Cargando…

Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features

It is important for Mars exploration rovers to achieve autonomous and safe mobility over rough terrain. Terrain classification can help rovers to select a safe terrain to traverse and avoid sinking and/or damaging the vehicle. Mars terrains are often classified using visual methods. However, the acc...

Descripción completa

Detalles Bibliográficos
Autores principales: Lv, Fengtian, Li, Nan, Liu, Chuankai, Gao, Haibo, Ding, Liang, Deng, Zongquan, Liu, Guangjun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9498237/
https://www.ncbi.nlm.nih.gov/pubmed/36141190
http://dx.doi.org/10.3390/e24091304
_version_ 1784794708499759104
author Lv, Fengtian
Li, Nan
Liu, Chuankai
Gao, Haibo
Ding, Liang
Deng, Zongquan
Liu, Guangjun
author_facet Lv, Fengtian
Li, Nan
Liu, Chuankai
Gao, Haibo
Ding, Liang
Deng, Zongquan
Liu, Guangjun
author_sort Lv, Fengtian
collection PubMed
description It is important for Mars exploration rovers to achieve autonomous and safe mobility over rough terrain. Terrain classification can help rovers to select a safe terrain to traverse and avoid sinking and/or damaging the vehicle. Mars terrains are often classified using visual methods. However, the accuracy of terrain classification has been less than 90% in read operations. A high-accuracy vision-based method for Mars terrain classification is presented in this paper. By analyzing Mars terrain characteristics, novel image features, including multiscale gray gradient-grade features, multiscale edges strength-grade features, multiscale frequency-domain mean amplitude features, multiscale spectrum symmetry features, and multiscale spectrum amplitude-moment features, are proposed that are specifically targeted for terrain classification. Three classifiers, K-nearest neighbor (KNN), support vector machine (SVM), and random forests (RF), are adopted to classify the terrain using the proposed features. The Mars image dataset MSLNet that was collected by the Mars Science Laboratory (MSL, Curiosity) rover is used to conduct terrain classification experiments. The resolution of Mars images in the dataset is 256 × 256. Experimental results indicate that the RF classifies Mars terrain at the highest level of accuracy of 94.66%.
format Online
Article
Text
id pubmed-9498237
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-94982372022-09-23 Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features Lv, Fengtian Li, Nan Liu, Chuankai Gao, Haibo Ding, Liang Deng, Zongquan Liu, Guangjun Entropy (Basel) Article It is important for Mars exploration rovers to achieve autonomous and safe mobility over rough terrain. Terrain classification can help rovers to select a safe terrain to traverse and avoid sinking and/or damaging the vehicle. Mars terrains are often classified using visual methods. However, the accuracy of terrain classification has been less than 90% in read operations. A high-accuracy vision-based method for Mars terrain classification is presented in this paper. By analyzing Mars terrain characteristics, novel image features, including multiscale gray gradient-grade features, multiscale edges strength-grade features, multiscale frequency-domain mean amplitude features, multiscale spectrum symmetry features, and multiscale spectrum amplitude-moment features, are proposed that are specifically targeted for terrain classification. Three classifiers, K-nearest neighbor (KNN), support vector machine (SVM), and random forests (RF), are adopted to classify the terrain using the proposed features. The Mars image dataset MSLNet that was collected by the Mars Science Laboratory (MSL, Curiosity) rover is used to conduct terrain classification experiments. The resolution of Mars images in the dataset is 256 × 256. Experimental results indicate that the RF classifies Mars terrain at the highest level of accuracy of 94.66%. MDPI 2022-09-15 /pmc/articles/PMC9498237/ /pubmed/36141190 http://dx.doi.org/10.3390/e24091304 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Lv, Fengtian
Li, Nan
Liu, Chuankai
Gao, Haibo
Ding, Liang
Deng, Zongquan
Liu, Guangjun
Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features
title Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features
title_full Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features
title_fullStr Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features
title_full_unstemmed Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features
title_short Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features
title_sort highly accurate visual method of mars terrain classification for rovers based on novel image features
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9498237/
https://www.ncbi.nlm.nih.gov/pubmed/36141190
http://dx.doi.org/10.3390/e24091304
work_keys_str_mv AT lvfengtian highlyaccuratevisualmethodofmarsterrainclassificationforroversbasedonnovelimagefeatures
AT linan highlyaccuratevisualmethodofmarsterrainclassificationforroversbasedonnovelimagefeatures
AT liuchuankai highlyaccuratevisualmethodofmarsterrainclassificationforroversbasedonnovelimagefeatures
AT gaohaibo highlyaccuratevisualmethodofmarsterrainclassificationforroversbasedonnovelimagefeatures
AT dingliang highlyaccuratevisualmethodofmarsterrainclassificationforroversbasedonnovelimagefeatures
AT dengzongquan highlyaccuratevisualmethodofmarsterrainclassificationforroversbasedonnovelimagefeatures
AT liuguangjun highlyaccuratevisualmethodofmarsterrainclassificationforroversbasedonnovelimagefeatures