J 2022

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

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

Basic information

Original name

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

Authors

NARISETTI, Narendra, Michael HENKE (276 Germany, belonging to the institution), Kerstin NEUMANN, Frieder STOLZENBURG, Thomas ALTMANN and Evgeny GLADILIN

Edition

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

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10600 1.6 Biological sciences

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

Impact factor

Impact factor: 5.600

RIV identification code

RIV/00216224:14740/22:00127315

Organization unit

Central European Institute of Technology

UT WoS

000832787800001

Keywords in English

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

Tags

Tags

International impact, Reviewed
Změněno: 6/2/2023 19:35, Mgr. Pavla Foltynová, Ph.D.

Abstract

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.

Links

EF16_026/0008446, research and development project
Name: Integrace signálu a epigenetické reprogramování pro produktivitu rostlin