中文

用于数据驱动纸箱定位的新型合成数据工具

计算机视觉与模式识别 2024-02-27 v2

摘要

神经网络在工业环境中的应用,例如带有拣箱(bin-picking)解决方案的自动化工厂,需要昂贵地制作大型标注数据集。本文提出一种带有纸箱程序化模型的自动数据生成工具。我们简要展示了系统的能力及其各种参数,并通过训练一个简单的神经网络实证证明了所生成合成数据的有用性。我们公开提供了该工具生成的合成数据样本。

关键词

引用

@article{arxiv.2305.05215,
  title  = {Novel Synthetic Data Tool for Data-Driven Cardboard Box Localization},
  author = {Lukáš Gajdošech and Peter Kravár},
  journal= {arXiv preprint arXiv:2305.05215},
  year   = {2024}
}

备注

Extended Abstract Published in 2023 Artificial Neural Networks and Machine Learning (ICANN). Published version copyrighted by Springer Nature Switzerland. Accepted: 29.6.2023. Published: 22.9.2023. This work was funded by the Horizon-Widera-2021 European Twinning project TERAIS G.A. n. 101079338. Code: https://doi.org/10.5281/zenodo.10649535 Data: https://doi.org/10.5281/zenodo.10650158