Convolutional-Neural-Network-Based Onboard Band Selection for Hyperspectral Data With Coarse Band-to-Band Alignment

Abstract

Band selection is a key strategy to address the challenges of managing large hyperspectral datasets and reduce the dimensionality problem associated with the simultaneous analysis of hundreds of spectral bands. However, the computational complexity of traditional methods makes the algorithms difficult to be deployed on board satellites. This is especially true for small satellites with limited computational and power resources. Moreover, the existing band selection techniques often require the hypercube to be processed at least at Level-1B product, i.e., the bands need to be finely aligned before selecting them, demanding more computational resources for the onboard computer. This study presents a novel neural-network-based approach for onboard band selection using data with coarse band-to-band aligned. This methodology not only simplifies the preprocessing requirements but also opens new possibilities for efficient hyperspectral imaging from space onboard small satellites, such as classification, change, and target detection.

Keywords

• Artificial intelligence
• band selection
• coregistration
• hyperspectral imaging
• neural networks (NNs)
• remote sensing