Uncertainty-aware Vision-based Metric Cross-view Geolocalization

TL;DR

This paper introduces a novel, uncertainty-aware vision-based cross-view geolocalization method that matches ground vehicle images with aerial images to accurately determine vehicle positions without region-specific training.

Contribution

The paper presents an end-to-end differentiable model for cross-view geolocalization that outperforms previous methods, even in cross-area scenarios, and incorporates uncertainty estimation for improved tracking.

Findings

Achieves a mean position error of 0.78m on KITTI-360.

Outperforms previous state-of-the-art in cross-area geolocalization.

Demonstrates feasibility of global-scale application without region-specific training.

Abstract

This paper proposes a novel method for vision-based metric cross-view geolocalization (CVGL) that matches the camera images captured from a ground-based vehicle with an aerial image to determine the vehicle's geo-pose. Since aerial images are globally available at low cost, they represent a potential compromise between two established paradigms of autonomous driving, i.e. using expensive high-definition prior maps or relying entirely on the sensor data captured at runtime. We present an end-to-end differentiable model that uses the ground and aerial images to predict a probability distribution over possible vehicle poses. We combine multiple vehicle datasets with aerial images from orthophoto providers on which we demonstrate the feasibility of our method. Since the ground truth poses are often inaccurate w.r.t. the aerial images, we implement a pseudo-label approach to produce more accurate ground truth poses and make them publicly available. While previous works require training data from the target region to achieve reasonable localization accuracy (i.e. same-area evaluation), our approach overcomes this limitation and outperforms previous results even in the strictly more challenging cross-area case. We improve the previous state-of-the-art by a large margin even without ground or aerial data from the test region, which highlights the model's potential for global-scale application. We further integrate the uncertainty-aware predictions in a tracking framework to determine the vehicle's trajectory over time resulting in a mean position error on KITTI-360 of 0.78m.