Hyperspectral Imaging Platform for the European Defence

Overview

• Project Code: HYPER-IP
• Start Date: Januari 27, 2025
• End Date: May 26, 2027
• Reference: N/A
• Funding: European Defence Agency (EDA)
• Royal Military Academy Involvement: Partner
• Quad Chart

Team

Staff

Partners

• Coordinator: Andrea Massini
• Coordinator Affiliation: FlySight
• Project Co-promotor: Rob Haelterman, Skralan Hosteaux
• RMA Researchers: Hannes De Meulemeester

• Project Partners (RMA): Department of Mathematics (MWMW)
• Project Partners (BE-DEF): N/A
• Project Partners (Other): FlySight, National Institute of Optics of the National Research Council (CNR-INO), Leonardo , Norsk Elektro Optikk (NEO), Imec

Context

The project aims to overcome some of the current technological gaps of the hyperspectral technologies in the defence sector by developing a technological demonstrator for space and airborne remote sensing applications.

Objectives

HYPER-IP project will progress the state of the art by developing an advanced miniaturized and militarized SWaP-C (Small Size, Weight, Power and Cost) demonstrator to achieve high performance in terms of signal to noise ratio and frame rate. The demonstrator will be integrated with a processing tool to enable real time understanding of the data. The final goal is to develop a hyperspectral system (imager and real time processor) to be used on small spaceborne platforms.

Methodology

To overcome issues linked to SWIR spectral bands, new promising solutions for Hyperspectral short infrared imagers will be analysed and new technical approaches to achieve better SWaP-C factors will be studied. Specifically, the use of nanostructured surfaces, rapid tuneable filters and snapshot imagers technologies will be considered. For a trade-off analysis of the development of the small hyperspectral demonstrator for the European Defence, a model and simulation of the identified solutions will be conducted. A new processing solution will be designed and developed to overcome the challenges associated with the processing of the large amount of data in real time. New methodologies for target detection, material classifications and spectral matching will be analysed and studied. The use of advanced machine learning techniques including AI and deep learning will be considered in order to better understand the acquired data. Potential computational system architectures (i.e. HW and SW) for real time processing will be identified and implemented. Processing techniques will be adopted and tested using real and simulated imaging data. Validation of the new design concepts will be achieved through the use of an airborne platform.