摘要
针对传统人工采集和判定的方法受到诸多因素的影响,导致效率低下且评定结果的波动性的问题.探索了一种基于深度学习方法进行民居建筑的多项特征指标的量化评定.采用CNN神经网络结构对民居建筑进行特征的自动分类.结果表明,EfficientNet是性能最优秀的CNN架构.采用这样的研究途径有助于更为全面地了解民居建筑的演化趋势和相关保护政策的制定.
The traditional manual collection and judgment methods are affected by many factors,resulting in slow efficiency and fluctuation of evaluation results.This study explored a quantitative evaluation of multiple characteristic indexes of residential buildings based on deep learning method.CNN neural network structure was used to automatically classify the characteristics of residential buildings.The results showed that EfficientNet was the best CNN architecture.Adopting such a research approach will help to have a more comprehensive understanding of the evolution trend of residential buildings and the formulation of relevant protection policies.
作者
张春明
谭人殊
宋晨明
赵党书
ZHANG Chunming;TAN Renshu;SONG Chengming;ZHAO Dangshu(Yunnan Arts University,Kunming 650101,China;Xi an Jiaotong University,Xian 710049,China;Kunming University of Science and Technology,Kunming 650031,China)
出处
《西南师范大学学报（自然科学版）》
CAS
2023年第6期1-11,共11页
Journal of Southwest China Normal University(Natural Science Edition)
基金
云南艺术学院科研基金项目(2021KYJJ05)
教育部人文社会科学研究青年基金项目(21YJC760070)。
关键词
民居建筑
量化评测
卷积神经网络
风貌特征
residential buildings
quantitative evaluation
convolution neural network
style characteristics
