Texas A&M Engineering Experiment Station, Texas A&M AgriLife Research Plant Growth and Phenotyping Facility, and Department of Electrical & Computer Engineering

A Data-Driven Image Extraction and Analysis Pipeline for Plant Phenotyping in Controlled Environments

Published in The Plant Phenome Journal, 2026 · doi:10.1002/ppj2.70116
Fahimeh Orvati Nia1*,  Joshua Peeples1*,  Seth C. Murray2,  Andrew McFarland3,  Troy Vann3,  Shima Salehi1,  Robert Hardin4,  David D. Baltensperger2,  Amir M. H. Ibrahim3,  J. Alex Thomasson5,  Henry Fadamiro6,  Nithya K. Subramanian2,  Suresh D. Pillai7,  Rebecca Roston8,  Joslin Ishimwe8,  Diptadeep Basak8,  Nazar Oladepo1, and  Uday Vysyaraju1
1Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
2Department of Soil and Crop Sciences, Texas A&M University, College Station, TX, USA
3Texas A&M AgriLife Research, Texas A&M University, College Station, TX, USA
4Department of Biological and Agricultural Engineering, Texas A&M University, College Station, TX, USA
5Department of Agricultural and Biological Engineering, Mississippi State University, Mississippi State, MS, USA
6Department of Entomology, Texas A&M University, College Station, TX, USA
7National Center for Electron Beam Research, Texas A&M University, College Station, TX, USA
8Department of Biochemistry, University of Nebraska–Lincoln, Lincoln, NE, USA
*Correspondence: fahimehorvatinia@tamu.edu, jpeeples@tamu.edu

Materials

The Plant Phenome Journal Paper
Dataset Dataset
Code Code
Hugging Face Hugging Face Demo
Read the Docs Documentation
Texas A&M AgriLife Institution
Abstract

Temporal imaging of plants in controlled environments helps scientists better understand growth and biological processes. However, analyzing large volumes of images has been limited by a lack of accessible, standardized datasets and automated analytical tools. This website presents a comprehensive dataset and analysis pipeline for plant phenotyping. The system integrates image acquisition, segmentation, feature extraction, and interpretation to support high-throughput phenotyping in greenhouse settings. The dataset includes multiple plant species and developmental stages, enabling researchers to benchmark detection and trait estimation approaches at scale.

Project Organization and Workflow Integration
Figure 1: Integration of teams and responsibilities in the Texas A&M AgriLife Phenotyping Greenhouse project.
Comprehensive Phenotyping Pipeline
Figure 2: Comprehensive pipeline for multispectral plant phenotyping and feature analysis.
Plant Growth and Phenotyping Version 2 Dataset

This study introduces the expanded Plant Growth and Phenotyping Version 2 dataset (PGP v2), which substantially increases both scale and diversity from the initial release, comprising approximately 220,000 plant images spanning four crop species—corn, cotton, rice, and sorghum—under controlled greenhouse conditions. Across the dataset, each plant image is paired with complementary metadata describing treatment variables, environmental conditions, and temporal indices, creating a standardized platform for training and benchmarking analytical models. The dataset was designed to support reproducible monitoring of phenological development, stress responses, and trait estimation across multiple plant growth stages while preserving the fidelity required for downstream segmentation and classification workflows.

Dataset Samples
Corn (~14,000 images)
Corn sample 1
Corn sample 2
Corn sample 3
Corn sample 4
Cotton (~27,000 images)
Cotton sample 1
Cotton sample 2
Cotton sample 3
Cotton sample 4
Rice (~1,376 images)
Rice sample 1
Rice sample 2
Rice sample 3
Rice sample 4
Sorghum (~10,608 images)
Sorghum sample 1
Sorghum sample 2
Sorghum sample 3
Sorghum sample 4
Citation
Plain Text (APA):
Nia, F. O., Peeples, J., Murray, S. C., McFarland, A., Vann, T., Salehi, S., Hardin, R., Baltensperger, D. D., Ibrahim, A. M. H., Thomasson, J. A., Fadamiro, H., Subramanian, N. K., Pillai, S. D., Roston, R., Ishimwe, J., Basak, D., Oladepo, N., & Vysyaraju, U. (2026). A data-driven image extraction and analysis pipeline for plant phenotyping in controlled environments. The Plant Phenome Journal, 9(1), e70116. https://doi.org/10.1002/ppj2.70116
BibTeX:
@article{nia2026datadriven,
  title     = {A data-driven image extraction and analysis pipeline for plant phenotyping in controlled environments},
  author    = {Nia, Fahimeh Orvati and Peeples, Joshua and Murray, Seth C. and McFarland, Andrew and Vann, Troy and Salehi, Shima and Hardin, Robert and Baltensperger, David D. and Ibrahim, Amir M. H. and Thomasson, J. Alex and Fadamiro, Henry and Subramanian, Nithya K. and Pillai, Suresh D. and Roston, Rebecca and Ishimwe, Joslin and Basak, Diptadeep and Oladepo, Nazar and Vysyaraju, Uday},
  journal   = {The Plant Phenome Journal},
  volume    = {9},
  number    = {1},
  pages     = {e70116},
  year      = {2026},
  publisher = {Wiley},
  doi       = {10.1002/ppj2.70116},
  url       = {https://doi.org/10.1002/ppj2.70116}
}