EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Visual-Inertial Odometry with Learning-Based Line Features in a Illumination-Changing Environment

Xinkai Li, Cong Liu iD, Xu Yan

Sensors · 13.08.2025 · 25 (16) · 5029

DOI: 10.3390/s25165029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.08.2025. Verfasst von Xinkai Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual-Inertial Odometry (VIO) systems often suffer from degraded performance in environments with low texture. Although some previous works have combined line features with point features to mitigate this problem, the line features still degrade under more challenging conditions, such as varying illumination. To tackle this, we propose DeepLine-VIO, a robust VIO framework that integrates learned line features extracted via an attraction-field-based deep network. These features are geometrically consistent and illumination-invariant, offering improved visual robustness in challenging conditions. Our system tightly couples these learned line features with point observations and inertial data within a sliding-window optimization framework. We further introduce a geometry-aware filtering and parameterization strategy to ensure the reliability of extracted line segments. Extensive experiments on the EuRoC dataset under synthetic illumination perturbations show that DeepLine-VIO consistently outperforms existing point- and line-based methods. On the most challenging sequences under illumination-changing conditions, our approach reduces Absolute Trajectory Error (ATE) by up to 15.87% and improves Relative Pose Error (RPE) in translation by up to 58.45% compared to PL-VINS. These results highlight the robustness and accuracy of DeepLine-VIO in visually degraded environments.

Schlagwörter

Stichwörter der Autor:innen

deep learningline featuressimultaneous localization and mapping (SLAM)visual-inertial odometry (VIO)

Autor:innen und Institutionen

  • James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK.

ORCID-Profile: Cong Liu

Zitieren

APA

Li, X., Liu, C., & Yan, X. (2025). Robust Visual-Inertial Odometry with Learning-Based Line Features in a Illumination-Changing Environment. Sensors, 25(16), 5029. https://doi.org/10.3390/s25165029

Vancouver

Li X, Liu C, Yan X. Robust Visual-Inertial Odometry with Learning-Based Line Features in a Illumination-Changing Environment. Sensors. 2025;25(16):5029. doi:10.3390/s25165029

BibTeX
@article{Li2025,
  author = {Li, Xinkai and Liu, Cong and Yan, Xu},
  title = {Robust Visual-Inertial Odometry with Learning-Based Line Features in a Illumination-Changing Environment},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {5029},
  doi = {10.3390/s25165029}
}
Kostenlos starten →