Wilhelm Kilian ^* Jaco Prinsloo Jan Vosloo Stéphan Taljaard

• North-West University, Potchefstroom, South Africa

Many industries utilise deep learning methods to increase efficiency and reduce costs. One of these methods, image segmentation, is used for object detection and recognition in localisation and mapping. Segmentation models are trained using labelled datasets; however, manually creating datasets for every application, including deep-level mining, is time-consuming and typically expensive. Recently, many papers have shown that using synthetic datasets (digital recreations of real-world scenes) for training produces highly accurate segmentation models. This paper proposes a synthetic segmentation dataset generator using a 3D modelling framework and raycaster. The generator was applied to a deep-level mining case study and produced a dataset containing labelled images of scenes typically found in this environment, therefore removing the requirement to create the dataset manually. Validation showed high accuracy segmentation after model training using the generated dataset (compared to other applications that use real-world datasets). Furthermore, the generator can be customised to produce datasets for many other applications.