Attention-Enhanced Cross-modal Localization Between 360 Images and Point Clouds

TL;DR

This paper introduces an attention-based deep learning method for cross-modal localization between 360-degree images and LiDAR point clouds, improving robustness and accuracy in autonomous navigation.

Contribution

The paper proposes an end-to-end learnable network utilizing attention mechanisms to enhance cross-modal localization between 360 images and point clouds.

Findings

Effective localization demonstrated on KITTI-360 dataset

Attention mechanism improves feature matching accuracy

Outperforms existing methods in robustness and precision

Abstract

Visual localization plays an important role for intelligent robots and autonomous driving, especially when the accuracy of GNSS is unreliable. Recently, camera localization in LiDAR maps has attracted more and more attention for its low cost and potential robustness to illumination and weather changes. However, the commonly used pinhole camera has a narrow Field-of-View, thus leading to limited information compared with the omni-directional LiDAR data. To overcome this limitation, we focus on correlating the information of 360 equirectangular images to point clouds, proposing an end-to-end learnable network to conduct cross-modal visual localization by establishing similarity in high-dimensional feature space. Inspired by the attention mechanism, we optimize the network to capture the salient feature for comparing images and point clouds. We construct several sequences containing 360 equirectangular images and corresponding point clouds based on the KITTI-360 dataset and conduct extensive experiments. The results demonstrate the effectiveness of our approach.