茂密植被区域LiDAR点云数据滤波方法研究  

The Airborne LiDAR Point Clouds Data Filtering Method of the Dense Forest Area

作　　者：杨应[1,2] 苏国中[2] 周梅[2] 

机构地区：[1]中国科学院研究生院,北京100049 [2]中国科学院光电研究院,北京100190

出　　处：《遥感信息》2010年第6期9-13,共5页Remote Sensing Information

基　　金：国家自然科学基金支持项目编号:40871202

摘　　要：点云数据的滤波和分类是激光雷达数据应用处理重要环节,是当前研究的热点问题。本文针对茂密植被区域点云数据的特点,提出了以移动窗口和坡度算法为基础的改进的点云数据滤波算法。试验结果表明,改进的滤波算法对地形变化复杂、植被郁闭度较高覆盖、地面激光脚点比少的点云数据有良好的效果。The filtering of airborne LiDAR point clouds data is an important step for application and it is also a hot issue.This paper proposes a new filtering method of dense vegetation area point clouds data with the moving window and gradient technology,and uses the trend surface and elevation interpolation to improve the accuracy of classification.The experimental results show that it is effective in the complex and dense forest terrain.It has obvious advantages in the dense forest area airborne LiDAR point clouds classification.

关 键 词：LIDAR 趋势面 滤波 插值 坡度 移动窗口 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]