AGL-NET: Aerial-Ground Cross-Modal Global Localization with Varying Scales

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guan, Tianrui, Xian, Ruiqi, Wang, Xijun, Wu, Xiyang, Elnoor, Mohamed, Song, Daeun, Manocha, Dinesh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929532297019392
author Guan, Tianrui
Xian, Ruiqi
Wang, Xijun
Wu, Xiyang
Elnoor, Mohamed
Song, Daeun
Manocha, Dinesh
author_facet Guan, Tianrui
Xian, Ruiqi
Wang, Xijun
Wu, Xiyang
Elnoor, Mohamed
Song, Daeun
Manocha, Dinesh
contents We present AGL-NET, a novel learning-based method for global localization using LiDAR point clouds and satellite maps. AGL-NET tackles two critical challenges: bridging the representation gap between image and points modalities for robust feature matching, and handling inherent scale discrepancies between global view and local view. To address these challenges, AGL-NET leverages a unified network architecture with a novel two-stage matching design. The first stage extracts informative neural features directly from raw sensor data and performs initial feature matching. The second stage refines this matching process by extracting informative skeleton features and incorporating a novel scale alignment step to rectify scale variations between LiDAR and map data. Furthermore, a novel scale and skeleton loss function guides the network toward learning scale-invariant feature representations, eliminating the need for pre-processing satellite maps. This significantly improves real-world applicability in scenarios with unknown map scales. To facilitate rigorous performance evaluation, we introduce a meticulously designed dataset within the CARLA simulator specifically tailored for metric localization training and assessment. The code and data can be accessed at https://github.com/rayguan97/AGL-Net.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AGL-NET: Aerial-Ground Cross-Modal Global Localization with Varying Scales
Guan, Tianrui
Xian, Ruiqi
Wang, Xijun
Wu, Xiyang
Elnoor, Mohamed
Song, Daeun
Manocha, Dinesh
Computer Vision and Pattern Recognition
We present AGL-NET, a novel learning-based method for global localization using LiDAR point clouds and satellite maps. AGL-NET tackles two critical challenges: bridging the representation gap between image and points modalities for robust feature matching, and handling inherent scale discrepancies between global view and local view. To address these challenges, AGL-NET leverages a unified network architecture with a novel two-stage matching design. The first stage extracts informative neural features directly from raw sensor data and performs initial feature matching. The second stage refines this matching process by extracting informative skeleton features and incorporating a novel scale alignment step to rectify scale variations between LiDAR and map data. Furthermore, a novel scale and skeleton loss function guides the network toward learning scale-invariant feature representations, eliminating the need for pre-processing satellite maps. This significantly improves real-world applicability in scenarios with unknown map scales. To facilitate rigorous performance evaluation, we introduce a meticulously designed dataset within the CARLA simulator specifically tailored for metric localization training and assessment. The code and data can be accessed at https://github.com/rayguan97/AGL-Net.
title AGL-NET: Aerial-Ground Cross-Modal Global Localization with Varying Scales
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.03187