IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS

This work evaluates an impact of image feature extractors on the performance of a visual SLAM method in terms of pose accuracy and computational requirements. In particular, the S-PTAM (Stereo Parallel Tracking and Mapping) method is considered as the visual SLAM framework for which both the feature...

Full description

Bibliographic Details
Main Authors: Taihú Pire, Thomas Fischer, Jan Faigl
Format: Article
Language:English
Published: CTU Central Library 2015-12-01
Series:Acta Polytechnica CTU Proceedings
Online Access:https://ojs.cvut.cz/ojs/index.php/APP/article/view/3401
id doaj-5d93bcef9fac4e4c9e95e7332e7a8980
record_format Article
spelling doaj-5d93bcef9fac4e4c9e95e7332e7a89802020-11-24T23:43:25ZengCTU Central LibraryActa Polytechnica CTU Proceedings2336-53822015-12-0122455010.14311/APP.2015.1.00453063IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMSTaihú Pire0Thomas Fischer1Jan Faigl2University of Buenos Aires, Intendente Güiraldes 2160, Ciudad Autónoma de Buenos Aires, ArgentinaUniversity of Buenos Aires, Intendente Güiraldes 2160, Ciudad Autónoma de Buenos Aires, ArgentinaDepartment of Computer Science, Faculty of Electrical Engineering, Czech Technical University in Prague, Technická 2, 166 27, Prague, Czech RepublicThis work evaluates an impact of image feature extractors on the performance of a visual SLAM method in terms of pose accuracy and computational requirements. In particular, the S-PTAM (Stereo Parallel Tracking and Mapping) method is considered as the visual SLAM framework for which both the feature detector and feature descriptor are parametrized. The evaluation was performed with a standard dataset with ground-truth information and six feature detectors and four descriptors. The presented results indicate that the combination of the GFTT detector and the BRIEF descriptor provides the best trade-off between the localization precision and computational requirements among the evaluated combinations of the detectors and descriptors.https://ojs.cvut.cz/ojs/index.php/APP/article/view/3401
collection DOAJ
language English
format Article
sources DOAJ
author Taihú Pire
Thomas Fischer
Jan Faigl
spellingShingle Taihú Pire
Thomas Fischer
Jan Faigl
IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS
Acta Polytechnica CTU Proceedings
author_facet Taihú Pire
Thomas Fischer
Jan Faigl
author_sort Taihú Pire
title IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS
title_short IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS
title_full IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS
title_fullStr IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS
title_full_unstemmed IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS
title_sort impact assessment of image feature extractors on the performance of slam systems
publisher CTU Central Library
series Acta Polytechnica CTU Proceedings
issn 2336-5382
publishDate 2015-12-01
description This work evaluates an impact of image feature extractors on the performance of a visual SLAM method in terms of pose accuracy and computational requirements. In particular, the S-PTAM (Stereo Parallel Tracking and Mapping) method is considered as the visual SLAM framework for which both the feature detector and feature descriptor are parametrized. The evaluation was performed with a standard dataset with ground-truth information and six feature detectors and four descriptors. The presented results indicate that the combination of the GFTT detector and the BRIEF descriptor provides the best trade-off between the localization precision and computational requirements among the evaluated combinations of the detectors and descriptors.
url https://ojs.cvut.cz/ojs/index.php/APP/article/view/3401
work_keys_str_mv AT taihupire impactassessmentofimagefeatureextractorsontheperformanceofslamsystems
AT thomasfischer impactassessmentofimagefeatureextractorsontheperformanceofslamsystems
AT janfaigl impactassessmentofimagefeatureextractorsontheperformanceofslamsystems
_version_ 1725501716836646912