基于3D激光投影的室内场景三维重建模型

3D Reconstruction Model of Indoor Scene Based on 3D Laser Projection

当前已有的3D激光投影技术在应用中忽略了对投影坐标的规范处理,无法实现曲面上的全角度激光扫描,导致激光点云数据融合性差,场景重建误差较大。为此,构建基于3D激光投影应用优化的室内场景三维重建模型。利用点云曲面特征值和拆分单元格构建体素化栅格采样算法,对激光点云数据去噪。利用世界坐标系规范化3D激光投影坐标,建立3D激光投影模型,并获取最优投影旋转角度。利用标定板和旋转角度拼接融合点云数据,实现重建室内场景三维模型。试验结果表明,所提方法在3D激光投影应用下室内场景重建效果理想,且激光点云数据误差较小,峰值信噪比较高,可较好地融合点云的各项性能。

In the current application of 3 D laser projection technology,the standard processing of projection coordinates is ignored and the full-angle laser scanning on the surface cannot be realized,resulting in poor fusion of laser point cloud data and large scene reconstruction error.Therefore,a 3 D reconstruction model of interior scene based on 3 D laser projection application optimization is constructed.A voxelized raster sampling algorithm is constructed based on point cloud surface eigenvalues and split cells to denoise laser point cloud data.Using the world coordinate system to normalize the 3 D laser projection coordinates,the 3 D laser projection model is established and the optimal projection rotation angle is obtained.The 3 D model of indoor scene is reconstructed by using calibration plate and rotation angle stitching fusion point cloud data.The experimental results show that the proposed method has a good indoor scene reconstruction effect under the application of 3 D laser projection,the error of laser point cloud data is small,the peak signal-to-noise ratio is high,and the performance of point cloud can be better fused.