Plant Seedlings
2D Semantic Segmentation
License: CC BY-SA 4.0


The Plant Seedlings Dataset contains images of approximately 960 unique plants belonging to 12 species at several growth stages. It comprises annotated RGB images with a physical resolution of roughly 10 pixels per mm.

The database have been recorded at Aarhus University Flakkebjerg Research station in a collaboration between University of Southern Denmark and Aarhus University.

We hope that the database will provide researchers a foundation for training weed recognition algorithms. For more info about dataset, see the dataset description paper


author = {Giselsson, Thomas Mosgaard and Dyrmann, Mads and J{\o}rgensen, Rasmus Nyholm and
Jensen, Peter Kryger and Midtiby, Henrik Skov},
journal = {arXiv preprint},
keywords = {benchmark,database,plant seedlings,segmentation,site-specific weed control},
title = {{A Public Image Database for Benchmark of Plant Seedling Classification Algorithms}},
year = {2017}


CC BY-SA 4.0

Data Summary
Provided by
Department of Engineering – Aarhus University
In recent years, computer vision and machine learning have gained popularity at a near exponential pace due to the impressive achievement on real-world problems. In our group, we research techniques and devise methodologies for acquiring, processing and analyzing information in image data and other types for data. Researching these methodologies lead to concrete solutions to real-world problems for facilitating analysis and decision making in industry and research. We devise methodologies for acquiring domain specific dataset. We research computer vision and machine learning methods in e.g. Convolutional Neural Networks, Generative Adversarial Networks and Deep Reinforcement Learning. Applications include precision agriculture, weed and crop classification and analysis and autonomous systems. Our ambition is to advance computer vision and machine learning technology and facilitate the adoption of state-of-the-art solutions in our society through industrial and academic collaboration. Our research is primary founded by Innovation Fund Denmark, GUDP Denmark, public consultancy funds, industrial and private founding.
Start Building AI Now