Publication Date:
2022-01-12
Description:
Abstract
Description:
A typical situation in many developing countries is sparse data availability. Thus, many issues of applied research need to be tackled in spite of poor data disposability. We exemplify these issues in the coastal area of Benin in Western Africa by a time series using a grey scale aerial image (1995), QuickBird data (2002), and a colour aerial image (2007, scale 1:20000). Coastal regions are in general areas of high attraction worldwide. Due to migration and population growth, the coastal zone of Benin, like in other developing countries, encounters extreme land use pressure, causing conflicts of interest and fast changes. Especially settlement structures show high dynamics. In order to study these, dwellings need to be detected. The multitude of appearances of dwellings makes process analysis based on remotely sensed data a challenging – yet interesting – task. This paper shows how to analyse settlement processes in developing countries with heterogeneous remote sensing data sets, combining remote sensing with pattern recognition and GIS. At first, building detection was accomplished by manual digitization. In the next step, we made an initial attempt to develop automated methods for detecting dwellings. Both approaches for building detection were then followed by GIS-based process analysis. Finally, a comparison of both detection approaches based on quality assessments is presented and a thorough evaluation of the usability of automation is given.
Description:
SeriesInformation
Description:
Proceedings on the Workshop of Remote Sensing Methods for Change Detection and Process Modelling, 18-19 November 2010, University of Cologne, Germany, Kölner Geographische Arbeiten, 92, pp. 131-142
Keywords:
Other
;
None
;
Change Detection
;
Remote Sensing
;
Remote Sensing Methods
Type:
Text
,
Book Section
Format:
1601 Kilobytes
Format:
12 Pages
Format:
PDF
Permalink