Discriminating Building Density Using Maximium Likelihood Classification Algorithms Of The Federal Capital City Abuja, Nigeria
This research used supervised classification (maximium likelihood classification-MLC) across varying spatial resolutions to classify building density types at three different test sites to find the optimum data source for the identification of high, medium and low density. Multi-band data with spatial resolutions of 15m, spectral band 8 (0.52-0.92 micrometers) and spectral resolutions of 30m, spectral band 1, 2 & 3 (0.45-0.52, 0.52-0.60 and 0.63-0.69 micromemter) from Landsat-7 ETM+ were used.
... he result indicates that building density has a positive relationship with urban and rural morphology; it plays an important role in the shaping of the physical environment. The studies identified settlements with the same building density, but in different urban forms ranging from high rise, medium-rise and parallel rows of building. The medium and low building density creates small areas of open land that are suitable enough for other functions. Nevertheless, without efficient land-use planning, these spaces can run the risk of being not properly managed. The proportion of open space area resulted from the high density form (Alexander, E.R, 1993), although it is larger than that of the medium and low-rise combined. However, unlike the former, the open space is enclosed and clearly defined, thus encourages full use of space. Comparative rating analysis used indicates that predictive accuracies has a positive effect, and shows improvement of 37.96% of high density, 33.58% medium density and low density 28.47%. Results also provided an opportunity to examine-valuable information of building density in terms of level of densities identification.