Using the KiwiVision™ software, Berlin researchers conduct detailed traffic analyses in the German capital, without interfering with the personal rights of civilians.
Explore this project in photos
All around the Ernst-Reuther-Place in Berlin, the future of inner-city road traffic is being reshaped. Several companies have come together to contribute to the "Smart City Berlin" project and it's subsequent activities. Amongst them we find T-Systems, Cisco, TÜV Nord, along with the Technische Universität Berlin (TU Berlin). The group aims to research the digitization of road environments, the opportunities for autonomous driving, traffic low management, and the environmental protection of Berlin's metropolitan regions. Numerous cameras and other sensors were installed to provide information about road users and traffic density, road conditions, parking space occupancy, traffic light synchronization, and weather.
On the one hand, the precise recording and categorization of all road users is an indispensable basis for meaningful data models; on the other hand, the German Data Protection Act and the European General Data Protection Regulation (GDPR) demands privacy protection, especially in public spaces. “We have the actual data on all road users, so we can simulate traffic at any given time," says Dr. Ing. Habil Manzoor Ahmed Khan, one of the lead researchers at the DAI Laboratory. “This was only made possible because from the outset, we have paid attention to the rights of road users, whose consent we cannot obtain. We had to come up with a viable approach to privacy that was rigorously tested.”
“Because capture and identification are so central to our project, we have looked at several technologies and conducted comparative studies. KiwiVision definitely fits our requirements the best, so we decided to use it and this turned out to be the right decision.”
Dr. Ing. Habil Manzoor Ahmed Khan, director of network & mobility at the Distributed Artificial Intelligence Laboratory (DAI)
The cameras use KiwiVision video analytics, which recognizes objects in the traffic flow, categorizes them and anonymizes the data obtained. Only after anonymization is the data collected by a self-developed IoT middleware of the DAI laboratory and forwarded to processing systems. Trucks, cars, and even pedestrians appear as circles, squares, or triangles in the analyses and simulations. The researchers do not require any more information than that. Subsequent de-anonymization is impossible because the video streams are not recorded.
Precise traffic data
The KiwiVision algorithms cannot be fooled by different weather conditions such as snow or rain and can even identify moving objects just as reliably as static ones.
Data models require accurate information about road users. But the collection of data on road users is restricted by the European General Data Protection Regulation (GDPR). By employing KiwiVision technology, these opposing interests could successfully be united.
Integration with Security Center™
The algorithms that provide the data for Berlin are also used in the Genetec KiwiVision® Privacy Protector®. With this pixelation and masking solution, companies can ensure that employees and visitors are made unrecognizable despite comprehensive video surveillance. Privacy Protector fully integrates with Security Center, the unified security platform from Genetec.
European Privacy Seal
The KiwiVision® Privacy Protector® is one of few solutions that has received the European Privacy Seal. This seal of approval is only awarded after extensive technical and legal examination of the compatibility of IT products with European data protection directives.
Need more information about this project?