Road-network-based rapid geolocalization

In this article, a road-network-based geolocalization method is proposed. We match roads in the onboard images to the reference road vector map, and realize successful localization over areas as large as a whole city. The road network matching problem is treated as a point cloud registration problem...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Yongfei, Yang, Dongfang, Wang, Shicheng, He, Hao, Hu, Jiaxing, Liu, Huaping
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/159973
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-159973
record_format dspace
spelling sg-ntu-dr.10356-1599732022-07-06T08:21:18Z Road-network-based rapid geolocalization Li, Yongfei Yang, Dongfang Wang, Shicheng He, Hao Hu, Jiaxing Liu, Huaping School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Aerial Image Geolocalization In this article, a road-network-based geolocalization method is proposed. We match roads in the onboard images to the reference road vector map, and realize successful localization over areas as large as a whole city. The road network matching problem is treated as a point cloud registration problem under the homography transformation and solved under the hypothesize-and-test framework. To tackle the point cloud registration problem, a global projective-invariant feature is proposed, which consists of two road intersections augmented with their tangents. In addition, we propose the necessary conditions for the features to match. This can reduce the candidate matching features, thus accelerating the search to a great extent. These matching candidates are first “filtered” with the model consistency check in parameter space and then tested with similarity metrics to identify the correct transformation. The experiments show that our method can localize an aerial image over an area larger than 1000 km2 within several seconds on a single CPU. Our code can be found at: https://github.com/FlyAlCode/ RCLGeolocalization-2.0. This work was supported in part by the National Natural Science Foundation of China under Grant 61673017 and Grant 61403398; and in part by the Natural Science Foundation of Shaanxi Province under Grant 2017JM6077 and Grant 201805040YD18CG24. 2022-07-06T08:21:18Z 2022-07-06T08:21:18Z 2020 Journal Article Li, Y., Yang, D., Wang, S., He, H., Hu, J. & Liu, H. (2020). Road-network-based rapid geolocalization. IEEE Transactions On Geoscience and Remote Sensing, 59(7), 6065-6076. https://dx.doi.org/10.1109/TGRS.2020.3011034 0196-2892 https://hdl.handle.net/10356/159973 10.1109/TGRS.2020.3011034 2-s2.0-85112300583 7 59 6065 6076 en IEEE Transactions on Geoscience and Remote Sensing © 2020 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Aerial Image
Geolocalization
spellingShingle Engineering::Electrical and electronic engineering
Aerial Image
Geolocalization
Li, Yongfei
Yang, Dongfang
Wang, Shicheng
He, Hao
Hu, Jiaxing
Liu, Huaping
Road-network-based rapid geolocalization
description In this article, a road-network-based geolocalization method is proposed. We match roads in the onboard images to the reference road vector map, and realize successful localization over areas as large as a whole city. The road network matching problem is treated as a point cloud registration problem under the homography transformation and solved under the hypothesize-and-test framework. To tackle the point cloud registration problem, a global projective-invariant feature is proposed, which consists of two road intersections augmented with their tangents. In addition, we propose the necessary conditions for the features to match. This can reduce the candidate matching features, thus accelerating the search to a great extent. These matching candidates are first “filtered” with the model consistency check in parameter space and then tested with similarity metrics to identify the correct transformation. The experiments show that our method can localize an aerial image over an area larger than 1000 km2 within several seconds on a single CPU. Our code can be found at: https://github.com/FlyAlCode/ RCLGeolocalization-2.0.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Li, Yongfei
Yang, Dongfang
Wang, Shicheng
He, Hao
Hu, Jiaxing
Liu, Huaping
format Article
author Li, Yongfei
Yang, Dongfang
Wang, Shicheng
He, Hao
Hu, Jiaxing
Liu, Huaping
author_sort Li, Yongfei
title Road-network-based rapid geolocalization
title_short Road-network-based rapid geolocalization
title_full Road-network-based rapid geolocalization
title_fullStr Road-network-based rapid geolocalization
title_full_unstemmed Road-network-based rapid geolocalization
title_sort road-network-based rapid geolocalization
publishDate 2022
url https://hdl.handle.net/10356/159973
_version_ 1738844950755278848