文章基本信息

标题：Extraction of 3D Feature from LiDAR Data Fused with Aerial Images Using Improved Mean-shift Algorithm
本地全文：下载
作者：Liu Chun ; Zhang Yunling
期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2009
卷号：XXXVIII-7/C4
页码：20-24
出版社：Copernicus Publications
摘要：An innovative approach is proposed for the extraction of the complex urban three dimensional feature efficiently and accurately. In this method, firstly, both the LiDAR data and the aerial images are respectively pre-processed and matched using an affine transformation technique. Then, an improved mean-shift algorithm is employed to classify the LiDAR data fused with reflected intensity and spectrum attribute into groups by kinds of feature, such as buildings, vegetation, water etc. The spectral information are extracted from aerial-image to extend the attribute of the LiDAR data. The classification accuracy is evaluated by a confusion matrix. Finally, the 3D model of interested region is quickly constructed based on the classified points and the aerial-image in software SketchUp. During the experiment, the key issue is how to control the results of classification through parameters setting
关键词：LiDAR; Feature Extraction; Mean-Shift