3D Reconstruction for Stadium CAD Drawings Based on Graphic Element Arrangement Pattern Analysis

doi:10.16182/j.issn1004731x.joss.25-0835

Abstract

Abstract:

To address the issue of the time-consuming and labor-intensive manual conversion of two-dimensional CAD design drawings of buildings into three-dimensional models, and leveraging the characteristic that stadiums contain a large number of repetitively and regularly arranged objects, this study proposes a similar graphical element detection algorithm. This algorithm detects similarities between graphical elements by constructing their bounding boxes and calculating the L2-Norm distance, identifying all graphical elements of the same type within the CAD drawing. Furthermore, a transformation sequence detection algorithm is proposed. Based on the geometric transformation relationships between graphical elements, a geometric transformation space is defined. By performing cluster analysis within this transformation space, the transformation sequences among the graphical elements are discovered. The height information of the graphical elements is automatically calculated based on the analyzed arrangement patterns. Simulation and validation experiments demonstrate that the proposed method can rapidly achieve similar graphical element detection and arrangement pattern analysis, effectively accelerating the 3D modeling process for stadiums.

Key words: 3D modeling, similarity detection, arrangement analysis, AutoCAD, geometric transformation space

CLC Number:

TP391.9

Ma Shang, Zhang Mengyu, Zhang Lan, Yang Gang. 3D Reconstruction for Stadium CAD Drawings Based on Graphic Element Arrangement Pattern Analysis[J]. Journal of System Simulation, 2026, 38(1): 58-72.

Figures/Tables 21

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Fig. 13

Fig. 14

Fig. 15

Fig. 16

Fig. 17

Fig. 18

Table 1

Table 2

Table 3

References 20

[1]	张桓源. 基于BIM的室内空间结构模型提取与重建[D]. 南京: 南京师范大学, 2019.
	Zhang Huanyuan. Extraction and Reconstruction of Indoor Space Structure Model Based on BIM[D]. Nanjing: Nanjing Normal University, 2019.
[2]	李锐. DXF建筑工程图的读取、识别与三维重建[D]. 天津: 天津大学, 2016.
	Li Rui. Reading, Recognition and 3D Reconstruction of DXF Architectural Drawings[D]. Tianjin: Tianjin University, 2016.
[3]	许通. 建筑工程图的图形理解与三维重建算法研究[D]. 沈阳: 东北大学, 2012.
	Xu Tong. Research on Building Plans Interpretation and 3D Reconstruction[D]. Shenyang: Northeastern University, 2012.
[4]	万小飞. 基于施工图的建筑物三维建模数据抽取方法研究[D]. 南京: 南京师范大学, 2013.
	Wan Xiaofei. Data Extraction from the Construction Drawing for 3D Building Modeling[D]. Nanjing: Nanjing Normal University, 2013.
[5]	李晋芳, 施法中. 商品化CAD软件中基于二维视图的三维重建模块的设计与实现[J]. 计算机辅助设计与图形学学报, 2005, 17(4): 795-799.
	Li Jinfang, Shi Fazhong. Research and Development on 3D Reconstruction Based on 2D Engineering Drawing in CAD System[J]. Journal of Computer-aided Design & Computer Graphics, 2005, 17(4): 795-799.
[6]	薛梅. 一种基于形状文法的建筑物三维建模新方法[J]. 地理与地理信息科学, 2012, 28(6): 31-34.
	Xue Mei. A Shape Grammar Based Method for 3D Building Modeling[J]. Geography and Geo-Information Science, 2012, 28(6): 31-34.
[7]	Lewis R, Séquin Carlo. Generation of 3D Building Models from 2D Architectural Plans[J]. Computer Aided Design, 1998, 30(10): 765-779.
[8]	Belongie S, Malik J, Puzicha J. Shape Context: A New Descriptor for Shape Matching and Object Recognition[C]//Proceedings of the 14th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2000: 798-804.
[9]	谭建荣, 岳小莉, 陆国栋. 图形相似的基本原理、方法及其在结构模式识别中的应用[J]. 计算机学报, 2002, 25(9): 959-967.
	Tan Jianrong, Yue Xiaoli, Lu Guodong. Basic Principle, Method of Graphic Similarity and Its Application to Structure Pattern Recognition[J]. Chinese Journal of Computers, 2002, 25(9): 959-967.
[10]	丁克松, 岳建伟, 唐宏, 等. 矢量图形相似性度量方法研究进展[J]. 地理空间信息, 2020, 18(4): 53-56.
	Ding Kesong, Yue Jianwei, Tang Hong, et al. Research on Similarity Measurement Method of Vector Graphic[J]. Geospatial Information, 2020, 18(4): 53-56.
[11]	徐剑, 张皓, 徐航, 等. 一种基于Faster RCNN的电网图元识别方法[J]. 计算机与现代化, 2021(12): 53-57.
	Xu Jian, Zhang Hao, Xu Hang, et al. Detecting Electrical Circuit Elements Based on Faster RCNN[J]. Computer and Modernization, 2021(12): 53-57.
[12]	江志. 基于图形相似性和零件相关性的模具零件库检索技术的研究及应用[D]. 杭州: 浙江大学, 2020.
	Jiang Zhi. Research and Application of Mould Parts Library Retrieval Technology Based on Graphic Similarity and Part Relevance[D]. Hangzhou: Zhejiang University, 2020.
[13]	Mitra N J, Guibas L J, Pauly Mark. Partial and Approximate Symmetry Detection for 3D Geometry[J]. ACM Transactions on Graphics, 2006, 25(3): 560-568.
[14]	Št'ava O, Beneš B, Měch R, et al. Inverse Procedural Modeling by Automatic Generation of L-systems[J]. Computer Graphics Forum, 2010, 29(2): 665-674.
[15]	彭钰蘅. 基于学习的自然图像对称性目标检测[D]. 大连: 大连理工大学, 2018.
	Peng Yuheng. Learning-based Symmetry Detection from Real World Images[D]. Dalian: Dalian University of Technology, 2018.
[16]	Guo Jianwei, Jiang Haiyong, Benes B, et al. Inverse Procedural Modeling of Branching Structures by Inferring L-systems[J]. ACM Transactions on Graphics, 2020, 39(5): 155.
[17]	Pauly Mark, Mitra Niloy J, Wallner Johannes, et al. Discovering Structural Regularity in 3D Geometry[J]. ACM Transactions on Graphics, 2008, 27(3): 43.
[18]	Liangliang Nan, Jiang Caigui, Ghanem Bernard, et al. Template Assembly for Detailed Urban Reconstruction[J]. Computer Graphics Forum, 2015, 34(2): 217-228.
[19]	Wang Jinglu, Lu Yonghua, Liu Jingbo, et al. A Robust Three-stage Approach to Large-scale Urban Scene Recognition[J]. Science China Information Sciences, 2017, 60(10): 103101.
[20]	黄艳华. 基于二维工程图的三维实体重构[D]. 乌鲁木齐: 新疆大学, 2003.
	Huang Yanhua. 3D Solid Reconstruction Based on 2D Orthographic Drawings[D]. Urumqi: Xinjiang University, 2003.

场景	图元种类	复合图元总数	P	R	排列覆盖率/%
场景1(图14)	5	768	1	1	100
场景2(图15)	2	162	1	1	100
场景3(图16)	8	1 203	1	1	100
场景4(图17)	15	3 520	1	0.99(漏检4个)	100

场景	方法	P	R	时间/s
场景1 (图14)	本文方法	1	1	8.77
场景1 (图14)	形状上下文	0.97	0.98	95.4
场景3 (图16)	本文方法	1	1	12.03
场景3 (图16)	形状上下文	0.98	0.99	142.8

场景	图元种类	复合图元总数	检测出的变换序列数	相似检测用时/s	排列规律分析用时/s
场景1(图14)	5	768	58	8.77	1.6
场景2(图15)	2	162	22	0.29	0.13
场景3(图16)	8	1 203	71	12.03	2.56
场景4(图17)	15	3 520	105	18.21	3.42