BEVLoc: Cross-View Localization and Matching via Birds-Eye-View Synthesis

TL;DR

BEVLoc introduces a novel birds-eye-view synthesis framework for cross-view localization in challenging outdoor environments, enabling effective matching and GNSS-independent positioning in forests and urban areas.

Contribution

The paper presents a new BEV synthesis approach combined with contrastive learning for improved cross-view localization without GPS in complex terrains.

Findings

Promising initial results in forest environments with limited semantic diversity.

Effective coarse-to-fine matching strategy for localization.

Potential as a GNSS replacement in challenging outdoor scenarios.

Abstract

Ground to aerial matching is a crucial and challenging task in outdoor robotics, particularly when GPS is absent or unreliable. Structures like buildings or large dense forests create interference, requiring GNSS replacements for global positioning estimates. The true difficulty lies in reconciling the perspective difference between the ground and air images for acceptable localization. Taking inspiration from the autonomous driving community, we propose a novel framework for synthesizing a birds-eye-view (BEV) scene representation to match and localize against an aerial map in off-road environments. We leverage contrastive learning with domain specific hard negative mining to train a network to learn similar representations between the synthesized BEV and the aerial map. During inference, BEVLoc guides the identification of the most probable locations within the aerial map through a coarse-to-fine matching strategy. Our results demonstrate promising initial outcomes in extremely difficult forest environments with limited semantic diversity. We analyze our model's performance for coarse and fine matching, assessing both the raw matching capability of our model and its performance as a GNSS replacement. Our work delves into off-road map localization while establishing a foundational baseline for future developments in localization. Our code is available at: https://github.com/rpl-cmu/bevloc