Image Processing Reference
In-Depth Information
Chapter 8
Classification of Urban Areas: Inferring Land
Use from the Interpretation of Land Cover
Victor Mesev
Ancillary data are vital for successful image classification of urban areas. This
chapter explores the role of ancillary data (information from beyond remote sensing)
for improving the contextual interpretation of satellite sensor imagery during
spectral-based and spatial-based classification. In addition, careful consideration is
given to the crucial distinctions between urban land cover and urban land use, and
how the inherent heterogeneous structure of urban morphologies is statistically
represented between hard and soft classifications.
Learning Objectives
Upon completion of this chapter, you should be able to:
Distinguish between land use and land cover
Explain how between hard and soft classification
Speculate on the role of ancillary data for spectral-based and
spatial-based classification
8.1
Introduction
We live in a multi-faceted world where our cities are composed of a complex assem-
blage of both tangible substances and communicable interaction. In order to avoid
sensory overload the human brain is designed to focus on objects in a systematic
order while at the same time filtering out excess noise. Similar principles apply to
the classification of digital remotely sensed data where, instead of the brain, a com-
puter algorithm is employed to make sense of pixels by identifying intrinsic spectral
V. Mesev (
*
)
Department of Geography, Florida State University, Tallahassee, FL 32306-2190, USA
e-mail: vmesev@fsu.edu
