View Consistent Purification for Accurate Cross-View Localization

TL;DR

This paper introduces a view-consistent purification method for cross-view localization in outdoor robotics, improving accuracy and robustness by detecting view-consistent features and removing noise sources like moving objects and seasonal variations.

Contribution

It presents the first sparse visual-only localization method that enhances perception in dynamic environments using view consistency and spatial embedding techniques.

Findings

Achieves median spatial accuracy errors below 0.5 meters.

Attains median orientation accuracy errors below 2 degrees.

Outperforms existing state-of-the-art methods on KITTI and Ford datasets.

Abstract

This paper proposes a fine-grained self-localization method for outdoor robotics that utilizes a flexible number of onboard cameras and readily accessible satellite images. The proposed method addresses limitations in existing cross-view localization methods that struggle to handle noise sources such as moving objects and seasonal variations. It is the first sparse visual-only method that enhances perception in dynamic environments by detecting view-consistent key points and their corresponding deep features from ground and satellite views, while removing off-the-ground objects and establishing homography transformation between the two views. Moreover, the proposed method incorporates a spatial embedding approach that leverages camera intrinsic and extrinsic information to reduce the ambiguity of purely visual matching, leading to improved feature matching and overall pose estimation accuracy. The method exhibits strong generalization and is robust to environmental changes, requiring only geo-poses as ground truth. Extensive experiments on the KITTI and Ford Multi-AV Seasonal datasets demonstrate that our proposed method outperforms existing state-of-the-art methods, achieving median spatial accuracy errors below $0.5$ meters along the lateral and longitudinal directions, and a median orientation accuracy error below 2 degrees.