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：2005
卷号：XXXVI-8/W27
出版社：Copernicus Publications
摘要：The automatic classification of urban materials from airborne and spatial acquisitions remains difficult today because of two main reasons: the spatial resolution of the images and the need for pre-processing algorithms to extract ground surface intrinsic properties. This work examines the feasibility of using 8 spectral information distributed in the visible and the near-infrared spectral regions (0.4 - 1 μm), acquired at a 20 cm spatial resolution, for recognizing the urban materials. The motivation for this study is the development of very high spatial resolution sensors which has introduced a promising capability for the study of urban areas. In this study, an experiment campaign took place in Toulouse. The airborne measurements were carried out using 8 cameras associated with 8 narrow filters (30 nm). Ground spectral measurements of Toulouse's urban materials were performed within the configuration of the airborne acquisitions. These measurements allow us to determine and quantify three types of reflectance spatial variability. The results show that urban materials have low reflectances with no significant spectral features and are then difficult to discriminate. To determine which material classes could be discriminate over the 8 spectral bands of the airborne acquisitions, a statistical analysis was performed on the ground measurements. This analysis highlights that 5 material classes could be discriminated from good quality measurements
