Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognition

TL;DR

This paper introduces a quantile transfer method that automatically selects optimal operating points for visual place recognition systems, improving recall and robustness across environments without manual tuning.

Contribution

It proposes a novel quantile normalization approach for threshold transfer, enabling automatic, environment-adaptive operating point selection in VPR systems.

Findings

Up to 25% higher recall in high-precision regimes

Robust threshold transfer across different environments

Elimination of manual tuning for VPR operating points

Abstract

Visual Place Recognition (VPR) is a key component for localisation in GNSS-denied environments, but its performance critically depends on selecting an image matching threshold (operating point) that balances precision and recall. Thresholds are typically hand-tuned offline for a specific environment and fixed during deployment, leading to degraded performance under environmental change. We propose a method that, given a user-defined precision requirement, automatically selects the operating point of a VPR system to maximise recall. The method uses a small calibration traversal with known correspondences and transfers thresholds to deployment via quantile normalisation of similarity score distributions. This quantile transfer ensures that thresholds remain stable across calibration sizes and query subsets, making the method robust to sampling variability. Experiments with multiple state-of-the-art VPR techniques and datasets show that the proposed approach consistently outperforms the state-of-the-art, delivering up to 25% higher recall in high-precision operating regimes. The method eliminates manual tuning by adapting to new environments and generalising across operating conditions. Our code will be released upon acceptance.