An Integrated Method Using a Convolutional Autoencoder, Thresholding Techniques, and a Residual Network for Anomaly Detection on Heritage Roof Surfaces

• Published in: Buildings (Basel) Vol. 14; no. 9; p. 2828
• Main Authors: Zhang, Yongcheng, Kong, Liulin, Antwi-Afari, Maxwell Fordjour, Zhang, Qingzhi
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2024
• Subjects: Accuracy; Algorithms; Anomalies; Architecture; Artificial intelligence; Buildings; Case studies; Classification; Computer vision; Cracks; Cultural heritage; Damage detection; Damage prevention; Deep learning; detection and evaluation; Drone aircraft; Efficiency; heritage buildings; Historic buildings & sites; Historic preservation; Historical buildings; Insulation; Machine learning; Masonry; Methods; Neural networks; Protection and preservation; Remodeling, restoration, etc; Repair & maintenance; roof damage; Roofing; Roofs; Semantics; UAV; Unmanned aerial vehicles; Vision systems; Water damage; Germany

The roofs of heritage buildings are subject to long-term degradation, resulting in poor heat insulation, heat regulation, and water leakage prevention. Researchers have predominantly employed feature-based traditional machine learning methods or individual deep learning techniques for the detection...