摘要
为了完成地面激光点云数据的分类工作,不同于传统方法利用点云的几何特性和辐射信息,本文利用非量测相机获取影像数据实现点云的分类。首先,通过相机检校获取相机的参数,从而得到影像内方位元素;然后,将影像与点云进行配准,计算出影像的外方位元素;最后,对上述参数进行优化,实现二维影像与三维点云信息的融合,进而完成点云分类。实验表明该方案可实现地面激光点云数据的分类。
To complete the classification of terrestrial Li DAR point cloud data,this paper uses the image data to realize the classification process of point cloud,which is different from the traditional method using the geometric characteristics or radiation information of point cloud. First step,the camera parameters are obtained by camera calibration,and the inner azimuth elements in the image can be calculated. Then,the image and the point cloud are registered to calculate the external azimuth of the image. Finally,with the integration of two different type of data which can be realized with the above parameters taken into advantage,the classification can be completed. Experiments show that this scheme can realize the classification of terrestrial lidar point cloud data.
引文
[1]廖丽琼,罗德安.地面激光雷达的数据处理及其精度分析[J].测绘,2004,27(4):153-155.
[2]喻垚慎.基于点云数据的植物器官分割方法[D].南京:南京林业大学,2015.
[3]李文宁,张爱武,王书民,等.地面激光点云阶层式分类方法[J].计算机辅助设计与图形学学报,2015,27(8):1 555-1 561.
[4]韦江霞.面向快速建模的车载激光点云的城市典型地物分类方法研究[D].北京:首都师范大学,2014.
[5]陈源恺.地面固定式激光扫描点云中建筑物墙面信息的识别提取[J].测绘与空间地理信息,2015,38(11):158-160.
[6]程小龙,程效军,郭王,等.基于激光强度的建筑立面点云分类及信息提取[J].同济大学学报:自然科学版,2015,43(9):1 432-1 437.
[7]谭凯,程效军.基于强度数据的地面激光点云自适应非监督分类[J].激光与光电子学进展,2016(3):234-240.
[8]张毅,闫利.地面激光点云强度噪声的三维扩散滤波方法[J].测绘学报,2013,42(4):568-573.