Infrared Multi-Pedestrian Tracking in Vertical View via Siamese Convolution Network
Target tracking has become one of the research hotspots in the field of computer vision in recent years. In this paper, a new intelligent algorithm of infrared multi-pedestrian tracking in vertical view is proposed. In the algorithm, the pedestrians in the infrared image can be quickly detected and...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2019, Vol.7, p.42718-42725 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 42725 |
|---|---|
| container_issue | |
| container_start_page | 42718 |
| container_title | IEEE access |
| container_volume | 7 |
| creator | Shen, Guojiang Zhu, Linfeng Lou, Jihan Shen, Si Liu, Zhi Tang, Longfeng |
| description | Target tracking has become one of the research hotspots in the field of computer vision in recent years. In this paper, a new intelligent algorithm of infrared multi-pedestrian tracking in vertical view is proposed. In the algorithm, the pedestrians in the infrared image can be quickly detected and located with the method of the Faster Regions with CNN features (RCNN) and then are tracked with the improved Siamese network. The tracking method based on Siamese network transforms the tracking problem into a similarity verification problem and evaluates the similarity score between new frame feature and target frame feature by convolution network. The candidate region with the highest score is considered as the current position of the target. In this paper, the Siamese network is combined with Faster RCNN for multi-pedestrian tracking. In addition, the tracking results of adjacent frames are introduced into the similarity evaluation of current frames to improve the tracking accuracy when the pedestrian posture changes. The experimental results show that the algorithm has good robustness and tracking result and achieves competitive performance. |
| doi_str_mv | 10.1109/ACCESS.2019.2892469 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_8610285</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8610285</ieee_id><doaj_id>oai_doaj_org_article_3466ef78b5be4a55af35129885efe951</doaj_id><sourcerecordid>2455636187</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-f989026611a8a2bd31c4ed38318bb2fb0157c46602fbe2fcb62e45c202ac08773</originalsourceid><addsrcrecordid>eNpNUctOwzAQjBBIVMAX9GKJc4ofsWMfUVSgEi-pwNVynHXlNsTFSVvx9yQEVexlR6Od2dVOkkwJnhGC1c1tUcyXyxnFRM2oVDQT6iSZUCJUyjgTp__weXLVtmvcl-wpnk-S5aJx0USo0NOu7nz6ChW0XfSmQW_R2I1vVsg36ANi562p0YeHA9p7g5befEILqAjNPtS7zocGPUN3CHFzmZw5U7dw9dcvkve7-VvxkD6-3C-K28fUZlh2qVNSYSoEIUYaWlaM2AwqJhmRZUldiQnPbSYE7jFQZ0tBIeOWYmoslnnOLpLF6FsFs9bb6D9N_NbBeP1LhLjSZji7Bs16H3C5LHkJmeHcOMYJVVJycKA46b2uR69tDF-7_gV6HXax6c_XNONcMEHksJGNUzaGto3gjlsJ1kMYegxDD2HovzB61XRUeQA4KqQgmErOfgAGV4TC</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2455636187</pqid></control><display><type>article</type><title>Infrared Multi-Pedestrian Tracking in Vertical View via Siamese Convolution Network</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Shen, Guojiang ; Zhu, Linfeng ; Lou, Jihan ; Shen, Si ; Liu, Zhi ; Tang, Longfeng</creator><creatorcontrib>Shen, Guojiang ; Zhu, Linfeng ; Lou, Jihan ; Shen, Si ; Liu, Zhi ; Tang, Longfeng</creatorcontrib><description>Target tracking has become one of the research hotspots in the field of computer vision in recent years. In this paper, a new intelligent algorithm of infrared multi-pedestrian tracking in vertical view is proposed. In the algorithm, the pedestrians in the infrared image can be quickly detected and located with the method of the Faster Regions with CNN features (RCNN) and then are tracked with the improved Siamese network. The tracking method based on Siamese network transforms the tracking problem into a similarity verification problem and evaluates the similarity score between new frame feature and target frame feature by convolution network. The candidate region with the highest score is considered as the current position of the target. In this paper, the Siamese network is combined with Faster RCNN for multi-pedestrian tracking. In addition, the tracking results of adjacent frames are introduced into the similarity evaluation of current frames to improve the tracking accuracy when the pedestrian posture changes. The experimental results show that the algorithm has good robustness and tracking result and achieves competitive performance.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2019.2892469</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Computer vision ; Convolution ; convolution network ; Feature extraction ; infrared detection ; Infrared imagery ; Infrared tracking ; pedestrian tracking ; Pedestrians ; Proposals ; Real-time systems ; Siamese network ; Similarity ; Target tracking ; Tracking ; Tracking problem ; Training</subject><ispartof>IEEE access, 2019, Vol.7, p.42718-42725</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-f989026611a8a2bd31c4ed38318bb2fb0157c46602fbe2fcb62e45c202ac08773</citedby><cites>FETCH-LOGICAL-c408t-f989026611a8a2bd31c4ed38318bb2fb0157c46602fbe2fcb62e45c202ac08773</cites><orcidid>0000-0001-7746-9294</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8610285$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,2102,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Shen, Guojiang</creatorcontrib><creatorcontrib>Zhu, Linfeng</creatorcontrib><creatorcontrib>Lou, Jihan</creatorcontrib><creatorcontrib>Shen, Si</creatorcontrib><creatorcontrib>Liu, Zhi</creatorcontrib><creatorcontrib>Tang, Longfeng</creatorcontrib><title>Infrared Multi-Pedestrian Tracking in Vertical View via Siamese Convolution Network</title><title>IEEE access</title><addtitle>Access</addtitle><description>Target tracking has become one of the research hotspots in the field of computer vision in recent years. In this paper, a new intelligent algorithm of infrared multi-pedestrian tracking in vertical view is proposed. In the algorithm, the pedestrians in the infrared image can be quickly detected and located with the method of the Faster Regions with CNN features (RCNN) and then are tracked with the improved Siamese network. The tracking method based on Siamese network transforms the tracking problem into a similarity verification problem and evaluates the similarity score between new frame feature and target frame feature by convolution network. The candidate region with the highest score is considered as the current position of the target. In this paper, the Siamese network is combined with Faster RCNN for multi-pedestrian tracking. In addition, the tracking results of adjacent frames are introduced into the similarity evaluation of current frames to improve the tracking accuracy when the pedestrian posture changes. The experimental results show that the algorithm has good robustness and tracking result and achieves competitive performance.</description><subject>Algorithms</subject><subject>Computer vision</subject><subject>Convolution</subject><subject>convolution network</subject><subject>Feature extraction</subject><subject>infrared detection</subject><subject>Infrared imagery</subject><subject>Infrared tracking</subject><subject>pedestrian tracking</subject><subject>Pedestrians</subject><subject>Proposals</subject><subject>Real-time systems</subject><subject>Siamese network</subject><subject>Similarity</subject><subject>Target tracking</subject><subject>Tracking</subject><subject>Tracking problem</subject><subject>Training</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUctOwzAQjBBIVMAX9GKJc4ofsWMfUVSgEi-pwNVynHXlNsTFSVvx9yQEVexlR6Od2dVOkkwJnhGC1c1tUcyXyxnFRM2oVDQT6iSZUCJUyjgTp__weXLVtmvcl-wpnk-S5aJx0USo0NOu7nz6ChW0XfSmQW_R2I1vVsg36ANi562p0YeHA9p7g5befEILqAjNPtS7zocGPUN3CHFzmZw5U7dw9dcvkve7-VvxkD6-3C-K28fUZlh2qVNSYSoEIUYaWlaM2AwqJhmRZUldiQnPbSYE7jFQZ0tBIeOWYmoslnnOLpLF6FsFs9bb6D9N_NbBeP1LhLjSZji7Bs16H3C5LHkJmeHcOMYJVVJycKA46b2uR69tDF-7_gV6HXax6c_XNONcMEHksJGNUzaGto3gjlsJ1kMYegxDD2HovzB61XRUeQA4KqQgmErOfgAGV4TC</recordid><startdate>2019</startdate><enddate>2019</enddate><creator>Shen, Guojiang</creator><creator>Zhu, Linfeng</creator><creator>Lou, Jihan</creator><creator>Shen, Si</creator><creator>Liu, Zhi</creator><creator>Tang, Longfeng</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-7746-9294</orcidid></search><sort><creationdate>2019</creationdate><title>Infrared Multi-Pedestrian Tracking in Vertical View via Siamese Convolution Network</title><author>Shen, Guojiang ; Zhu, Linfeng ; Lou, Jihan ; Shen, Si ; Liu, Zhi ; Tang, Longfeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-f989026611a8a2bd31c4ed38318bb2fb0157c46602fbe2fcb62e45c202ac08773</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Computer vision</topic><topic>Convolution</topic><topic>convolution network</topic><topic>Feature extraction</topic><topic>infrared detection</topic><topic>Infrared imagery</topic><topic>Infrared tracking</topic><topic>pedestrian tracking</topic><topic>Pedestrians</topic><topic>Proposals</topic><topic>Real-time systems</topic><topic>Siamese network</topic><topic>Similarity</topic><topic>Target tracking</topic><topic>Tracking</topic><topic>Tracking problem</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shen, Guojiang</creatorcontrib><creatorcontrib>Zhu, Linfeng</creatorcontrib><creatorcontrib>Lou, Jihan</creatorcontrib><creatorcontrib>Shen, Si</creatorcontrib><creatorcontrib>Liu, Zhi</creatorcontrib><creatorcontrib>Tang, Longfeng</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials 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>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shen, Guojiang</au><au>Zhu, Linfeng</au><au>Lou, Jihan</au><au>Shen, Si</au><au>Liu, Zhi</au><au>Tang, Longfeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Infrared Multi-Pedestrian Tracking in Vertical View via Siamese Convolution Network</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2019</date><risdate>2019</risdate><volume>7</volume><spage>42718</spage><epage>42725</epage><pages>42718-42725</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Target tracking has become one of the research hotspots in the field of computer vision in recent years. In this paper, a new intelligent algorithm of infrared multi-pedestrian tracking in vertical view is proposed. In the algorithm, the pedestrians in the infrared image can be quickly detected and located with the method of the Faster Regions with CNN features (RCNN) and then are tracked with the improved Siamese network. The tracking method based on Siamese network transforms the tracking problem into a similarity verification problem and evaluates the similarity score between new frame feature and target frame feature by convolution network. The candidate region with the highest score is considered as the current position of the target. In this paper, the Siamese network is combined with Faster RCNN for multi-pedestrian tracking. In addition, the tracking results of adjacent frames are introduced into the similarity evaluation of current frames to improve the tracking accuracy when the pedestrian posture changes. The experimental results show that the algorithm has good robustness and tracking result and achieves competitive performance.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2019.2892469</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0001-7746-9294</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2019, Vol.7, p.42718-42725 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_ieee_primary_8610285 |
| source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals |
| subjects | Algorithms Computer vision Convolution convolution network Feature extraction infrared detection Infrared imagery Infrared tracking pedestrian tracking Pedestrians Proposals Real-time systems Siamese network Similarity Target tracking Tracking Tracking problem Training |
| title | Infrared Multi-Pedestrian Tracking in Vertical View via Siamese Convolution Network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T05%3A43%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Infrared%20Multi-Pedestrian%20Tracking%20in%20Vertical%20View%20via%20Siamese%20Convolution%20Network&rft.jtitle=IEEE%20access&rft.au=Shen,%20Guojiang&rft.date=2019&rft.volume=7&rft.spage=42718&rft.epage=42725&rft.pages=42718-42725&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2019.2892469&rft_dat=%3Cproquest_ieee_%3E2455636187%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2455636187&rft_id=info:pmid/&rft_ieee_id=8610285&rft_doaj_id=oai_doaj_org_article_3466ef78b5be4a55af35129885efe951&rfr_iscdi=true |