Mapping Informal Settlements with a GUS Land Use Legend

Informal settlements are gaining interest in the remote sensing community, due to the fact that they are human settlements with large extensions, experiencing rapid changes and mixed land uses, which make them very difficult to be automatically extracted from remotely sensed imagery. However, the availability of high resolution optical and (in the near future) SAR data may improve the mapping and monitoring requirements of administrations and NGOs. We propose rapid mapping techniques based on spectral and spatial information at different scales, depending on phenomena to be monitored. Results are shown using SPOT and Quickbird data over two towns in Sudan. The goal of this work is the application of sensors and techniques usually employed for the analysis of more structured cities to the extraction of informal settlements. We evaluate the properties of SPOT and Quickbird images in order to establish advantages and limits of these two sensors in land- cover and land-use mapping and to propose ad hoc processing techniques. Dataset at our disposal is a panchromatic SPOT5 image (5m resolution) and a pan-sharpened Quickbird one (61cm resolution, but for simplicity we regard it as 1m) of the city of Nyala, Sudan, acquired in 2003. In order to evaluate sensors' performances, from the complete scene we extracted two areas: the first one is purely residential, the second one, instead, includes both residential and pseudo-industrial buildings.