MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning

The High-Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter provides remotely sensed imagery at the highest spatial resolution at 25–50 cm/pixel of the surface of Mars. However, due to the spatial resolution being so high, the total area covered by HiRISE targeted...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu Tao, Jan-Peter Muller, Siting Xiong, Susan J. Conway
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	3D mapping digital terrain model DTM topography small-scale high-resolution Science Q
Acceso en línea:	https://doaj.org/article/0886883f11b4422da1a277c429a7264a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0886883f11b4422da1a277c429a7264a
record_format	dspace
spelling	oai:doaj.org-article:0886883f11b4422da1a277c429a7264a2021-11-11T18:50:29ZMADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning10.3390/rs132142202072-4292https://doaj.org/article/0886883f11b4422da1a277c429a7264a2021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4220https://doaj.org/toc/2072-4292The High-Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter provides remotely sensed imagery at the highest spatial resolution at 25–50 cm/pixel of the surface of Mars. However, due to the spatial resolution being so high, the total area covered by HiRISE targeted stereo acquisitions is very limited. This results in a lack of the availability of high-resolution digital terrain models (DTMs) which are better than 1 m/pixel. Such high-resolution DTMs have always been considered desirable for the international community of planetary scientists to carry out fine-scale geological analysis of the Martian surface. Recently, new deep learning-based techniques that are able to retrieve DTMs from single optical orbital imagery have been developed and applied to single HiRISE observational data. In this paper, we improve upon a previously developed single-image DTM estimation system called MADNet (1.0). We propose optimisations which we collectively call MADNet 2.0, which is based on a supervised image-to-height estimation network, multi-scale DTM reconstruction, and 3D co-alignment processes. In particular, we employ optimised single-scale inference and multi-scale reconstruction (in MADNet 2.0), instead of multi-scale inference and single-scale reconstruction (in MADNet 1.0), to produce more accurate large-scale topographic retrieval with boosted fine-scale resolution. We demonstrate the improvements of the MADNet 2.0 DTMs produced using HiRISE images, in comparison to the MADNet 1.0 DTMs and the published Planetary Data System (PDS) DTMs over the ExoMars Rosalind Franklin rover’s landing site at Oxia Planum. Qualitative and quantitative assessments suggest the proposed MADNet 2.0 system is capable of producing pixel-scale DTM retrieval at the same spatial resolution (25 cm/pixel) of the input HiRISE images.Yu TaoJan-Peter MullerSiting XiongSusan J. ConwayMDPI AGarticle3D mappingdigital terrain modelDTMtopographysmall-scalehigh-resolutionScienceQENRemote Sensing, Vol 13, Iss 4220, p 4220 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	3D mapping digital terrain model DTM topography small-scale high-resolution Science Q
spellingShingle	3D mapping digital terrain model DTM topography small-scale high-resolution Science Q Yu Tao Jan-Peter Muller Siting Xiong Susan J. Conway MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning
description	The High-Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter provides remotely sensed imagery at the highest spatial resolution at 25–50 cm/pixel of the surface of Mars. However, due to the spatial resolution being so high, the total area covered by HiRISE targeted stereo acquisitions is very limited. This results in a lack of the availability of high-resolution digital terrain models (DTMs) which are better than 1 m/pixel. Such high-resolution DTMs have always been considered desirable for the international community of planetary scientists to carry out fine-scale geological analysis of the Martian surface. Recently, new deep learning-based techniques that are able to retrieve DTMs from single optical orbital imagery have been developed and applied to single HiRISE observational data. In this paper, we improve upon a previously developed single-image DTM estimation system called MADNet (1.0). We propose optimisations which we collectively call MADNet 2.0, which is based on a supervised image-to-height estimation network, multi-scale DTM reconstruction, and 3D co-alignment processes. In particular, we employ optimised single-scale inference and multi-scale reconstruction (in MADNet 2.0), instead of multi-scale inference and single-scale reconstruction (in MADNet 1.0), to produce more accurate large-scale topographic retrieval with boosted fine-scale resolution. We demonstrate the improvements of the MADNet 2.0 DTMs produced using HiRISE images, in comparison to the MADNet 1.0 DTMs and the published Planetary Data System (PDS) DTMs over the ExoMars Rosalind Franklin rover’s landing site at Oxia Planum. Qualitative and quantitative assessments suggest the proposed MADNet 2.0 system is capable of producing pixel-scale DTM retrieval at the same spatial resolution (25 cm/pixel) of the input HiRISE images.
format	article
author	Yu Tao Jan-Peter Muller Siting Xiong Susan J. Conway
author_facet	Yu Tao Jan-Peter Muller Siting Xiong Susan J. Conway
author_sort	Yu Tao
title	MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning
title_short	MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning
title_full	MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning
title_fullStr	MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning
title_full_unstemmed	MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning
title_sort	madnet 2.0: pixel-scale topography retrieval from single-view orbital imagery of mars using deep learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0886883f11b4422da1a277c429a7264a
work_keys_str_mv	AT yutao madnet20pixelscaletopographyretrievalfromsinglevieworbitalimageryofmarsusingdeeplearning AT janpetermuller madnet20pixelscaletopographyretrievalfromsinglevieworbitalimageryofmarsusingdeeplearning AT sitingxiong madnet20pixelscaletopographyretrievalfromsinglevieworbitalimageryofmarsusingdeeplearning AT susanjconway madnet20pixelscaletopographyretrievalfromsinglevieworbitalimageryofmarsusingdeeplearning
_version_	1718431685117214720

MADNet 2.0: Pixel-Scale Topography Retrieval from Single-View Orbital Imagery of Mars Using Deep Learning

Ejemplares similares