Detecting surface defects of heritage buildings based on deep learning

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Detecting surface defects of heritage buildings based on deep learning
Συγγραφείς: Fu Xiaoli, Angkawisittpan Niwat
Πηγή: Journal of Intelligent Systems, Vol 33, Iss 1, Pp 163-9 (2024)
Στοιχεία εκδότη: De Gruyter, 2024.
Έτος έκδοσης: 2024
Συλλογή: LCC:Science
LCC:Electronic computers. Computer science
Θεματικοί όροι: deep learning, flipping, historical places, images, sustainability, thermography, transformer-based segmentation, Science, Electronic computers. Computer science, QA75.5-76.95
Περιγραφή: The present study examined the usage of deep convolutional neural networks (DCNNs) for the classification, segmentation, and detection of the images of surface defects in heritage buildings. A survey was conducted on the building surface defects in Gulang Island (a UNESCO World Cultural Heritage Site), which were subsequently classified into six categories according to relevant standards. A Swin Transformer- and YOLOv5-based model was built for the automated detection of surface defects. Experimental results suggested that the proposed model was 99.2% accurate at classifying plant penetration and achieved a mean intersection-over-union (mIoU) of over 92% in relation to moss, cracking, alkalization, staining, and deterioration, outperforming CNN-based semantic segmentation networks such as FCN, PSPNet, and DeepLabv3plus. The Swin Transformer-based approach for the segmentation of building surface defect images achieved the highest accuracy regardless of the evaluation metric (with an mIoU of 90.96% and an mAcc of 95.78%), when contrasted to mainstream DCNNs such as SegFormer, PSPNet, and DANet.
Τύπος εγγράφου: article
Περιγραφή αρχείου: electronic resource
Γλώσσα: English
ISSN: 2191-026X
Relation: https://doaj.org/toc/2191-026X
DOI: 10.1515/jisys-2023-0048
Σύνδεσμος πρόσβασης: https://doaj.org/article/0268a861afb545a0b2dc790a6ef80ecf
Αριθμός Καταχώρησης: edsdoj.0268a861afb545a0b2dc790a6ef80ecf
Βάση Δεδομένων: Directory of Open Access Journals
Περιγραφή
ISSN:2191026X
DOI:10.1515/jisys-2023-0048