Holistic and component plant phenotyping using temporal image sequence

Sruti Das Choudhury, Srinidhi Bashyam, Yumou Qiu, Ashok K Samal, Tala Awada

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Background: Image-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time. It has the potential to compute advanced phenotypes by considering the whole plant as a single object (holistic phenotypes) or as individual components, i.e., leaves and the stem (component phenotypes), to investigate the biophysical characteristics of the plants. The emergence timing, total number of leaves present at any point of time and the growth of individual leaves during vegetative stage life cycle of the maize plants are significant phenotypic expressions that best contribute to assess the plant vigor. However, image-based automated solution to this novel problem is yet to be explored. Results: A set of new holistic and component phenotypes are introduced in this paper. To compute the component phenotypes, it is essential to detect the individual leaves and the stem. Thus, the paper introduces a novel method to reliably detect the leaves and the stem of the maize plants by analyzing 2-dimensional visible light image sequences captured from the side using a graph based approach. The total number of leaves are counted and the length of each leaf is measured for all images in the sequence to monitor leaf growth. To evaluate the performance of the proposed algorithm, we introduce University of Nebraska-Lincoln Component Plant Phenotyping Dataset (UNL-CPPD) and provide ground truth to facilitate new algorithm development and uniform comparison. The temporal variation of the component phenotypes regulated by genotypes and environment (i.e., greenhouse) are experimentally demonstrated for the maize plants on UNL-CPPD. Statistical models are applied to analyze the greenhouse environment impact and demonstrate the genetic regulation of the temporal variation of the holistic phenotypes on the public dataset called Panicoid Phenomap-1. Conclusion: The central contribution of the paper is a novel computer vision based algorithm for automated detection of individual leaves and the stem to compute new component phenotypes along with a public release of a benchmark dataset, i.e., UNL-CPPD. Detailed experimental analyses are performed to demonstrate the temporal variation of the holistic and component phenotypes in maize regulated by environment and genetic variation with a discussion on their significance in the context of plant science.

Original languageEnglish (US)
Article number35
JournalPlant Methods
Volume14
Issue number1
DOIs
StatePublished - May 10 2018

Fingerprint

Plant Structures
Phenotype
phenotype
Zea mays
leaves
temporal variation
stems
corn
Plant Stems
Benchmarking
Statistical Models
Growth
Life Cycle Stages
greenhouses
computer vision
plant characteristics
Genotype
Datasets
statistical models
Light

Keywords

  • Component phenotypes
  • Holistic phenotypes
  • Image sequence analysis
  • Plant architecture
  • Plant phenotyping

ASJC Scopus subject areas

  • Biotechnology
  • Genetics
  • Plant Science

Cite this

Holistic and component plant phenotyping using temporal image sequence. / Das Choudhury, Sruti; Bashyam, Srinidhi; Qiu, Yumou; Samal, Ashok K; Awada, Tala.

In: Plant Methods, Vol. 14, No. 1, 35, 10.05.2018.

Research output: Contribution to journalArticle

Das Choudhury, Sruti ; Bashyam, Srinidhi ; Qiu, Yumou ; Samal, Ashok K ; Awada, Tala. / Holistic and component plant phenotyping using temporal image sequence. In: Plant Methods. 2018 ; Vol. 14, No. 1.
@article{25c7add15c6c4179ade27fc53fdd965e,
title = "Holistic and component plant phenotyping using temporal image sequence",
abstract = "Background: Image-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time. It has the potential to compute advanced phenotypes by considering the whole plant as a single object (holistic phenotypes) or as individual components, i.e., leaves and the stem (component phenotypes), to investigate the biophysical characteristics of the plants. The emergence timing, total number of leaves present at any point of time and the growth of individual leaves during vegetative stage life cycle of the maize plants are significant phenotypic expressions that best contribute to assess the plant vigor. However, image-based automated solution to this novel problem is yet to be explored. Results: A set of new holistic and component phenotypes are introduced in this paper. To compute the component phenotypes, it is essential to detect the individual leaves and the stem. Thus, the paper introduces a novel method to reliably detect the leaves and the stem of the maize plants by analyzing 2-dimensional visible light image sequences captured from the side using a graph based approach. The total number of leaves are counted and the length of each leaf is measured for all images in the sequence to monitor leaf growth. To evaluate the performance of the proposed algorithm, we introduce University of Nebraska-Lincoln Component Plant Phenotyping Dataset (UNL-CPPD) and provide ground truth to facilitate new algorithm development and uniform comparison. The temporal variation of the component phenotypes regulated by genotypes and environment (i.e., greenhouse) are experimentally demonstrated for the maize plants on UNL-CPPD. Statistical models are applied to analyze the greenhouse environment impact and demonstrate the genetic regulation of the temporal variation of the holistic phenotypes on the public dataset called Panicoid Phenomap-1. Conclusion: The central contribution of the paper is a novel computer vision based algorithm for automated detection of individual leaves and the stem to compute new component phenotypes along with a public release of a benchmark dataset, i.e., UNL-CPPD. Detailed experimental analyses are performed to demonstrate the temporal variation of the holistic and component phenotypes in maize regulated by environment and genetic variation with a discussion on their significance in the context of plant science.",
keywords = "Component phenotypes, Holistic phenotypes, Image sequence analysis, Plant architecture, Plant phenotyping",
author = "{Das Choudhury}, Sruti and Srinidhi Bashyam and Yumou Qiu and Samal, {Ashok K} and Tala Awada",
year = "2018",
month = "5",
day = "10",
doi = "10.1186/s13007-018-0303-x",
language = "English (US)",
volume = "14",
journal = "Plant Methods",
issn = "1746-4811",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Holistic and component plant phenotyping using temporal image sequence

AU - Das Choudhury, Sruti

AU - Bashyam, Srinidhi

AU - Qiu, Yumou

AU - Samal, Ashok K

AU - Awada, Tala

PY - 2018/5/10

Y1 - 2018/5/10

N2 - Background: Image-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time. It has the potential to compute advanced phenotypes by considering the whole plant as a single object (holistic phenotypes) or as individual components, i.e., leaves and the stem (component phenotypes), to investigate the biophysical characteristics of the plants. The emergence timing, total number of leaves present at any point of time and the growth of individual leaves during vegetative stage life cycle of the maize plants are significant phenotypic expressions that best contribute to assess the plant vigor. However, image-based automated solution to this novel problem is yet to be explored. Results: A set of new holistic and component phenotypes are introduced in this paper. To compute the component phenotypes, it is essential to detect the individual leaves and the stem. Thus, the paper introduces a novel method to reliably detect the leaves and the stem of the maize plants by analyzing 2-dimensional visible light image sequences captured from the side using a graph based approach. The total number of leaves are counted and the length of each leaf is measured for all images in the sequence to monitor leaf growth. To evaluate the performance of the proposed algorithm, we introduce University of Nebraska-Lincoln Component Plant Phenotyping Dataset (UNL-CPPD) and provide ground truth to facilitate new algorithm development and uniform comparison. The temporal variation of the component phenotypes regulated by genotypes and environment (i.e., greenhouse) are experimentally demonstrated for the maize plants on UNL-CPPD. Statistical models are applied to analyze the greenhouse environment impact and demonstrate the genetic regulation of the temporal variation of the holistic phenotypes on the public dataset called Panicoid Phenomap-1. Conclusion: The central contribution of the paper is a novel computer vision based algorithm for automated detection of individual leaves and the stem to compute new component phenotypes along with a public release of a benchmark dataset, i.e., UNL-CPPD. Detailed experimental analyses are performed to demonstrate the temporal variation of the holistic and component phenotypes in maize regulated by environment and genetic variation with a discussion on their significance in the context of plant science.

AB - Background: Image-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time. It has the potential to compute advanced phenotypes by considering the whole plant as a single object (holistic phenotypes) or as individual components, i.e., leaves and the stem (component phenotypes), to investigate the biophysical characteristics of the plants. The emergence timing, total number of leaves present at any point of time and the growth of individual leaves during vegetative stage life cycle of the maize plants are significant phenotypic expressions that best contribute to assess the plant vigor. However, image-based automated solution to this novel problem is yet to be explored. Results: A set of new holistic and component phenotypes are introduced in this paper. To compute the component phenotypes, it is essential to detect the individual leaves and the stem. Thus, the paper introduces a novel method to reliably detect the leaves and the stem of the maize plants by analyzing 2-dimensional visible light image sequences captured from the side using a graph based approach. The total number of leaves are counted and the length of each leaf is measured for all images in the sequence to monitor leaf growth. To evaluate the performance of the proposed algorithm, we introduce University of Nebraska-Lincoln Component Plant Phenotyping Dataset (UNL-CPPD) and provide ground truth to facilitate new algorithm development and uniform comparison. The temporal variation of the component phenotypes regulated by genotypes and environment (i.e., greenhouse) are experimentally demonstrated for the maize plants on UNL-CPPD. Statistical models are applied to analyze the greenhouse environment impact and demonstrate the genetic regulation of the temporal variation of the holistic phenotypes on the public dataset called Panicoid Phenomap-1. Conclusion: The central contribution of the paper is a novel computer vision based algorithm for automated detection of individual leaves and the stem to compute new component phenotypes along with a public release of a benchmark dataset, i.e., UNL-CPPD. Detailed experimental analyses are performed to demonstrate the temporal variation of the holistic and component phenotypes in maize regulated by environment and genetic variation with a discussion on their significance in the context of plant science.

KW - Component phenotypes

KW - Holistic phenotypes

KW - Image sequence analysis

KW - Plant architecture

KW - Plant phenotyping

UR - http://www.scopus.com/inward/record.url?scp=85046689713&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046689713&partnerID=8YFLogxK

U2 - 10.1186/s13007-018-0303-x

DO - 10.1186/s13007-018-0303-x

M3 - Article

C2 - 29760766

AN - SCOPUS:85046689713

VL - 14

JO - Plant Methods

JF - Plant Methods

SN - 1746-4811

IS - 1

M1 - 35

ER -