View in EDS HTML Full Text PDF Full Text

CenterPoint-UAV: Context-Detail BEV Refinement for 3D Object Detection in UAV Point Clouds.

Saved in:
Bibliographic Details
Title: CenterPoint-UAV: Context-Detail BEV Refinement for 3D Object Detection in UAV Point Clouds.
Authors: Wu, Yutian1,2 (AUTHOR), Mei, Sifan1,2 (AUTHOR), Liu, Shengli3 (AUTHOR), Wang, Yichen4 (AUTHOR), Ogai, Harutoshi1,4 (AUTHOR), Li, Qing1,2 (AUTHOR) liqing@ies.ustb.edu.cn
Source: Remote Sensing. Sep2026, Vol. 18 Issue 17, p2994. 26p.
Subjects: Point cloud, Remote sensing, Object recognition (Computer vision)
Abstract: UAV-based 3D object detection is important for remote-sensing applications such as autonomous inspection, search and rescue, aerial mapping, flight cooperation, and scene-level environmental understanding, where a detector must localize diverse objects in large and sparsely observed point clouds. Existing 3D object detectors provide a strong foundation, but most of them are developed around autonomous-driving scenarios and are not fully adapted to UAV scenes. Compared with road scenes, UAV point clouds usually cover larger areas, contain more diverse object categories, and include many small, sparse, and structurally varied targets. Many small targets therefore occupy only a few BEV cells and contain limited point returns; subsequent feature aggregation and downsampling can further smooth these sparse local responses, making object boundaries and center-related responses less distinguishable from the background. We propose CenterPoint-UAV, an end-to-end voxel-based detector that refines BEV features for UAV-based 3D object detection. CenterPoint-UAV introduces Context-Detail BEV Enhance (CDBE), which uses a Context Enhancement Branch (CEB) and a Detail Enhancement Branch (DEB) to produce complementary BEV feature maps and fuses them using Adaptive Residual Fusion (ARF). It then uses Cross-Level BEV Fusion (CLBF) to combine early BEV details with deep semantic features, followed by a Fine Center Head (FCH) for denser center prediction. Experiments on WiSAR3D, a large-scale real-world UAV point-cloud dataset for multi-category object detection, show that CenterPoint-UAV achieves state-of-the-art mAP among existing methods and maintains a low parameter budget, demonstrating its effectiveness for UAV-based 3D remote sensing. [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: 197043844
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: CenterPoint-UAV: Context-Detail BEV Refinement for 3D Object Detection in UAV Point Clouds.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wu%2C+Yutian%22">Wu, Yutian</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mei%2C+Sifan%22">Mei, Sifan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Shengli%22">Liu, Shengli</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Yichen%22">Wang, Yichen</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ogai%2C+Harutoshi%22">Ogai, Harutoshi</searchLink><relatesTo>1,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Qing%22">Li, Qing</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> liqing@ies.ustb.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Sep2026, Vol. 18 Issue 17, p2994. 26p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Point+cloud%22">Point cloud</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: UAV-based 3D object detection is important for remote-sensing applications such as autonomous inspection, search and rescue, aerial mapping, flight cooperation, and scene-level environmental understanding, where a detector must localize diverse objects in large and sparsely observed point clouds. Existing 3D object detectors provide a strong foundation, but most of them are developed around autonomous-driving scenarios and are not fully adapted to UAV scenes. Compared with road scenes, UAV point clouds usually cover larger areas, contain more diverse object categories, and include many small, sparse, and structurally varied targets. Many small targets therefore occupy only a few BEV cells and contain limited point returns; subsequent feature aggregation and downsampling can further smooth these sparse local responses, making object boundaries and center-related responses less distinguishable from the background. We propose CenterPoint-UAV, an end-to-end voxel-based detector that refines BEV features for UAV-based 3D object detection. CenterPoint-UAV introduces Context-Detail BEV Enhance (CDBE), which uses a Context Enhancement Branch (CEB) and a Detail Enhancement Branch (DEB) to produce complementary BEV feature maps and fuses them using Adaptive Residual Fusion (ARF). It then uses Cross-Level BEV Fusion (CLBF) to combine early BEV details with deep semantic features, followed by a Fine Center Head (FCH) for denser center prediction. Experiments on WiSAR3D, a large-scale real-world UAV point-cloud dataset for multi-category object detection, show that CenterPoint-UAV achieves state-of-the-art mAP among existing methods and maintains a low parameter budget, demonstrating its effectiveness for UAV-based 3D remote sensing. [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=197043844
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs18172994
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 26
        StartPage: 2994
    Subjects:
      – SubjectFull: Point cloud
        Type: general
      – SubjectFull: Remote sensing
        Type: general
      – SubjectFull: Object recognition (Computer vision)
        Type: general
    Titles:
      – TitleFull: CenterPoint-UAV: Context-Detail BEV Refinement for 3D Object Detection in UAV Point Clouds.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Wu, Yutian
      – PersonEntity:
          Name:
            NameFull: Mei, Sifan
      – PersonEntity:
          Name:
            NameFull: Liu, Shengli
      – PersonEntity:
          Name:
            NameFull: Wang, Yichen
      – PersonEntity:
          Name:
            NameFull: Ogai, Harutoshi
      – PersonEntity:
          Name:
            NameFull: Li, Qing
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 17
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1