Slum mapping- the relationship between geometry and urban poverty in Ghana - a remote sensing and geographical information systems approach
MITGLIED IM KOLLEG
seit
JProf. Dr. Meng Lu
Forschungsschwerpunkte:
Statistical Modelling
Spatio-temporal Data
Remote Sensing
Air Pollution and Geohealth
Betreutes Projekt:
Slum mapping- the relationship between geometry and urban poverty in Ghana - a remote sensing and geographical information systems approach
Prof. Dr.-Ing. Ansgar Brunn
Lehr- und Forschungsschwerpunkte:
- Photogrammetrie und Bildverarbeitung
- Fernerkundung
- Terrestrisches Laserscanning/Airborne Laserscanning
- Punktwolkenverarbeitung und -analyse
- 3D-Koordinatenmesstechnik in der Industrievermessung
- Web-Anwendungen und Geovisualisierung
- 3D-Modellierung
- Aus- und Weiterbildung
- Online-Lehre
Betreute Projekte:
- Pro Mobile: Efficient and precise optimal positioning of mobile mapping system
- Slum mapping- the relationship between geometry and urban poverty in Ghana - a remote sensing and geographical information systems approach
- Virtuelle 3D-Rekonstruktion von zerstörten russisch-orthodoxen Kirchen aus unvollständigen Punktwolken
- Change detection for indoor construction progress monitoring based on BIM, point clouds and uncertainties
Franz Okyere
Technische Hochschule Würzburg-Schweinfurt
Building extraction for slum areas or informal settlement is very important, given the complexity that exists within this special place within the urban area. Slums are unique in terms of the population density, spatial complexity, heterogeneity and even ontologies. It is worth looking at the existing works and their contribution to the detection and delineation of these informal settlements. The application of new knowledge that is scalable is desirable taking into consideration the variability of socio-economic data and relationships that may exist between them and the geography of slum areas. Slum building extraction in many studies have looked at underdeveloped countries or developing countries but is there a need for a closer look; slums cause severe societal problems or are important indicators of poverty or deprivation. In this proposed study, we will employ existing deep learning methods and investigate the possibility of selecting optimal statistical learning methods with one objective in mind - relate the presence of slum buildings in parts of the city of Accra, Ghana to deprivation. We will apply statistical learning specifically to very high-resolution (VHR) remote sensing imagery. We hope to effectively extract the outline of slum building outlines and by extension establish a relationship between geometry and/or morphology and urban poverty. Precisely, we hope to prove that the morphology of buildings may reveal the property of deprivation and be tested across other cities characterized by slums.
