摘要
为了提高构件吊装施工的安全性,探索了一种多方向阈值下的装配式建筑构件吊装施工场景三维重建方法。该方法利用三维激光扫描仪获取场景点云数据,采用最小曲率区域增长法进行场景分割,采用随机采样一致性算法进行图像精分割,得到数个不相交的平面点云区域集合。利用移动最小二乘法进行曲面拟合,建立施工场景三维参数优化模型;通过改进麻雀搜索算法求解模型,得到三维模型参数优化结果,实现装配式建筑构件吊装施工场景三维重建。实验结果表明,该方法能够有效地采集构件吊装施工场景点云数据,实现高精度的施工场景三维重建。
In order to improve the safety of component hoisting construction,this study explores a threedimensional reconstruction method for prefabricated building component hoisting construction scene under multi-directional threshold.This method uses a 3D laser scanner to obtain scene point cloud data,uses the minimum curvature region growth method for scene segmentation,and uses a random sampling consistency algorithm for image fine segmentation to obtain a set of several disjoint planar point cloud regions.Using the moving least squares method for surface fitting,a three-dimensional parameter optimization model for construction scenes is established.By improving the sparrow search algorithm to solve the model,the optimization results of 3D model parameters are obtained,and the iterative reconstruction of the construction scene of prefabricated building component hoisting is realized.The experimental results show that this method can effectively collect point cloud data from component lifting construction scenes and achieve high-precision 3D reconstruction of construction scenes.
作者
林国潮
凌礼贤
柴吉元
林荣顺
LIN Guochao;LING Lixian;CHAI Jiyuan;LIN Rongshun(China Construction Seventh Engineering Division Co.,LTD.,Zhengzhou 450000,China)
出处
《结构工程师》
2024年第3期172-178,共7页
Structural Engineers
关键词
多方向阈值
装配式建筑
施工场景
三维重建
multi-directional threshold
prefabricated construction
construction scene
three-dimensional reconstruction
