Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network

TL;DR

This paper introduces Deep Pushbroom Super-Resolution (DPSR), a lightweight neural network designed for real-time hyperspectral image super-resolution onboard satellites, processing data line-by-line with minimal memory and computational needs.

Contribution

The paper proposes a novel neural network architecture tailored for pushbroom hyperspectral sensors, enabling real-time onboard super-resolution with low resource consumption.

Findings

DPSR achieves real-time super-resolution performance on low-power hardware.

The method produces super-resolved images that are competitive with or better than more complex state-of-the-art techniques.

DPSR's line-by-line processing reduces memory and computational requirements significantly.

Abstract

Hyperspectral imagers on satellites obtain the fine spectral signatures essential for distinguishing one material from another at the expense of limited spatial resolution. Enhancing the latter is thus a desirable preprocessing step in order to further improve the detection capabilities offered by hyperspectral images on downstream tasks. At the same time, there is a growing interest towards deploying inference methods directly onboard of satellites, which calls for lightweight image super-resolution methods that can be run on the payload in real time. In this paper, we present a novel neural network design, called Deep Pushbroom Super-Resolution (DPSR) that matches the pushbroom acquisition of hyperspectral sensors by processing an image line by line in the along-track direction with a causal memory mechanism to exploit previously acquired lines. This design greatly limits memory requirements and computational complexity, achieving onboard real-time performance, i.e., the ability to super-resolve a line in the time it takes to acquire the next one, on low-power hardware. Experiments show that the quality of the super-resolved images is competitive or even outperforms state-of-the-art methods that are significantly more complex.