Share Email Print

Proceedings Paper

Advanced automated classification strategy for settlement area detection
Author(s): Ulrich Michel
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper is based on the research project "State-wide acquisition of settlement area in North Rhine-Westphalia, Germany focusing on residential and industrial areas". The integrated GIS/Remote Sensing environment facilitated the combined processing of ground truth measurement, scanned topographic maps and multisensor imagery from SPOT 5, Landsat 7 and Aster satellites. In selected urban and suburban areas, methods for multisensor data fusion were developed and tested. The goal of this project is an accurate and current information layer about the urban and suburban state for North Rhine-Westphalia. The methodology is based mainly on an adapted texture and object oriented hierarchical classification approach: based on SPOT 5 imagery segments in different scales (levels) were created. These segments are the basis for a hierarchical based classification procedure. For each segment we calculated not only a texture but also the shape parameter. In addition we used the normalized vegetation index (NDVI) calculated from the multispectral satellite images to distinguish between vegetation and non vegetation areas. The GIS environment is of prime importance because it offers adapted tools for data modelling and data combination. For the verification of our results we developed a GPS based mobile application running on a windows mobile pocket pc. It allows a direct communication with our GIS environment which is necessary to import or export our datasets.

Paper Details

Date Published: 28 October 2005
PDF: 8 pages
Proc. SPIE 5983, Remote Sensing for Environmental Monitoring, GIS Applications, and Geology V, 598308 (28 October 2005); doi: 10.1117/12.627034
Show Author Affiliations
Ulrich Michel, Univ. of Osnabrück (Germany)

Published in SPIE Proceedings Vol. 5983:
Remote Sensing for Environmental Monitoring, GIS Applications, and Geology V
Manfred Ehlers; Ulrich Michel, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?