AI Modules for Defence Image Analysis: Intermediate results from the EDF-Store project
conference paper
Kuijf, H.J.
Boehrer, N.
Marchill, C.
Limone, M.
Messina, F.
Liezenga, A.M.
Nijskens, L.
Woerden, J.E. van
Ermis, O.
Ellenfeld, M.
Schwaiger, M.
Schiegg, S.
Renaudat, M.
Bascle, B.
Bonnier, P.
Lafont, M.
Chartrin, S.
Allaire, F.
Eiring, H.
Johnsgaard, A.W.
Baumann, H.R.
Ruzicka, L.
Becker, S.
Marturini, M.
Liiv, T.
Wolpert, A.
Lee, Z.
Hadi, B.
Bensberg, S.
Fournier, P.
Herbin, S.
Barbanson, C.
Martino, G.
Fokkinga, E.P.
Leeuwen, M.C. van
Santini, M.
The document presents intermediate results from the EDF-STORE project, which focuses on developing artificial intelligence (AI) modules for defence image analysis. These modules are designed to extract actionable insights from large volumes of optronic sensor data, supporting tasks such as automatic target detection and recognition
(including ground vehicles and drones), object classification, change detection, and semantic segmentation. Delivered as standardized, containerized components, each module encapsulates specific functionalities and is
compatible with the STORE AI Software Factory, ensuring easy integration and reproducible benchmarking. The AI solutions focus on two main defence use-cases: threats from main battle tanks and infantry fighting vehicles, and threats from drones and drone swarms. Over 35 AI modules have been developed by the European consortium,
each documented in a standardized way and designed for scalability and reusability. These results provide a foundation for further benchmarking and development toward robust, trustworthy AI for defence image analysis.
(including ground vehicles and drones), object classification, change detection, and semantic segmentation. Delivered as standardized, containerized components, each module encapsulates specific functionalities and is
compatible with the STORE AI Software Factory, ensuring easy integration and reproducible benchmarking. The AI solutions focus on two main defence use-cases: threats from main battle tanks and infantry fighting vehicles, and threats from drones and drone swarms. Over 35 AI modules have been developed by the European consortium,
each documented in a standardized way and designed for scalability and reusability. These results provide a foundation for further benchmarking and development toward robust, trustworthy AI for defence image analysis.
TNO Identifier
1024376
Source title
12th International Symposium on Optronics in Defence & Security (OPTRO2026)
Pages
1-6
Files
To receive the publication files, please send an e-mail request to TNO Repository.