A survey of datasets for computer vision in agriculture

TL;DR

This paper surveys 45 publicly available datasets of field images for agricultural computer vision, highlighting the scarcity of high-quality datasets and the need for a centralized data repository to advance research.

Contribution

It provides a comprehensive catalog of agricultural image datasets and discusses challenges in data availability and sharing in agricultural computer vision research.

Findings

45 datasets identified and cataloged

Lack of high-quality datasets hampers research progress

Need for a centralized agricultural data repository

Abstract

In agricultural research, there has been a recent surge in the amount of Computer Vision (CV) focused work. But unlike general CV research, large high-quality public datasets are sparsely available. This can be partially attributed to the high variability between different agricultural tasks, crops and environments as well as the complexity of data collection, but it is also influenced by the reticence to publish datasets by many authors. This, as well as the lack of a widely used agricultural data repository, are impactful factors that hinder research in applied CV for agriculture as well as the usage of agricultural data in general-purpose CV research. In this survey, we provide a large number of high-quality datasets of images taken on fields. Overall, we find 45 datasets, which are listed in this paper as well as in an online catalog on the project website: https://smartfarminglab.github.io/field_dataset_survey/.