Automatic Detection of Linear Thermal Bridges from Infrared Thermal Images Using Neural Network

Detecting thermal bridges in building envelopes should be a priority to improve the performance of buildings. Recently, thermographic surveys are being used detect bridges. However, conventional methods detecting from images rely on subjective judgment audits. Research has been conducted automatically problems caused by such judgment, but most these studies still early stage. Therefore, this study proposes linear bridge detection method based image processing and machine learning. The proposed includes anomaly area clustering, feature extraction, an artificial-neural-network-based detection. was validated actual As result, average precision, recall, F-score were 89.29%, 87.29, 87.63%, respectively.