Decay detection in historic buildings through image-based deep learning
Nowadays, built heritage condition assessment is realized through on-site or photo-aided visual inspections, reporting pathologies manually on drawings, photographs, notes. The knowledge of the state of conservation goes through subjective and time or cost consuming procedures. This is even relevant...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitat Politècnica de València
2023-04-01
|
| Series: | Vitruvio: International Journal of Architectural Technology and Sustainability |
| Subjects: | |
| Online Access: | http://polipapers.upv.es/index.php/vitruvio/article/view/18662 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846096940835536896 |
|---|---|
| author | Silvana Bruno Rosella Alessia Galantucci Antonella Musicco |
| author_facet | Silvana Bruno Rosella Alessia Galantucci Antonella Musicco |
| author_sort | Silvana Bruno |
| collection | DOAJ |
| description | Nowadays, built heritage condition assessment is realized through on-site or photo-aided visual inspections, reporting pathologies manually on drawings, photographs, notes. The knowledge of the state of conservation goes through subjective and time or cost consuming procedures. This is even relevant for a historic building characterized by geometrical and morphological complexity and huge extension, or at risk of collapse. In this context, advancements in the field of Computer Vision and Artificial Intelligence provide an opportunity to address these criticalities. The proposed methodology is based on a Mask R-CNN model, for the detection of decay morphologies on built heritages, and, particularly on historic buildings. The experimentation has been carried out and validated on a highly heterogeneous dataset of images of historic buildings, representative of the regional Architectural Heritage, such as: castles, monasteries, noble buildings, rural buildings. The outcomes highlighted the significance of this remote, non-invasive inspection technique, in support of the technicians in the preliminary knowledge of the building state of conservation, and, most of all, in the decay mapping of some particular classes of alterations (moist area, biological colonization). |
| format | Article |
| id | doaj-art-48a8cac8473e4866a98180e2414512f3 |
| institution | Kabale University |
| issn | 2444-9091 |
| language | English |
| publishDate | 2023-04-01 |
| publisher | Universitat Politècnica de València |
| record_format | Article |
| series | Vitruvio: International Journal of Architectural Technology and Sustainability |
| spelling | doaj-art-48a8cac8473e4866a98180e2414512f32025-01-02T05:48:39ZengUniversitat Politècnica de ValènciaVitruvio: International Journal of Architectural Technology and Sustainability2444-90912023-04-01861710.4995/vitruvioijats.2023.1866217852Decay detection in historic buildings through image-based deep learningSilvana Bruno0https://orcid.org/0000-0002-7633-9989Rosella Alessia Galantucci1https://orcid.org/0000-0002-2742-1492Antonella Musicco2https://orcid.org/0000-0001-9130-8753Polytechnic University of BariPolytechnic University of BariPolytechnic University of BariNowadays, built heritage condition assessment is realized through on-site or photo-aided visual inspections, reporting pathologies manually on drawings, photographs, notes. The knowledge of the state of conservation goes through subjective and time or cost consuming procedures. This is even relevant for a historic building characterized by geometrical and morphological complexity and huge extension, or at risk of collapse. In this context, advancements in the field of Computer Vision and Artificial Intelligence provide an opportunity to address these criticalities. The proposed methodology is based on a Mask R-CNN model, for the detection of decay morphologies on built heritages, and, particularly on historic buildings. The experimentation has been carried out and validated on a highly heterogeneous dataset of images of historic buildings, representative of the regional Architectural Heritage, such as: castles, monasteries, noble buildings, rural buildings. The outcomes highlighted the significance of this remote, non-invasive inspection technique, in support of the technicians in the preliminary knowledge of the building state of conservation, and, most of all, in the decay mapping of some particular classes of alterations (moist area, biological colonization).http://polipapers.upv.es/index.php/vitruvio/article/view/18662built heritagehistoric buildingsdecay detectiondeep learningmask r-cnn |
| spellingShingle | Silvana Bruno Rosella Alessia Galantucci Antonella Musicco Decay detection in historic buildings through image-based deep learning Vitruvio: International Journal of Architectural Technology and Sustainability built heritage historic buildings decay detection deep learning mask r-cnn |
| title | Decay detection in historic buildings through image-based deep learning |
| title_full | Decay detection in historic buildings through image-based deep learning |
| title_fullStr | Decay detection in historic buildings through image-based deep learning |
| title_full_unstemmed | Decay detection in historic buildings through image-based deep learning |
| title_short | Decay detection in historic buildings through image-based deep learning |
| title_sort | decay detection in historic buildings through image based deep learning |
| topic | built heritage historic buildings decay detection deep learning mask r-cnn |
| url | http://polipapers.upv.es/index.php/vitruvio/article/view/18662 |
| work_keys_str_mv | AT silvanabruno decaydetectioninhistoricbuildingsthroughimagebaseddeeplearning AT rosellaalessiagalantucci decaydetectioninhistoricbuildingsthroughimagebaseddeeplearning AT antonellamusicco decaydetectioninhistoricbuildingsthroughimagebaseddeeplearning |