Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization

Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization

Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the \emph{Danish Airs and Grounds} (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extrem...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vallone, Andrea, Warburg, Frederik, Hansen, Hans, Hauberg, Søren, Civera, Javier
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Robotics
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Vallone, Andrea
Warburg, Frederik
Hansen, Hans
Hauberg, Søren
Civera, Javier
description Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the \emph{Danish Airs and Grounds} (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of road in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. We also propose a map-to-image re-localization pipeline, that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at: https://frederikwarburg.github.io/DAG
doi_str_mv 10.48550/arxiv.2202.01821
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2202_01821</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2202_01821</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-c65a3771d64b1c92bf44effea7f097f0d2e91cf78e62fe9fb6a6f3a646b429ff3</originalsourceid><addsrcrecordid>eNotj8FKxDAURbNxIaMf4Mr8QGqTpmnrrszoKBQUnX19Td_TQG0kiYP69Tp1FpcDd3HgMHYh80zXZZlfQfhy-0ypXGW5rJU8ZS8bmF18460LkcM88m3wn_MYr3nLN5AgYuLkA28xOJhE8uI5BcQkOtzjxB8nsMif0PrX2SXn58XReQuT-4HDccZOCKaI50eu2O72Zre-E93D9n7ddgJMJYU1JRRVJUejB2kbNZDWSIRQUd78bVTYSEtVjUYRNjQYMFSA0WbQqiEqVuzyX7sk9h_BvUP47g-p_ZJa_AI5iE9m</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization</title><source>arXiv.org</source><creator>Vallone, Andrea ; Warburg, Frederik ; Hansen, Hans ; Hauberg, Søren ; Civera, Javier</creator><creatorcontrib>Vallone, Andrea ; Warburg, Frederik ; Hansen, Hans ; Hauberg, Søren ; Civera, Javier</creatorcontrib><description>Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the \emph{Danish Airs and Grounds} (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of road in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. We also propose a map-to-image re-localization pipeline, that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at: https://frederikwarburg.github.io/DAG</description><identifier>DOI: 10.48550/arxiv.2202.01821</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Robotics</subject><creationdate>2022-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2202.01821$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2202.01821$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Vallone, Andrea</creatorcontrib><creatorcontrib>Warburg, Frederik</creatorcontrib><creatorcontrib>Hansen, Hans</creatorcontrib><creatorcontrib>Hauberg, Søren</creatorcontrib><creatorcontrib>Civera, Javier</creatorcontrib><title>Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization</title><description>Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the \emph{Danish Airs and Grounds} (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of road in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. We also propose a map-to-image re-localization pipeline, that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at: https://frederikwarburg.github.io/DAG</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8FKxDAURbNxIaMf4Mr8QGqTpmnrrszoKBQUnX19Td_TQG0kiYP69Tp1FpcDd3HgMHYh80zXZZlfQfhy-0ypXGW5rJU8ZS8bmF18460LkcM88m3wn_MYr3nLN5AgYuLkA28xOJhE8uI5BcQkOtzjxB8nsMif0PrX2SXn58XReQuT-4HDccZOCKaI50eu2O72Zre-E93D9n7ddgJMJYU1JRRVJUejB2kbNZDWSIRQUd78bVTYSEtVjUYRNjQYMFSA0WbQqiEqVuzyX7sk9h_BvUP47g-p_ZJa_AI5iE9m</recordid><startdate>20220203</startdate><enddate>20220203</enddate><creator>Vallone, Andrea</creator><creator>Warburg, Frederik</creator><creator>Hansen, Hans</creator><creator>Hauberg, Søren</creator><creator>Civera, Javier</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220203</creationdate><title>Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization</title><author>Vallone, Andrea ; Warburg, Frederik ; Hansen, Hans ; Hauberg, Søren ; Civera, Javier</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-c65a3771d64b1c92bf44effea7f097f0d2e91cf78e62fe9fb6a6f3a646b429ff3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Vallone, Andrea</creatorcontrib><creatorcontrib>Warburg, Frederik</creatorcontrib><creatorcontrib>Hansen, Hans</creatorcontrib><creatorcontrib>Hauberg, Søren</creatorcontrib><creatorcontrib>Civera, Javier</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Vallone, Andrea</au><au>Warburg, Frederik</au><au>Hansen, Hans</au><au>Hauberg, Søren</au><au>Civera, Javier</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization</atitle><date>2022-02-03</date><risdate>2022</risdate><abstract>Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the \emph{Danish Airs and Grounds} (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of road in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. We also propose a map-to-image re-localization pipeline, that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at: https://frederikwarburg.github.io/DAG</abstract><doi>10.48550/arxiv.2202.01821</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2202.01821
ispartof
issn
language eng
recordid cdi_arxiv_primary_2202_01821
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Robotics
title Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T14%3A32%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Danish%20Airs%20and%20Grounds:%20A%20Dataset%20for%20Aerial-to-Street-Level%20Place%20Recognition%20and%20Localization&rft.au=Vallone,%20Andrea&rft.date=2022-02-03&rft_id=info:doi/10.48550/arxiv.2202.01821&rft_dat=%3Carxiv_GOX%3E2202_01821%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true