Affiliation:
1. Tongji University, School of Automotive Studies
2. Tongji University
Abstract
<div class="section abstract"><div class="htmlview paragraph">LiDAR and camera fusion have emerged as a promising approach for improving place
recognition in robotics and autonomous vehicles. However, most existing
approaches often treat sensors separately, overlooking the potential benefits of
correlation between them. In this paper, we propose a <b>C</b>ross-
<b>M</b>odality <b>M</b>odule (CMM) to leverage the potential
correlation of LiDAR and camera features for place recognition. Besides, to
fully exploit potential of each modality, we propose a Local-Global Fusion
Module to supplement global coarse-grained features with local fine-grained
features. The experiment results on public datasets demonstrate that our
approach effectively improves the average recall by 2.3%, reaching 98.7%,
compared with simply stacking of LiDAR and camera.</div></div>