机载激光点云与摄影测量点云非监督建筑物变化检测  

An Unsupervised Method for Change Detection between Airborne Laser Scanning and Photogrammetric Data

作　　者：张振超[1] 张永生[1] 戴晨光[1] 李凯[1] 季虹良 ZHANG Zhenchao;ZHANG Yongsheng;DAI Chenguang;LI Kai;JI Hongliang(Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]信息工程大学,河南郑州450001

出　　处：《测绘科学技术学报》2019年第5期523-530,共8页Journal of Geomatics Science and Technology

基　　金：高分辨率对地观测系统重大专项(GFZX04032201-1-1);地理信息工程国家重点实验室开放研究基金项目(SKLGIE2017-M-3-6)。

摘　　要：机载激光扫描和航空摄影测量两种技术获取的点云属性差异大,变化检测易受噪声和数据误差影响。为此设计了一种非监督的建筑物变化检测方法。首先利用基于坡度信息的渐进三角网加密和基于表面生长的点云分割方法,从激光点云中提取出地面、屋顶和植被3类要素;其次以激光扫描数据为基准检测建筑物拆除和加高两类变化;并对剩下的区域以密集匹配点云为基准探测出新建的建筑物;最后对检测的变化结果进行形态学滤波。实验证明,该方法能有效克服两种点云的差异和密集匹配噪声的影响,不仅能获得锐利的建筑物变化轮廓,而且能得到建筑物增高或拆除的类别标签。The point clouds acquired by airborne laser scanning and photogrammetry show heterogeneous properties. Change detection between them is sensitive to data inaccuracy and noise. Therefore, an unsupervised method is proposed to detect building changes. Firstly, terrain, roofs and vegetation are extracted from laser points based on Progressive TIN Densification and surface-based segmentation. Secondly, demolished and heightened building changes are detected from laser segments. Then newly-built buildings are detected from the dense matching data. Finally, the change detection masks are post-processed by morphological operation. The experimental results show that the proposed method is robust to data property differences and noise, in which building changes with sharp boundaries and heightened or demolished labels are obtained.

关 键 词：机载激光扫描 摄影测量 变化检测 点云分割 

分 类 号：P237[天文地球—摄影测量与遥感]