P2.38 Small satellite energy-efficient on-board AI processing of hyperspectral imagery for early fire-smoke detection
Advanced Satellite Systems, Sensors & Intelligence
Stefan Peters, University of South Australia
This research aims to provide a solution for energy-efficient AI-based on-board processing of hyperspectral imagery supporting automated early detection of fire smoke. We propose using modified and resampled MODIS imagery data that emulates the swath as well as spectral, spatial, and radiometric resolution of HyperScout-2 channel 1 hyperspectral imagery. In doing so, we intent to provide a solution that meets on-board processing limitations and up/downlink data transfer restrictions of the SASAT-1/ HyperScout-2/ with Intel’s Myriad X VPU chip.