Academic Journal
View in EDS
HTML Full Text

An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation.

Bibliographic Details
Title: An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation.
Authors: Chen, Meida1 (AUTHOR) feng@ict.usc.edu, Han, Kangle2 (AUTHOR) kangleha@usc.edu, Yu, Zifan3 (AUTHOR) zifanyu@asu.edu, Feng, Andrew1 (AUTHOR), Hou, Yu4 (AUTHOR) yu.hou@wne.edu, You, Suya5 (AUTHOR) suya.you.civ@army.mil, Soibelman, Lucio2 (AUTHOR) soibelma@usc.edu
Source: Remote Sensing. Nov2024, Vol. 16 Issue 22, p4240. 27p.
Subject Terms: *AERIAL photogrammetry, *POINT cloud, *ACQUISITION of data, *RESEARCH personnel, *ANNOTATIONS
Abstract: The recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and small teams. To this end, we present a novel synthetic 3D point cloud generation framework that can produce detailed outdoor aerial photogrammetric 3D datasets with accurate ground truth annotations without the labor-intensive and time-consuming data collection/annotation processes. Our pipeline procedurally generates synthetic environments, mirroring real-world data collection and 3D reconstruction processes. A key feature of our framework is its ability to replicate consistent quality, noise patterns, and diversity similar to real-world datasets. This is achieved by adopting UAV flight patterns that resemble those used in real-world data collection processes (e.g., the cross-hatch flight pattern) across various synthetic terrains that are procedurally generated, thereby ensuring data consistency akin to real-world scenarios. Moreover, the generated datasets are enriched with precise semantic and instance annotations, eliminating the need for manual labeling. Our approach has led to the development and release of the Semantic Terrain Points Labeling—Synthetic 3D (STPLS3D) benchmark, an extensive outdoor 3D dataset encompassing over 16 km 2 , featuring up to 19 semantic labels. We also collected, reconstructed, and annotated four real-world datasets for validation purposes. Extensive experiments on these datasets demonstrate our synthetic datasets' effectiveness, superior quality, and their value as a benchmark dataset for further point cloud research. [ABSTRACT FROM AUTHOR]
Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. 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: Academic Search Complete
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
CustomLinks:
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:a9h&genre=article&issn=20724292&ISBN=&volume=16&issue=22&date=20241115&spage=4240&pages=4240-4266&title=Remote Sensing&atitle=An%20Aerial%20Photogrammetry%20Benchmark%20Dataset%20for%20Point%20Cloud%20Segmentation%20and%20Style%20Translation.&aulast=Chen%2C%20Meida&id=DOI:10.3390/rs16224240
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
Header DbId: a9h
DbLabel: Academic Search Complete
An: 181203471
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chen%2C+Meida%22">Chen, Meida</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> feng@ict.usc.edu</i><br /><searchLink fieldCode="AR" term="%22Han%2C+Kangle%22">Han, Kangle</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> kangleha@usc.edu</i><br /><searchLink fieldCode="AR" term="%22Yu%2C+Zifan%22">Yu, Zifan</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> zifanyu@asu.edu</i><br /><searchLink fieldCode="AR" term="%22Feng%2C+Andrew%22">Feng, Andrew</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hou%2C+Yu%22">Hou, Yu</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> yu.hou@wne.edu</i><br /><searchLink fieldCode="AR" term="%22You%2C+Suya%22">You, Suya</searchLink><relatesTo>5</relatesTo> (AUTHOR)<i> suya.you.civ@army.mil</i><br /><searchLink fieldCode="AR" term="%22Soibelman%2C+Lucio%22">Soibelman, Lucio</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> soibelma@usc.edu</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Nov2024, Vol. 16 Issue 22, p4240. 27p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22AERIAL+photogrammetry%22">AERIAL photogrammetry</searchLink><br />*<searchLink fieldCode="DE" term="%22POINT+cloud%22">POINT cloud</searchLink><br />*<searchLink fieldCode="DE" term="%22ACQUISITION+of+data%22">ACQUISITION of data</searchLink><br />*<searchLink fieldCode="DE" term="%22RESEARCH+personnel%22">RESEARCH personnel</searchLink><br />*<searchLink fieldCode="DE" term="%22ANNOTATIONS%22">ANNOTATIONS</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and small teams. To this end, we present a novel synthetic 3D point cloud generation framework that can produce detailed outdoor aerial photogrammetric 3D datasets with accurate ground truth annotations without the labor-intensive and time-consuming data collection/annotation processes. Our pipeline procedurally generates synthetic environments, mirroring real-world data collection and 3D reconstruction processes. A key feature of our framework is its ability to replicate consistent quality, noise patterns, and diversity similar to real-world datasets. This is achieved by adopting UAV flight patterns that resemble those used in real-world data collection processes (e.g., the cross-hatch flight pattern) across various synthetic terrains that are procedurally generated, thereby ensuring data consistency akin to real-world scenarios. Moreover, the generated datasets are enriched with precise semantic and instance annotations, eliminating the need for manual labeling. Our approach has led to the development and release of the Semantic Terrain Points Labeling—Synthetic 3D (STPLS3D) benchmark, an extensive outdoor 3D dataset encompassing over 16 km 2 , featuring up to 19 semantic labels. We also collected, reconstructed, and annotated four real-world datasets for validation purposes. Extensive experiments on these datasets demonstrate our synthetic datasets' effectiveness, superior quality, and their value as a benchmark dataset for further point cloud research. [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 or posted to a listserv without the copyright holder's express written permission. 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://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=a9h&AN=181203471
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs16224240
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 27
        StartPage: 4240
    Subjects:
      – SubjectFull: AERIAL photogrammetry
        Type: general
      – SubjectFull: POINT cloud
        Type: general
      – SubjectFull: ACQUISITION of data
        Type: general
      – SubjectFull: RESEARCH personnel
        Type: general
      – SubjectFull: ANNOTATIONS
        Type: general
    Titles:
      – TitleFull: An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen, Meida
      – PersonEntity:
          Name:
            NameFull: Han, Kangle
      – PersonEntity:
          Name:
            NameFull: Yu, Zifan
      – PersonEntity:
          Name:
            NameFull: Feng, Andrew
      – PersonEntity:
          Name:
            NameFull: Hou, Yu
      – PersonEntity:
          Name:
            NameFull: You, Suya
      – PersonEntity:
          Name:
            NameFull: Soibelman, Lucio
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 11
              Text: Nov2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 16
            – Type: issue
              Value: 22
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1