PROJECT TITLE :

Determining the Relationship Between Census Data and Spatial Features Derived From High-Resolution Imagery in Accra, Ghana

ABSTRACT:

Remotely sensed-based estimates of dwelling and population characteristics can provide timely and spatially explicit data for Urban Planning and development in rising cities. This exploratory analysis quantifies spatial options of built-up areas derived from high-resolution satellite imagery and directly relates them to census-derived variables in Accra, Ghana. Spatial options are image metrics that analyze pixel teams in order to describe the geometry, orientation, and patterns of objects in a picture. By using spatial features in an urban setting, town infrastructure variations, like roads and buildings, can be quantified and connected to census variables, like living standards and housing conditions. To take a look at the associations between spatial patterns and demographic variables, 5 spatial options (line support regions, PanTex, histograms of oriented gradients, local binary patterns, and Fourier transform) were quantified and extracted from the imagery, and then correlated to the census variables. Findings indicate each spatial options and spectral info (such as NDVI) correlate strongly with standards of living like population and housing density. Results from this study recommend that spatial features derived from satellite imagery can be used to assist map socioeconomic characteristics at intervals the town of Accra, Ghana, and that this technique may be transferable to different developing cities.