arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.07139cs.CVcs.LGcs.RO
收藏

FSOCO:上下文中的大学生方程式赛车对象数据集

FSOCO: The Formula Student Objects in Context Dataset

ETH Zürich(苏黎世联邦理工学院);LMU Munich(慕尼黑大学);Deggendorf Institute of Technology(德根多夫应用技术大学)

Niclas Vödisch, David Dodel, Michael Schötz

AI总结:

本文介绍FSOCO数据集,通过协作共享与标注规范机制,为大学生方程式无人驾驶竞赛提供高质量锥桶检测数据,并验证了其有效性。

摘要:

本文介绍了FSOCO数据集,这是一个用于大学生方程式无人驾驶竞赛中基于视觉的锥桶检测系统的协作型数据集。它包含人工标注的真实标签,涵盖边界框和实例级分割掩码。FSOCO的数据共享理念要求学生团队先向数据库贡献数据,然后才能获得访问权限,以确保其持续增长。通过提供清晰的标注指南和用于复杂原始图像选择的工具,确保新标注达到所需的质量。通过比较在FSOCO及其无监管前身数据集上训练的网络的预测结果,展示了该方法的有效性。FSOCO数据集可在https://fsoco.github.io/fsoco-dataset/ 找到。

英文摘要:

This paper presents the FSOCO dataset, a collaborative dataset for vision-based cone detection systems in Formula Student Driverless 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 prediction results of a network trained on FSOCO and its unregulated predecessor. The FSOCO dataset can be found at https://fsoco.github.io/fsoco-dataset/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑