ABOUT

SORDI (Synthetic Object Recognition Dataset for Industries) is a collaboration between BMW IT TechOffice Munich, idealworks, NVIDIA and Microsoft which enables software developers to utilise industry standard datasets to train computer vision models. The dataset is comprised of synthetic images of a library of 3D assets; many of which are authored by the QUT interns and Academy staff (i.e. our 3D asset library for the BMW iFACTORY).

For the launch of SORDI and their online presence, the Academy was responsible for a short animation to feature on the landing page of the SORDI website. The final result is a carousel of industrial assets that seamlessly loop. Each one pauses with coloured bounding boxes appearing, to visualise and communicate the object recognition process that occurs. Each year since it was launched, new AI capabilities are being developed and added to the SORDI dataset, as shown in the other Special Projects for TechOffice.