ReLoc-PDR: Visual Relocalization Enhanced Pedestrian Dead Reckoning via Graph Optimization

TL;DR

ReLoc-PDR is a novel fusion framework that combines pedestrian dead reckoning and visual relocalization through graph optimization to improve pedestrian positioning accuracy in challenging, satellite-denied environments.

Contribution

It introduces a graph optimization-based fusion method that effectively corrects PDR drift using visual observations, even in visually-degraded conditions.

Findings

Outperforms existing methods in accuracy and robustness.

Effective in low-texture and dark environments.

Achieves reliable positioning with only a smartphone.

Abstract

Accurately and reliably positioning pedestrians in satellite-denied conditions remains a significant challenge. Pedestrian dead reckoning (PDR) is commonly employed to estimate pedestrian location using low-cost inertial sensor. However, PDR is susceptible to drift due to sensor noise, incorrect step detection, and inaccurate stride length estimation. This work proposes ReLoc-PDR, a fusion framework combining PDR and visual relocalization using graph optimization. ReLoc-PDR leverages time-correlated visual observations and learned descriptors to achieve robust positioning in visually-degraded environments. A graph optimization-based fusion mechanism with the Tukey kernel effectively corrects cumulative errors and mitigates the impact of abnormal visual observations. Real-world experiments demonstrate that our ReLoc-PDR surpasses representative methods in accuracy and robustness, achieving accurte and robust pedestrian positioning results using only a smartphone in challenging environments such as less-textured corridors and dark nighttime scenarios.