摘要
震损建筑的震害研究对于建筑的震后安全评估具有重要作用,然而目前仅基于二维震害图像的方法,难以满足对建筑整体震损状况认识的需求。提出了应用图像三维重建法对震损建筑进行实体建模,实现震损建筑的三维模型重建。首先围绕建筑拍摄一系列图像,然后依次应用由运动恢复结构方法进行稀疏重建、多视图立体视觉方法进行密集重建,经尺度变换后,再用泊松表面重建方法进行表面重建,最后通过纹理映射方法重建出真实感强的三维模型。试验分析表明,方法对建筑的重建误差仅为1.5%,能够较好地满足整体震害研究的需要。
The study of earthquake damaged structures is of great significance to the safety assessment of buildings after an earthquake. However, the current 2D image-based method has some limitations on the overall damaged sit- uation study of the structure. The paper uses image-based 3D reconstruction method to build 3D model of the real earthquake damaged structure. Firstly, a series of photos are taken around the structure, and then sparse point cloud reconstruction is conducted using the structure from motion method. Secondly, multi-view stereo method is processed to achieve the dense point cloud reconstruction. After scaling, surface reconstruction of the dense point cloud is going on with Poisson surface construction method. At last, texture mapping is used to obtain 3D model with reality. The test results show that the relative error of the proposed method is only 1.5 %, and it is applicable to the requirement of the overall damaged situation study of the structure.
出处
《世界地震工程》
CSCD
北大核心
2017年第2期113-118,共6页
World Earthquake Engineering
基金
国家自然科学基金创新群体项目(51421064)
关键词
图像三维重建
震损建筑
三维建模
多视图立体视觉
泊松表面重建
image-based 3 D reconstruction
earthquake damaged structure
3 D modeling
multi-view stereo
Poisson surface reconstruction