R.V. Sliuzas

An ontology of slums for image - based classification

Abstract Information about rapidly changing slum areas may support the development of appropriate interventions by concerned authorities. Often, however, traditional data collection methods lack information on the spatial distribution of slum-dwellers. Remote sensing based methods could be used for a rapid inventory of the location and physical composition of slums. (Semi-)automatic detection of slums in image data is challenging, owing to the high variability in appearance and definitions across different contexts. This paper develops an ontological framework to conceptualize slums using input from 50 domain-experts covering 16 different countries. This generic slum ontology (GSO) comprises concepts identified at three levels that refer to the morphology of the built environment: the environs level, the settlement level and the object level. It serves as a comprehensive basis for image-based classification of slums, in particular, using object-oriented image analysis (OOA) techniques. This is demonstrated by with an example of local adaptation of GSO and OOA parameterization for a study area in Kisumu, Kenya. At the object level, building and road characteristics are major components of the ontology. At the settlement level, texture measures can be potentially used to represent the contrast between planned and unplanned settlements. At the environs level, factors which extend beyond the site itself are important indicators, e.g. hazards due to floods plains and marshy conditions. The GSO provides a comprehensive framework that includes all potentially relevant indicators that can be used for image-based slum identification. These characteristics may be different for other study areas, but show the applicability of the developed framework.

Understanding heterogeneity in metropolitan India : the added value of remote sensing data for analyzing sub - standard residential areas

Abstract Analyzing the heterogeneity in metropolitan areas of India utilizing remote sensing data can help to identify more precise patterns of sub-standard residential areas. Earlier work analyzing inequalities in Indian cities employed a constructed index of multiple deprivations (IMDs) utilizing data from the Census of India 2001 ( http://censusindia.gov.in ). While that index, described in an earlier paper, provided a first approach to identify heterogeneity at the citywide scale, it neither provided information on spatial variations within the geographical boundaries of the Census database, nor about physical characteristics, such as green spaces and the variation in housing density and quality. In this article, we analyze whether different types of sub-standard residential areas can be identified through remote sensing data, combined, where relevant, with ground-truthing and local knowledge. The specific questions address: (1) the extent to which types of residential sub-standard areas can be drawn from remote sensing data, based on patterns of green space, structure of layout, density of built-up areas, size of buildings and other site characteristics; (2) the spatial diversity of these residential types for selected electoral wards; and (3) the correlation between different types of sub-standard residential areas and the results of the index of multiple deprivations utilized at electoral ward level found previously. The results of a limited number of test wards in Delhi showed that it was possible to extract different residential types matching existing settlement categories using the physical indicators structure of layout, built-up density, building size and other site characteristics. However, the indicator ‘amount of green spaces’ was not useful to identify informal areas. The analysis of heterogeneity showed that wards with higher IMD scores displayed more or less the full range of residential types, implying that visual image interpretation is able to zoom in on clusters of deprivation of varying size. Finally, the visual interpretation of the diversity of residential types matched the results of the IMD analysis quite well, although the limited number of test wards would need to be expanded to strengthen this statement. Visual image analysis strengthens the robustness of the IMD, and in addition, gives a better idea of the degree of heterogeneity in deprivations within a ward.

Evaluating the compatibility of multi - functional and intensive urban land uses

This research is aimed at developing a model for assessing land use compatibility in densely built-up urban areas. In this process, a new model was developed through the combination of a suite of existing methods and tools: geographical information system, Delphi methods and spatial decision support tools: namely multi-criteria evaluation analysis, analytical hierarchy process and ordered weighted average method. The developed model has the potential to calculate land use compatibility in both horizontal and vertical directions. Furthermore, the compatibility between the use of each floor in a building and its neighboring land uses can be evaluated. The method was tested in a built-up urban area located in Tehran, the capital city of Iran. The results show that the model is robust in clarifying different levels of physical compatibility between neighboring land uses. This paper describes the various steps and processes of developing the proposed land use compatibility evaluation model (CEM).

Slums from Space: 15 Years of Slum Mapping Using Remote Sensing

The body of scientific literature on slum mapping employing remote sensing methods has increased since the availability of more very-high-resolution (VHR) sensors. This improves the ability to produce information for pro-poor policy development and to build methods capable of supporting systematic global slum monitoring required for international policy development such as the Sustainable Development Goals. This review provides an overview of slum mapping-related remote sensing publications over the period of 2000–2015 regarding four dimensions: contextual factors, physical slum characteristics, data and requirements, and slum extraction methods. The review has shown the following results. First, our contextual knowledge on the diversity of slums across the globe is limited, and slum dynamics are not well captured. Second, a more systematic exploration of physical slum characteristics is required for the development of robust image-based proxies. Third, although the latest commercial sensor technologies provide image data of less than 0.5 m spatial resolution, thereby improving object recognition in slums, the complex and diverse morphology of slums makes extraction through standard methods difficult. Fourth, successful approaches show diversity in terms of extracted information levels (area or object based), implemented indicator sets (single or large sets) and methods employed (e.g., object-based image analysis (OBIA) or machine learning). In the context of a global slum inventory, texture-based methods show good robustness across cities and imagery. Machine-learning algorithms have the highest reported accuracies and allow working with large indicator sets in a computationally efficient manner, while the upscaling of pixel-level information requires further research. For local slum mapping, OBIA approaches show good capabilities of extracting both area- and object-based information. Ultimately, establishing a more systematic relationship between higher-level image elements and slum characteristics is essential to train algorithms able to analyze variations in slum morphologies to facilitate global slum monitoring.

Transferability of object - oriented image analysis methods for slum identification

Updated spatial information on the dynamics of slums can be helpful to measure and evaluate progress of policies. Earlier studies have shown that semi-automatic detection of slums using remote sensing can be challenging considering the large variability in definition and appearance. In this study, we explored the potential of an object-oriented image analysis (OOA) method to detect slums, using very high resolution (VHR) imagery. This method integrated expert knowledge in the form of a local slum ontology. A set of image-based parameters was identified that was used for differentiating slums from non-slum areas in an OOA environment. The method was implemented on three subsets of the city of Ahmedabad, India. Results show that textural features such as entropy and contrast derived from a grey level co-occurrence matrix (GLCM) and the size of image segments are stable parameters for classification of built-up areas and the identification of slums. Relation with classified slum objects, in terms of enclosed by slums and relative border with slums was used to refine classification. The analysis on three different subsets showed final accuracies ranging from 47% to 68%. We conclude that our method produces useful results as it allows including location specific adaptation, whereas generically applicable rulesets for slums are still to be developed.

Extraction of Slum Areas From VHR Imagery Using GLCM Variance

Many cities in the global South are facing the emergence and growth of highly dynamic slum areas, but often lack detailed information on these developments. Available statistical data are commonly aggregated to large, heterogeneous administrative units that are geographically meaningless for informing effective pro-poor policies. General base information neither allows spatially disaggregated analysis of deprived areas nor monitoring of rapidly changing settlement dynamics, which characterize slums. This paper explores the utility of the gray-level co-occurrence matrix (GLCM) variance to distinguish between slums and formal built-up (formal) areas in very high spatial and spectral resolution satellite imagery such as WorldView-2, OrbView, Quickbird, and Resourcesat. Three geographically different cities are selected for this investigation: Mumbai and Ahmedabad, India and Kigali, Rwanda. The exploration of the utility and transferability of the GLCM shows that the variance of the GLCM combined with the normalized difference vegetation index (NDVI) is able to separate slums and formal areas. The overall accuracy achieved is 84% in Kigali, 87% in Mumbai, and 88% in Ahmedabad. Furthermore, combining spectral information with the GLCM variance within a random forest classifier results in a pixel-based classification accuracy of 90%. The final slum map, aggregated to homogenous urban patches (HUPs), shows an accuracy of 88%-95% for slum locations depending on the scale parameter.

The development of a morphological unplanned settlement index using very-high-resolution (VHR) imagery

Spatial metrics combined with spectral information extracted from very-high-resolution (VHR) imagery allow quantification of the general spatial characteristics of urban areas, as well as specific morphological features (i.e., density, size, and pattern) of unplanned settlements. Such morphological features are visible in VHR imagery, but they are challenging to quantify. Still, quantification of the morphological differences between planned and unplanned areas is an important step towards automatic extraction of unplanned areas from VHR imagery. In this work, we discuss how image segmentation assists in the extraction of homogenous urban patches (HUPs), and use spatial metrics to quantify the morphological differences between planned and unplanned HUPs. A set of spatial metrics meaningful to describe morphological features of unplanned areas is selected and combined into an unplanned settlement index (USI) using a multi-criteria evaluation approach. Two case study areas are used to test the USI, i.e., Dar es Salaam, Tanzania, and New Delhi, India. The ability of the developed USI to extract unplanned areas is confirmed via visual comparison with existing land use data, and a quantitative accuracy assessment shows that areas of high USI coincide well with unplanned areas in the reference data. The quantitative accuracy assessment presents an accuracy of greater than 70% for five selected test areas in both cities.

The land-use diversity in urban villages in Shenzhen

Chinas dynamic urbanisation since 1978 has led to the proliferation of so-called ‘urban villages’ in many cities. Their development, via a self-help approach by indigenous villagers, delivers low-cost housing and various other social and economic activities. Consequently, urban villages are characterised by growing numbers of buildings and a mix of functions, including residential, industrial, commercial, and public services. These uses enable different activities in urban villages, assimilating migrants into the city by providing an alternative niche for working and living. Variations in land-use diversity in Shenzhens 318 urban villages were analysed using 2009 data, for more than 333 000 buildings. Four statistical models, including three based on a spatial regimes analysis, are used to explain their land-use diversity. The results reveal that an urban villages land-use pattern is linked to its location in the urban fabric, its phase of development, and the development level of its environs. Different patterns are apparent inside and outside the Special Economic Zone of Shenzhen, suggesting that the current uniform redevelopment policy for urban villages may not be appropriate.

Uncertainty analysis for image interpretations of urban slums

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.

The spatial and temporal nature of urban objects

The purpose of this chapter is to examine, from an application perspective, the utility of remote sensing to collect data on urban and suburban areas for Urban Planning and Management (UPM). Specifically, the chapter discusses the use of remote sensing at two different spatial levels, the information needs with respect to monitoring planned and unplanned development, and the optimal spatial and temporal requirements for images used in this regard.