Affiliation:
1. Department of Civil, Environmental, Land, Construction and Chemistry (DICATECh), Polytechnic University of Bari, 70125 Bari, Italy
Abstract
Recent advancements in digital technologies and automated analysis techniques applied to Historic Built Environment (HBE) demonstrate significant advantages in efficiently collecting and interpreting data for building conservation activities. Integrating digital image processing through Artificial Intelligence approaches further streamlines data analysis for diagnostic assessments. In this context, this paper presents a scoping review based on Scopus and Web of Science databases, following the PRISMA protocol, focusing on applying Deep Learning (DL) architectures for image-based classification of decay phenomena in the HBE, aiming to explore potential implementations in decision support system. From the literature screening process, 29 selected articles were analyzed according to methods for identifying buildings’ surface deterioration, cracks, and post-disaster damage at a district scale, with a particular focus on the innovative DL architectures developed, the accuracy of results obtained, and the classification methods adopted to understand limitations and strengths. The results highlight current research trends and the potential of DL approaches for diagnostic purposes in the built heritage conservation field, evaluating methods and tools for data acquisition and real-time monitoring, and emphasizing the advantages of implementing the adopted techniques in interoperable environments for information sharing among stakeholders. Future challenges involve implementing DL models in mobile apps, using sensors and IoT systems for on-site defect detection and long-term monitoring, integrating multimodal data from non-destructive inspection techniques, and establishing direct connections between data, intervention strategies, timing, and costs, thereby improving heritage diagnosis and management practices.
Reference58 articles.
1. Automated defect detection and classification in ashlar masonry walls using machine learning;Valero;Autom. Constr.,2019
2. A Rapid pipeline for periodic inspection and maintenance of architectural surfaces;Galantucci;Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. ISPRS Arch.,2023
3. On Assisting and Automatizing the Semantic Segmentation of Masonry Walls;Pavoni;J. Comput. Cult. Herit.,2022
4. Llamas, J., Lerones, P.M., Medina, R., Zalama, E., and Gómez-García-Bermejo, J. (2017). Classification of architectural heritage images using deep learning techniques. Appl. Sci., 7.
5. Ceravolo, R., Invernizzi, S., Lenticchia, E., Matteini, I., Patrucco, G., and Spanò, A. (2023). Integrated 3D Mapping and Diagnosis for the Structural Assessment of Architectural Heritage: Morano’s Parabolic Arch. Sensors, 23.