摘要
车载激光扫描测量方法较传统摄影测量方法具有更多优点,它能快速采集大面积、高精度的三维空间数据,具有广阔的应用前景。针对车载激光扫描数据的分类问题,提出了一种基于地物特征提取的点云数据分类方法,即采用主成分分析(PCA)方法,在提取多种街区地物点云数据几何特征和总结地物对象特征知识规则的基础上,根据选取的主特征设计一套阶层式的分类方法,并利用该方法对一套车载激光点云数据进行了分类试验。结果表明,该方法的分类效果良好,具有一定的实用性。
Compared with traditional survey technologies,mobile laser scanning has many advantages.Its characteristics make it possible to rapidly acquire large-area high-precision 3D spatial data for reconstruction of 3D（three-dimensional） model.This paper focuses on the classification of mobile laser scanning data.The authors present a multi-level classification method based on object feature extraction,namely extraction of main features by PCA（Principal Component Analysis）.This method was applied to blocks point data obtained by mobile laser scanning,and the results show that the proposed classification method is promising.
出处
《国土资源遥感》
CSCD
北大核心
2012年第1期17-21,共5页
Remote Sensing for Land & Resources
基金
国家高技术研究发展计划(863计划)项目(编号:2006AA12Z151)
国家自然科学基金项目(编号:40871211)共同资助
