中文摘要：

针对较复杂场景的点云自动分类方法中目标类别为地面、植被、建筑物、电力塔、电力线等的问题，在对数据进行粗差剔除的基础上，首先归纳、定义了点云分类所需的关键特征，并利用JointBoost实现地物分类；同时，考虑到点云数据量大，其分类速度较慢，通过结合地物空间上的相互关联关系，提出一种序列化的点云分类及特征降维方法。该方法在保证分类精度的前提下，使分类所需特征维数降低，缩短了分类所需时间。激光扫描点云数据分类试验证明了该分类方法的有效性。

英文摘要：

This study focuses on complex scenes and presents an approach to automatically classify point clouds in building, ground, vegetation, power-line, and tower classes. Based on gross error elimination, many key features of points cloud are introduced for classification using the JointBoost classifier. Due to the data of points cloud is ＂big data＊＇ and its classification rate is slow, a method of serialized points cloud classification is proposed using spatial contextual information between objects for features reduction. The experiments prove that the classification method can be effectively used for points cloud classification on complex scenes.