Synthetic Data Generation on Dynamic Industrial Environment for Object Detection, Tracking, and Segmentation CNNs

Abstract

The ability of Convolutional Neural Networks (CNNs) to learn from vast amounts of data and improve accuracy over time makes them an attractive solution for many industrial problems. In the context of Future Assembly Systems such as Line-Less Mobile Assembly Systems, CNNs can be used to monitor the networked system of mobile robots, human operators, and other movable objects that assemble products in flexible environment configurations. This paper explores the use of a simulated industrial environment to autonomously generate training data for object detection, tracking, and segmentation CNNs. The goal is to adapt state-of-the-art CNN solutions to specific industry use cases, where real data annotation can be time-consuming and expensive. The developed algorithm efficiently generates new random image data, allowing accurate object detection, tracking, and segmentation in dynamic industrial scenarios. The results show the effectiveness of this approach in improving the testing of CNNs for industrial applications.