Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection
This addresses the data scarcity issue for industrial automation applications, but it is incremental as it applies existing methods to a specific domain with minor optimizations.
The paper tackled the problem of insufficient real training data for deep learning object detection in industrial settings by investigating the sim-to-real generalization of standard object detectors on terminal strip detection, finding that under optimized scaling conditions, the performance difference in mean average precision was 2.69% for RetinaNet and 0.98% for Faster R-CNN.
In industrial manufacturing, numerous tasks of visually inspecting or detecting specific objects exist that are currently performed manually or by classical image processing methods. Therefore, introducing recent deep learning models to industrial environments holds the potential to increase productivity and enable new applications. However, gathering and labeling sufficient data is often intractable, complicating the implementation of such projects. Hence, image synthesis methods are commonly used to generate synthetic training data from 3D models and annotate them automatically, although it results in a sim-to-real domain gap. In this paper, we investigate the sim-to-real generalization performance of standard object detectors on the complex industrial application of terminal strip object detection. Combining domain randomization and domain knowledge, we created an image synthesis pipeline for automatically generating the training data. Moreover, we manually annotated 300 real images of terminal strips for the evaluation. The results show the cruciality of the objects of interest to have the same scale in either domain. Nevertheless, under optimized scaling conditions, the sim-to-real performance difference in mean average precision amounts to 2.69 % for RetinaNet and 0.98 % for Faster R-CNN, qualifying this approach for industrial requirements.