Academic Journal
Building Change Detection Network Based on Multilevel Geometric Representation Optimization Using Frame Fields
| العنوان: | Building Change Detection Network Based on Multilevel Geometric Representation Optimization Using Frame Fields |
|---|---|
| المؤلفون: | Fachuan He, Hao Chen, Shuting Yang, Zhixiang Guo |
| المصدر: | Remote Sensing, Vol 16, Iss 22, p 4223 (2024) |
| بيانات النشر: | MDPI AG, 2024. |
| سنة النشر: | 2024 |
| المجموعة: | LCC:Science |
| مصطلحات موضوعية: | change detection, multi-scale aggregation, frame fields, geometric representation, remote sensing, Science |
| الوصف: | To address the challenges of accurately segmenting irregular building boundaries in complex urban environments faced by existing remote sensing change detection methods, this paper proposes a building change detection network based on multilevel geometric representation optimization using frame fields called BuildingCDNet. The proposed method employs a multi-scale feature aggregation encoder–decoder architecture, leveraging contextual information to capture the characteristics of buildings of varying sizes in the imagery. Cross-attention mechanisms are incorporated to enhance the feature correlations between the change pairs. Additionally, the frame field is introduced into the network to model the complex geometric structure of the building target. By learning the local orientation information of the building structure, the frame field can effectively capture the geometric features of complex building features. During the training process, a multi-task learning strategy is used to align the predicted frame field with the real building outline, while learning the overall segmentation, edge outline, and corner point features of the building. This improves the accuracy of the building polygon representation. Furthermore, a discriminative loss function is constructed through multi-task learning to optimize the polygonal structured information of the building targets. The proposed method achieves state-of-the-art results on two commonly used datasets. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2072-4292 |
| Relation: | https://www.mdpi.com/2072-4292/16/22/4223; https://doaj.org/toc/2072-4292 |
| DOI: | 10.3390/rs16224223 |
| URL الوصول: | https://doaj.org/article/603a45facd014cd2a95ef026c8f76919 |
| رقم الانضمام: | edsdoj.603a45facd014cd2a95ef026c8f76919 |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | ResultId |
1 |
|---|---|
| Header |
edsdoj Directory of Open Access Journals edsdoj.603a45facd014cd2a95ef026c8f76919 1013 3 Academic Journal academicJournal 1013.02990722656 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsdoj&AN=edsdoj.603a45facd014cd2a95ef026c8f76919&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => https://doaj.org/article/603a45facd014cd2a95ef026c8f76919 [Name] => EDS - DOAJ [Category] => fullText [Text] => View record in DOAJ [MouseOverText] => View record in DOAJ ) [1] => Array ( [Url] => https://resolver.ebscohost.com/openurl?custid=s6537998&groupid=main&authtype=ip,guest&sid=EBSCO:edsdoj&genre=article&issn=20724292&ISBN=&volume=16&issue=22&date=20241101&spage=4223&pages=4223-4223&title=Remote Sensing&atitle=Building%20Change%20Detection%20Network%20Based%20on%20Multilevel%20Geometric%20Representation%20Optimization%20Using%20Frame%20Fields&id=DOI:10.3390/rs16224223 [Name] => Full Text Finder (s6537998api) [Category] => fullText [Text] => Full Text Finder [Icon] => https://imageserver.ebscohost.com/branding/images/FTF.gif [MouseOverText] => Full Text Finder ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Building Change Detection Network Based on Multilevel Geometric Representation Optimization Using Frame Fields
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Fachuan+He%22">Fachuan He</searchLink><br /><searchLink fieldCode="AR" term="%22Hao+Chen%22">Hao Chen</searchLink><br /><searchLink fieldCode="AR" term="%22Shuting+Yang%22">Shuting Yang</searchLink><br /><searchLink fieldCode="AR" term="%22Zhixiang+Guo%22">Zhixiang Guo</searchLink> ) Array ( [Name] => TitleSource [Label] => Source [Group] => Src [Data] => Remote Sensing, Vol 16, Iss 22, p 4223 (2024) ) Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => MDPI AG, 2024. ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2024 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => LCC:Science ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22change+detection%22">change detection</searchLink><br /><searchLink fieldCode="DE" term="%22multi-scale+aggregation%22">multi-scale aggregation</searchLink><br /><searchLink fieldCode="DE" term="%22frame+fields%22">frame fields</searchLink><br /><searchLink fieldCode="DE" term="%22geometric+representation%22">geometric representation</searchLink><br /><searchLink fieldCode="DE" term="%22remote+sensing%22">remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Science%22">Science</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => To address the challenges of accurately segmenting irregular building boundaries in complex urban environments faced by existing remote sensing change detection methods, this paper proposes a building change detection network based on multilevel geometric representation optimization using frame fields called BuildingCDNet. The proposed method employs a multi-scale feature aggregation encoder–decoder architecture, leveraging contextual information to capture the characteristics of buildings of varying sizes in the imagery. Cross-attention mechanisms are incorporated to enhance the feature correlations between the change pairs. Additionally, the frame field is introduced into the network to model the complex geometric structure of the building target. By learning the local orientation information of the building structure, the frame field can effectively capture the geometric features of complex building features. During the training process, a multi-task learning strategy is used to align the predicted frame field with the real building outline, while learning the overall segmentation, edge outline, and corner point features of the building. This improves the accuracy of the building polygon representation. Furthermore, a discriminative loss function is constructed through multi-task learning to optimize the polygonal structured information of the building targets. The proposed method achieves state-of-the-art results on two commonly used datasets. ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => article ) Array ( [Name] => Format [Label] => File Description [Group] => SrcInfo [Data] => electronic resource ) Array ( [Name] => Language [Label] => Language [Group] => Lang [Data] => English ) Array ( [Name] => ISSN [Label] => ISSN [Group] => ISSN [Data] => 2072-4292 ) Array ( [Name] => NoteTitleSource [Label] => Relation [Group] => SrcInfo [Data] => https://www.mdpi.com/2072-4292/16/22/4223; https://doaj.org/toc/2072-4292 ) Array ( [Name] => DOI [Label] => DOI [Group] => ID [Data] => 10.3390/rs16224223 ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="https://doaj.org/article/603a45facd014cd2a95ef026c8f76919" linkWindow="_blank">https://doaj.org/article/603a45facd014cd2a95ef026c8f76919</link> ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsdoj.603a45facd014cd2a95ef026c8f76919 ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Identifiers] => Array
(
[0] => Array
(
[Type] => doi
[Value] => 10.3390/rs16224223
)
)
[Languages] => Array
(
[0] => Array
(
[Text] => English
)
)
[PhysicalDescription] => Array
(
[Pagination] => Array
(
[PageCount] => 1
[StartPage] => 4223
)
)
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => change detection
[Type] => general
)
[1] => Array
(
[SubjectFull] => multi-scale aggregation
[Type] => general
)
[2] => Array
(
[SubjectFull] => frame fields
[Type] => general
)
[3] => Array
(
[SubjectFull] => geometric representation
[Type] => general
)
[4] => Array
(
[SubjectFull] => remote sensing
[Type] => general
)
[5] => Array
(
[SubjectFull] => Science
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Building Change Detection Network Based on Multilevel Geometric Representation Optimization Using Frame Fields
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Fachuan He
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Hao Chen
)
)
)
[2] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Shuting Yang
)
)
)
[3] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Zhixiang Guo
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 01
[M] => 11
[Type] => published
[Y] => 2024
)
)
[Identifiers] => Array
(
[0] => Array
(
[Type] => issn-print
[Value] => 20724292
)
)
[Numbering] => Array
(
[0] => Array
(
[Type] => volume
[Value] => 16
)
[1] => Array
(
[Type] => issue
[Value] => 22
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Remote Sensing
[Type] => main
)
)
)
)
)
)
)
|
| IllustrationInfo |