Parsing architecture within plan drawings with application to medieval castles and fortresses

A. Willis, Yunfeng Sui, K. Galor
{"title":"Parsing architecture within plan drawings with application to medieval castles and fortresses","authors":"A. Willis, Yunfeng Sui, K. Galor","doi":"10.2312/VAST/VAST09/017-024","DOIUrl":null,"url":null,"abstract":"Plan drawings are graphical documents critical to the documentation of architectural features at historic sites. These drawings include important geometric information such as the location, shape, and size of architectural features, which, for decaying or collapsed structures, may be the only existing records of the intact structure. This paper discusses an algorithm that estimates the geometry and semantic interpretation of architectural structures from a plan drawing. The estimated values are used to automatically generate a 3D structure using the estimated semantic labels of structural elements in the plan drawing. We demonstrate the utility of this approach by parsing several plan drawings of medieval castles and fortresses and generating 3D reconstructions of these structures and detail typical circumstances that prevent the system from generating a valid reconstruction. Since the 3D model is derived from plan drawings where the architectural contour is well-defined, the approach automatically provides near-pixel level accuracy at all locations which is very difficult and time-consuming to guarantee when manually constructing 3D models from the same drawing. Hence, these automatically-produced models can provide unprecedented accuracy to the in-situ remains not feasible with conventional manual model-building techniques. While this article represents initial work on this topic with limited scope (castles/fortresses), we envision that subsequent enhancements to this method will be a valuable tool for efficiently generating accurate 3D models for many different historic structures.","PeriodicalId":168094,"journal":{"name":"IEEE Conference on Visual Analytics Science and Technology","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Conference on Visual Analytics Science and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2312/VAST/VAST09/017-024","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Plan drawings are graphical documents critical to the documentation of architectural features at historic sites. These drawings include important geometric information such as the location, shape, and size of architectural features, which, for decaying or collapsed structures, may be the only existing records of the intact structure. This paper discusses an algorithm that estimates the geometry and semantic interpretation of architectural structures from a plan drawing. The estimated values are used to automatically generate a 3D structure using the estimated semantic labels of structural elements in the plan drawing. We demonstrate the utility of this approach by parsing several plan drawings of medieval castles and fortresses and generating 3D reconstructions of these structures and detail typical circumstances that prevent the system from generating a valid reconstruction. Since the 3D model is derived from plan drawings where the architectural contour is well-defined, the approach automatically provides near-pixel level accuracy at all locations which is very difficult and time-consuming to guarantee when manually constructing 3D models from the same drawing. Hence, these automatically-produced models can provide unprecedented accuracy to the in-situ remains not feasible with conventional manual model-building techniques. While this article represents initial work on this topic with limited scope (castles/fortresses), we envision that subsequent enhancements to this method will be a valuable tool for efficiently generating accurate 3D models for many different historic structures.
解析平面图中的建筑,并应用于中世纪的城堡和堡垒
平面图是记录历史遗址建筑特征的关键图形文件。这些图纸包括重要的几何信息,如建筑特征的位置、形状和大小,对于腐朽或倒塌的结构,这些可能是完整结构的唯一现存记录。本文讨论了一种从平面图中估计建筑结构的几何和语义解释的算法。这些估计值被用于自动生成三维结构,并使用平面图中结构元素的估计语义标签。我们通过解析中世纪城堡和堡垒的几张平面图,并生成这些结构的3D重建,以及详细说明阻止系统生成有效重建的典型情况,来演示这种方法的实用性。由于3D模型来源于建筑轮廓明确的平面图纸,因此该方法在所有位置自动提供接近像素级的精度,这在从同一张图纸手动构建3D模型时是非常困难和耗时的。因此,这些自动生成的模型可以提供前所未有的精度,而传统的人工模型构建技术是无法实现的。虽然本文代表了该主题的初步工作,范围有限(城堡/堡垒),但我们设想,对该方法的后续增强将成为有效生成许多不同历史建筑的精确3D模型的宝贵工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信