View in EDS HTML Full Text PDF Full Text

Abnormal event detection in surveillance videos based on multi-scale feature and channel-wise attention mechanism.

Saved in:
Bibliographic Details
Title: Abnormal event detection in surveillance videos based on multi-scale feature and channel-wise attention mechanism.
Authors: Xia, Limin1 (AUTHOR), Wei, Changhong1 (AUTHOR) weichanghong@csu.edu.cn
Source: Journal of Supercomputing. Jul2022, Vol. 78 Issue 11, p13470-13490. 21p.
Subjects: Video surveillance, Surveillance detection, Machine learning, Intrusion detection systems (Computer security)
Abstract: Abnormal event detection is a challenging task, due to object scale variation, impact of background and anomaly defined differently in different context. In this paper, we propose a new multi-scale feature prediction framework for abnormal event detection. Firstly, we construct a multi-scale alignment feature generator to fuse the characteristic of different receptive fields so that address the objects of different scales in video frame. Secondly, in order to weak the influence of background, a novel channel-wise attention mechanism is introduced to highlight those informative channels while suppressing the confusing ones. Finally, an autoencoder-based deep feature prediction module is applied to capture temporal information and contextual information to generate predicted features. Instead of giving a definition of anomaly, we treat predicted features that differ from the actual features as abnormal features. Experimental results on four benchmark datasets demonstrate the superiority of the proposed framework over the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Supercomputing 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: 157789794
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Abnormal event detection in surveillance videos based on multi-scale feature and channel-wise attention mechanism.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Xia%2C+Limin%22">Xia, Limin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wei%2C+Changhong%22">Wei, Changhong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> weichanghong@csu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Supercomputing%22">Journal of Supercomputing</searchLink>. Jul2022, Vol. 78 Issue 11, p13470-13490. 21p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Video+surveillance%22">Video surveillance</searchLink><br /><searchLink fieldCode="DE" term="%22Surveillance+detection%22">Surveillance detection</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Intrusion+detection+systems+%28Computer+security%29%22">Intrusion detection systems (Computer security)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Abnormal event detection is a challenging task, due to object scale variation, impact of background and anomaly defined differently in different context. In this paper, we propose a new multi-scale feature prediction framework for abnormal event detection. Firstly, we construct a multi-scale alignment feature generator to fuse the characteristic of different receptive fields so that address the objects of different scales in video frame. Secondly, in order to weak the influence of background, a novel channel-wise attention mechanism is introduced to highlight those informative channels while suppressing the confusing ones. Finally, an autoencoder-based deep feature prediction module is applied to capture temporal information and contextual information to generate predicted features. Instead of giving a definition of anomaly, we treat predicted features that differ from the actual features as abnormal features. Experimental results on four benchmark datasets demonstrate the superiority of the proposed framework over the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Supercomputing 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=157789794
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11227-022-04410-w
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
        StartPage: 13470
    Subjects:
      – SubjectFull: Video surveillance
        Type: general
      – SubjectFull: Surveillance detection
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Intrusion detection systems (Computer security)
        Type: general
    Titles:
      – TitleFull: Abnormal event detection in surveillance videos based on multi-scale feature and channel-wise attention mechanism.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xia, Limin
      – PersonEntity:
          Name:
            NameFull: Wei, Changhong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 05
              M: 07
              Text: Jul2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 09208542
          Numbering:
            – Type: volume
              Value: 78
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Journal of Supercomputing
              Type: main
ResultId 1