Recognition and classification of illegal dumps with object based image analysis of satellite data

The focus on environmental issues is pursued through a land monitoring in order to prevent abuse, for example, the uncontrolled storage of waste. As part of this control is significant the availability of object-based techniques for an elaboration of satellite data to detect situations of illegality as that cited. Traditional image processing and image interpretation methods are usually based only on the information extracted from features intrinsic of single pixel: the object’s physical properties, which are determined by the real world and the imaging situation - basically sensor and illumination. One of the limitations of this method is that it allows to evaluate only a part of the information content of the images, without exploring the appearance as important as geometric-textural information (Pitea et al., 1998). The application of Object Based Image Analysis on very high resolution data allows, with an automatic or semi-automatic process – with a minimal manual participation - a good classification also in presence of high and very high resolution data, where higher is the chance of error. The final classification, through a suitable hierarchy of classes that takes into account the relationships between the produced segmentation levels, may be highly accurate (Baatz et al., 2004). Thus we introduce other rules for the location of the context, and the relations between the objects meaningfully increases the chance of automatic recognition of objects on the land surface. The choice of the scale factor allows to calibrate the largeness of the resultant polygons, and its definition is tied to the cartographic scale reference that the end user must obtain. Through the inclusion in the segmentation process of a shapefile containing some detected test areas, we proceed to the recognition of the landfill areas. In this work we also use some cadastral data for multiresolution segmentation and object-based classification. This is re-usable in any geographic context.