一种机载点云数据局部漏洞自动修复方法

An automatic Inpainting Method for Airborne LiDAR Point Cloud Data Local Holes

受地形起伏与山体遮挡等因素影响,机载点云数据有时存在局部数据缺失现象。在山体遮挡严重的区域,点云数据局部漏洞严重影响高精度DEM数据的质量。针对机载点云数据中存在的局部漏洞,提出一种融合DEM的机载点云数据局部漏洞自动修复方法。首先,对原始点云数据进行滤波得到地面点云,提出一种多尺度模板滑动的漏洞区域检测算法识别点云数据中的局部漏洞区域;进而,针对点云局部漏洞,结合既有的DEM数据进行漏洞修补。该算法在最大化保持原始地貌形态特征的基础上,最小化插值点云数据与漏洞区域边界点云数据的几何位置偏差。最后,采用实际采集的机载激光点云数据进行实验分析。实验结果表明,漏洞修复后的点云数据高程中误差为0.353米,满足生产1:1000比例尺高精度DEM的需求。相比于修复前点云数据生成的DEM数据,数据质量了有了较大的提升,且修复后的点云数据保持了原始地形走势和地貌形态特征。

Topographic relief and mountain shelter may cause local data loss in Airborne LiDAR point cloud data. Point cloud data hole seriously affect the quality of high-precision DEM. For the data blanks in the airborne LiDAR point cloud data, an automatic inpainting method by fusing digital elevation model is proposed. Firstly, the original point cloud data is filtered to extract the ground points, and the region analysis algorithm based on multi-scale template sliding is used to detect the location of data blanks. Then combining the existing DEM data to deal with the local holes in the point cloud. This algorithm minimizes the geometric position deviation between interpolated point cloud data and point cloud data in the hole on the basis of maximizing the original morphological features. The experimental results show that the root mean square error of point cloud elevation after inpainting data blanks is 0.353 m, which meets requirement for 1:1000 DEM production, and the restored point cloud maintains the real topographic trend and morphological features.