A comparison of automated settlement detection for an integrated topographic map information system update in South Africa

Luncedo Dalithemba Ngcofe, Thabisile Rambau, Mark McLachlan, Fezekile Hantibi, Nale Mudau


Complete, accurate and up-to-date topographic data is of considerable importance as it is widely required by different government agencies, non-governmental organisations, the private sector as well as the general public for urban mapping, rural development and environmental management, to mention but a few applications.

Efficient automatic / semi-automatic methods for detecting settlements as change area indicators are required in order to achieve a sustainable up-to-date topographic database. This leads to the aim of this study which seeks to investigate the automated / semi-automated settlement detection from remote sensing imagery to enhance the topographic database update in the KwaZulu-Natal Province, South Africa.

This study focuses on two methods for automated / semi-automated settlement detection using 2012 SPOT 5 imagery. The first method focused on geographic object based image analysis (GEOBIA) technique through the eCognition software application, while the second method, is based on the South African global human settlement layer (SA_GHSL).

The GEOBIA provided 78% accuracy for settlement detection while SA_GHSL obtained 62.6% accuracy. The results from the automated / semi-automated methods provide the topographic update analyst to be drawn to more areas of new settlement development at an enhanced efficient rate. However a review on the enhancement of processing parameters applied on the automated / semi-automated methods is a research gap to be investigated to improve the accuracy of these methods.

Full Text: PDF