SafetyQuantifiable-PLVINS

Safety-quantifiable line feature-based monocular visual localization with 3D prior map and integrity monitoring.

SafetyQuantifiable-PLVINS addresses drift and safety quantification challenges in visual localization by proposing a novel map-aided method that delivers both accurate pose estimates and a measurable error bound.

Key Contributions:

• Tightly integrates visual-inertial odometry with a prior 3D line map via geometric constraints between 2D image features and 3D map lines
• Introduces a GNSS-inspired integrity monitoring framework to compute a Protection Level (PL)
• Quantifies potential error in both position and orientation, certifying the solution’s safety
• First application of integrity monitoring to visual localization systems

Citation:

@article{zheng2025safety,
  title={Safety-quantifiable line feature-based monocular visual localization with 3D prior map},
  author={Zheng, Xi and Wen, Weisong and Hsu, Li-Ta},
  journal={IEEE Transactions on Intelligent Transportation Systems},
  year={2025},
  publisher={IEEE}
}

GitHub: https://github.com/ZHENGXi-git/SafetyQuantifiable-PLVINS