Novel Synthetic Data Tool for Data-Driven Cardboard Box Localization
This addresses data scarcity for automated factories, but it is incremental as it applies an existing synthetic data approach to a specific domain.
The paper tackles the problem of costly labeled data production for neural networks in industrial bin-picking by presenting an automatic synthetic data generation tool with a procedural cardboard box model, and empirically proves its usefulness by training a neural network.
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.