特征分块重构的视频行人重识别算法
TP391.41; 基于视频的行人重识别是将一段视频轨迹与剪辑后的视频帧进行匹配,从而实现在不同的摄像头下识别同一行人.但由于现实场景的复杂性,采集到的行人轨迹会存在严重的外观丢失和错位,传统的三维卷积将不再适用于视频行人重识别任务.针对这一问题,提出三维特征分块重构模型,利用第一张特征图在水平分块的级别上对后续特征图进行对齐.在保证特征质量的前提下充分挖掘轨迹的时间信息,在特征重构模型后加入三维卷积核,并且将它与现有的三维卷积网络相结合.此外,还引入一种由粗到细的特征分块重构网络,不仅能使模型在两种不同尺度的空间维度上进行特征重构,还能进一步减少计算开销.实验表明,由粗到细的特征分块重构网络...
Saved in:
| Published in | 数据采集与处理 Vol. 38; no. 3; pp. 565 - 573 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
重庆邮电大学通信与信息工程学院,重庆 400065
01.05.2023
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1004-9037 |
| DOI | 10.16337/j.1004-9037.2023.03.006 |
Cover
Loading…
| Abstract | TP391.41; 基于视频的行人重识别是将一段视频轨迹与剪辑后的视频帧进行匹配,从而实现在不同的摄像头下识别同一行人.但由于现实场景的复杂性,采集到的行人轨迹会存在严重的外观丢失和错位,传统的三维卷积将不再适用于视频行人重识别任务.针对这一问题,提出三维特征分块重构模型,利用第一张特征图在水平分块的级别上对后续特征图进行对齐.在保证特征质量的前提下充分挖掘轨迹的时间信息,在特征重构模型后加入三维卷积核,并且将它与现有的三维卷积网络相结合.此外,还引入一种由粗到细的特征分块重构网络,不仅能使模型在两种不同尺度的空间维度上进行特征重构,还能进一步减少计算开销.实验表明,由粗到细的特征分块重构网络在MARS和DukeMTMC?VideoReID数据集上取得了良好的结果. |
|---|---|
| AbstractList | TP391.41; 基于视频的行人重识别是将一段视频轨迹与剪辑后的视频帧进行匹配,从而实现在不同的摄像头下识别同一行人.但由于现实场景的复杂性,采集到的行人轨迹会存在严重的外观丢失和错位,传统的三维卷积将不再适用于视频行人重识别任务.针对这一问题,提出三维特征分块重构模型,利用第一张特征图在水平分块的级别上对后续特征图进行对齐.在保证特征质量的前提下充分挖掘轨迹的时间信息,在特征重构模型后加入三维卷积核,并且将它与现有的三维卷积网络相结合.此外,还引入一种由粗到细的特征分块重构网络,不仅能使模型在两种不同尺度的空间维度上进行特征重构,还能进一步减少计算开销.实验表明,由粗到细的特征分块重构网络在MARS和DukeMTMC?VideoReID数据集上取得了良好的结果. |
| Author | 周非 舒浩峰 王锦华 白梦林 |
| AuthorAffiliation | 重庆邮电大学通信与信息工程学院,重庆 400065 |
| AuthorAffiliation_xml | – name: 重庆邮电大学通信与信息工程学院,重庆 400065 |
| Author_FL | ZHOU Fei SHU Haofeng WANG Jinhua BAI Menglin |
| Author_FL_xml | – sequence: 1 fullname: WANG Jinhua – sequence: 2 fullname: ZHOU Fei – sequence: 3 fullname: BAI Menglin – sequence: 4 fullname: SHU Haofeng |
| Author_xml | – sequence: 1 fullname: 王锦华 – sequence: 2 fullname: 周非 – sequence: 3 fullname: 白梦林 – sequence: 4 fullname: 舒浩峰 |
| BookMark | eNrjYmDJy89LZWBQMDTQMzQzNjbXz9IzNDAw0bU0MDbXMzIwMtYzACIDMxYGTrg4BwNvcXFmElDSzMTM0NKMk8HgeefOp_san3a0PZ07_WV777N5Lc9ntbxY3vZy0cQXC3ue7NoFFHyxvu1px-rn66Y_2zyVh4E1LTGnOJUXSnMzhLq5hjh76Pr4u3s6O_roFhsaGJvpGppampommpmbGZqbpiSap5iYmSWbGyYapCWamiclWyalGVskGhhZGFlamholGqYYG1kmJhokpyQam1qapaQYJhpzM2hAzC1PzEtLzEuPz8ovLcoD2hhfnJWcVZmcA_KigTHQg8YAT15YfA |
| ClassificationCodes | TP391.41 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.16337/j.1004-9037.2023.03.006 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | Video?Based Person Re?identification Algorithm Based on Feature Block Recon?struction |
| EndPage | 573 |
| ExternalDocumentID | sjcjycl202303006 |
| GroupedDBID | 2B. 4A8 92I 93N ADMLS ALMA_UNASSIGNED_HOLDINGS PSX TCJ |
| ID | FETCH-LOGICAL-s1036-15955a676175da7d466c71a0fa57bc9bf38a02829952a1d329aa0cda3596dd1a3 |
| ISSN | 1004-9037 |
| IngestDate | Thu May 29 04:00:12 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 3 |
| Keywords | 特征分块 三维卷积 由粗到细的特征分块重构网络 特征重构 视频行人重识别 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1036-15955a676175da7d466c71a0fa57bc9bf38a02829952a1d329aa0cda3596dd1a3 |
| PageCount | 9 |
| ParticipantIDs | wanfang_journals_sjcjycl202303006 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-05-01 |
| PublicationDateYYYYMMDD | 2023-05-01 |
| PublicationDate_xml | – month: 05 year: 2023 text: 2023-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 数据采集与处理 |
| PublicationTitle_FL | Journal of Data Acquisition & Processing |
| PublicationYear | 2023 |
| Publisher | 重庆邮电大学通信与信息工程学院,重庆 400065 |
| Publisher_xml | – name: 重庆邮电大学通信与信息工程学院,重庆 400065 |
| SSID | ssib023646196 ssib001102757 ssib000459638 ssib001164671 ssib006568634 ssib002264227 ssib036439733 ssib057620134 ssib023167944 ssib051372606 |
| Score | 2.3447635 |
| Snippet | TP391.41;... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 565 |
| Title | 特征分块重构的视频行人重识别算法 |
| URI | https://d.wanfangdata.com.cn/periodical/sjcjycl202303006 |
| Volume | 38 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Na9VAEA-1XryIouI3FdyTvJrsZr-OSV9KEfTUQm9lk7woRZ5g24O9CeVZoR48SEFQ0IsHQQ-e7MG_xte-_hfOTPJe1lahCo-wbGZnZ36TZGfyZidBcJvzqNBCVx3wBapOXBnVcabKO3EZC17l0pa0Pfr-A7WwFN9blstTp3a8rKWN9Xy22PzjvpL_sSr0gV1xl-w_WHbCFDqgDfaFI1gYjieyMcs0M5allmWSpRl4hdgwhhmFDdtlVrPMMgj4TZdlilmgiXGUTahhWKKJ2LKEMxtRT8TMHMtilib4a4fDqfmGM0yRpMgnyWgKxVLB6s9Yjj1dmg6kCrEBw4GyYUUi2ZRYwSwgbYY8k3gsW8jM5H0hqQhSpzQoZkk9fxc6WxKJoieGSEDnzB9sAR_SHRTEwQSC1S2JQW0sJyVAihpLAYL7L0S4l35Il7CHi0SYahANJz01SgrMaq0AYmx0aXpLqSUJaT6PWLcQTHoUGhKwRs4AsSSgDWHg8bFkMz53XJI7Mfl83nqDeUA2rOvejBckYbwbT3iri2yG1o6KrL8Bc2wNVILKKKzOTpjPIkx1Ld8jZcfJkVlbLVafFY-RCB75WL_-NNe6TnpoXlA0zv9vT2twHLn2_jOPsFSdF1zgFm3O_V3Myqi2GCHHGgzermz8kgFE8xPnWJCv3AYjMhIagu_JeQiUwXmt00bGijapeojA3b_oT5vz-pXrP_T8yMVzwdkmAJxJ6rv5fDC1-ehCEB68_D788Xy4PRi-2z188Wr__dbB263Rp8Hhx9ejDzs_9_agc_R1MNz-fPBld__bm4vB0ny2OLfQab5l0lmLsOY3RA1SOqUhYJCl02WsVKEjF1ZO6ryweSWMo6wGK7mLSsGtc2FROgGYl2XkxKVguv-k37sczCgM0uJKSFfksTDKlbKQPfREQ9HTxl4JbjUarjTPqrWVoya-egKaa8GZ9va6HkyvP93o3QAPfD2_SRfGL4WEl1A |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E7%89%B9%E5%BE%81%E5%88%86%E5%9D%97%E9%87%8D%E6%9E%84%E7%9A%84%E8%A7%86%E9%A2%91%E8%A1%8C%E4%BA%BA%E9%87%8D%E8%AF%86%E5%88%AB%E7%AE%97%E6%B3%95&rft.jtitle=%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E5%A4%84%E7%90%86&rft.au=%E7%8E%8B%E9%94%A6%E5%8D%8E&rft.au=%E5%91%A8%E9%9D%9E&rft.au=%E7%99%BD%E6%A2%A6%E6%9E%97&rft.au=%E8%88%92%E6%B5%A9%E5%B3%B0&rft.date=2023-05-01&rft.pub=%E9%87%8D%E5%BA%86%E9%82%AE%E7%94%B5%E5%A4%A7%E5%AD%A6%E9%80%9A%E4%BF%A1%E4%B8%8E%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E9%87%8D%E5%BA%86+400065&rft.issn=1004-9037&rft.volume=38&rft.issue=3&rft.spage=565&rft.epage=573&rft_id=info:doi/10.16337%2Fj.1004-9037.2023.03.006&rft.externalDocID=sjcjycl202303006 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fsjcjycl%2Fsjcjycl.jpg |