Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network
This addresses the need for efficient preprocessing to enhance detection capabilities in hyperspectral imaging for satellite applications, representing an incremental improvement in method design for onboard deployment.
The paper tackles the problem of limited spatial resolution in hyperspectral satellite imagery by proposing a lightweight neural network, DPSR, that processes images line by line to achieve real-time super-resolution onboard satellites, with results competitive or superior to more complex state-of-the-art methods.
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.