Constrained-covisibility marginalization for efficient on-board stereo SLAM

When targeting embedded applications such as on-board visual localization for small Unmanned Air Vehicles (UAV), available hardware generally becomes a limiting factor. For this reason, the usual strategy is to rely on pure motion integration and/or restricting the size of the map, i.e. performing v...

Descripción completa

Guardado en:

Detalles Bibliográficos
Publicado:	2017
Materias:	Mobile robots Stereo image processing Unmanned aerial vehicles (UAV) Vision Computational costs Computational time Embedded application Embedded computers Monocular vision Parallelizations Unmanned air vehicles Visual localization Stereo vision
Acceso en línea:	https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815386_v_n_p_Nitsche http://hdl.handle.net/20.500.12110/paper_97815386_v_n_p_Nitsche
Aporte de:	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires

id	paper:paper_97815386_v_n_p_Nitsche
record_format	dspace
spelling	paper:paper_97815386_v_n_p_Nitsche2023-06-08T16:38:02Z Constrained-covisibility marginalization for efficient on-board stereo SLAM Mobile robots Stereo image processing Unmanned aerial vehicles (UAV) Vision Computational costs Computational time Embedded application Embedded computers Monocular vision Parallelizations Unmanned air vehicles Visual localization Stereo vision When targeting embedded applications such as on-board visual localization for small Unmanned Air Vehicles (UAV), available hardware generally becomes a limiting factor. For this reason, the usual strategy is to rely on pure motion integration and/or restricting the size of the map, i.e. performing visual odometry. Moreover, if monocular vision is employed, due to the additional computational cost of stereo vision, this requires dealing with the problem of unknown scale. In this work we discuss how the cost of the tracking task can be reduced without limiting the size of the global map. To do so, the notion of covisibility is strongly used which allows choosing a fixed and optimal set of points to be tracked. Moreover, this work delves into the concept of parallel tracking and mapping and presents some finer parallelization opportunities. Finally, we show how these strategies improve the computational times of a stereo visual SLAM framework called S-PTAM running on-board an embedded computer, close to camera frame-rates and with negligible precision loss. © 2017 IEEE. 2017 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815386_v_n_p_Nitsche http://hdl.handle.net/20.500.12110/paper_97815386_v_n_p_Nitsche
institution	Universidad de Buenos Aires
institution_str	I-28
repository_str	R-134
collection	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic	Mobile robots Stereo image processing Unmanned aerial vehicles (UAV) Vision Computational costs Computational time Embedded application Embedded computers Monocular vision Parallelizations Unmanned air vehicles Visual localization Stereo vision
spellingShingle	Mobile robots Stereo image processing Unmanned aerial vehicles (UAV) Vision Computational costs Computational time Embedded application Embedded computers Monocular vision Parallelizations Unmanned air vehicles Visual localization Stereo vision Constrained-covisibility marginalization for efficient on-board stereo SLAM
topic_facet	Mobile robots Stereo image processing Unmanned aerial vehicles (UAV) Vision Computational costs Computational time Embedded application Embedded computers Monocular vision Parallelizations Unmanned air vehicles Visual localization Stereo vision
description	When targeting embedded applications such as on-board visual localization for small Unmanned Air Vehicles (UAV), available hardware generally becomes a limiting factor. For this reason, the usual strategy is to rely on pure motion integration and/or restricting the size of the map, i.e. performing visual odometry. Moreover, if monocular vision is employed, due to the additional computational cost of stereo vision, this requires dealing with the problem of unknown scale. In this work we discuss how the cost of the tracking task can be reduced without limiting the size of the global map. To do so, the notion of covisibility is strongly used which allows choosing a fixed and optimal set of points to be tracked. Moreover, this work delves into the concept of parallel tracking and mapping and presents some finer parallelization opportunities. Finally, we show how these strategies improve the computational times of a stereo visual SLAM framework called S-PTAM running on-board an embedded computer, close to camera frame-rates and with negligible precision loss. © 2017 IEEE.
title	Constrained-covisibility marginalization for efficient on-board stereo SLAM
title_short	Constrained-covisibility marginalization for efficient on-board stereo SLAM
title_full	Constrained-covisibility marginalization for efficient on-board stereo SLAM
title_fullStr	Constrained-covisibility marginalization for efficient on-board stereo SLAM
title_full_unstemmed	Constrained-covisibility marginalization for efficient on-board stereo SLAM
title_sort	constrained-covisibility marginalization for efficient on-board stereo slam
publishDate	2017
url	https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815386_v_n_p_Nitsche http://hdl.handle.net/20.500.12110/paper_97815386_v_n_p_Nitsche
_version_	1768542715085062144

Constrained-covisibility marginalization for efficient on-board stereo SLAM

Ejemplares similares