Persistent Identifier
|
doi:10.7910/DVN/MAYDHT |
Publication Date
|
2023-10-15 |
Title
| HyperPRI: A Dataset of Hyperspectral Images for Underground Plant Root Study |
Author
| Chang, Spencer JUniversity of FloridaORCID0009-0007-6272-2905
Chowdhry, RiteshUniversity of FloridaORCID0009-0001-5605-2075
Song, YangyangUniversity of FloridaORCID0000-0002-4385-4538
Mejia, TomasUniversity of Florida
Hampton, AnnaUniversity of FloridaORCID0000-0002-5335-3016
Kucharski, ShelbyUniversity of FloridaORCID0009-0001-6068-3187
Sazzad, TMUniversity of Florida
Zhang, YuxuanUniversity of FloridaORCID0009-0002-4044-3191
Koppal, Sanjeev JUniversity of FloridaORCID0000-0001-6769-8974
Wilson, Chris HUniversity of FloridaORCID0000-0001-7695-8299
Gerber, StefanUniversity of FloridaORCID0000-0002-1474-4188
Tillman, BarryUniversity of FloridaORCID0000-0001-5558-0231
Resende Jr., Marcio FRUniversity of FloridaORCID0000-0002-2367-0766
Hammon, William MUniversity of FloridaORCID0000-0002-2904-810X
Zare, AlinaUniversity of FloridaORCID0000-0002-4847-7604 |
Point of Contact
|
Use email button above to contact.
Chang, Spencer (University of Florida)
Zare, Alina (University of Florida) |
Description
| Here we present Hyperspectral Plant Root Imagery (HyperPRI), the first available dataset of RGB and HSI data for in situ, non-destructive, underground plant root analysis using machine learning tools. HyperPRI contains images of plant roots grown in rhizoboxes for two annual crop species – peanut (Arachis hypogaea) and sweet corn (Zea mays). Drought conditions are simulated once, and the boxes are imaged and weighed on select days across two months. Along with the images, we provide hand-labeled semantic masks and imaging environment metadata. HyperPRI may be applied to semantic segmentation, plant phenotyping, and drought resilience studies. The proposed dataset may also have transferable insights for other datasets containing thin object features among highly textured backgrounds. Dataset Features
- Red-green-blue (RGB) and hyperspectral imaging (HSI) data
- Temporal data for rhizoboxes - plants are monitored from seedling till they are reproductively mature.
- Thin roots as narrow as 1-3 pixels
- Highly texture soil background
- High-resolution spectral data with high correlation between channels
Computer Vision Tasks
- Compute root characteristics (length, diameter, angle, count, system architecture, hyperspectral)
- Determine root turnover
- Observe drought resiliency and response
- Compare multiple physical and hyperspectral plant traits across time
- Investigate texture analysis techniques
- Segment roots vs. soil
(2023-10-15) |
Subject
| Agricultural Sciences |
Keyword
| root physiology
hyperspectral imagery
minirhizotron
rhizotron
semantic segmentation |
Related Publication
| Spencer J. Chang, Ritesh Chowdhry, Yangyang Song, Tomas Mejia, Anna Hampton, Shelby Kucharski, T.M. Sazzad, Yuxuan Zhang, Sanjeev J. Koppal, Chris H. Wilson, Stefan Gerber, Barry Tillman, Marcio F.R. Resende, William M. Hammond, Alina Zare, HyperPRI: A dataset of hyperspectral images for underground plant root study, Computers and Electronics in Agriculture, Volume 225, 2024, 109307, ISSN 0168-1699, doi 10.1016/j.compag.2024.109307 https://doi.org/10.1016/j.compag.2024.109307 |
Notes
| Related Publication accepted to Elsevier's Computer and Electronics in Agriculture as of August 2024. Presented through a poster in the CVPPA workshop at ICCV 2023. Related code: https://github.com/GatorSense/HyperPRI. |
Language
| English |
Production Date
| 2022-05-23 |
Funding Information
| United States Department of Agriculture: Accession No. 1024671
Southeastern Peanut Research Initiative
Florida Peanut Producers Association |
Depositor
| Chang, Spencer |
Deposit Date
| 2023-10-12 |
Time Period
| Start Date: 2022-06-15; End Date: 2022-08-24 |
Date of Collection
| Start Date: 2022-06-15; End Date: 2022-07-28
Start Date: 2022-06-24; End Date: 2022-08-24 |
Data Type
| RGB images (.png); HSI images (.hdr, .dat); tabular metadata (.csv) |