BMW Group has developed an AI-based solution that can anonymise objects in photos and videos, enabling the company to blur objects or people in images of their production sites.
The system builds on BMW’s Lite labelling tool and uses algorithms for targeted protection of relevant information.
According to the German automotive manufacturer, the software uses AI to automatically classify image areas according to their features, so any areas that need to be made unrecognisable can be blocked out.
The granularity and degree of anonymisation can be intuitively adjusted while different modes of anonymisation can be selected, which means respective areas in photos or videos can be blurred, blacked out or pixelated.
Markus Grüneisl, head of production system, digitalisation at BMW Group, said: “AI applications support us with quality assurance, such as inspection of parts and components, as well as development of our autonomous, smart logistics robots.
“The AI anonymisation algorithms now published also ensure optimal data privacy and information protection.
“Making the anonymisation solution intuitive to operate was an important aspect of development for us, to ensure it can easily be used for a wide range of applications.”
Furthermore, with no-code AI the system enables production staff to create their own solutions, supporting them in their individual processes.
BMW said the solution is based on a plug-and-play principle with the user requiring no further programming skills, specific hardware or additional software.
The system is also designed to offer a high level of robustness, even under highly variable boundary conditions.
BMW has made the made algorithms freely available to software developers to view, modify and further develop the source code.
Additional AI applications used by BWM include a system to recognise and classify objects in images and for the development of autonomous smart logistics robots.
