Novel Synthetic Data Tool for Data-Driven Cardboard Box Localization
Paper
32nd International Conference on Artificial Neural Networks (ICANN 2023)
Lukáš Gajdošech, Peter Kravár, Martin Madaras
Abstract
Application of neural networks in industrial settings, such as automated factories with bin-picking solutions requires costly production of large labeled datasets. This paper presents an automatic data generation tool with a procedural model of a cardboard box. We briefly demonstrate the capabilities of the system, and 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.
