Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks

Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks

We propose a novel image based localization system using graph neural networks (GNN). The pretrained ResNet50 convolutional neural network (CNN) architecture is used to extract the important features for each image. Following, the extracted features are input to GNN to find the pose of each image by...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Elmoogy, Ahmed, Dong, Xiaodai, Lu, Tao, Westendorp, Robert, Reddy, Kishore
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
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 Elmoogy, Ahmed
Dong, Xiaodai
Lu, Tao
Westendorp, Robert
Reddy, Kishore
description We propose a novel image based localization system using graph neural networks (GNN). The pretrained ResNet50 convolutional neural network (CNN) architecture is used to extract the important features for each image. Following, the extracted features are input to GNN to find the pose of each image by either using the image features as a node in a graph and formulate the pose estimation problem as node pose regression or modelling the image features themselves as a graph and the problem becomes graph pose regression. We do an extensive comparison between the proposed two approaches and the state of the art single image localization methods and show that using GNN leads to enhanced performance for both indoor and outdoor environments.
doi_str_mv 10.48550/arxiv.2103.09435
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2103_09435</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2103_09435</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-f393da7258f5d302ceea1b7c8b9a82f87abeaf0149b4d8460c0bdc8a665c7eeb3</originalsourceid><addsrcrecordid>eNotj71uwjAURr10qGgfoBN-gQQntmOHrQo0rYTSSsAcXTvXEJUQZAda3r78dDrSN3w6h5CXhMVCS8km4H_bU5wmjMcsF1w-ktlXHzAqq4pOaQEdeqDXhc7D0HYwtP2eLs9hwI6uQ7vf0NLDYUsrPHrYXTD89P47PJEHB7uAz_8ckdXbfFW8R4vP8qN4XUSQKRk5nvMGVCq1kw1nqUWExCirTQ46dVqBQXAsEbkRjRYZs8w0VkOWSasQDR-R8f32llEf_MXQn-trTn3L4X-zQUUm</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks</title><source>arXiv.org</source><creator>Elmoogy, Ahmed ; Dong, Xiaodai ; Lu, Tao ; Westendorp, Robert ; Reddy, Kishore</creator><creatorcontrib>Elmoogy, Ahmed ; Dong, Xiaodai ; Lu, Tao ; Westendorp, Robert ; Reddy, Kishore</creatorcontrib><description>We propose a novel image based localization system using graph neural networks (GNN). The pretrained ResNet50 convolutional neural network (CNN) architecture is used to extract the important features for each image. Following, the extracted features are input to GNN to find the pose of each image by either using the image features as a node in a graph and formulate the pose estimation problem as node pose regression or modelling the image features themselves as a graph and the problem becomes graph pose regression. We do an extensive comparison between the proposed two approaches and the state of the art single image localization methods and show that using GNN leads to enhanced performance for both indoor and outdoor environments.</description><identifier>DOI: 10.48550/arxiv.2103.09435</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2021-03</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2103.09435$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2103.09435$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Elmoogy, Ahmed</creatorcontrib><creatorcontrib>Dong, Xiaodai</creatorcontrib><creatorcontrib>Lu, Tao</creatorcontrib><creatorcontrib>Westendorp, Robert</creatorcontrib><creatorcontrib>Reddy, Kishore</creatorcontrib><title>Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks</title><description>We propose a novel image based localization system using graph neural networks (GNN). The pretrained ResNet50 convolutional neural network (CNN) architecture is used to extract the important features for each image. Following, the extracted features are input to GNN to find the pose of each image by either using the image features as a node in a graph and formulate the pose estimation problem as node pose regression or modelling the image features themselves as a graph and the problem becomes graph pose regression. We do an extensive comparison between the proposed two approaches and the state of the art single image localization methods and show that using GNN leads to enhanced performance for both indoor and outdoor environments.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71uwjAURr10qGgfoBN-gQQntmOHrQo0rYTSSsAcXTvXEJUQZAda3r78dDrSN3w6h5CXhMVCS8km4H_bU5wmjMcsF1w-ktlXHzAqq4pOaQEdeqDXhc7D0HYwtP2eLs9hwI6uQ7vf0NLDYUsrPHrYXTD89P47PJEHB7uAz_8ckdXbfFW8R4vP8qN4XUSQKRk5nvMGVCq1kw1nqUWExCirTQ46dVqBQXAsEbkRjRYZs8w0VkOWSasQDR-R8f32llEf_MXQn-trTn3L4X-zQUUm</recordid><startdate>20210317</startdate><enddate>20210317</enddate><creator>Elmoogy, Ahmed</creator><creator>Dong, Xiaodai</creator><creator>Lu, Tao</creator><creator>Westendorp, Robert</creator><creator>Reddy, Kishore</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210317</creationdate><title>Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks</title><author>Elmoogy, Ahmed ; Dong, Xiaodai ; Lu, Tao ; Westendorp, Robert ; Reddy, Kishore</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-f393da7258f5d302ceea1b7c8b9a82f87abeaf0149b4d8460c0bdc8a665c7eeb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Elmoogy, Ahmed</creatorcontrib><creatorcontrib>Dong, Xiaodai</creatorcontrib><creatorcontrib>Lu, Tao</creatorcontrib><creatorcontrib>Westendorp, Robert</creatorcontrib><creatorcontrib>Reddy, Kishore</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Elmoogy, Ahmed</au><au>Dong, Xiaodai</au><au>Lu, Tao</au><au>Westendorp, Robert</au><au>Reddy, Kishore</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks</atitle><date>2021-03-17</date><risdate>2021</risdate><abstract>We propose a novel image based localization system using graph neural networks (GNN). The pretrained ResNet50 convolutional neural network (CNN) architecture is used to extract the important features for each image. Following, the extracted features are input to GNN to find the pose of each image by either using the image features as a node in a graph and formulate the pose estimation problem as node pose regression or modelling the image features themselves as a graph and the problem becomes graph pose regression. We do an extensive comparison between the proposed two approaches and the state of the art single image localization methods and show that using GNN leads to enhanced performance for both indoor and outdoor environments.</abstract><doi>10.48550/arxiv.2103.09435</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2103.09435
ispartof
issn
language eng
recordid cdi_arxiv_primary_2103_09435
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T04%3A10%3A31IST&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=Pose-GNN%20:%20Camera%20Pose%20Estimation%20System%20Using%20Graph%20Neural%20Networks&rft.au=Elmoogy,%20Ahmed&rft.date=2021-03-17&rft_id=info:doi/10.48550/arxiv.2103.09435&rft_dat=%3Carxiv_GOX%3E2103_09435%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