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

Casablanca, Morocco's economic capital continues today to fight against the proliferation of informal settlements affecting its urban fabric illustrated especially by the slums. Actually Casablanca represents 25% of the total slums of Morocco (Banque Mondiale, 2006). 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 inhabitants 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such as information gathering, mapping, use of databases and statistics often have shown their limits and are sometimes outdated.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 detection of slums in Casablanca. This paper is actually to develop new approaches based mainly on objectoriented classification of high spatial resolution satellite images for the detection of slums. The data from this classification will then be used in a spatial database.