Enhancing Lunar Reconnaissance Orbiter Images via Multi-Frame Super Resolution for Future Robotic Space Missions

J I Delgado-Centeno,P J Sanchez-Cuevas,M.A Olivares-Mendez,C Martinez

doi:10.1109/lra.2021.3097510

J I Delgado-Centeno, P J Sanchez-Cuevas + Show 2 more

Open Access

https://doi.org/10.1109/lra.2021.3097510

Copy DOI

Abstract

This paper presents a novel application of a Multi-frame Super Resolution (MFSR) method for lunar surface imagery called Lunar HighRes-net (L-HRN). In this work, we adapted and used NASA's Lunar Reconnaissance Orbiter (LRO) image database to train the Deep Learning architecture for image super resolution. Additionally, we also gathered an artificial image dataset from our virtual Moon to improve the amount of input data in the neural network training process. The network's architecture follows a standard MFSR algorithm that was enhanced for this specific use case. The proposed MFSR method has been evaluated using the well-known peak signal-to-noise ratio (PSNR) metric against other generic super-resolution methods of the state of the art. This work aims to improve environmental knowledge about the lunar surface to enhance future autonomous robots capabilities on the surface of the Moon.

Highlights

S PACE applications are currently attracting the interest of several agencies and companies such as NASA, ESA, SpaceX and Blue Origin
We validate the usage of the Lunar HighRes-net neural network for obtaining super resolution (SR) images of the lunar surface
We presented Lunar HighRes-net, a deeplearning based Multi-Frame Super Resolution method to enhance images of the Moon’s surface

Summary

Introduction

S PACE applications are currently attracting the interest of several agencies and companies such as NASA, ESA, SpaceX and Blue Origin They are investing a lot of resources in new missions [1]–[4] and exploitation plans. These missions present a wide variety of objectives and challenges, such as the study of the geological composition of celestial bodies and the study of life’s presence at some point in the history of Mars, among others. In most cases, they involve robotic systems to perform in-situ and remote-sensing operations to avoid putting at risk human life or integrity.

Objectives

Methods

Results

Conclusion