Celantur and Virtual Vehicle Collaborate for Privacy Preserving Driving Technology

Enabling automotive companies to develop AD/ADAS systems while respecting privacy.


27 November 2023, by Alexander PetkovAsk a question


The team of Celantur and Virtual Vehicle. (c) Bernhard Lehner
The team of Celantur and Virtual Vehicle. (c) Bernhard Lehner

Celantur GmbH and Virtual Vehicle GmbH have teamed up to enable automotive companies to develop AD/ADAS systems while respecting privacy, by improving Celantur's image and video anonymization technology.

The initiative, born out of a chance encounter at the "Cross-border testing of Automated Driving Conference" in April 2023, started in July 2023. The partnership also navigated legal complexities, especially those related to GDPR, with the support of the Virtual Vehicle legal team.

The project* has yielded a substantial volume of street-level data, providing a realistic representation of scenarios encountered by automotive companies. This comprehensive dataset serves a dual purpose—enabling improvements to Celantur's anonymization solutions through enhanced training data and adding support for new industry-standard data formats (MCAP).

Building on the success of the initial phase, Celantur and Virtual Vehicle GmbH plan to broaden their collaboration efforts. The upcoming stages will involve capturing a more diverse array of regions, camera systems, and other variables, ensuring a comprehensive dataset for further advancements in Advanced Driver Assistance Systems (ADAS) technology.

*The cooperation was carried out as part of the European Digital Innovation Hub EDIH Applied CPS with the kind support of the European Commission, the Federal Ministry of Labour & Economy and the FFG.

Anonymized automotive imagery.
Anonymized automotive imagery.

Ask us Anything. We'll get back to you shortly

automotivedata protectiongdprenglish
Start Demo Contact Us

Latest Blog Posts

Using object tracking to combat flickering detections in videos

How to decrease the amount of flickering detections in videos with object tracking.


How to copy XMP metadata between JPEG images (again)

Copying XMP metadata between images isn't straightforward. Read how it's done correctly.


20x Faster Than NumPy: Mean & Std for uint8 Arrays

How to calculate mean and standard deviation 20 times faster than NumPy for uint8 arrays.