Application of neural networks in industrial settings, such as automated factories with bin-picking solutions requires costly production of large labeled data-sets. This paper presents an automatic data generation tool with a procedural model of a cardboard box. We briefly demonstrate the capabilities of the system, its various parameters and empirically prove the usefulness of the generated synthetic data by training a simple neural network. We make sample synthetic data generated by the tool publicly available.
Cite
@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}
}
Comments
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