摘要
针对震害损毁房屋评估的实际需求,研究利用灾前矢量辅助进行震害房屋多种三维损毁特征的提取,进一步基于三维损毁特征进行震害房屋评估分类。灾前矢量的主要作用是分割出独立的单体房屋,同时为震害房屋的损毁提取提供顶面轮廓和面积等先验信息,避免以往点云分割的不确定性,提高损毁评估的准确度。利用提取出的多种损毁特征基于SVM的分类方法对震害房屋进行评估分类,验证了针对震害房屋三维损毁特征损毁评估的适应性和可靠性。
According to the actual requirement of seismic damaged buildings assessment, this paper used pre-disaster vector as an auxiliary data to produce the 3 D damage assessment of seismic damaged buildings by the point cloud from multi-view remote sensing images. The pre-disaster vector was mainly used for segmentation of single building, which could avoid the uncertainty of the previous point cloud segmentation. At the same time, it could also provide prior information, such as the outline and area of roof, which could improve the accuracy and efficiency of the assessment. On the basis of this, this paper extracted a variety of 3D features from seismic damaged buildings, and used those features to make a classification of seismic damaged buildings. The experimental results verified the adaptability and reliability of the method.
出处
《地理空间信息》
2017年第10期63-66,69,共5页
Geospatial Information
关键词
三维特征
灾前矢量
震害房屋
损毁评估
3D feature
pre-disaster vector
seismic damaged building
damage assessment
作者简介
李强，主要研究方向为智慧城市、北斗导航、时空信息服务等方面。;通讯作者
