Data from: No More Laborious Stem Counting: AI-powered Computer Vision Enables Identification and Quantification of Solid and Hollow Alfalfa Stems at the Pixel Level
The data collected for the article "No More Laborious Stem Counting: AI-powered Computer Vision Enables Identification and Quantification of Solid and Hollow Alfalfa Stems at the Pixel Level" includes image data, labeled JSON data, and machine and deep learning model data. This data was gathered to develop and validate an AI-powered computer vision system designed to accurately identify and quantify solid and hollow alfalfa (Medicago sativa L.) stems at the pixel level. The images were captured under controlled conditions to ensure consistency and quality. The labeled JSON data provides detailed annotations for each image, which were used to train and evaluate the machine and deep learning models. These models were developed to automate the stem counting process, significantly reducing the manual labor involved and improving accuracy. By using this data and the provided models, researchers can reproduce the experiments and achieve the same results, facilitating further research and application in agricultural studies.
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| bureauCode |
[
"005:18"
]
|
| contactPoint |
{
"fn": "Xu, Zhanyou",
"hasEmail": "mailto:zhanyou.xu@usda.gov"
}
|
| description | <p dir="ltr">The data collected for the article "No More Laborious Stem Counting: AI-powered Computer Vision Enables Identification and Quantification of Solid and Hollow Alfalfa Stems at the Pixel Level" includes image data, labeled JSON data, and machine and deep learning model data. This data was gathered to develop and validate an AI-powered computer vision system designed to accurately identify and quantify solid and hollow alfalfa (<i>Medicago sativa</i> L.) stems at the pixel level. The images were captured under controlled conditions to ensure consistency and quality. The labeled JSON data provides detailed annotations for each image, which were used to train and evaluate the machine and deep learning models. These models were developed to automate the stem counting process, significantly reducing the manual labor involved and improving accuracy. By using this data and the provided models, researchers can reproduce the experiments and achieve the same results, facilitating further research and application in agricultural studies.</p> |
| distribution |
[
{
"@type": "dcat:Distribution",
"title": "Stem_Data_Labeled_250.zip",
"format": "zip",
"mediaType": "application/zip",
"downloadURL": "https://ndownloader.figshare.com/files/53624039"
}
]
|
| identifier | 10.15482/USDA.ADC/28783748.v1 |
| keyword |
[
"Otsu's Method",
"Otsu_Thresholding",
"Phenotyping",
"Stem",
"YOLO",
"You Only Look Once",
"hollowness",
"solidness"
]
|
| license | https://creativecommons.org/publicdomain/zero/1.0/ |
| modified | 2025-05-16 |
| programCode |
[
"005:040"
]
|
| publisher |
{
"name": "Agricultural Research Service",
"@type": "org:Organization"
}
|
| temporal | 2025-04-12/2025-04-12 |
| title | Data from: No More Laborious Stem Counting: AI-powered Computer Vision Enables Identification and Quantification of Solid and Hollow Alfalfa Stems at the Pixel Level |
