Skip to main navigation Skip to search Skip to main content

VINS-ACI: A Visual-Inertial Navigation System Adaptive to Complex Illumination by Feature Quality

  • Yi Lin Zhao
  • , Long Zhao*
  • *Corresponding author for this work
  • Beihang University
  • Beijing Natural Science Foundation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The research proposes VINS-ACI, a visual-inertial navigation algorithm to guarantee proper operation of a carrier in complex lighting environment where the system may not work due to poor quality and quantity of features. There are two innovation in the proposed localization algorithm. Firstly, gamma correction is used to adjust the image gray level under different lighting conditions to improve the feature quality. Secondly, we suppress the influence of poor quality features on the location results by adding nonlinear weights of features and images. In addition, the system is inspected on both the public datasets and the actual data under different illumination. Experiment results prove that VINS-ACI can serve as a practical approach of navigation in complex lighting environment, and improve the reliability and accuracy of positioning.

Original languageEnglish
Title of host publicationAdvances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control
EditorsLiang Yan, Haibin Duan, Yimin Deng, Liang Yan
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1237-1247
Number of pages11
ISBN (Print)9789811966125
DOIs
StatePublished - 2023
EventInternational Conference on Guidance, Navigation and Control, ICGNC 2022 - Harbin, China
Duration: 5 Aug 20227 Aug 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume845 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Guidance, Navigation and Control, ICGNC 2022
Country/TerritoryChina
CityHarbin
Period5/08/227/08/22

Keywords

  • Gamma correction
  • Line feature
  • Nonlinear weight
  • Visual-inertial navigation

Fingerprint

Dive into the research topics of 'VINS-ACI: A Visual-Inertial Navigation System Adaptive to Complex Illumination by Feature Quality'. Together they form a unique fingerprint.

Cite this