Triticale field phenotyping using RGB camera for ear counting
and yield estimation

J 2024

Triticale field phenotyping using RGB camera for ear counting and yield estimation

STEFAŃSKI, Piotr, Sajid ULLAH, Przemysław MATYSIK a Krystyna RYBKA

Základní údaje

Originální název

Triticale field phenotyping using RGB camera for ear counting and yield estimation

Autoři

STEFAŃSKI, Piotr, Sajid ULLAH (586 Pákistán, domácí), Przemysław MATYSIK a Krystyna RYBKA

Vydání

Journal of Applied Genetics, Springer, 2024, 1234-1983

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10611 Plant sciences, botany

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 2.400 v roce 2022

Organizační jednotka

Přírodovědecká fakulta

DOI

http://dx.doi.org/10.1007/s13353-024-00835-6

UT WoS

001161689400002

Klíčová slova anglicky

plant breeding; yield potential; ear detection; deep learning; field imaging; statistical analysis

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 16. 4. 2024 11:09, Mgr. Marie Šípková, DiS.

Anotace

V originále

Triticale (X Triticosecale Wittmack), a wheat-rye small grain crop hybrid, combines wheat and rye attributes in one hexaploid genome. It is characterized by high adaptability to adverse environmental conditions: drought, soil acidity, salinity and heavy metal ions, poorer soil quality, and waterlogging. So that its cultivation is prospective in a changing climate. Here, we describe RGB on-ground phenotyping of field-grown eighteen triticale market-available cultivars, made in naturally changing light conditions, in two consecutive winter cereals growing seasons: 2018–2019 and 2019–2020. The number of ears was counted on top-down images with an accuracy of 95% and mean average precision (mAP) of 0.71 using advanced object detection algorithm YOLOv4, with ensemble modeling of field imaging captured in two different illumination conditions. A correlation between the number of ears and yield was achieved at the statistical importance of 0.16 for data from 2019. Results are discussed from the perspective of modern breeding and phenotyping bottleneck.

Návaznosti

EF16_026/0008446, projekt VaV

Název: Integrace signálu a epigenetické reprogramování pro produktivitu rostlin

Citovat

STEFAŃSKI, Piotr, Sajid ULLAH, Przemysław MATYSIK a Krystyna RYBKA. Triticale field phenotyping using RGB camera for ear counting and yield estimation. Journal of Applied Genetics. Springer, 2024, roč. 65, č. 2, s. 271-281. ISSN 1234-1983. Dostupné z: https://dx.doi.org/10.1007/s13353-024-00835-6.

@article{2363177,
   author = {Stefański, Piotr and Ullah, Sajid and Matysik, Przemysław and Rybka, Krystyna and Rybka, Krystyna},
   article_number = {2},
   doi = {http://dx.doi.org/10.1007/s13353-024-00835-6},
   keywords = {plant breeding; yield potential; ear detection; deep learning; field imaging; statistical analysis},
   language = {eng},
   issn = {1234-1983},
   journal = {Journal of Applied Genetics},
   title = {Triticale field phenotyping using RGB camera for ear counting and yield estimation},
   url = {https://link.springer.com/article/10.1007/s13353-024-00835-6},
   volume = {65},
   year = {2024}
}

TY  - JOUR
ID  - 2363177
AU  - Stefański, Piotr - Ullah, Sajid - Matysik, Przemysław - Rybka, Krystyna - Rybka, Krystyna
PY  - 2024
TI  - Triticale field phenotyping using RGB camera for ear counting and yield estimation
JF  - Journal of Applied Genetics
VL  - 65
IS  - 2
SP  - 271-281
EP  - 271-281
PB  - Springer
SN  - 12341983
KW  - plant breeding
KW  - yield potential
KW  - ear detection
KW  - deep learning
KW  - field imaging
KW  - statistical analysis
UR  - https://link.springer.com/article/10.1007/s13353-024-00835-6
N2  - Triticale (X Triticosecale Wittmack), a wheat-rye small grain crop hybrid, combines wheat and rye attributes in one hexaploid genome. It is characterized by high adaptability to adverse environmental conditions: drought, soil acidity, salinity and heavy metal ions, poorer soil quality, and waterlogging. So that its cultivation is prospective in a changing climate. Here, we describe RGB on-ground phenotyping of field-grown eighteen triticale market-available cultivars, made in naturally changing light conditions, in two consecutive winter cereals growing seasons: 2018–2019 and 2019–2020. The number of ears was counted on top-down images with an accuracy of 95% and mean average precision (mAP) of 0.71 using advanced object detection algorithm YOLOv4, with ensemble modeling of field imaging captured in two different illumination conditions. A correlation between the number of ears and yield was achieved at the statistical importance of 0.16 for data from 2019. Results are discussed from the perspective of modern breeding and phenotyping bottleneck.
ER  -

STEFA$\backslash$'NSKI, Piotr, Sajid ULLAH, Przemysław MATYSIK a Krystyna RYBKA. Triticale field phenotyping using RGB camera for ear counting and yield estimation. \textit{Journal of Applied Genetics}. Springer, 2024, roč.~65, č.~2, s.~271-281. ISSN~1234-1983. Dostupné z: https://dx.doi.org/10.1007/s13353-024-00835-6.

Podrobný výpis o publikaci