2020
DOI: 10.1101/2020.10.19.345199
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

High-throughput phenotyping analysis of maize at the seedling stage using end-to-end segmentation network

Abstract: Image processing technologies are available for high-throughput acquisition and analysis of phenotypes for crop populations, which is of great significance for crop growth monitoring, evaluation of seedling condition, and cultivation management. However, existing methods rely on empirical segmentation thresholds, thus can have insufficient accuracy of extracted phenotypes. Taking maize as an example crop, we propose a phenotype extraction approach from top-view images at the seedling stage. An end-to-end segme… Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 44 publications
0
3
0
Order By: Relevance
“…π‘š 𝑙=1 (10) where m represents the number of comparison objects, 𝑣 𝑙 denotes the value of manual measurement results, 𝑣 𝑙 β€² denotes the values of the phenotypic parameters extracted from the segmentation results according to the PointNet model, and 𝑣̅ 𝑙 indicates the mean value of the manual measurement results.…”
Section: Evaluation Indicatormentioning
confidence: 99%
See 1 more Smart Citation
“…π‘š 𝑙=1 (10) where m represents the number of comparison objects, 𝑣 𝑙 denotes the value of manual measurement results, 𝑣 𝑙 β€² denotes the values of the phenotypic parameters extracted from the segmentation results according to the PointNet model, and 𝑣̅ 𝑙 indicates the mean value of the manual measurement results.…”
Section: Evaluation Indicatormentioning
confidence: 99%
“…The conventional method of phenotype acquisition is mainly urate-based. Phenotype traits obtained using images can be used for studies such as biomass estimation [6], nutritional diagnosis [7], growth and development monitoring [8], plant structural analysis [9], quantitative description of phenotypic traits [10], and pest and disease identification [11]. In recent years, significant breakthroughs have been achieved in digital image processing using deep learning; the performance of deep learning-based image processing has been much better than traditional methods in applications such as object recognition and segmentation [12][13][14].…”
Section: Introductionmentioning
confidence: 99%
“…Successful application of HTP platforms for use in drought, salinity and heat/ cold stress tolerance in plants, particularly cereal crops need capacity infrastructure for data management and analysis. (Shakoor et al, 2017;Li et al, 2021). The application of HTP for abiotic stress resilience in various cereal crops has been summarized (Table 1).…”
Section: High Throughput Phenotyping (Htp) Data Analysis and Managementmentioning
confidence: 99%