Uncertainty analysis for image interpretations of urban slums. (November 2016)

• Record Type: Journal Article
• Authors: Kohli, Divyani; Stein, Alfred; Sliuzas, Richard
• Is Part Of: Computers, environment and urban systems. Volume 60(2016)
• Page Start: 37
• Page End: 49
• Publication Date: 2016-11
• Subjects: Slums -- Existential uncertainty -- Extensional uncertainty -- Informal settlements -- Remote sensing -- Random sets -- Object-oriented image analysis (OOA); City planning -- Data processing -- Periodicals; Regional planning -- Data processing -- Periodicals; 303.4834
• DOI: 10.1016/j.compenvurbsys.2016.07.010
• Languages: English
• ISSNs: 0198-9715

Abstract

Abstract: Image interpretations are used to identify slums in object-oriented image analysis (OOA). Such interpretations, however, contain uncertainties which may negatively impact the accuracy of classification. In this paper, we study the spatial uncertainties related to the delineations of slums as observed from very high resolution (VHR) images in the contexts of Ahmedabad (India), Nairobi (Kenya) and Cape Town (South Africa). Nineteen image interpretations and supplementary data were acquired for each context by means of semi-structured questionnaires. Slum areas agreed upon by different experts were determined. Uncertainty was modelled using random sets, and boundary variation was quantified using the bootstrapping method. Results show a highly significant difference between slum identification and delineation for the three contexts, whereas the level of experience in slum-related studies of experts is not significant. Factors of the built environment used by experts to distinguish slums from non-slum areas or leading to deviations in slum identification are discussed. We conclude that uncertainties in slum delineations from VHR images can be quantified successfully using modern spatial statistical methods. Highlights: Image interpretations of slums contain uncertainties which may negatively impact the accuracy of classification. We study deviations in slum identification and their delineations as observed from images of three cities. Existential and extensional uncertainties of slums are modelled in terms of random sets. Factors of the built environment that experts use to distinguish slums from non-slum areas are identified. Factors leading to deviations in slum identification and hence the reasons for uncertainties are explored.