TaMaCare: Integrating multi-spectral and SLAM for mine and environment mapping

This paper outlines the objectives of the Belgian Defence research project « Tactical Environment Mapping for Battlefield Casualty Care » (TaMaCare), which focuses on integrating multi-spectral imaging (MSI) data with a simultaneous localization and mapping (SLAM) system to create a digital twin of the battlefield that contains precise information for first responders about potential threats (UXO, landmines, …). HSI captures detailed spectral signatures across the electromagnetic spectrum, making it invaluable for mine detection by distinguishing various materials. Surface mines can employ camouflage to evade detection by RGB imaging systems, but developing camouflage that effectively covers broad portions of the electromagnetic spectrum is significantly more challenging. The rich data from HSI sensors therefore facilitate robust anomaly detection. However, the limitations of HSI sensors make the technology impractical for dynamic and unpredictable scenarios. Therefore, multi-spectral (MSI) sensors will be carefully selected based on HSI measurement campaigns which will study the spectral signature of threats. Data from the measuring campaigns will be published. SLAM technology enables systems to map unknown environments while determining their location, either through LiDAR or cameras and functioning independently of external networks. This capability is crucial in GPS-denied or jammed environments, as assumed by the project. By combining SLAM with MSI, a digital twin of an environment can be created, precisely identifying threat locations. The project will include regular validation experiments in Belgian Defense camps. Although the primary focus is on post-disaster scenarios, the technological advancements from this project are directly applicable to humanitarian demining, particularly in the acquisitions of datasets and in the advancements of mine detection through HSI.