检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:周俭[1] 叶振 俞文彬 宋俊锋[2] 李燕宁 Zhou Jian;Ye Zhen;Yu Wenbin;Song Junfeng;Li Yanning(College of Architecture and Urban Planning,Tongji University,Shanghai 200092;Engineering College of Lishui University,Lishui 323000;Shanghai Tongji Urban Planning and Design Institute Co.,Ltd,Shanghai 200092)
机构地区:[1]同济大学建筑与城市规划学院,上海200092 [2]丽水学院工学院,丽水323000 [3]上海同济城市规划设计研究院有限公司,上海200092
出 处:《建筑遗产》2020年第3期102-110,共9页Heritage Architecture
基 金:国家自然科学基金(51778430)。
摘 要:随着数字技术的快速发展,利用数据信息对历史建筑进行判定已成为可能。文章以数字影像为切入点,建构了一种基于历史建筑数字影像特征,借助智能检测模型,实现在复杂环境中识别历史建筑的方法。该方法通过无人机采集的正射影像,采用两阶段物体检测算法和深度神经网络模型,以具体实景为对象,经过反复实验获得了对江南水乡古镇进行历史建筑智能识别的初步模型。同时通过案例,进一步分析了该方法的适用性和下一步优化升级的方向。该项研究将有力地辅助专家和技术人员进行现场判定工作,包括对历史建筑资源的先期预调查、历史建筑保护状况的持续监测,以及为相关的评估工作提供依据。Because of the rapid development of digital technology, it is now possible to identify and analyse historic buildings using data and information science. Starting with digital images, this article applies intelligent detection techniques to construct a program for the identification of historic buildings in complex environments, based on their digital image features. A preliminary model for the intelligent recognition of historic architecture was produced by this program after repeated experiments on Jiangnan water towns. The model uses real scenes as the images and employs a two-phase object detection algorithm and a deep neural network model on orthophoto maps collected by unmanned aerial vehicles. The article analyses the applicability of the program and proposes directions for optimisation and updating in the future. This study will effectively facilitate on-site inspections conducted by experts and technicians to identify and analyse historic buildings. In addition, it will provide evidence for preliminary surveys of historic building resources, continuous monitoring of the buildings’ state of conservation, and relevant assessment work.
关 键 词:历史建筑 建筑特征 正射影像 数字图像检测模型 智能识别 空间定位 江南水乡古镇 震泽 同里
分 类 号:TU-87[艺术—艺术设计] TP75[建筑科学—建筑设计及理论]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.16.44.178