Deep Learning Model for Form Recognition and Structural Member Classification of East Asian Traditional Buildings

摘要: The unique characteristics of traditional buildings can provide fresh insights for sustainable building development. In this study, a deep learning model and methodology were developed classifying by using artificial intelligence (AI)-based image analysis technology. was constructed based on expert knowledge East Asian buildings. Videos images from Korea, Japan, China used to determine types classify locate structural members. Two algorithms applied object recognition: region-based convolutional neural network (R-CNN) distinguish country you only look once (YOLO) recognise A cloud environment develop practical that handle various environments in real time.