Cargando…

REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors

Visual-inertial odometry is critical for Unmanned Aerial Vehicles (UAVs) and robotics. However, there are problems of motion drift and motion blur in sharp brightness changes and fast-motion scenes. It may cause the degradation of image quality, which leads to poor location. Event cameras are bio-in...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Yingxun, Shao, Bo, Zhang, Chongchong, Zhao, Jiang, Cai, Zhihao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9624318/
https://www.ncbi.nlm.nih.gov/pubmed/36278726
http://dx.doi.org/10.3390/biomimetics7040169
_version_ 1784822207470370816
author Wang, Yingxun
Shao, Bo
Zhang, Chongchong
Zhao, Jiang
Cai, Zhihao
author_facet Wang, Yingxun
Shao, Bo
Zhang, Chongchong
Zhao, Jiang
Cai, Zhihao
author_sort Wang, Yingxun
collection PubMed
description Visual-inertial odometry is critical for Unmanned Aerial Vehicles (UAVs) and robotics. However, there are problems of motion drift and motion blur in sharp brightness changes and fast-motion scenes. It may cause the degradation of image quality, which leads to poor location. Event cameras are bio-inspired vision sensors that offer significant advantages in high-dynamic scenes. Leveraging this property, this paper presents a new range and event-based visual-inertial odometry (REVIO). Firstly, we propose an event-based visual-inertial odometry (EVIO) using sliding window nonlinear optimization. Secondly, REVIO is developed on the basis of EVIO, which fuses events and distances to obtain clear event images and improves the accuracy of position estimation by constructing additional range constraints. Finally, the EVIO and REVIO are tested in three experiments—dataset, handheld and flight—to evaluate the localization performance. The error of REVIO can be reduced by nearly 29% compared with EVIO in the handheld experiment and almost 28% compared with VINS-Mono in the flight experiment, which demonstrates the higher accuracy of REVIO in some fast-motion and high-dynamic scenes.
format Online
Article
Text
id pubmed-9624318
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96243182022-11-02 REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors Wang, Yingxun Shao, Bo Zhang, Chongchong Zhao, Jiang Cai, Zhihao Biomimetics (Basel) Article Visual-inertial odometry is critical for Unmanned Aerial Vehicles (UAVs) and robotics. However, there are problems of motion drift and motion blur in sharp brightness changes and fast-motion scenes. It may cause the degradation of image quality, which leads to poor location. Event cameras are bio-inspired vision sensors that offer significant advantages in high-dynamic scenes. Leveraging this property, this paper presents a new range and event-based visual-inertial odometry (REVIO). Firstly, we propose an event-based visual-inertial odometry (EVIO) using sliding window nonlinear optimization. Secondly, REVIO is developed on the basis of EVIO, which fuses events and distances to obtain clear event images and improves the accuracy of position estimation by constructing additional range constraints. Finally, the EVIO and REVIO are tested in three experiments—dataset, handheld and flight—to evaluate the localization performance. The error of REVIO can be reduced by nearly 29% compared with EVIO in the handheld experiment and almost 28% compared with VINS-Mono in the flight experiment, which demonstrates the higher accuracy of REVIO in some fast-motion and high-dynamic scenes. MDPI 2022-10-18 /pmc/articles/PMC9624318/ /pubmed/36278726 http://dx.doi.org/10.3390/biomimetics7040169 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
Wang, Yingxun
Shao, Bo
Zhang, Chongchong
Zhao, Jiang
Cai, Zhihao
REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors
title REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors
title_full REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors
title_fullStr REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors
title_full_unstemmed REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors
title_short REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors
title_sort revio: range- and event-based visual-inertial odometry for bio-inspired sensors
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9624318/
https://www.ncbi.nlm.nih.gov/pubmed/36278726
http://dx.doi.org/10.3390/biomimetics7040169
work_keys_str_mv AT wangyingxun reviorangeandeventbasedvisualinertialodometryforbioinspiredsensors
AT shaobo reviorangeandeventbasedvisualinertialodometryforbioinspiredsensors
AT zhangchongchong reviorangeandeventbasedvisualinertialodometryforbioinspiredsensors
AT zhaojiang reviorangeandeventbasedvisualinertialodometryforbioinspiredsensors
AT caizhihao reviorangeandeventbasedvisualinertialodometryforbioinspiredsensors