Deep-learning-ready RGB-depth images of seedling development

• Published in: Plant methods Vol. 21; no. 1; p. 16
• Main Authors: Mercier, Félix, Couasnet, Geoffroy, El Ghaziri, Angelina, Bouhlel, Nizar, Sarniguet, Alain, Marchi, Muriel, Barret, Matthieu, Rousseau, David
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 11.02.2025; BioMed Central; BMC
• Subjects: Bioinformatics; Computer Science; Data Analysis, Statistics and Probability; data collection; Deep learning; Development; Image processing; Machine learning; phenotype; Physics; Physiological aspects; Plants; RGB-depth; seedling emergence; Seedling kinetics; Seedlings; species; Technology application; France; Deep learning; Data set; RGB-depth; Seedling kinetics
• ISSN: 1746-4811; 1746-4811
• DOI: 10.1186/s13007-025-01334-3

In the era of machine learning-driven plant imaging, the production of annotated datasets is a very important contribution. In this data paper, a unique annotated dataset of seedling emergence kinetics is proposed. It is composed of almost 70,000 RGB-depth frames and more than 700,000 plant annotations. The dataset is shown valuable for training deep learning models and performing high-throughput phenotyping by imaging. The ability of such models to generalize to several species and outperform the state-of-the-art owing to the delivered dataset is demonstrated. We also discuss how this dataset raises new questions in plant phenotyping.