Academic Journal
Semantic Segmentation Method for Surface Gaps of Brick‐Built Cultural Relic Buildings Based on the Improved U‐Net Network.
| Τίτλος: | Semantic Segmentation Method for Surface Gaps of Brick‐Built Cultural Relic Buildings Based on the Improved U‐Net Network. |
|---|---|
| Συγγραφείς: | Zhang, Yage, Yu, Yongbo, Zhang, Chunhang, Yue, Jianwei, Yang, Qiong, Guan, Yijie, Chen, Zeyu, Zhao, Shihang, Chen, Zhihua, Yuen, Ka-Veng |
| Πηγή: | Structural Control & Health Monitoring; 5/31/2026, Vol. 2026, p1-20, 20p |
| Θεματικοί όροι: | Image segmentation, Convolutional neural networks, Surface cracks, Historic buildings, Structural health monitoring, Mathematical convolutions, Feature extraction, Pattern recognition systems |
| Περίληψη: | To achieve pixel‐level semantic segmentation of surface cracks in cultural relic buildings, depth‐separable convolution (DSC), neighboring information fusion (NIF) module, dual‐domain coordination module (DCM), and feature refinement module (FRM) are introduced into the U‐Net model. Construct an improved U‐Net model (MAU‐Net) with multiscale perception optimization suitable for crack identification in cultural relic buildings. DSC reconstructs the decoder to reduce the computational load of the model. NIF effectively fuses the feature information of adjacent layers. DCM integrates the characteristics of the Convolutional Block Attention Module (CBAM) and the Channel Squeeze and Excitation (CSE). FRM further optimizes the extracted features to improve the accuracy and robustness of segmentation. Experiments were conducted on the self‐made dataset of gaps on the Ming and Qing Dynasty city walls in Kaifeng. MAU‐Net was compared against several state‐of‐the‐art models, including U‐Net, DcsNet, SegFormer, CrackformerII, DECS, DTrc, TransMUNet, and DeepLabv3+. The results show that the Pr, Re, F1, and MIoU of the MAU‐Net model are 87.36%, 77.98%, 82.41%, and 72.53%, respectively, which are higher than those of other models. The comparison of the performance of the detection tasks, the classification confusion matrix, and the heat map generated by the Grad‐CAM method shows that the MAU‐Net model has the best detection effect. The research results provide a high‐precision and lightweight automated method for the health monitoring of brick cultural relic buildings. [ABSTRACT FROM AUTHOR] |
| Copyright of Structural Control & Health Monitoring is the property of Wiley-Blackwell 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.) | |
| Βάση Δεδομένων: | Complementary Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=15452255&ISBN=&volume=2026&issue=&date=20260531&spage=1&pages=1-20&title=Structural Control & Health Monitoring&atitle=Semantic%20Segmentation%20Method%20for%20Surface%20Gaps%20of%20Brick%E2%80%90Built%20Cultural%20Relic%20Buildings%20Based%20on%20the%20Improved%20U%E2%80%90Net%20Network.&aulast=Zhang%2C%20Yage&id=DOI:10.1155/stc/3717731 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 194754641 RelevancyScore: 1061 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1060.76342773438 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Semantic Segmentation Method for Surface Gaps of Brick‐Built Cultural Relic Buildings Based on the Improved U‐Net Network. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Yage%22">Zhang, Yage</searchLink><br /><searchLink fieldCode="AR" term="%22Yu%2C+Yongbo%22">Yu, Yongbo</searchLink><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Chunhang%22">Zhang, Chunhang</searchLink><br /><searchLink fieldCode="AR" term="%22Yue%2C+Jianwei%22">Yue, Jianwei</searchLink><br /><searchLink fieldCode="AR" term="%22Yang%2C+Qiong%22">Yang, Qiong</searchLink><br /><searchLink fieldCode="AR" term="%22Guan%2C+Yijie%22">Guan, Yijie</searchLink><br /><searchLink fieldCode="AR" term="%22Chen%2C+Zeyu%22">Chen, Zeyu</searchLink><br /><searchLink fieldCode="AR" term="%22Zhao%2C+Shihang%22">Zhao, Shihang</searchLink><br /><searchLink fieldCode="AR" term="%22Chen%2C+Zhihua%22">Chen, Zhihua</searchLink><br /><searchLink fieldCode="AR" term="%22Yuen%2C+Ka-Veng%22">Yuen, Ka-Veng</searchLink> – Name: TitleSource Label: Source Group: Src Data: Structural Control & Health Monitoring; 5/31/2026, Vol. 2026, p1-20, 20p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Image+segmentation%22">Image segmentation</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Surface+cracks%22">Surface cracks</searchLink><br /><searchLink fieldCode="DE" term="%22Historic+buildings%22">Historic buildings</searchLink><br /><searchLink fieldCode="DE" term="%22Structural+health+monitoring%22">Structural health monitoring</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+convolutions%22">Mathematical convolutions</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Pattern+recognition+systems%22">Pattern recognition systems</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: To achieve pixel‐level semantic segmentation of surface cracks in cultural relic buildings, depth‐separable convolution (DSC), neighboring information fusion (NIF) module, dual‐domain coordination module (DCM), and feature refinement module (FRM) are introduced into the U‐Net model. Construct an improved U‐Net model (MAU‐Net) with multiscale perception optimization suitable for crack identification in cultural relic buildings. DSC reconstructs the decoder to reduce the computational load of the model. NIF effectively fuses the feature information of adjacent layers. DCM integrates the characteristics of the Convolutional Block Attention Module (CBAM) and the Channel Squeeze and Excitation (CSE). FRM further optimizes the extracted features to improve the accuracy and robustness of segmentation. Experiments were conducted on the self‐made dataset of gaps on the Ming and Qing Dynasty city walls in Kaifeng. MAU‐Net was compared against several state‐of‐the‐art models, including U‐Net, DcsNet, SegFormer, CrackformerII, DECS, DTrc, TransMUNet, and DeepLabv3+. The results show that the Pr, Re, F1, and MIoU of the MAU‐Net model are 87.36%, 77.98%, 82.41%, and 72.53%, respectively, which are higher than those of other models. The comparison of the performance of the detection tasks, the classification confusion matrix, and the heat map generated by the Grad‐CAM method shows that the MAU‐Net model has the best detection effect. The research results provide a high‐precision and lightweight automated method for the health monitoring of brick cultural relic buildings. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Structural Control & Health Monitoring is the property of Wiley-Blackwell 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=edb&AN=194754641 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1155/stc/3717731 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 20 StartPage: 1 Subjects: – SubjectFull: Image segmentation Type: general – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Surface cracks Type: general – SubjectFull: Historic buildings Type: general – SubjectFull: Structural health monitoring Type: general – SubjectFull: Mathematical convolutions Type: general – SubjectFull: Feature extraction Type: general – SubjectFull: Pattern recognition systems Type: general Titles: – TitleFull: Semantic Segmentation Method for Surface Gaps of Brick‐Built Cultural Relic Buildings Based on the Improved U‐Net Network. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhang, Yage – PersonEntity: Name: NameFull: Yu, Yongbo – PersonEntity: Name: NameFull: Zhang, Chunhang – PersonEntity: Name: NameFull: Yue, Jianwei – PersonEntity: Name: NameFull: Yang, Qiong – PersonEntity: Name: NameFull: Guan, Yijie – PersonEntity: Name: NameFull: Chen, Zeyu – PersonEntity: Name: NameFull: Zhao, Shihang – PersonEntity: Name: NameFull: Chen, Zhihua – PersonEntity: Name: NameFull: Yuen, Ka-Veng IsPartOfRelationships: – BibEntity: Dates: – D: 31 M: 05 Text: 5/31/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 15452255 Numbering: – Type: volume Value: 2026 Titles: – TitleFull: Structural Control & Health Monitoring Type: main |
| ResultId | 1 |