Deviation detection in production processes based on video data using unsupervised machine learning approaches

Sorry you have no rights to view this entry!

3 Comments

  1. Hi Matthias,

    Very interesting presentation! Sorry, I am a bit confused, the benchmark datasets you created are frames recorded from simulation software? or frames recorded from real 3D printers and screws’ movements?

    • matthias.muehlbauer

      Hello Zhu,

      Thank you for the question! We have recorded two real processes. However, using simulated data as a basis would also be an interesting approach!

      • Hi Matthias,
        Thank you for the replying.
        That’s very nice. I wonder if the benchmark dataset will be open source?
        And yes. I am also very curious how simulate data can help in anomaly detection.
        Beside, If you are interested can check my paper under Assembly section, using unsupervised domain adaptive object detection with simulated data for assembly quality inspection.

Leave a Reply

Your email address will not be published. Required fields are marked *