Multi-perspective vehicle detection and tracking: Challenges, dataset, and metrics

The research community has shown significant improvements in both vision-based detection and tracking of vehicles, working towards a high level understanding of on-road maneuvers. Behaviors of surrounding vehicles in a highway environment is found as an interesting starting point, of why this datase...

Full description

Saved in:
Bibliographic Details
Main Authors: Dueholm, Jacob V., Kristoffersen, Miklas S., Satzoda, Ravi K., Ohn-Bar, Eshed, Moeslund, Thomas B., Trivedi, Mohan M.
Format: Conference Proceeding
Language:English
Subjects:
autonomous driving
Cameras
Measurement
multi-perspective behavior analysis
Roads
Three-dimensional displays
Trajectory
Vehicle detection
vehicle tracking
Vehicles
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 964
container_issue
container_start_page 959
container_title
container_volume
creator Dueholm, Jacob V.
Kristoffersen, Miklas S.
Satzoda, Ravi K.
Ohn-Bar, Eshed
Moeslund, Thomas B.
Trivedi, Mohan M.
description The research community has shown significant improvements in both vision-based detection and tracking of vehicles, working towards a high level understanding of on-road maneuvers. Behaviors of surrounding vehicles in a highway environment is found as an interesting starting point, of why this dataset is introduced along with its challenges and evaluation metrics. A vision-based multi-perspective dataset is presented, containing a full panoramic view from a moving platform driving on U.S. highways capturing 2704×1440 resolution images at 12 frames per second. The dataset serves multiple purposes to be used as traditional detection and tracking, together with tracking of vehicles across perspectives. Each of the four perspectives have been annotated, resulting in more than 4000 bounding boxes in order to evaluate and compare novel methods.
doi_str_mv 10.1109/ITSC.2016.7795671
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_7795671</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7795671</ieee_id><sourcerecordid>7795671</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-de609d64c46ff48c4ea7bd3116ef97a20a1afe0e4f778bed0e098f63e2d262873</originalsourceid><addsrcrecordid>eNotkMtKAzEYhaMgWOo8gLjJA3TGP8lMLu5k8FKoCDr7kiZ_2uh0HCax4Nt769kc-Dh8i0PIJYOKMTDXy-61rTgwWSllGqnYCSmM0qwBA0xr05ySGWeNKAGYOidFSm_wE8G1FDAjL0-ffY7liFMa0eV4QHrAXXQ9Uo_5l3wM1A6e5sm69zhsb2i7s32PwxbTgnqbbcK8-JvsMU_RpQtyFmyfsDj2nHT3d137WK6eH5bt7aqMBnLpUYLxsna1DKHWrkarNl4wJjEYZTlYZgMC1kEpvUEPCEYHKZB7LrlWYk6u_rUREdfjFPd2-lofTxDf7iZRPw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Multi-perspective vehicle detection and tracking: Challenges, dataset, and metrics</title><source>IEEE Xplore All Conference Series</source><creator>Dueholm, Jacob V. ; Kristoffersen, Miklas S. ; Satzoda, Ravi K. ; Ohn-Bar, Eshed ; Moeslund, Thomas B. ; Trivedi, Mohan M.</creator><creatorcontrib>Dueholm, Jacob V. ; Kristoffersen, Miklas S. ; Satzoda, Ravi K. ; Ohn-Bar, Eshed ; Moeslund, Thomas B. ; Trivedi, Mohan M.</creatorcontrib><description>The research community has shown significant improvements in both vision-based detection and tracking of vehicles, working towards a high level understanding of on-road maneuvers. Behaviors of surrounding vehicles in a highway environment is found as an interesting starting point, of why this dataset is introduced along with its challenges and evaluation metrics. A vision-based multi-perspective dataset is presented, containing a full panoramic view from a moving platform driving on U.S. highways capturing 2704×1440 resolution images at 12 frames per second. The dataset serves multiple purposes to be used as traditional detection and tracking, together with tracking of vehicles across perspectives. Each of the four perspectives have been annotated, resulting in more than 4000 bounding boxes in order to evaluate and compare novel methods.</description><identifier>EISSN: 2153-0017</identifier><identifier>EISBN: 9781509018895</identifier><identifier>EISBN: 1509018891</identifier><identifier>DOI: 10.1109/ITSC.2016.7795671</identifier><language>eng</language><publisher>IEEE</publisher><subject>autonomous driving ; Cameras ; Measurement ; multi-perspective behavior analysis ; Roads ; Three-dimensional displays ; Trajectory ; Vehicle detection ; vehicle tracking ; Vehicles</subject><ispartof>2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), 2016, p.959-964</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7795671$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7795671$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Dueholm, Jacob V.</creatorcontrib><creatorcontrib>Kristoffersen, Miklas S.</creatorcontrib><creatorcontrib>Satzoda, Ravi K.</creatorcontrib><creatorcontrib>Ohn-Bar, Eshed</creatorcontrib><creatorcontrib>Moeslund, Thomas B.</creatorcontrib><creatorcontrib>Trivedi, Mohan M.</creatorcontrib><title>Multi-perspective vehicle detection and tracking: Challenges, dataset, and metrics</title><title>2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)</title><addtitle>ITSC</addtitle><description>The research community has shown significant improvements in both vision-based detection and tracking of vehicles, working towards a high level understanding of on-road maneuvers. Behaviors of surrounding vehicles in a highway environment is found as an interesting starting point, of why this dataset is introduced along with its challenges and evaluation metrics. A vision-based multi-perspective dataset is presented, containing a full panoramic view from a moving platform driving on U.S. highways capturing 2704×1440 resolution images at 12 frames per second. The dataset serves multiple purposes to be used as traditional detection and tracking, together with tracking of vehicles across perspectives. Each of the four perspectives have been annotated, resulting in more than 4000 bounding boxes in order to evaluate and compare novel methods.</description><subject>autonomous driving</subject><subject>Cameras</subject><subject>Measurement</subject><subject>multi-perspective behavior analysis</subject><subject>Roads</subject><subject>Three-dimensional displays</subject><subject>Trajectory</subject><subject>Vehicle detection</subject><subject>vehicle tracking</subject><subject>Vehicles</subject><issn>2153-0017</issn><isbn>9781509018895</isbn><isbn>1509018891</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2016</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkMtKAzEYhaMgWOo8gLjJA3TGP8lMLu5k8FKoCDr7kiZ_2uh0HCax4Nt769kc-Dh8i0PIJYOKMTDXy-61rTgwWSllGqnYCSmM0qwBA0xr05ySGWeNKAGYOidFSm_wE8G1FDAjL0-ffY7liFMa0eV4QHrAXXQ9Uo_5l3wM1A6e5sm69zhsb2i7s32PwxbTgnqbbcK8-JvsMU_RpQtyFmyfsDj2nHT3d137WK6eH5bt7aqMBnLpUYLxsna1DKHWrkarNl4wJjEYZTlYZgMC1kEpvUEPCEYHKZB7LrlWYk6u_rUREdfjFPd2-lofTxDf7iZRPw</recordid><startdate>201611</startdate><enddate>201611</enddate><creator>Dueholm, Jacob V.</creator><creator>Kristoffersen, Miklas S.</creator><creator>Satzoda, Ravi K.</creator><creator>Ohn-Bar, Eshed</creator><creator>Moeslund, Thomas B.</creator><creator>Trivedi, Mohan M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201611</creationdate><title>Multi-perspective vehicle detection and tracking: Challenges, dataset, and metrics</title><author>Dueholm, Jacob V. ; Kristoffersen, Miklas S. ; Satzoda, Ravi K. ; Ohn-Bar, Eshed ; Moeslund, Thomas B. ; Trivedi, Mohan M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-de609d64c46ff48c4ea7bd3116ef97a20a1afe0e4f778bed0e098f63e2d262873</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2016</creationdate><topic>autonomous driving</topic><topic>Cameras</topic><topic>Measurement</topic><topic>multi-perspective behavior analysis</topic><topic>Roads</topic><topic>Three-dimensional displays</topic><topic>Trajectory</topic><topic>Vehicle detection</topic><topic>vehicle tracking</topic><topic>Vehicles</topic><toplevel>online_resources</toplevel><creatorcontrib>Dueholm, Jacob V.</creatorcontrib><creatorcontrib>Kristoffersen, Miklas S.</creatorcontrib><creatorcontrib>Satzoda, Ravi K.</creatorcontrib><creatorcontrib>Ohn-Bar, Eshed</creatorcontrib><creatorcontrib>Moeslund, Thomas B.</creatorcontrib><creatorcontrib>Trivedi, Mohan M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Dueholm, Jacob V.</au><au>Kristoffersen, Miklas S.</au><au>Satzoda, Ravi K.</au><au>Ohn-Bar, Eshed</au><au>Moeslund, Thomas B.</au><au>Trivedi, Mohan M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Multi-perspective vehicle detection and tracking: Challenges, dataset, and metrics</atitle><btitle>2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)</btitle><stitle>ITSC</stitle><date>2016-11</date><risdate>2016</risdate><spage>959</spage><epage>964</epage><pages>959-964</pages><eissn>2153-0017</eissn><eisbn>9781509018895</eisbn><eisbn>1509018891</eisbn><abstract>The research community has shown significant improvements in both vision-based detection and tracking of vehicles, working towards a high level understanding of on-road maneuvers. Behaviors of surrounding vehicles in a highway environment is found as an interesting starting point, of why this dataset is introduced along with its challenges and evaluation metrics. A vision-based multi-perspective dataset is presented, containing a full panoramic view from a moving platform driving on U.S. highways capturing 2704×1440 resolution images at 12 frames per second. The dataset serves multiple purposes to be used as traditional detection and tracking, together with tracking of vehicles across perspectives. Each of the four perspectives have been annotated, resulting in more than 4000 bounding boxes in order to evaluate and compare novel methods.</abstract><pub>IEEE</pub><doi>10.1109/ITSC.2016.7795671</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2153-0017
ispartof 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), 2016, p.959-964
issn 2153-0017
language eng
recordid cdi_ieee_primary_7795671
source IEEE Xplore All Conference Series
subjects autonomous driving
Cameras
Measurement
multi-perspective behavior analysis
Roads
Three-dimensional displays
Trajectory
Vehicle detection
vehicle tracking
Vehicles
title Multi-perspective vehicle detection and tracking: Challenges, dataset, and metrics
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T03%3A15%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Multi-perspective%20vehicle%20detection%20and%20tracking:%20Challenges,%20dataset,%20and%20metrics&rft.btitle=2016%20IEEE%2019th%20International%20Conference%20on%20Intelligent%20Transportation%20Systems%20(ITSC)&rft.au=Dueholm,%20Jacob%20V.&rft.date=2016-11&rft.spage=959&rft.epage=964&rft.pages=959-964&rft.eissn=2153-0017&rft_id=info:doi/10.1109/ITSC.2016.7795671&rft.eisbn=9781509018895&rft.eisbn_list=1509018891&rft_dat=%3Cieee_CHZPO%3E7795671%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-de609d64c46ff48c4ea7bd3116ef97a20a1afe0e4f778bed0e098f63e2d262873%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=7795671&rfr_iscdi=true