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：2008
卷号：XXXVII Part B7
页码：1599-1606
出版社：Copernicus Publications
摘要：This paper presents improvements of an existing building damage detection and classification method based on airborne laser scanning data especially identifying damage types in affected areas. Furthermore, it deals with the question if the integration of spectral information like laser intensity data, multi-spectral scanner data or high resolution digital orthophotos can contribute to a further enhancement of the classification results. For this purpose, the characteristics of these three different data types for undamaged and damaged buildings are analysed and different texture parameters are tested in order to select features which can be included into the classification process. The results obtained for different input data and textures are compared and analy
