Attention Mask-Based Network With Simple Color Annotation for UAV Vehicle Re-Identification

Vehicle re-identification (VeID) has attracted a growing research interest in recent years, and excellent performance has been shown with fixed traffic cameras. However, vehicle ReID in aerial images taken by unmanned aerial vehicles (UAVs), possessing both variable locations and special viewpoints,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE geoscience and remote sensing letters 2022, Vol.19, p.1-5
Hauptverfasser: Yao, Aihuan, Huang, Mengmeng, Qi, Jiahao, Zhong, Ping
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 5
container_issue
container_start_page 1
container_title IEEE geoscience and remote sensing letters
container_volume 19
creator Yao, Aihuan
Huang, Mengmeng
Qi, Jiahao
Zhong, Ping
description Vehicle re-identification (VeID) has attracted a growing research interest in recent years, and excellent performance has been shown with fixed traffic cameras. However, vehicle ReID in aerial images taken by unmanned aerial vehicles (UAVs), possessing both variable locations and special viewpoints, is still under-explored. Recent works tend to extract meaningful local features by careful annotation, which are effective but time-consuming. In order to extract discriminative features and avoid tedious annotating work, this letter develops an attention mask (AM)-based network with simple color annotation for object enhancement and background reduction. The network makes full use of deep features obtained by a pretrained color classification network and then utilizes principal component analysis (PCA) as a mapping function to achieve AMs without partial annotation. Besides, we introduce weighted triplet loss (WTL) function to deal with the problem of great similarity between classes caused by overlook views of UAVs. The loss function concentrates more on negative pairs to facilitate the identification ability of network. Rich experiments are conducted on both UAV dataset and surveillance dataset, and our method achieves competitive performance compared with recent ReID works.
doi_str_mv 10.1109/LGRS.2021.3092369
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2615513305</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9497319</ieee_id><sourcerecordid>2615513305</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-ae5afe913c6ed2e6d7027deb0023e89e25ecc7ca2e00db8ad1fb2074d4692b1a3</originalsourceid><addsrcrecordid>eNo9kN9LwzAQx4MoOKd_gPhS8LkzP5q2eaxD52AqbG4KPoQ0ubJus5lJhvjf227Dp7uDz_fu-CB0TfCAECzuJqPpbEAxJQOGBWWpOEE9wnkeY56R065PeMxF_nGOLrxfYUyTPM966LMIAZpQ2yZ6Vn4d3ysPJnqB8GPdOnqvwzKa1V_bDURDu7EuKprGBrXnq3acF4toActat8AU4rHpdlW13hOX6KxSGw9Xx9pH88eHt-FTPHkdjYfFJNZUsBAr4KoCQZhOwVBITYZpZqBsf2SQC6ActM60ooCxKXNlSFVSnCUmSQUtiWJ9dHvYu3X2ewc-yJXduaY9KWnaSiCMYd5S5EBpZ713UMmtq7-U-5UEy86h7BzKzqE8OmwzN4dMDQD_vEhExohgf7uAbf4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2615513305</pqid></control><display><type>article</type><title>Attention Mask-Based Network With Simple Color Annotation for UAV Vehicle Re-Identification</title><source>IEEE Electronic Library (IEL)</source><creator>Yao, Aihuan ; Huang, Mengmeng ; Qi, Jiahao ; Zhong, Ping</creator><creatorcontrib>Yao, Aihuan ; Huang, Mengmeng ; Qi, Jiahao ; Zhong, Ping</creatorcontrib><description>Vehicle re-identification (VeID) has attracted a growing research interest in recent years, and excellent performance has been shown with fixed traffic cameras. However, vehicle ReID in aerial images taken by unmanned aerial vehicles (UAVs), possessing both variable locations and special viewpoints, is still under-explored. Recent works tend to extract meaningful local features by careful annotation, which are effective but time-consuming. In order to extract discriminative features and avoid tedious annotating work, this letter develops an attention mask (AM)-based network with simple color annotation for object enhancement and background reduction. The network makes full use of deep features obtained by a pretrained color classification network and then utilizes principal component analysis (PCA) as a mapping function to achieve AMs without partial annotation. Besides, we introduce weighted triplet loss (WTL) function to deal with the problem of great similarity between classes caused by overlook views of UAVs. The loss function concentrates more on negative pairs to facilitate the identification ability of network. Rich experiments are conducted on both UAV dataset and surveillance dataset, and our method achieves competitive performance compared with recent ReID works.</description><identifier>ISSN: 1545-598X</identifier><identifier>EISSN: 1558-0571</identifier><identifier>DOI: 10.1109/LGRS.2021.3092369</identifier><identifier>CODEN: IGRSBY</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Annotations ; Attention mask (AM) ; Bibliographic information ; Cameras ; Color ; Colour ; Datasets ; Feature extraction ; Identification ; Image color analysis ; Principal component analysis ; principal component analysis (PCA) ; Principal components analysis ; Training ; unmanned aerial vehicle (UAV) vehicle re-identification (VeID) ; Unmanned aerial vehicles ; weighted triplet loss (WTL)</subject><ispartof>IEEE geoscience and remote sensing letters, 2022, Vol.19, p.1-5</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-ae5afe913c6ed2e6d7027deb0023e89e25ecc7ca2e00db8ad1fb2074d4692b1a3</citedby><cites>FETCH-LOGICAL-c293t-ae5afe913c6ed2e6d7027deb0023e89e25ecc7ca2e00db8ad1fb2074d4692b1a3</cites><orcidid>0000-0002-2560-8157 ; 0000-0002-1609-4406 ; 0000-0002-8686-3928 ; 0000-0002-0057-8748</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9497319$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,4024,27923,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9497319$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yao, Aihuan</creatorcontrib><creatorcontrib>Huang, Mengmeng</creatorcontrib><creatorcontrib>Qi, Jiahao</creatorcontrib><creatorcontrib>Zhong, Ping</creatorcontrib><title>Attention Mask-Based Network With Simple Color Annotation for UAV Vehicle Re-Identification</title><title>IEEE geoscience and remote sensing letters</title><addtitle>LGRS</addtitle><description>Vehicle re-identification (VeID) has attracted a growing research interest in recent years, and excellent performance has been shown with fixed traffic cameras. However, vehicle ReID in aerial images taken by unmanned aerial vehicles (UAVs), possessing both variable locations and special viewpoints, is still under-explored. Recent works tend to extract meaningful local features by careful annotation, which are effective but time-consuming. In order to extract discriminative features and avoid tedious annotating work, this letter develops an attention mask (AM)-based network with simple color annotation for object enhancement and background reduction. The network makes full use of deep features obtained by a pretrained color classification network and then utilizes principal component analysis (PCA) as a mapping function to achieve AMs without partial annotation. Besides, we introduce weighted triplet loss (WTL) function to deal with the problem of great similarity between classes caused by overlook views of UAVs. The loss function concentrates more on negative pairs to facilitate the identification ability of network. Rich experiments are conducted on both UAV dataset and surveillance dataset, and our method achieves competitive performance compared with recent ReID works.</description><subject>Annotations</subject><subject>Attention mask (AM)</subject><subject>Bibliographic information</subject><subject>Cameras</subject><subject>Color</subject><subject>Colour</subject><subject>Datasets</subject><subject>Feature extraction</subject><subject>Identification</subject><subject>Image color analysis</subject><subject>Principal component analysis</subject><subject>principal component analysis (PCA)</subject><subject>Principal components analysis</subject><subject>Training</subject><subject>unmanned aerial vehicle (UAV) vehicle re-identification (VeID)</subject><subject>Unmanned aerial vehicles</subject><subject>weighted triplet loss (WTL)</subject><issn>1545-598X</issn><issn>1558-0571</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kN9LwzAQx4MoOKd_gPhS8LkzP5q2eaxD52AqbG4KPoQ0ubJus5lJhvjf227Dp7uDz_fu-CB0TfCAECzuJqPpbEAxJQOGBWWpOEE9wnkeY56R065PeMxF_nGOLrxfYUyTPM966LMIAZpQ2yZ6Vn4d3ysPJnqB8GPdOnqvwzKa1V_bDURDu7EuKprGBrXnq3acF4toActat8AU4rHpdlW13hOX6KxSGw9Xx9pH88eHt-FTPHkdjYfFJNZUsBAr4KoCQZhOwVBITYZpZqBsf2SQC6ActM60ooCxKXNlSFVSnCUmSQUtiWJ9dHvYu3X2ewc-yJXduaY9KWnaSiCMYd5S5EBpZ713UMmtq7-U-5UEy86h7BzKzqE8OmwzN4dMDQD_vEhExohgf7uAbf4</recordid><startdate>2022</startdate><enddate>2022</enddate><creator>Yao, Aihuan</creator><creator>Huang, Mengmeng</creator><creator>Qi, Jiahao</creator><creator>Zhong, Ping</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>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TG</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H8D</scope><scope>H96</scope><scope>JQ2</scope><scope>KL.</scope><scope>KR7</scope><scope>L.G</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-2560-8157</orcidid><orcidid>https://orcid.org/0000-0002-1609-4406</orcidid><orcidid>https://orcid.org/0000-0002-8686-3928</orcidid><orcidid>https://orcid.org/0000-0002-0057-8748</orcidid></search><sort><creationdate>2022</creationdate><title>Attention Mask-Based Network With Simple Color Annotation for UAV Vehicle Re-Identification</title><author>Yao, Aihuan ; Huang, Mengmeng ; Qi, Jiahao ; Zhong, Ping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-ae5afe913c6ed2e6d7027deb0023e89e25ecc7ca2e00db8ad1fb2074d4692b1a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Annotations</topic><topic>Attention mask (AM)</topic><topic>Bibliographic information</topic><topic>Cameras</topic><topic>Color</topic><topic>Colour</topic><topic>Datasets</topic><topic>Feature extraction</topic><topic>Identification</topic><topic>Image color analysis</topic><topic>Principal component analysis</topic><topic>principal component analysis (PCA)</topic><topic>Principal components analysis</topic><topic>Training</topic><topic>unmanned aerial vehicle (UAV) vehicle re-identification (VeID)</topic><topic>Unmanned aerial vehicles</topic><topic>weighted triplet loss (WTL)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yao, Aihuan</creatorcontrib><creatorcontrib>Huang, Mengmeng</creatorcontrib><creatorcontrib>Qi, Jiahao</creatorcontrib><creatorcontrib>Zhong, Ping</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>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Meteorological &amp; Geoastrophysical Abstracts</collection><collection>Water Resources Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>ProQuest Computer Science Collection</collection><collection>Meteorological &amp; Geoastrophysical Abstracts - Academic</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE geoscience and remote sensing letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yao, Aihuan</au><au>Huang, Mengmeng</au><au>Qi, Jiahao</au><au>Zhong, Ping</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Attention Mask-Based Network With Simple Color Annotation for UAV Vehicle Re-Identification</atitle><jtitle>IEEE geoscience and remote sensing letters</jtitle><stitle>LGRS</stitle><date>2022</date><risdate>2022</risdate><volume>19</volume><spage>1</spage><epage>5</epage><pages>1-5</pages><issn>1545-598X</issn><eissn>1558-0571</eissn><coden>IGRSBY</coden><abstract>Vehicle re-identification (VeID) has attracted a growing research interest in recent years, and excellent performance has been shown with fixed traffic cameras. However, vehicle ReID in aerial images taken by unmanned aerial vehicles (UAVs), possessing both variable locations and special viewpoints, is still under-explored. Recent works tend to extract meaningful local features by careful annotation, which are effective but time-consuming. In order to extract discriminative features and avoid tedious annotating work, this letter develops an attention mask (AM)-based network with simple color annotation for object enhancement and background reduction. The network makes full use of deep features obtained by a pretrained color classification network and then utilizes principal component analysis (PCA) as a mapping function to achieve AMs without partial annotation. Besides, we introduce weighted triplet loss (WTL) function to deal with the problem of great similarity between classes caused by overlook views of UAVs. The loss function concentrates more on negative pairs to facilitate the identification ability of network. Rich experiments are conducted on both UAV dataset and surveillance dataset, and our method achieves competitive performance compared with recent ReID works.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LGRS.2021.3092369</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0002-2560-8157</orcidid><orcidid>https://orcid.org/0000-0002-1609-4406</orcidid><orcidid>https://orcid.org/0000-0002-8686-3928</orcidid><orcidid>https://orcid.org/0000-0002-0057-8748</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1545-598X
ispartof IEEE geoscience and remote sensing letters, 2022, Vol.19, p.1-5
issn 1545-598X
1558-0571
language eng
recordid cdi_proquest_journals_2615513305
source IEEE Electronic Library (IEL)
subjects Annotations
Attention mask (AM)
Bibliographic information
Cameras
Color
Colour
Datasets
Feature extraction
Identification
Image color analysis
Principal component analysis
principal component analysis (PCA)
Principal components analysis
Training
unmanned aerial vehicle (UAV) vehicle re-identification (VeID)
Unmanned aerial vehicles
weighted triplet loss (WTL)
title Attention Mask-Based Network With Simple Color Annotation for UAV Vehicle Re-Identification
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T15%3A04%3A53IST&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=Attention%20Mask-Based%20Network%20With%20Simple%20Color%20Annotation%20for%20UAV%20Vehicle%20Re-Identification&rft.jtitle=IEEE%20geoscience%20and%20remote%20sensing%20letters&rft.au=Yao,%20Aihuan&rft.date=2022&rft.volume=19&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.issn=1545-598X&rft.eissn=1558-0571&rft.coden=IGRSBY&rft_id=info:doi/10.1109/LGRS.2021.3092369&rft_dat=%3Cproquest_RIE%3E2615513305%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=2615513305&rft_id=info:pmid/&rft_ieee_id=9497319&rfr_iscdi=true