Onboard Hyperspectral Classification Enables Georeferencing

• Published in: 2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) pp. 1 - 5
• Main Authors: Chiatante, C., Langer, D. D., Garrett, J. L., Birkeland, R., Berg, S., Orlandic, M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 31.10.2023
• Subjects: Autonomous surface vehicle; Autonomous Systems; Classification; Classification algorithms; Cubesats; Georeferencing; Hyperspectral imaging; Onboard processing; Signal processing algorithms; Small satellites; Surface treatment; Task analysis; Testing
• ISSN: 2158-6276
• DOI: 10.1109/WHISPERS61460.2023.10430746

The Norwegian University of Science and Technology (NTNU) has been building a system composed of multiple remote sensing agents for ocean observations. NTNU launched the first HYPerspectral Smallsat for Ocean observation (HYPSO-1) satellite on the 13 th of January 2022, adding a Hyperspectral Imager satellite to its disposal, while HYPSO-2 will be launched in 2024. However, due to the high dimensionality of the collected data, onboard processing has been introduced on the satellite to potentially deliver information in a more rapid and condensed manner. In this paper, the operational use of onboard classification will be explored, investigating how different algorithms can be applied for data reduction to potentially enable decision-making onboard the satellite such as the use of classified images for onboard georeferencing. The classification could be used to enable near real-time data latency cooperation between the satellite and the other agents, such as autonomous surface vehicles for in-situ measurements.