Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization

TL;DR

This paper introduces a novel approach for vehicle localization that leverages dynamic vehicle motion constraints to enhance accuracy in autonomous driving scenarios, without complex object modeling.

Contribution

It proposes a method to incorporate dynamic vehicle constraints into a 6-DoF localization pipeline, improving robustness and recall over traditional static landmark methods.

Findings

Improved recall across localization tolerances from 0.25m to 5m.

Constraint detection active 35% of the time on Ford AV dataset.

Localization accuracy is notably enhanced when constraints are detected.

Abstract

Most 6-DoF localization and SLAM systems use static landmarks but ignore dynamic objects because they cannot be usefully incorporated into a typical pipeline. Where dynamic objects have been incorporated, typical approaches have attempted relatively sophisticated identification and localization of these objects, limiting their robustness or general utility. In this research, we propose a middle ground, demonstrated in the context of autonomous vehicles, using dynamic vehicles to provide limited pose constraint information in a 6-DoF frame-by-frame PnP-RANSAC localization pipeline. We refine initial pose estimates with a motion model and propose a method for calculating the predicted quality of future pose estimates, triggered based on whether or not the autonomous vehicle's motion is constrained by the relative frame-to-frame location of dynamic vehicles in the environment. Our approach detects and identifies suitable dynamic vehicles to define these pose constraints to modify a pose filter, resulting in improved recall across a range of localization tolerances from $0.25m$ to $5m$, compared to a state-of-the-art baseline single image PnP method and its vanilla pose filtering. Our constraint detection system is active for approximately $35\%$ of the time on the Ford AV dataset and localization is particularly improved when the constraint detection is active.