View in EDS HTML Full Text PDF Full Text

ViTrans: Inter-Frame Alignment Enhancement for Moving Vehicle Detection in Satellite Videos with Stabilization Offsets.

Saved in:
Bibliographic Details
Title: ViTrans: Inter-Frame Alignment Enhancement for Moving Vehicle Detection in Satellite Videos with Stabilization Offsets.
Authors: He, Tao1 (AUTHOR), Sun, Kaimin1,2 (AUTHOR) sunkm@whu.edu.cn, Duan, Yu1,3 (AUTHOR), Cui, Wei1 (AUTHOR), Wang, Ziang1,2 (AUTHOR), Gao, Song1,3 (AUTHOR), Yao, Yuan1,2 (AUTHOR), Chen, Zijie3 (AUTHOR)
Source: Remote Sensing. Sep2025, Vol. 17 Issue 17, p2973. 22p.
Subjects: Image registration, Image stabilization, Motion analysis, Image processing, Aerial surveillance, Object recognition (Computer vision)
Abstract: Satellite videos typically employ image registration techniques for video stabilization in order to achieve persistent observation. However, existing methods largely neglect the residual stabilization offsets, particularly when exceeding the physical dimensions of target vehicles, which inevitably causes performance degradation. Furthermore, the detection pipeline struggles with hard-to-discriminate samples that exhibit low contrast, motion blur, or occlusion, while conventional sample assignment strategies fail to address the inherent annotation ambiguity for extremely small objects. We propose an end-to-end method called ViTrans for detecting moving vehicles in satellite video under stabilization offsets. ViTrans consists of three core modules: (1) a feature-aligned stabilization offset correction module (SCM) that mitigates feature misalignment by aligning features between the reference frame and the current frame; (2) a feature adaptive aggregation enhancement module (AAEM) based on vehicle trajectory consistency, which leverages the motion characteristics of objects across consecutive frames to eliminate dynamic clutter and false-alarm artifacts; and (3) a Gaussian distribution-based metric that dynamically adapts to bounding box dimensions, thereby providing more accurate positive sample feedback during model training. Extensive experiments on the VISO and SDM-Car datasets under simulated stabilization offsets demonstrate that ViTrans achieves state-of-the-art performance, improving F1-score by 14.4% on VISO and 6.9% on SDM-Car over existing methods. [ABSTRACT FROM AUTHOR]
Copyright of Remote Sensing is the property of MDPI 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: 187981693
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: ViTrans: Inter-Frame Alignment Enhancement for Moving Vehicle Detection in Satellite Videos with Stabilization Offsets.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22He%2C+Tao%22">He, Tao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Kaimin%22">Sun, Kaimin</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> sunkm@whu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Duan%2C+Yu%22">Duan, Yu</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cui%2C+Wei%22">Cui, Wei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Ziang%22">Wang, Ziang</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gao%2C+Song%22">Gao, Song</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yao%2C+Yuan%22">Yao, Yuan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Zijie%22">Chen, Zijie</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Sep2025, Vol. 17 Issue 17, p2973. 22p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+registration%22">Image registration</searchLink><br /><searchLink fieldCode="DE" term="%22Image+stabilization%22">Image stabilization</searchLink><br /><searchLink fieldCode="DE" term="%22Motion+analysis%22">Motion analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Aerial+surveillance%22">Aerial surveillance</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Satellite videos typically employ image registration techniques for video stabilization in order to achieve persistent observation. However, existing methods largely neglect the residual stabilization offsets, particularly when exceeding the physical dimensions of target vehicles, which inevitably causes performance degradation. Furthermore, the detection pipeline struggles with hard-to-discriminate samples that exhibit low contrast, motion blur, or occlusion, while conventional sample assignment strategies fail to address the inherent annotation ambiguity for extremely small objects. We propose an end-to-end method called ViTrans for detecting moving vehicles in satellite video under stabilization offsets. ViTrans consists of three core modules: (1) a feature-aligned stabilization offset correction module (SCM) that mitigates feature misalignment by aligning features between the reference frame and the current frame; (2) a feature adaptive aggregation enhancement module (AAEM) based on vehicle trajectory consistency, which leverages the motion characteristics of objects across consecutive frames to eliminate dynamic clutter and false-alarm artifacts; and (3) a Gaussian distribution-based metric that dynamically adapts to bounding box dimensions, thereby providing more accurate positive sample feedback during model training. Extensive experiments on the VISO and SDM-Car datasets under simulated stabilization offsets demonstrate that ViTrans achieves state-of-the-art performance, improving F1-score by 14.4% on VISO and 6.9% on SDM-Car over existing methods. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Remote Sensing is the property of MDPI 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=187981693
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs17172973
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 22
        StartPage: 2973
    Subjects:
      – SubjectFull: Image registration
        Type: general
      – SubjectFull: Image stabilization
        Type: general
      – SubjectFull: Motion analysis
        Type: general
      – SubjectFull: Image processing
        Type: general
      – SubjectFull: Aerial surveillance
        Type: general
      – SubjectFull: Object recognition (Computer vision)
        Type: general
    Titles:
      – TitleFull: ViTrans: Inter-Frame Alignment Enhancement for Moving Vehicle Detection in Satellite Videos with Stabilization Offsets.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: He, Tao
      – PersonEntity:
          Name:
            NameFull: Sun, Kaimin
      – PersonEntity:
          Name:
            NameFull: Duan, Yu
      – PersonEntity:
          Name:
            NameFull: Cui, Wei
      – PersonEntity:
          Name:
            NameFull: Wang, Ziang
      – PersonEntity:
          Name:
            NameFull: Gao, Song
      – PersonEntity:
          Name:
            NameFull: Yao, Yuan
      – PersonEntity:
          Name:
            NameFull: Chen, Zijie
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 17
            – Type: issue
              Value: 17
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1