Key-features
The STORE project is dedicated to the development of AI-based image recognition systems for threat assessment and to the creation of a shared European database of annotated defence images from optronic systems. To meet these high level requirements, the project focuses on the following critical key features.
STORE is developing a new type of distributed database architecture based on a set of local database nodes with dedicated synchronization and coordination services, secured by advanced technologies.
The resulting architecture enables shared governance among member states by applying exchange restriction rules based on policy and releasability. Furthermore, the architecture allows for a strong decoupling of data acquisition, cleaning and consolidation processes from database exploitation for scientific or engineering purposes.
Shared European Database
Leading edge AI factory dedicated to image recognition for detection
STORE enables the extension of the operational use of image recognition systems by making them more robust to a variety of observation conditions and by addressing new forms of threats such as small drones and drone swarms, loitering munitions and hypersonic threats. Additionally, STORE’s potential to mature AI methods provides an effective approach to assessing emerging threats supported by AI-based systems.
STORE addresses the latest technologies for sharing data and models across borders, companies and defence institutions in a controlled and trustworthy manner while maintaining privacy and security.
A software architecture framework is maturing decentralized learning techniques to decouple model training from a central database, therefore allowing AI models to be trained without exposing critical data.
Future technologies for decentralized learning techniques exploiting shared database
Evaluation of AI recognition systems integrated on demonstrators
STORE ensures an objective evaluation of the performance of AI recognition methods through a common annotation platform for acquired images, the use of shared metrics and benchmark tools to measure the performance of partners’ algorithms on the addressed use cases. The benchmark is independent, as it is conducted by a dedicated team.
The evaluation is carried out on integrated demonstrators comprising optronic sensors used for data collection. AI technologies selected through benchmark activities are integrated into customized hardware close to sensors and are tested during field demonstrations implementing the STORE use cases at the end of the project.