Reconfigurable manufacturing systems are becoming the only viable option to respond to changing product volumes and product specification, which are currently major challenges for the manufacturing industry. Part of this adaptation requires vision systems to be quickly updated to handle new unseen products. For deep learning-based vision systems, this means re-training on images that might not be available. Although there is some existing work on synthetic image generation in manufacturing contexts using a variety of domain randomisation techniques, there is a lack of understanding of which domains are critical in the effectiveness of the resulting trained model. There are currently no open tools to systematically conduct such ablation studies. This paper presents a tool based on Blender and CAD models to enable the study of domain randomisation in the generation of synthetic-only datasets that can yield accurate object recognition models. Preliminary results to validate the implemented domain randomisation techniques and the ability to generate the synthetic images are presented. Once generated, synthetic data sets are used to train a YOLOv8 model for object detection as a second tool validation step. Future work will look at performing ablation studies and expanding the range of domain randomisation methods to further study the capabilities of synthetic images.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    A Tool for Generating and Labelling Domain Randomised Synthetic Images for Object Recognition in Manufacturing


    Weitere Titelangaben:

    Lect.Notes Mechanical Engineering


    Beteiligte:
    Alexopoulos, Kosmas (Herausgeber:in) / Makris, Sotiris (Herausgeber:in) / Stavropoulos, Panagiotis (Herausgeber:in) / Martínez-Arellano, Giovanna (Autor:in) / Buck, Michael G. (Autor:in)

    Kongress:

    European Symposium on Artificial Intelligence in Manufacturing ; 2024 ; Athens, Greece October 16, 2024 - October 16, 2024



    Erscheinungsdatum :

    22.03.2025


    Format / Umfang :

    8 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Hybrid object labelling in digital images

    Martín-Herrero, J. | British Library Online Contents | 2007


    LABELLING - Labelling News

    Online Contents | 2003


    LABELLING - Labelling news

    Online Contents | 2002


    Object Recognition by Combining Paraperspective Images

    Sugimoto, A. | British Library Online Contents | 1996