| 摘要: |
| 在实际应用中,现有的三维重建算法无法有效地应用到建筑领域.以建筑行业的基本制图规范为指导,结合图形识别理解和人工智能技术,提出了一种基于图形理解的建筑结构三视图自动识别与重建方法.该方法以自动识别建筑构件的轮廓为基础,通过对符号、注释等语义信息的理解与综合以及对相邻实体间拓扑关系的分析,快捷、有效地完成对建筑物的整体重建.实验结果表明,在少量人机交互的基础上,该方法对实际的建筑图是有效的. |
| 关键词: 特征抽取 知识规则 理解 投影轮廓 三维重建 拉伸体 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| 3D Reconstruction Technology for Architectural Structure Based on Graphics Understanding |
|
HU Jia,YANG Ruo-yu,CAO Yang,CAI Shi-jie
|
| Abstract: |
| The existing 3D reconstruction methods cannot be effectively applied in architecture domain. A new method that is based on the architectural cartography criterion, techniques of AI and graphics recognition and understanding, is presented for automatic recognition and reconstruction of architectural structures by interpreting three-view drawings. In this method, automatic recognition of the architectural components?contours, integration of semantic information interpreted from symbols and notes etc., and analyzing topology relation of adjacent components are applied to reconstruct the whole building rapidly and effectually.Experimental results show that the method is efficient and accurate for automatic reconstruction of buildings composed of large number of components from their structure drawings with little user correction. |
| Key words: feature extraction knowledge rule understanding projective contour 3D reconstruction stretch object |
