Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data

Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle cameras. In this paper, we develop a geo-context aw...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics 2022-01, Vol.28 (1), p.1019-1029
Hauptverfasser: Jamonnak, Suphanut, Zhao, Ye, Huang, Xinyi, Amiruzzaman, Md
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1029
container_issue 1
container_start_page 1019
container_title IEEE transactions on visualization and computer graphics
container_volume 28
creator Jamonnak, Suphanut
Zhao, Ye
Huang, Xinyi
Amiruzzaman, Md
description Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle cameras. In this paper, we develop a geo-context aware visualization system for the study of Autonomous Driving Model (ADM) predictions together with large-scale ADM video data. The visual study is seamlessly integrated with the geographical environment by combining DL model performance with geospatial visualization techniques. Model performance measures can be studied together with a set of geospatial attributes over map views. Users can also discover and compare prediction behaviors of multiple DL models in both city-wide and street-level analysis, together with road images and video contents. Therefore, the system provides a new visual exploration platform for DL model designers in autonomous driving. Use cases and domain expert evaluation show the utility and effectiveness of the visualization system.
doi_str_mv 10.1109/TVCG.2021.3114853
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2613369280</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9555830</ieee_id><sourcerecordid>2578781281</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-c5fb014fe9c9c131aaae5fde4b755eab4221eb9bea5949726093c2bad438fa763</originalsourceid><addsrcrecordid>eNpdkE1r20AQhpeS0Hz1B5RCWcilF7k7-yXt0bFbN5CSQz7IbRlJo6Igax2t1Cb_Pmvs5pDTDMzzDi8PY59BzACE-357v1jNpJAwUwC6MOoDOwanIRNG2IO0izzPpJX2iJ3E-CgEaF24j-xIaeOs0faYPawoZIvQj_Q88vk_HIjfjFP9wkPD79vYhj67wEg1n09j6MM6TJEvh_Zv2__hv0NNXeTY1_xmg2OLXYrUFPgSRzxjhw12kT7t5ym7-_njdvEru7peXS7mV1mltBuzyjRlqtWQq1wFChCRTFOTLnNjCEstJVDpSkLjtMulFU5VssRaq6LB3KpT9m33dzOEp4ni6NdtrKjrsKdU1kuTF3kBsoCEnr9DH8M09KmdlxaUsk4WIlGwo6ohxDhQ4zdDu8bhxYPwW-1-q91vtfu99pT5uv88lWuq3xL_PSfgyw5oiejt7IwxhRLqFR0EhaU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2613369280</pqid></control><display><type>article</type><title>Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data</title><source>IEEE Electronic Library (IEL)</source><creator>Jamonnak, Suphanut ; Zhao, Ye ; Huang, Xinyi ; Amiruzzaman, Md</creator><creatorcontrib>Jamonnak, Suphanut ; Zhao, Ye ; Huang, Xinyi ; Amiruzzaman, Md</creatorcontrib><description>Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle cameras. In this paper, we develop a geo-context aware visualization system for the study of Autonomous Driving Model (ADM) predictions together with large-scale ADM video data. The visual study is seamlessly integrated with the geographical environment by combining DL model performance with geospatial visualization techniques. Model performance measures can be studied together with a set of geospatial attributes over map views. Users can also discover and compare prediction behaviors of multiple DL models in both city-wide and street-level analysis, together with road images and video contents. Therefore, the system provides a new visual exploration platform for DL model designers in autonomous driving. Use cases and domain expert evaluation show the utility and effectiveness of the visualization system.</description><identifier>ISSN: 1077-2626</identifier><identifier>EISSN: 1941-0506</identifier><identifier>DOI: 10.1109/TVCG.2021.3114853</identifier><identifier>PMID: 34596546</identifier><identifier>CODEN: ITVGEA</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Analytical models ; Autonomous Driving ; Autonomous vehicles ; Computational modeling ; Context ; Data models ; Data visualization ; Deep learning ; Predictive models ; Spatial data ; Spatial Video ; Video data ; Vision ; Vision-based Deep Learning Models ; Visualization ; Visualization System</subject><ispartof>IEEE transactions on visualization and computer graphics, 2022-01, Vol.28 (1), p.1019-1029</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-c5fb014fe9c9c131aaae5fde4b755eab4221eb9bea5949726093c2bad438fa763</citedby><cites>FETCH-LOGICAL-c349t-c5fb014fe9c9c131aaae5fde4b755eab4221eb9bea5949726093c2bad438fa763</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9555830$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9555830$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/34596546$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Jamonnak, Suphanut</creatorcontrib><creatorcontrib>Zhao, Ye</creatorcontrib><creatorcontrib>Huang, Xinyi</creatorcontrib><creatorcontrib>Amiruzzaman, Md</creatorcontrib><title>Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data</title><title>IEEE transactions on visualization and computer graphics</title><addtitle>TVCG</addtitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><description>Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle cameras. In this paper, we develop a geo-context aware visualization system for the study of Autonomous Driving Model (ADM) predictions together with large-scale ADM video data. The visual study is seamlessly integrated with the geographical environment by combining DL model performance with geospatial visualization techniques. Model performance measures can be studied together with a set of geospatial attributes over map views. Users can also discover and compare prediction behaviors of multiple DL models in both city-wide and street-level analysis, together with road images and video contents. Therefore, the system provides a new visual exploration platform for DL model designers in autonomous driving. Use cases and domain expert evaluation show the utility and effectiveness of the visualization system.</description><subject>Analytical models</subject><subject>Autonomous Driving</subject><subject>Autonomous vehicles</subject><subject>Computational modeling</subject><subject>Context</subject><subject>Data models</subject><subject>Data visualization</subject><subject>Deep learning</subject><subject>Predictive models</subject><subject>Spatial data</subject><subject>Spatial Video</subject><subject>Video data</subject><subject>Vision</subject><subject>Vision-based Deep Learning Models</subject><subject>Visualization</subject><subject>Visualization System</subject><issn>1077-2626</issn><issn>1941-0506</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkE1r20AQhpeS0Hz1B5RCWcilF7k7-yXt0bFbN5CSQz7IbRlJo6Igax2t1Cb_Pmvs5pDTDMzzDi8PY59BzACE-357v1jNpJAwUwC6MOoDOwanIRNG2IO0izzPpJX2iJ3E-CgEaF24j-xIaeOs0faYPawoZIvQj_Q88vk_HIjfjFP9wkPD79vYhj67wEg1n09j6MM6TJEvh_Zv2__hv0NNXeTY1_xmg2OLXYrUFPgSRzxjhw12kT7t5ym7-_njdvEru7peXS7mV1mltBuzyjRlqtWQq1wFChCRTFOTLnNjCEstJVDpSkLjtMulFU5VssRaq6LB3KpT9m33dzOEp4ni6NdtrKjrsKdU1kuTF3kBsoCEnr9DH8M09KmdlxaUsk4WIlGwo6ohxDhQ4zdDu8bhxYPwW-1-q91vtfu99pT5uv88lWuq3xL_PSfgyw5oiejt7IwxhRLqFR0EhaU</recordid><startdate>202201</startdate><enddate>202201</enddate><creator>Jamonnak, Suphanut</creator><creator>Zhao, Ye</creator><creator>Huang, Xinyi</creator><creator>Amiruzzaman, Md</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope></search><sort><creationdate>202201</creationdate><title>Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data</title><author>Jamonnak, Suphanut ; Zhao, Ye ; Huang, Xinyi ; Amiruzzaman, Md</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-c5fb014fe9c9c131aaae5fde4b755eab4221eb9bea5949726093c2bad438fa763</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Analytical models</topic><topic>Autonomous Driving</topic><topic>Autonomous vehicles</topic><topic>Computational modeling</topic><topic>Context</topic><topic>Data models</topic><topic>Data visualization</topic><topic>Deep learning</topic><topic>Predictive models</topic><topic>Spatial data</topic><topic>Spatial Video</topic><topic>Video data</topic><topic>Vision</topic><topic>Vision-based Deep Learning Models</topic><topic>Visualization</topic><topic>Visualization System</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jamonnak, Suphanut</creatorcontrib><creatorcontrib>Zhao, Ye</creatorcontrib><creatorcontrib>Huang, Xinyi</creatorcontrib><creatorcontrib>Amiruzzaman, Md</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on visualization and computer graphics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jamonnak, Suphanut</au><au>Zhao, Ye</au><au>Huang, Xinyi</au><au>Amiruzzaman, Md</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data</atitle><jtitle>IEEE transactions on visualization and computer graphics</jtitle><stitle>TVCG</stitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><date>2022-01</date><risdate>2022</risdate><volume>28</volume><issue>1</issue><spage>1019</spage><epage>1029</epage><pages>1019-1029</pages><issn>1077-2626</issn><eissn>1941-0506</eissn><coden>ITVGEA</coden><abstract>Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle cameras. In this paper, we develop a geo-context aware visualization system for the study of Autonomous Driving Model (ADM) predictions together with large-scale ADM video data. The visual study is seamlessly integrated with the geographical environment by combining DL model performance with geospatial visualization techniques. Model performance measures can be studied together with a set of geospatial attributes over map views. Users can also discover and compare prediction behaviors of multiple DL models in both city-wide and street-level analysis, together with road images and video contents. Therefore, the system provides a new visual exploration platform for DL model designers in autonomous driving. Use cases and domain expert evaluation show the utility and effectiveness of the visualization system.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>34596546</pmid><doi>10.1109/TVCG.2021.3114853</doi><tpages>11</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1077-2626
ispartof IEEE transactions on visualization and computer graphics, 2022-01, Vol.28 (1), p.1019-1029
issn 1077-2626
1941-0506
language eng
recordid cdi_proquest_journals_2613369280
source IEEE Electronic Library (IEL)
subjects Analytical models
Autonomous Driving
Autonomous vehicles
Computational modeling
Context
Data models
Data visualization
Deep learning
Predictive models
Spatial data
Spatial Video
Video data
Vision
Vision-based Deep Learning Models
Visualization
Visualization System
title Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T03%3A37%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Geo-Context%20Aware%20Study%20of%20Vision-Based%20Autonomous%20Driving%20Models%20and%20Spatial%20Video%20Data&rft.jtitle=IEEE%20transactions%20on%20visualization%20and%20computer%20graphics&rft.au=Jamonnak,%20Suphanut&rft.date=2022-01&rft.volume=28&rft.issue=1&rft.spage=1019&rft.epage=1029&rft.pages=1019-1029&rft.issn=1077-2626&rft.eissn=1941-0506&rft.coden=ITVGEA&rft_id=info:doi/10.1109/TVCG.2021.3114853&rft_dat=%3Cproquest_RIE%3E2578781281%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2613369280&rft_id=info:pmid/34596546&rft_ieee_id=9555830&rfr_iscdi=true