This content is not included in your SAE MOBILUS subscription, or you are not logged in.
FSOCO: The Formula Student Objects in Context Dataset
ISSN: 2574-0741, e-ISSN: 2574-075X
Published January 06, 2022 by SAE International in United States
Citation: Vödisch, N., Dodel, D., and Schötz, M., "FSOCO: The Formula Student Objects in Context Dataset," SAE Intl. J CAV 5(1):23-32, 2022, https://doi.org/10.4271/12-05-01-0003.
This article presents the Formula Student Objects in Context (FSOCO) dataset, a collaborative dataset for vision-based cone detection systems in Formula Student Driverless (FSD) competitions. It contains human-annotated ground truth labels for both bounding boxes and instance-wise segmentation masks. The data buy-in philosophy of FSOCO asks student teams to contribute to the database first before being granted access, ensuring continuous growth. By providing clear labeling guidelines and tools for a sophisticated raw image selection, new annotations are guaranteed to meet the desired quality. The effectiveness of the approach is shown by comparing the prediction results of a network trained on FSOCO and its unregulated predecessor. The FSOCO dataset can be found at fsoco-dataset.com.