An annotated dataset of soybean root nodules for deep learning-based object detection

Abstract

Abstract Technological advances have expanded the adoption of digital technologies in agriculture, helping to reduce labour effort, increase profitability, improve crop efficiency and productivity, enhance product quality, mitigate environmental impacts, and promote human health. This context also extends to soybean farming, a sector of major economic importance in Brazil. Most importantly, Brazil has the global leadership in soybean production with biological nitrogen fixation (BNF) replacing chemical fertilisers. The research and evaluation of BNF is limited by manual counting of nodules, a time-consuming procedure. This study presents SoyNodules, designed for the automatic identification of soybean nodules, consisting of a dataset of images. The dataset includes 1,701 images acquired under controlled conditions: 1,662 images of soybean roots with nodules and 39 images of isolated nodules without roots. A total of 49,210 nodule instances are manually annotated with bounding boxes. SoyNodules was designed to promote reuse and interoperability in alignment with the FAIR principles (Findable, Accessible, Interoperable, Reusable) and to support the development, training, and evaluation of computer vision and deep learning methods for precision agriculture.

Code and data availability

The paper is a data descriptor for SoyNodules, an annotated dataset of 1,701 soybean root/nodule images with 49,210 bounding-box annotations, publicly deposited on Zenodo with a DOI. The same repository also hosts the authors' annotation-format conversion script (AnyLabeling to Pascal VOC/COCO), per the Code Availabil­