Towards an automated monitoring of human settlements in South Africa using high resolution SPOT satellite imagery
- 1European Commission, Joint Research Centre (JRC), Institute for the Protection and Security of the Citizen (IPSC), Global Security and Crisis Management Unit, Ispra, Italy
- 2South African National Space Agency (SANSA), Earth Observation, Pretoria, South Africa
Keywords: Automated Image Information Extraction, Settlement Mapping, Urbanization Monitoring, Informal Settlements, Low Cost Housing, South Africa
Abstract. Urban areas in sub-Saharan Africa are growing at an unprecedented pace. Much of this growth is taking place in informal settlements. In South Africa more than 10% of the population live in urban informal settlements. South Africa has established a National Informal Settlement Development Programme (NUSP) to respond to these challenges. This programme is designed to support the National Department of Human Settlement (NDHS) in its implementation of the Upgrading Informal Settlements Programme (UISP) with the objective of eventually upgrading all informal settlements in the country. Currently, the NDHS does not have access to an updated national dataset captured at the same scale using source data that can be used to understand the status of informal settlements in the country.
This pilot study is developing a fully automated workflow for the wall-to-wall processing of SPOT-5 satellite imagery of South Africa. The workflow includes an automatic image information extraction based on multiscale textural and morphological image features extraction. The advanced image feature compression and optimization together with innovative learning and classification techniques allow a processing of the SPOT-5 images using the Landsat-based National Land Cover (NLC) of South Africa from the year 2000 as low-resolution thematic reference layers as. The workflow was tested on 42 SPOT scenes based on a stratified sampling. The derived building information was validated against a visually interpreted building point data set and produced an accuracy of 97 per cent. Given this positive result, is planned to process the most recent wall-to-wall coverage as well as the archived imagery available since 2007 in the near future.