Enhanced Monocular Visual Odometry with AR Poses and Integrated INS-GPS for Robust Localization in Urban Environments

TL;DR

This paper presents a cost-effective localization system that combines monocular visual odometry, augmented reality poses, and integrated INS-GPS data, achieving lane-level accuracy in urban environments with minimal hardware.

Contribution

It introduces a novel fusion of AR poses and INS-GPS data to improve monocular visual odometry accuracy and address scale issues in urban localization.

Findings

Achieved RMSE of 1.529 meters over 1 km using Google Street View data.

Demonstrated lane-level accuracy with minimal hardware setup.

Validated approach with manually annotated trajectories.

Abstract

This paper introduces a cost effective localization system combining monocular visual odometry , augmented reality (AR) poses, and integrated INS-GPS data. We address monocular VO scale factor issues using AR poses and enhance accuracy with INS and GPS data, filtered through an Extended Kalman Filter . Our approach, tested using manually annotated trajectories from Google Street View, achieves an RMSE of 1.529 meters over a 1 km track. Future work will focus on real-time mobile implementation and further integration of visual-inertial odometry for robust localization. This method offers lane-level accuracy with minimal hardware, making advanced navigation more accessible.