View in EDS HTML Full Text PDF Full Text

Occlusion-Preserved Surveillance Video Synopsis with Flexible Object Graph.

Saved in:
Bibliographic Details
Title: Occlusion-Preserved Surveillance Video Synopsis with Flexible Object Graph.
Authors: Nie, Yongwei1 (AUTHOR), Ge, Wei1 (AUTHOR), Zeng, Siming1 (AUTHOR), Zhang, Qing2 (AUTHOR), Li, Guiqing1 (AUTHOR), Li, Ping3,4 (AUTHOR), Cai, Hongmin1,5 (AUTHOR) hmcai@scut.edu.cn
Source: International Journal of Computer Vision. May2025, Vol. 133 Issue 5, p2653-2669. 17p.
Subjects: Video summarization, Data structures, Artificial intelligence, Video surveillance, Flexible structures
Abstract: Video synopsis is a technique that condenses a long surveillance video to a short summary. It faces challenges to process objects originally occluding each other in the source video. Previous approaches either treat occlusion objects as a single object, which however reduce compression ratio; or have to separate occlusion objects individually, but destroy interactions between them and yield visual artifacts. This paper presents a novel data structure called Flexible Object Graph (FOG) to handle original occlusions. Our FOG-based video synopsis approach can manipulate each object flexibly while preserving the original occlusions between them, achieving high synopsis ratio while maintaining interactions of objects. A challenging issue that comes with the introduction of FOG is that FOG may contain circulations that yield conflicts. We solve this problem by proposing a circulation conflict resolving algorithm. Furthermore, video synopsis methods usually minimize a multi-objective energy function. Previous approaches optimize the multiple objectives simultaneously which needs to strike a balance between them. Instead, we propose a stepwise optimization strategy consuming less running time while producing higher quality. Experiments demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 184555890
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Occlusion-Preserved Surveillance Video Synopsis with Flexible Object Graph.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Nie%2C+Yongwei%22">Nie, Yongwei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ge%2C+Wei%22">Ge, Wei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zeng%2C+Siming%22">Zeng, Siming</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Qing%22">Zhang, Qing</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Guiqing%22">Li, Guiqing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Ping%22">Li, Ping</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cai%2C+Hongmin%22">Cai, Hongmin</searchLink><relatesTo>1,5</relatesTo> (AUTHOR)<i> hmcai@scut.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Computer+Vision%22">International Journal of Computer Vision</searchLink>. May2025, Vol. 133 Issue 5, p2653-2669. 17p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Video+summarization%22">Video summarization</searchLink><br /><searchLink fieldCode="DE" term="%22Data+structures%22">Data structures</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Video+surveillance%22">Video surveillance</searchLink><br /><searchLink fieldCode="DE" term="%22Flexible+structures%22">Flexible structures</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Video synopsis is a technique that condenses a long surveillance video to a short summary. It faces challenges to process objects originally occluding each other in the source video. Previous approaches either treat occlusion objects as a single object, which however reduce compression ratio; or have to separate occlusion objects individually, but destroy interactions between them and yield visual artifacts. This paper presents a novel data structure called Flexible Object Graph (FOG) to handle original occlusions. Our FOG-based video synopsis approach can manipulate each object flexibly while preserving the original occlusions between them, achieving high synopsis ratio while maintaining interactions of objects. A challenging issue that comes with the introduction of FOG is that FOG may contain circulations that yield conflicts. We solve this problem by proposing a circulation conflict resolving algorithm. Furthermore, video synopsis methods usually minimize a multi-objective energy function. Previous approaches optimize the multiple objectives simultaneously which needs to strike a balance between them. Instead, we propose a stepwise optimization strategy consuming less running time while producing higher quality. Experiments demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=184555890
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11263-024-02302-5
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 2653
    Subjects:
      – SubjectFull: Video summarization
        Type: general
      – SubjectFull: Data structures
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Video surveillance
        Type: general
      – SubjectFull: Flexible structures
        Type: general
    Titles:
      – TitleFull: Occlusion-Preserved Surveillance Video Synopsis with Flexible Object Graph.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Nie, Yongwei
      – PersonEntity:
          Name:
            NameFull: Ge, Wei
      – PersonEntity:
          Name:
            NameFull: Zeng, Siming
      – PersonEntity:
          Name:
            NameFull: Zhang, Qing
      – PersonEntity:
          Name:
            NameFull: Li, Guiqing
      – PersonEntity:
          Name:
            NameFull: Li, Ping
      – PersonEntity:
          Name:
            NameFull: Cai, Hongmin
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 09205691
          Numbering:
            – Type: volume
              Value: 133
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: International Journal of Computer Vision
              Type: main
ResultId 1