Detecting Slums from SPOT Data in Casablanca Morocco Using an Object Based Approach

Abstract

Casablanca, Morocco's economic capital continues today to fight against the proliferation of informal settle- ments affecting its urban fabric illustrated especially by the slums. Actually Casablanca represents 25% of the total slums of Morocco [1]. These are the habitats of all deprived of healthy sanitary conditions and judged precarious from the perspective humanitarian and below the acceptable. The majority of the inhabi- tants of these slums are from the rural exodus with insufficient income to meet the basic needs of daily life. Faced with this situation and to eradicate these habitats, the Moroccan government has launched since 2004 an entire program to create cities without slums (C.W.S.) to resettle or relocate families. Indeed the process control and monitoring of this program requires first identifying and detecting spatial habitats. To achieve these tasks, conventional methods such as information gathering, mapping, use of databases and statistics often have shown their limits and are sometimes outdated. It is within this framework and that of the great German Morocco project “Urban agriculture as an integrative factor of development that fits our project de- tection of slums in Casablanca. The use of satellite imagery, particulary the HSR, has the advantage of providing the physical coverage of urban land but it raises the difficulty of choosing the appropriate method to apply.This paper is actually to develop new approaches based mainly on object-oriented classification of high spatial resolution satellite images for the detection of slums.This approach has been developed for mapping the urban land through by integration of several types of information (spectral, spatial, contextual ...) (Hofmann, P ., 2001, Herold et al. 2002b; Van Der Sande et al., 2003, Benz et al., 2004, Nobrega et al., 2006). In order to refine the result of classification, we applied mathematical morphology and in particular the closing filter. The data from this classification (binary image), which then will be used in a spatial data- base (ArcGIS)

A Critical Review of High and Very High-Resolution Remote Sensing Approaches for Detecting and Mapping Slums: Trends, Challenges and Emerging Opportunities

“…Examples of such work include studies by Rhinane et al [94], Kit et al [51], Veljanovski et al [70]. These studies mainly differ in the segmentation parameters used for extracting slums as a result of variations in physical characteristics of slums, as captured in remote sensing imagery.…”

“…MM, which is based on set theory, uses a set of image operators (e.g., erosion and dilation) to extract features from an image based on the shape and size of quasi-homogeneous regions [92]. As it relates to slums, MM has largely been used to refine the outputs of processes used to extract features from binary images, such as the removal of trees, fences and other unwanted artifacts (e.g., [93,94]). Some work, albeit limited, has also applied MM to grayscale images as part of multi-scale applications within slums.…”

Automated detection of slum area change in Hyderabad, India using multitemporal satellite imagery

“…Successful examples of slum identification from very high resolution imagery include methods based on object-based image analysis (Hofmann et al, 2008), object segmentation and classification (Shekhar, 2012), morphological opening and closing (Rhinane et al, 2011). One of the last successful attempts to automatically identify slums in India has been made by Shekhar, 2012, where eCognition-supported object segmentation and classification has been used to identify slums in Pune.…”

Multiscale Geoscene Segmentation for Extracting Urban Functional Zones from VHR Satellite Images

“…Finally, functional zones can be labeled with categories based on their features. Previous efforts at functional-zone analysis focus mainly on feature representations [9][10][11][12][13][14] and classification methods [4,15,16], but ignore zone segmentation. This is unfortunate because zone segmentation is an essential precursor to the other two steps of functional-zone analysis and is hence fundamental to the entire undertaking.…”

“…Firstly, low-level features, such as spectral, geometrical, and textural image features, are widely used in image analyses [11], but they are weak in characterizing functional zones which are usually composed of diverse objects with variant characteristics [12]. Then, middle-level features, including object semantics [4,8], visual elements [7], and bag-of-visual-word (BOVW) representations [13], are more effective than low-level features in representing functional zones [7], but they ignore spatial and contextual information of objects, leading to inaccurate recognition results.…”