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.

翻译：本文提出了一种新颖的基于视觉的度量跨视角地理定位方法（CVGL），该方法将地面车辆拍摄的相机图像与航空图像进行匹配，以确定车辆的位姿。由于航空图像全球可用且成本低廉，它们在自动驾驶的两类既定范式——即使用昂贵的高精先验地图或完全依赖运行时传感器数据——之间提供了一种潜在的折衷方案。我们提出了一种端到端可微分的模型，该模型利用地面和航空图像预测车辆可能位姿的概率分布。我们结合了多个车辆数据集与来自正射影像提供商的航空图像，并在其上展示了我们方法的可行性。由于真实位姿相对于航空图像往往不准确，我们实现了伪标签方法以生成更精确的真实位姿，并将其公开。尽管先前的工作需要目标区域的训练数据才能达到合理的定位精度（即同区域评估），我们的方法突破了这一限制，即使在更具挑战性的跨区域情况下也优于先前结果。即使没有测试区域的地面或航空数据，我们仍大幅改进了先前的最先进水平，这突显了该模型在全球范围应用的潜力。我们进一步将基于不确定性的预测集成到跟踪框架中，以确定车辆的随时间变化的轨迹，在KITTI-360数据集上实现了0.78米的平均位置误差。