Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image

TL;DR

This paper introduces a novel neural network-based approach for highly accurate vehicle localization by matching ground images with satellite maps, outperforming traditional image retrieval methods and achieving localization within 5 meters.

Contribution

It proposes a differentiable, end-to-end neural network framework that formulates vehicle localization as pose estimation, bridging the cross-view domain gap with a geometry projection module and iterative optimization.

Findings

Achieves 80% likelihood of reducing localization error to within 5 meters.

Outperforms existing cross-view image retrieval methods in accuracy.

Demonstrates effectiveness on standard autonomous vehicle datasets.

Abstract

This paper addresses the problem of vehicle-mounted camera localization by matching a ground-level image with an overhead-view satellite map. Existing methods often treat this problem as cross-view image retrieval, and use learned deep features to match the ground-level query image to a partition (eg, a small patch) of the satellite map. By these methods, the localization accuracy is limited by the partitioning density of the satellite map (often in the order of tens meters). Departing from the conventional wisdom of image retrieval, this paper presents a novel solution that can achieve highly-accurate localization. The key idea is to formulate the task as pose estimation and solve it by neural-net based optimization. Specifically, we design a two-branch {CNN} to extract robust features from the ground and satellite images, respectively. To bridge the vast cross-view domain gap, we resort to a Geometry Projection module that projects features from the satellite map to the ground-view, based on a relative camera pose. Aiming to minimize the differences between the projected features and the observed features, we employ a differentiable Levenberg-Marquardt ({LM}) module to search for the optimal camera pose iteratively. The entire pipeline is differentiable and runs end-to-end. Extensive experiments on standard autonomous vehicle localization datasets have confirmed the superiority of the proposed method. Notably, e.g., starting from a coarse estimate of camera location within a wide region of 40m x 40m, with an 80% likelihood our method quickly reduces the lateral location error to be within 5m on a new KITTI cross-view dataset.