Urban image classification: Per-pixel classifiers, subpixel analysis, object-based image analysis, and geospatial methods

Remote-sensing methods used to generate base maps to analyze the urban environment rely predominantly on digital sensor data from spaceborne platforms. This 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. The goal of this chapter is to review the four groups of classification 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. They are used for simple calculations of environmental indices (e.g., normalized difference vegetation 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 classification methods therefore aim to statistically quantify the mixture of surfaces to improve overall classification accuracy (Myint, 2006a). While within-pixel variations exist, there is also significant evidence that groups of nearby pixels have similar spectral information and therefore belong to the same classification category. Object-oriented methods have emerged that group pixels prior to classification based on spectral similarity and spatial proximity. Classification accuracy using object-based methods shows significant 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 classification process. The primary difference though is that geostatistical methods (e.g., spatial autocorrelation methods) are utilized during both the pre- and postclassification steps (Myint and Mesev, 2012).