基于LiDAR数据的流域水系网络提取方法研究

Watershed Channel Network Extraction from LiDAR Data

LiDAR技术能够提供高分辨率DEM数据,可用于准确提取流域水系网络信息。研究中针对LiDAR系统提供的高精度DEM数据中存在的噪声,提出采用各向异性扩散滤波算法进行噪声平滑,与常用的DEM滤波算法比较,该方法既能有效去除噪声,同时又能保留高梯度的地形信息。在DEM噪声去除的基础上,采用基于局部地形曲面几何分析的Peuker&Douglas算法初步提取水系网络原型,进一步利用改进的基于坡面流物理模拟分析的加权D8算法提取水系网络,构建了基于LiDAR数据水系网络提取的技术流程。通过鹤壁市某小流域的LiDAR数据水系网络提取试验证明了该方法准确提取水系网络的有效性。

Light detection and ranging （LiDAR） technique can provide terrain data with high resolution and high accuracy, and can be used for accurate channel network extraction. The proposed approach incorporates anisotropic diffusion for the prepro- cessing of the DEM data, both to remove noise and to enhance features that are critical to the channel network extraction. The anisotropic diffusion filtering achieves noise reduction while preserving the right localization compared with the commonly used DEM filter algorithm. Following this preprocessing, Peuker ^- Douglas algorithm based on the analysis of the local terrain sur- face geometry was preliminary used for the extraction of channel network prototype, and then weighted D8 was used for the flow accumulation area and channel network extraction. The proposed methodology, especially the accurate localization of the extracted channels, is demonstrated using LiDAR data of a little basin in Hebi.