基于视差影像的规则建筑物自动检测方法  

Automatic Detection Method of Regular Buildings Based on Parallax Image

作　　者：宫一鸣 曹辉[1] GONG Yiming;CAO Hui(School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China)

机构地区：[1]武汉大学遥感信息工程学院,湖北武汉430079

出　　处：《测绘地理信息》2022年第2期82-86,共5页Journal of Geomatics

基　　金：国家自然科学基金(4197010834)。

摘　　要：以遥感影像和视差影像这两类数据为基础,将遥感影像中的光谱特征与视差影像中的三维信息相结合,对规则城市建筑物进行自动检测。首先,在核线影像对上利用逐像素密集匹配算法,实现3D/2D数据融合,获取视差影像和视差点云,通过八叉树算法对视差点云进行体素化分割,构建属性特征和空间特征,建立案例的推理模型,对分类结果中各个规则建筑物进行独立分割并编号存储,提取规则建筑物位置信息。最后,采用中点算法提高运行效率,在遥感影像上采用区域增长法进行建筑物轮廓提取,并从个体化的规则建筑物位置信息中选取种子点集合,寻找轮廓线单元并计算轮廓线,提取出高完整性和高准确性的规则建筑物轮廓。Based on the data of remote sensing image and parallax image,this paper combines the spectral features of remote sensing image with the three-dimensional information of parallax image to detect the regular urban buildings automatically.First of all,applying per-pixel dense matching algorithm on the epipolar image pair to realize 3 D/2 D data fusion and obtain parallax images and parallax points cloud.Then voxel segmentation of the parallax points cloud is achieved through octree algorithm,and the properties and spatial characteristics are established.A case reasoning model is also established to divide individual regular building in the result of the classification,to numbere storage buildings and to extract building location information.Finally,the midpoint algorithm is used to improve the operating efficiency,and the area growth method is used to extract the building contour from the remote sensing image,and the seed point set is selected from the individual regular building position information,and the contour unit is found and the contour is calculated,so as to extract the regular building contour with high integrity and accuracy.

关 键 词：视差影像 视差点云 八叉树算法 规则建筑物轮廓提取 中点算法 

分 类 号：P237[天文地球—摄影测量与遥感]