhouse Image Segmentation and Shoot
Phenotyping (DeepShoot)

J 2022

Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot)

NARISETTI, Narendra, Michael HENKE, Kerstin NEUMANN, Frieder STOLZENBURG, Thomas ALTMANN et. al.

Základní údaje

Originální název

Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot)

Autoři

NARISETTI, Narendra, Michael HENKE (276 Německo, domácí), Kerstin NEUMANN, Frieder STOLZENBURG, Thomas ALTMANN a Evgeny GLADILIN

Vydání

Frontiers in Plant Science, Lausanne, FRONTIERS MEDIA SA, 2022, 1664-462X

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10600 1.6 Biological sciences

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

odkaz na webovou stránku

Impakt faktor

Impact factor: 5.600

Kód RIV

RIV/00216224:14740/22:00127315

Organizační jednotka

Středoevropský technologický institut

DOI

http://dx.doi.org/10.3389/fpls.2022.906410

UT WoS

000832787800001

Klíčová slova anglicky

greenhouse image analysis; image segmentation; deep learning; U-net; quantitative plant phenotyping

Štítky

CF PLANT, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 6. 2. 2023 19:35, Mgr. Pavla Foltynová, Ph.D.

Anotace

V originále

BackgroundAutomated analysis of large image data is highly demanded in high-throughput plant phenotyping. Due to large variability in optical plant appearance and experimental setups, advanced machine and deep learning techniques are required for automated detection and segmentation of plant structures in complex optical scenes. MethodsHere, we present a GUI-based software tool (DeepShoot) for efficient, fully automated segmentation and quantitative analysis of greenhouse-grown shoots which is based on pre-trained U-net deep learning models of arabidopsis, maize, and wheat plant appearance in different rotational side- and top-views. ResultsOur experimental results show that the developed algorithmic framework performs automated segmentation of side- and top-view images of different shoots acquired at different developmental stages using different phenotyping facilities with an average accuracy of more than 90% and outperforms shallow as well as conventional and encoder backbone networks in cross-validation tests with respect to both precision and performance time. ConclusionThe DeepShoot tool presented in this study provides an efficient solution for automated segmentation and phenotypic characterization of greenhouse-grown plant shoots suitable also for end-users without advanced IT skills. Primarily trained on images of three selected plants, this tool can be applied to images of other plant species exhibiting similar optical properties.

Návaznosti

EF16_026/0008446, projekt VaV

Název: Integrace signálu a epigenetické reprogramování pro produktivitu rostlin

Citovat

NARISETTI, Narendra, Michael HENKE, Kerstin NEUMANN, Frieder STOLZENBURG, Thomas ALTMANN a Evgeny GLADILIN. Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot). Frontiers in Plant Science. Lausanne: FRONTIERS MEDIA SA, 2022, roč. 13, JUL, s. 1-16. ISSN 1664-462X. Dostupné z: https://dx.doi.org/10.3389/fpls.2022.906410.

@article{2235888,
   author = {Narisetti, Narendra and Henke, Michael and Neumann, Kerstin and Stolzenburg, Frieder and Altmann, Thomas and Gladilin, Evgeny},
   article_location = {Lausanne},
   article_number = {JUL},
   doi = {http://dx.doi.org/10.3389/fpls.2022.906410},
   keywords = {greenhouse image analysis; image segmentation; deep learning; U-net; quantitative plant phenotyping},
   language = {eng},
   issn = {1664-462X},
   journal = {Frontiers in Plant Science},
   title = {Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot)},
   url = {https://www.frontiersin.org/articles/10.3389/fpls.2022.906410/full},
   volume = {13},
   year = {2022}
}

TY  - JOUR
ID  - 2235888
AU  - Narisetti, Narendra - Henke, Michael - Neumann, Kerstin - Stolzenburg, Frieder - Altmann, Thomas - Gladilin, Evgeny
PY  - 2022
TI  - Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot)
JF  - Frontiers in Plant Science
VL  - 13
IS  - JUL
SP  - 1-16
EP  - 1-16
PB  - FRONTIERS MEDIA SA
SN  - 1664462X
KW  - greenhouse image analysis
KW  - image segmentation
KW  - deep learning
KW  - U-net
KW  - quantitative plant phenotyping
UR  - https://www.frontiersin.org/articles/10.3389/fpls.2022.906410/full
N2  - BackgroundAutomated analysis of large image data is highly demanded in high-throughput plant phenotyping. Due to large variability in optical plant appearance and experimental setups, advanced machine and deep learning techniques are required for automated detection and segmentation of plant structures in complex optical scenes. MethodsHere, we present a GUI-based software tool (DeepShoot) for efficient, fully automated segmentation and quantitative analysis of greenhouse-grown shoots which is based on pre-trained U-net deep learning models of arabidopsis, maize, and wheat plant appearance in different rotational side- and top-views. ResultsOur experimental results show that the developed algorithmic framework performs automated segmentation of side- and top-view images of different shoots acquired at different developmental stages using different phenotyping facilities with an average accuracy of more than 90% and outperforms shallow as well as conventional and encoder backbone networks in cross-validation tests with respect to both precision and performance time. ConclusionThe DeepShoot tool presented in this study provides an efficient solution for automated segmentation and phenotypic characterization of greenhouse-grown plant shoots suitable also for end-users without advanced IT skills. Primarily trained on images of three selected plants, this tool can be applied to images of other plant species exhibiting similar optical properties.
ER  -

NARISETTI, Narendra, Michael HENKE, Kerstin NEUMANN, Frieder STOLZENBURG, Thomas ALTMANN a Evgeny GLADILIN. Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot). \textit{Frontiers in Plant Science}. Lausanne: FRONTIERS MEDIA SA, 2022, roč.~13, JUL, s.~1-16. ISSN~1664-462X. Dostupné z: https://dx.doi.org/10.3389/fpls.2022.906410.

Podrobný výpis o publikaci