This is because many small objects are concentrated
in a small area when dealing with an urban space, and they
become more and more visible as the spatial resolution gets finer and
finer. This situation potentially leads to lower accuracy in urban image
classification. This may not be the case for other environments,
especially when dealing with other natural land covers and land uses
(rangeland, evergreen forests, broad leaved forests, pine forests,
mangroves, wetland, desert landscape, and agriculture).
Despite the above limitation, many urban spatial analysts and
modelers must take approaches for urban decision-making that
increasingly require urban land-use and land-cover maps generated
from very high resolution data. For example, a remote sensing
application to estimate population based on the number of dwellings
of different housing types in an urban environment (single-family,
multi-family), usually requires a pixel size ranging from about 0.25 to