Remote sensing provides a cost-effective alternative to the ground-based survey for land use/cover mapping and change analysis.
Time-series of remotely sensed data allow examining the temporal dynamics of urban attributes or processes. And postclassification comparison methods produce “frometo” change information
between land classes that can help capture the nature of land changes. Given the wide availability and longtime archive,Landsat data have been widely used in land use/cover classification and change detection at regional scales. However, land use/cover classification in urban areas using medium resolution remotely sensed data can be challenging due to the presence of heterogenous urban features and the spectral similarity between different urban land cover types.
Sub-pixel analysis, such as spectral mixture analysis (SMA), models each pixel as the percent cover of basic land cover materials that can help preserve the heterogeneity of urban areas.
Over the past years, a sizable number of research has demonstrated the usefulness of sub-pixel analysis in dealing with the “mixed” pixel problem associated with using medium resolution remotely sensed data in urban land mapping. For change analysis, the sub-pixel analysis has mostly been applied to the detection of land cover fraction change, such as percent
imperviousness change,vegetation fraction change. Some research has shown the potential of incorporating sub-pixel fraction in thematic land use/cover classification. However, using the spectral response from remote sensing alone may not be sufficient to differentiate specific land types in urban areas, which can be valuable for various applications
such as driving force analyses, urban morphological studies, and land use modeling. Previous studies have identified the importance of incorporating ancillary data in image classification.