Cargando…

Vehicle Localization Using 3D Building Models and Point Cloud Matching

Detecting buildings in the surroundings of an urban vehicle and matching them to building models available on map services is an emerging trend in robotics localization for urban vehicles. In this paper, we present a novel technique, which improves a previous work by detecting building façade, their...

Descripción completa

Detalles Bibliográficos
Autores principales: Ballardini, Augusto Luis, Fontana, Simone, Cattaneo, Daniele, Matteucci, Matteo, Sorrenti, Domenico Giorgio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8399152/
https://www.ncbi.nlm.nih.gov/pubmed/34450798
http://dx.doi.org/10.3390/s21165356
_version_ 1783745007372468224
author Ballardini, Augusto Luis
Fontana, Simone
Cattaneo, Daniele
Matteucci, Matteo
Sorrenti, Domenico Giorgio
author_facet Ballardini, Augusto Luis
Fontana, Simone
Cattaneo, Daniele
Matteucci, Matteo
Sorrenti, Domenico Giorgio
author_sort Ballardini, Augusto Luis
collection PubMed
description Detecting buildings in the surroundings of an urban vehicle and matching them to building models available on map services is an emerging trend in robotics localization for urban vehicles. In this paper, we present a novel technique, which improves a previous work by detecting building façade, their positions, and finding the correspondences with their 3D models, available in OpenStreetMap. The proposed technique uses segmented point clouds produced using stereo images, processed by a convolutional neural network. The point clouds of the façades are then matched against a reference point cloud, produced extruding the buildings’ outlines, which are available on OpenStreetMap (OSM). In order to produce a lane-level localization of the vehicle, the resulting information is then fed into our probabilistic framework, called Road Layout Estimation (RLE). We prove the effectiveness of this proposal, testing it on sequences from the well-known KITTI dataset and comparing the results concerning a basic RLE version without the proposed pipeline.
format Online
Article
Text
id pubmed-8399152
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83991522021-08-29 Vehicle Localization Using 3D Building Models and Point Cloud Matching Ballardini, Augusto Luis Fontana, Simone Cattaneo, Daniele Matteucci, Matteo Sorrenti, Domenico Giorgio Sensors (Basel) Article Detecting buildings in the surroundings of an urban vehicle and matching them to building models available on map services is an emerging trend in robotics localization for urban vehicles. In this paper, we present a novel technique, which improves a previous work by detecting building façade, their positions, and finding the correspondences with their 3D models, available in OpenStreetMap. The proposed technique uses segmented point clouds produced using stereo images, processed by a convolutional neural network. The point clouds of the façades are then matched against a reference point cloud, produced extruding the buildings’ outlines, which are available on OpenStreetMap (OSM). In order to produce a lane-level localization of the vehicle, the resulting information is then fed into our probabilistic framework, called Road Layout Estimation (RLE). We prove the effectiveness of this proposal, testing it on sequences from the well-known KITTI dataset and comparing the results concerning a basic RLE version without the proposed pipeline. MDPI 2021-08-09 /pmc/articles/PMC8399152/ /pubmed/34450798 http://dx.doi.org/10.3390/s21165356 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ballardini, Augusto Luis
Fontana, Simone
Cattaneo, Daniele
Matteucci, Matteo
Sorrenti, Domenico Giorgio
Vehicle Localization Using 3D Building Models and Point Cloud Matching
title Vehicle Localization Using 3D Building Models and Point Cloud Matching
title_full Vehicle Localization Using 3D Building Models and Point Cloud Matching
title_fullStr Vehicle Localization Using 3D Building Models and Point Cloud Matching
title_full_unstemmed Vehicle Localization Using 3D Building Models and Point Cloud Matching
title_short Vehicle Localization Using 3D Building Models and Point Cloud Matching
title_sort vehicle localization using 3d building models and point cloud matching
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8399152/
https://www.ncbi.nlm.nih.gov/pubmed/34450798
http://dx.doi.org/10.3390/s21165356
work_keys_str_mv AT ballardiniaugustoluis vehiclelocalizationusing3dbuildingmodelsandpointcloudmatching
AT fontanasimone vehiclelocalizationusing3dbuildingmodelsandpointcloudmatching
AT cattaneodaniele vehiclelocalizationusing3dbuildingmodelsandpointcloudmatching
AT matteuccimatteo vehiclelocalizationusing3dbuildingmodelsandpointcloudmatching
AT sorrentidomenicogiorgio vehiclelocalizationusing3dbuildingmodelsandpointcloudmatching