Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation

This paper presents a novel dense optical-flow algorithm to solve the monocular simultaneous localisation and mapping (SLAM) problem for ground or aerial robots. Dense optical flow can effectively provide the ego-motion of the vehicle while enabling collision avoidance with the potential obstacles....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yonhon Ng, Hongdong Li, Jonghyuk Kim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	monocular visual navigation dense optical flow uncertainty estimation epipolar constraints Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/3bc3de04fc5548fdb3de71978fa38551
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3bc3de04fc5548fdb3de71978fa38551
record_format	dspace
spelling	oai:doaj.org-article:3bc3de04fc5548fdb3de71978fa385512021-11-25T18:57:51ZUncertainty Estimation of Dense Optical Flow for Robust Visual Navigation10.3390/s212276031424-8220https://doaj.org/article/3bc3de04fc5548fdb3de71978fa385512021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7603https://doaj.org/toc/1424-8220This paper presents a novel dense optical-flow algorithm to solve the monocular simultaneous localisation and mapping (SLAM) problem for ground or aerial robots. Dense optical flow can effectively provide the ego-motion of the vehicle while enabling collision avoidance with the potential obstacles. Existing research has not fully utilised the uncertainty of the optical flow—at most, an isotropic Gaussian density model has been used. We estimate the full uncertainty of the optical flow and propose a new eight-point algorithm based on the statistical Mahalanobis distance. Combined with the pose-graph optimisation, the proposed method demonstrates enhanced robustness and accuracy for the public autonomous car dataset (KITTI) and aerial monocular dataset.Yonhon NgHongdong LiJonghyuk KimMDPI AGarticlemonocular visual navigationdense optical flowuncertainty estimationepipolar constraintsChemical technologyTP1-1185ENSensors, Vol 21, Iss 7603, p 7603 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	monocular visual navigation dense optical flow uncertainty estimation epipolar constraints Chemical technology TP1-1185
spellingShingle	monocular visual navigation dense optical flow uncertainty estimation epipolar constraints Chemical technology TP1-1185 Yonhon Ng Hongdong Li Jonghyuk Kim Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation
description	This paper presents a novel dense optical-flow algorithm to solve the monocular simultaneous localisation and mapping (SLAM) problem for ground or aerial robots. Dense optical flow can effectively provide the ego-motion of the vehicle while enabling collision avoidance with the potential obstacles. Existing research has not fully utilised the uncertainty of the optical flow—at most, an isotropic Gaussian density model has been used. We estimate the full uncertainty of the optical flow and propose a new eight-point algorithm based on the statistical Mahalanobis distance. Combined with the pose-graph optimisation, the proposed method demonstrates enhanced robustness and accuracy for the public autonomous car dataset (KITTI) and aerial monocular dataset.
format	article
author	Yonhon Ng Hongdong Li Jonghyuk Kim
author_facet	Yonhon Ng Hongdong Li Jonghyuk Kim
author_sort	Yonhon Ng
title	Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation
title_short	Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation
title_full	Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation
title_fullStr	Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation
title_full_unstemmed	Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation
title_sort	uncertainty estimation of dense optical flow for robust visual navigation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/3bc3de04fc5548fdb3de71978fa38551
work_keys_str_mv	AT yonhonng uncertaintyestimationofdenseopticalflowforrobustvisualnavigation AT hongdongli uncertaintyestimationofdenseopticalflowforrobustvisualnavigation AT jonghyukkim uncertaintyestimationofdenseopticalflowforrobustvisualnavigation
_version_	1718410457130205184

Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation

Ejemplares similares