Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems

TL;DR

This paper introduces a multi-modal place recognition system that uses spherical CNNs to match images and LiDAR data across different sensor setups, improving robustness and accuracy in heterogeneous environments.

Contribution

It presents a novel end-to-end pipeline that operates directly on sensor data projected onto a sphere, supporting arbitrary sensor configurations without local feature extraction.

Findings

Achieves up to 10% higher recall than state-of-the-art LiDAR-based methods.

Achieves up to 5% higher recall than vision-based methods.

Correctly identifies up to 95% of matching places.

Abstract

In this paper, we propose a robust end-to-end multi-modal pipeline for place recognition where the sensor systems can differ from the map building to the query. Our approach operates directly on images and LiDAR scans without requiring any local feature extraction modules. By projecting the sensor data onto the unit sphere, we learn a multi-modal descriptor of partially overlapping scenes using a spherical convolutional neural network. The employed spherical projection model enables the support of arbitrary LiDAR and camera systems readily without losing information. Loop closure candidates are found using a nearest-neighbor lookup in the embedding space. We tackle the problem of correctly identifying the closest place by correlating the candidates' power spectra, obtaining a confidence value per prospect. Our estimate for the correct place corresponds then to the candidate with the highest confidence. We evaluate our proposal w.r.t. state-of-the-art approaches in place recognition using real-world data acquired using different sensors. Our approach can achieve a recall that is up to 10% and 5% higher than for a LiDAR- and vision-based system, respectively, when the sensor setup differs between model training and deployment. Additionally, our place selection can correctly identify up to 95% matches from the candidate set.