ABSTRACT
ETM+ Enhanced Ÿematic Mapper Plus Geary’s C A spatial autocorrelation index GEOBIA Geographic Object-Based Image Analysis GeoEye High-resolution satellite operated by GeoEye company GIS Geographic information system or science GLCM Gray-level co-occurrence matrix ICAMS Image characterization and modeling system IKONOS High-resolution satellite operated by GeoEye LiDAR Light Detection and Ranging MESMA Multiple endmember spectral mixture analysis MIR Mid-infrared portion of the electromagnetic spectrum Moran’s I A spatial autocorrelation index MSS Multispectral scanner NIR Near-infrared portion of the electromagnetic
spectrum NDVI Normalized di§erence vegetation index OBIA Object-based image analysis OLI Operational Land Imager Pan Panchromatic
QuickBird High-resolution satellite operated by DigitalGlobe TIR Ÿermal infrared portion of the electromagnetic
spectrum USGS United States Geological Survey V-I-S Vegetation, impervious, and soil Vis Visible portion of the electromagnetic spectrum
Remote-sensing methods used to generate base maps to analyze the urban environment rely predominantly on digital sensor data from spaceborne platforms. Ÿis is due in part from new sources of high-spatial-resolution data covering the globe, a variety of multispectral and multitemporal sources, sophisticated statistical and geospatial methods, and compatibility with geographic information system or science (GIS) data sources and methods. Ÿe goal of this chapter is to review the four groups of classi¦cation methods for digital sensor data from spaceborne platforms; per-pixel, subpixel, object-based (spatial-based), and geospatial methods. Per-pixel methods are widely used methods that classify pixels into distinct categories based solely on the spectral and ancillary information within that pixel. Ÿey are used for simple calculations of environmental indices (e.g., normalized di§erence vegetation
Acronyms and De¦nitions .................................................................................................................219 10.1 Introduction .............................................................................................................................219 10.2 Remote-Sensing Methods for Urban Classi¦cation and Interpretation ........................ 220
index [NDVI]) to sophisticated expert systems to assign urban land covers (Stefanov et al., 2001). Researchers recognize, however, that even with the smallest pixel size, the spectral information within a pixel is really a combination of multiple urban surfaces. Subpixel classi¦cation methods therefore aim to statistically quantify the mixture of surfaces to improve overall classi¦cation accuracy (Myint, 2006a). While within-pixel variations exist, there is also signi¦cant evidence that groups of nearby pixels have similar spectral information and therefore belong to the same classi¦cation category. Object-oriented methods have emerged that group pixels prior to classi¦cation based on spectral similarity and spatial proximity. Classi¦cation accuracy using object-based methods shows signi¦cant success and promise for numerous urban applications (Myint et al., 2011). Like the object-oriented methods that recognize the importance of spatial proximity, geospatial methods for urban mapping also utilize neighboring pixels in the classi¦cation process. Ÿe primary di§erence though is that geostatistical methods (e.g., spatial autocorrelation methods) are utilized during both the pre-and postclassi¦cation steps (Myint and Mesev, 2012).
