TY - JOUR
T1 - EmergeNet
T2 - A novel deep-learning based ensemble segmentation model for emergence timing detection of coleoptile
AU - Das, Aankit
AU - Das Choudhury, Sruti
AU - Das, Amit Kumar
AU - Samal, Ashok
AU - Awada, Tala
N1 - Publisher Copyright:
Copyright © 2023 Das, Das Choudhury, Das, Samal and Awada.
PY - 2023/2/3
Y1 - 2023/2/3
N2 - The emergence timing of a plant, i.e., the time at which the plant is first visible from the surface of the soil, is an important phenotypic event and is an indicator of the successful establishment and growth of a plant. The paper introduces a novel deep-learning based model called EmergeNet with a customized loss function that adapts to plant growth for coleoptile (a rigid plant tissue that encloses the first leaves of a seedling) emergence timing detection. It can also track its growth from a time-lapse sequence of images with cluttered backgrounds and extreme variations in illumination. EmergeNet is a novel ensemble segmentation model that integrates three different but promising networks, namely, SEResNet, InceptionV3, and VGG19, in the encoder part of its base model, which is the UNet model. EmergeNet can correctly detect the coleoptile at its first emergence when it is tiny and therefore barely visible on the soil surface. The performance of EmergeNet is evaluated using a benchmark dataset called the University of Nebraska-Lincoln Maize Emergence Dataset (UNL-MED). It contains top-view time-lapse images of maize coleoptiles starting before the occurrence of their emergence and continuing until they are about one inch tall. EmergeNet detects the emergence timing with 100% accuracy compared with human-annotated ground-truth. Furthermore, it significantly outperforms UNet by generating very high-quality segmented masks of the coleoptiles in both natural light and dark environmental conditions.
AB - The emergence timing of a plant, i.e., the time at which the plant is first visible from the surface of the soil, is an important phenotypic event and is an indicator of the successful establishment and growth of a plant. The paper introduces a novel deep-learning based model called EmergeNet with a customized loss function that adapts to plant growth for coleoptile (a rigid plant tissue that encloses the first leaves of a seedling) emergence timing detection. It can also track its growth from a time-lapse sequence of images with cluttered backgrounds and extreme variations in illumination. EmergeNet is a novel ensemble segmentation model that integrates three different but promising networks, namely, SEResNet, InceptionV3, and VGG19, in the encoder part of its base model, which is the UNet model. EmergeNet can correctly detect the coleoptile at its first emergence when it is tiny and therefore barely visible on the soil surface. The performance of EmergeNet is evaluated using a benchmark dataset called the University of Nebraska-Lincoln Maize Emergence Dataset (UNL-MED). It contains top-view time-lapse images of maize coleoptiles starting before the occurrence of their emergence and continuing until they are about one inch tall. EmergeNet detects the emergence timing with 100% accuracy compared with human-annotated ground-truth. Furthermore, it significantly outperforms UNet by generating very high-quality segmented masks of the coleoptiles in both natural light and dark environmental conditions.
KW - benchmark dataset
KW - deep-learning
KW - emergence time detection
KW - ensemble segmentation
KW - event-based plant phenotyping
UR - http://www.scopus.com/inward/record.url?scp=85148458281&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85148458281&partnerID=8YFLogxK
U2 - 10.3389/fpls.2023.1084778
DO - 10.3389/fpls.2023.1084778
M3 - Article
C2 - 36818836
AN - SCOPUS:85148458281
SN - 1664-462X
VL - 14
JO - Frontiers in Plant Science
JF - Frontiers in Plant Science
M1 - 1084778
ER -