Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to proce...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-08
Hauptverfasser: Hornakova, Andrea, Kaiser, Timo, Swoboda, Paul, Rolinek, Michal, Rosenhahn, Bodo, Henschel, Roberto
Format: Artikel
Sprache:eng
Schlagworte:
Benchmarks
Message passing
Multiple target tracking
Solvers
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Hornakova, Andrea
Kaiser, Timo
Swoboda, Paul
Rolinek, Michal
Rosenhahn, Bodo
Henschel, Roberto
description We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to process the MOT15/16/17 benchmarks without sacrificing solution quality and allows for solving MOT20, which has been out of reach up to now for LDP solvers due to its size and complexity. On all these four standard MOT benchmarks we achieve performance comparable or better than current state-of-the-art methods including a tracker based on an optimal LDP solver.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2564322879</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2564322879</sourcerecordid><originalsourceid>FETCH-proquest_journals_25643228793</originalsourceid><addsrcrecordid>eNqNzM0OATEUBeBGIiHMO9zEWjJu5wc78RMLQsLOYlK03FEtbYnH14UHsDlncb6cBmsj54P-MENsscT7Ok1TLErMc95mh7W4kbnAki5X6WDjzjHXmz3sTkKLo5ZjmBiYK0UnkibA5PFw9kN3ESTsrH5HrayDFakgzzAjX1uKbCvC1XdZUwntZfLrDust5vvpsh8vni_pQ1XblzNxqjAvMo44LEf8P_UFrQFBzw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2564322879</pqid></control><display><type>article</type><title>Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths</title><source>Freely Accessible Journals</source><creator>Hornakova, Andrea ; Kaiser, Timo ; Swoboda, Paul ; Rolinek, Michal ; Rosenhahn, Bodo ; Henschel, Roberto</creator><creatorcontrib>Hornakova, Andrea ; Kaiser, Timo ; Swoboda, Paul ; Rolinek, Michal ; Rosenhahn, Bodo ; Henschel, Roberto</creatorcontrib><description>We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to process the MOT15/16/17 benchmarks without sacrificing solution quality and allows for solving MOT20, which has been out of reach up to now for LDP solvers due to its size and complexity. On all these four standard MOT benchmarks we achieve performance comparable or better than current state-of-the-art methods including a tracker based on an optimal LDP solver.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Benchmarks ; Message passing ; Multiple target tracking ; Solvers</subject><ispartof>arXiv.org, 2021-08</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Hornakova, Andrea</creatorcontrib><creatorcontrib>Kaiser, Timo</creatorcontrib><creatorcontrib>Swoboda, Paul</creatorcontrib><creatorcontrib>Rolinek, Michal</creatorcontrib><creatorcontrib>Rosenhahn, Bodo</creatorcontrib><creatorcontrib>Henschel, Roberto</creatorcontrib><title>Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths</title><title>arXiv.org</title><description>We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to process the MOT15/16/17 benchmarks without sacrificing solution quality and allows for solving MOT20, which has been out of reach up to now for LDP solvers due to its size and complexity. On all these four standard MOT benchmarks we achieve performance comparable or better than current state-of-the-art methods including a tracker based on an optimal LDP solver.</description><subject>Benchmarks</subject><subject>Message passing</subject><subject>Multiple target tracking</subject><subject>Solvers</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNzM0OATEUBeBGIiHMO9zEWjJu5wc78RMLQsLOYlK03FEtbYnH14UHsDlncb6cBmsj54P-MENsscT7Ok1TLErMc95mh7W4kbnAki5X6WDjzjHXmz3sTkKLo5ZjmBiYK0UnkibA5PFw9kN3ESTsrH5HrayDFakgzzAjX1uKbCvC1XdZUwntZfLrDust5vvpsh8vni_pQ1XblzNxqjAvMo44LEf8P_UFrQFBzw</recordid><startdate>20210824</startdate><enddate>20210824</enddate><creator>Hornakova, Andrea</creator><creator>Kaiser, Timo</creator><creator>Swoboda, Paul</creator><creator>Rolinek, Michal</creator><creator>Rosenhahn, Bodo</creator><creator>Henschel, Roberto</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210824</creationdate><title>Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths</title><author>Hornakova, Andrea ; Kaiser, Timo ; Swoboda, Paul ; Rolinek, Michal ; Rosenhahn, Bodo ; Henschel, Roberto</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25643228793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Benchmarks</topic><topic>Message passing</topic><topic>Multiple target tracking</topic><topic>Solvers</topic><toplevel>online_resources</toplevel><creatorcontrib>Hornakova, Andrea</creatorcontrib><creatorcontrib>Kaiser, Timo</creatorcontrib><creatorcontrib>Swoboda, Paul</creatorcontrib><creatorcontrib>Rolinek, Michal</creatorcontrib><creatorcontrib>Rosenhahn, Bodo</creatorcontrib><creatorcontrib>Henschel, Roberto</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hornakova, Andrea</au><au>Kaiser, Timo</au><au>Swoboda, Paul</au><au>Rolinek, Michal</au><au>Rosenhahn, Bodo</au><au>Henschel, Roberto</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths</atitle><jtitle>arXiv.org</jtitle><date>2021-08-24</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to process the MOT15/16/17 benchmarks without sacrificing solution quality and allows for solving MOT20, which has been out of reach up to now for LDP solvers due to its size and complexity. On all these four standard MOT benchmarks we achieve performance comparable or better than current state-of-the-art methods including a tracker based on an optimal LDP solver.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2564322879
source Freely Accessible Journals
subjects Benchmarks
Message passing
Multiple target tracking
Solvers
title Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T16%3A00%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Making%20Higher%20Order%20MOT%20Scalable:%20An%20Efficient%20Approximate%20Solver%20for%20Lifted%20Disjoint%20Paths&rft.jtitle=arXiv.org&rft.au=Hornakova,%20Andrea&rft.date=2021-08-24&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2564322879%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2564322879&rft_id=info:pmid/&rfr_iscdi=true