SPL-VINS: superpoint line vins mono

Xiaoyu Tian, Hongyu Cao, Li Li*

*Corresponding author for this work

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

Abstract

Deep learning, with its data-driven advantages, achieves robustness beyond that of traditional algorithms. The integration of deep learning with visual-inertial odometry (VIO) has been a prominent research topic. However, a mature integration solution has yet to emerge. In this paper, we propose SPL-VINS, which combines the deep learning-based feature point detection algorithm SuperPoint with the Vins Mono. Additionally, we add line features into Vins Mono and propose a non-maximum suppression(NMS) method for line features. The residual of line features is modeled in the form of point-to-line distance. Experimental results on the public dataset Euroc demonstrate a significant reduction in absolute translation error and rotation error compared to Vins Mono.

Original languageEnglish
Title of host publicationInternational Conference on Advanced Image Processing Technology, AIPT 2024
EditorsLu Leng, Zhenghao Shi
PublisherSPIE
ISBN (Electronic)9781510682542
DOIs
Publication statusPublished - 2024
Event2024 International Conference on Advanced Image Processing Technology, AIPT 2024 - Chongqing, China
Duration: 31 May 20242 Jun 2024

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume13257
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2024 International Conference on Advanced Image Processing Technology, AIPT 2024
Country/TerritoryChina
CityChongqing
Period31/05/242/06/24

Keywords

  • Deep learning
  • feature point detection
  • line feature
  • reprojection error
  • VIO

Fingerprint

Dive into the research topics of 'SPL-VINS: superpoint line vins mono'. Together they form a unique fingerprint.

Cite this