基于地面激光雷达技术点云的北川县城震害建筑物提取研究  

Research on Building Extraction of Earthquake Damage of Ground Li DAR Point Cloud Based on Object-oriented

作　　者：李强[1,2] 焦其松[2] 张景发[2] 

机构地区：[1]中国地震局工程力学研究所,哈尔滨1500801 [2]中国地震局地壳应力研究所,北京100085

出　　处：《科学技术与工程》2016年第19期244-249,共6页Science Technology and Engineering

基　　金：国家自然科学基金项目(41374050)资助

摘　　要：北川县城在汶川地震后变成一片废墟。以北川县城扫描获取的地面激光雷达数据为实验数据,在介绍地面LiDAR点云基本特征、面向对象方法思路的基础上,将面向对象方法引入到地面LiDAR点云建筑物提取中,从而实现了震害建筑物的自动提取。按照LiDAR点云数据建筑物的属性进行特征插值分解,通过分析震害建筑物在不同特征上的表现,构建适合于LiDAR点云震害建筑物提取的特征规则集。基于地面LiDAR数据提取北川地震遗址震害建筑物信息。结果表明:震害建筑物提取总体精度达92.3%,Kappa系数为0.873,提取精度满足地震遥感应急评估的需求,为遥感震害评估增添新的可用数据源。The seismic disaster information extraction method based on object-oriented method has been widely used in high-resolution optical image,while the application in the Li DAR point cloud especially the ground Li DAR point cloud data is less.Based on the introduction of the basic features of the point cloud and the method of object oriented,the laser point cloud data are decomposed and interpolated according to different features,and generated with different band layers.Through different features analysis,seismic damage buildings are identified based on object oriented method using ground Li DAR data of Beichuan earthquake site.By building the set of features which is suitable for the building of LiDAR point cloud,damage distribution was extracted.Through the analysis of the results,the overall accuracy of building earthquake damage building is 92.3%,the Kappa coefficient is 0.873,which meets the needs of earthquake remote sensing emergency assessment and adds new data sources available for remote sensing earthquake damage assessment.

关 键 词：面向对象 地面激光雷达技术(LiDAR) 震害建筑物 北川县城 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]