ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper EfficientNet을 이용한 안국동 별궁 지붕부 변위 예측
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
안정서, 이상윤
Issue Date
2023-06
Citation
대한전자공학회 학술 대회 (하계) 2023, pp.1046-1049
Publisher
대한전자공학회
Language
Korean
Type
Conference Paper
Abstract
Wooden cultural heritages can be deteriorated due to the aged materials or natural disasters such as earthquakes. If Deep Learning technology is used when such displacement occurs, it will be a great help to the conservation of cultural heritages. In this paper, we constructed data for each environment using CCTV images. Then, we confirmed whether it is possible to predict the sagging of the roof by experiments using EfficientNetB0 model. As a result of the experiment, it showed a high displacement prediction accuracy of 99% or more in all environments such as clear, overcast, cloud, snow, and rain.
KSP Keywords
CCTV images, Displacement prediction, Natural disaster, Prediction accuracy, deep learning(DL), learning technology