Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features
The article proposes a visual-inertial navigation method to support the autonomous operation of a quadrotor UAV during the building faade inspection tasks, where state-of-the-art vision-based localization methods may fail due to texture point feature insufficiency. Considering the appearance charact...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/163765 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-163765 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1637652022-12-16T02:23:57Z Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features Lyu, Yang Yuan, Shenghai Xie, Lihua School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Inspection Buildings The article proposes a visual-inertial navigation method to support the autonomous operation of a quadrotor UAV during the building faade inspection tasks, where state-of-the-art vision-based localization methods may fail due to texture point feature insufficiency. Considering the appearance characteristics of the building faades, we additionally fuse line features and their corresponding structure prior information to the sliding-window-based estimator to improve localization reliability and accuracy. The contribution of the proposed method lies mainly in two aspects. First, we develop an informative feature selection mechanism according to the faade patterns and the inspection trajectory patterns to make a balance between localization accuracy and computation overheads. Second, we further utilize structure prior information, which is defined as line-to-line and point-to-line relationships, as another source of high-fidelity measurement to restrain the localization drifts. The proposed method is tested not only on public datasets, but also on an actual flight data package recorded in a building inspection task. Experimental results show that the proposed method can serve as a practical tool for navigating a robot in a building inspection task, with improved localization reliability and accuracy. National Research Foundation (NRF) The work was supported by National Research Foundation (NRF) Singapore, ST Engineering-NTU Corporate Laboratory under its NRF Corporate Lab@ University Scheme. 2022-12-16T02:23:57Z 2022-12-16T02:23:57Z 2022 Journal Article Lyu, Y., Yuan, S. & Xie, L. (2022). Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features. IEEE Transactions On Aerospace and Electronic Systems, 58(4), 3037-3048. https://dx.doi.org/10.1109/TAES.2022.3142663 0018-9251 https://hdl.handle.net/10356/163765 10.1109/TAES.2022.3142663 2-s2.0-85123276475 4 58 3037 3048 en IEEE Transactions on Aerospace and Electronic Systems © 2022 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Inspection Buildings |
spellingShingle |
Engineering::Electrical and electronic engineering Inspection Buildings Lyu, Yang Yuan, Shenghai Xie, Lihua Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features |
description |
The article proposes a visual-inertial navigation method to support the autonomous operation of a quadrotor UAV during the building faade inspection tasks, where state-of-the-art vision-based localization methods may fail due to texture point feature insufficiency. Considering the appearance characteristics of the building faades, we additionally fuse line features and their corresponding structure prior information to the sliding-window-based estimator to improve localization reliability and accuracy. The contribution of the proposed method lies mainly in two aspects. First, we develop an informative feature selection mechanism according to the faade patterns and the inspection trajectory patterns to make a balance between localization accuracy and computation overheads. Second, we further utilize structure prior information, which is defined as line-to-line and point-to-line relationships, as another source of high-fidelity measurement to restrain the localization drifts. The proposed method is tested not only on public datasets, but also on an actual flight data package recorded in a building inspection task. Experimental results show that the proposed method can serve as a practical tool for navigating a robot in a building inspection task, with improved localization reliability and accuracy. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Lyu, Yang Yuan, Shenghai Xie, Lihua |
format |
Article |
author |
Lyu, Yang Yuan, Shenghai Xie, Lihua |
author_sort |
Lyu, Yang |
title |
Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features |
title_short |
Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features |
title_full |
Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features |
title_fullStr |
Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features |
title_full_unstemmed |
Structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features |
title_sort |
structure priors aided visual-inertial navigation in building inspection tasks with auxiliary line features |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/163765 |
_version_ |
1753801142383411200 |