Mapping informal settlement indicators using object-oriented analysis in the Middle East

Abstract

Mapping informal settlements is crucial for resource and utility management and planning. In 2003, the UN-Habitat developed a process for mapping and monitoring urban inequality to support reporting against the sustainable development goals (SDGs). Informal settlement indicators are used as a framework to carry out image analysis, and include vegetation extent, lacunarity of housing structures / vacant land, road segment type and materials, texture measures of built-up areas, roofing extent of built-up areas and dwelling size. Objectbased image analysis (OBIA) methods are recommended to identify informal settlements. This paper documents the application of OBIA to map informal settlements, drawing on the ontology of Kohli et al. (2012) and the indicators of Owen and Wong (2013) for a Middle Eastern city. Three informal settlements with different land use histories were selected to represent old and new informal settlements in the city of Jeddah, Saudi Arabia. Vegetation extent was the most successful indicator detected, with 100% producer accuracy and over 84% user accuracy, followed by the road network, with 84% producer and user accuracies in older informal settlements and 73% producer accuracy and 96% user accuracy across all case studies. Lacunarity of housing structures / vacant land was detected well in informal settlements. The texture measure indicator was detected using GLCM Ent (R) with low producer accuracy across all case studies. The roofing extent of the built-up area is detected with better producer and user accuracies than texture measures. The dwellings size indicator generally failed to distinguish formal from informal settlements. Informal and formal were distinguished with an overall accuracy of 83%. This research concludes that OBIA is a useful method to map informal settlement indicators in Middle Eastern cities. However, a generic ruleset for mapping informal settlements remains elusive, and each indicator requires significant localised 'tuning'.

Mapping Informal Settlements in the Middle East Environment using an Object-Based Machine-Learning Approach

“…Owen and Wong in [11] proposed 14 indicators using data from Guatemala (see Table 1) although mapping these indicators is a challenge especially in countries where key geographical data are missing [12]. Some indicators have been successfully mapped [roofing extent, vegetation, road network and lacunarity of housing structures/vacant land] however, others [texture measure and dwelling size] could not be retrieved [13]. Some of these indicators have been used to map informal settlements and slums [8,10,13] using a slum ontological framework proposed in [14].…”

“…Some indicators have been successfully mapped [roofing extent, vegetation, road network and lacunarity of housing structures/vacant land] however, others [texture measure and dwelling size] could not be retrieved [13]. Some of these indicators have been used to map informal settlements and slums [8,10,13] using a slum ontological framework proposed in [14]. In previous work, we adopted this approach, using object-based image analysis (OBIA) to classify informal settlement indicators in a Middle Eastern city [13].…”

“…Some of these indicators have been used to map informal settlements and slums [8,10,13] using a slum ontological framework proposed in [14]. In previous work, we adopted this approach, using object-based image analysis (OBIA) to classify informal settlement indicators in a Middle Eastern city [13]. We found that the OBIA approach can map informal settlements indicators at the object level and some indicators at the settlements level.…”

“…Although rather labour intensive, visual interpretation is still used for informal settlement and slum identification and produces reliable results in the hands of skilled interpreters. OBIA requires a local ontology framework, such as that in [14], to guide the OBIA parameterisation by defining the different features for classification, as discussed in [8,10,13]. The OBIA approach is knowledge based, typically producing a hierarchical classification and has been the dominant approach over the last decade [12,16].…”

“…Values of SP = 40, = 0.5 and = 0.5 were selected through interactive control (see section 4.1). The three parameters values were chosen based on qualitative analysis (visual inspection), after [8,10,13], of the resulting segmentation and the purpose of classification, representing basic land cover features (for example, buildings and the road network). For full details of this method see [13].…”