LiDAR Filtering of Urban Areas With Region Growing Based on Moving-Window Weighted Iterative Least-Squares Fitting

Terrain surfaces can be relatively accurately obtained from light detection and ranging data using least-squares interpolation. However, the accuracy of the extraction results is low in regions with relatively large terrain undulations, and large buildings and vegetation with large areas and relatively low permeabilities cannot be eliminated. In this letter, we propose a region growing filtering method based on moving-window weighted iterative least-squares fitting. This technique uses the moving-window weighted iterative least squares fitting method to select the seed point. After multiple iterations, we take the difference between the original data and the fitting results and retain the points with differences within the threshold range. We use these points as the seed points and adopt the region growing method to reconstruct the complete point set of ground points. We use five test data sets provided by the International Society for Photogrammetry and Remote Sensing and data from the Iowa River Basin in the United States for experiments. The results indicate that the proposed method can effectively remove buildings and vegetation, but it still requires further improvement for the removal of bridges and objects at the edge.