Object-based Method for Identifying New Constructions around Water Reservoirs: Preliminary Results

Identifying new constructions in large cities can be done simply, quickly, and at low cost by applying image processing techniques on time-series remote sensing (RS) images and producing land cover maps. In recent years, object-based (OB) image classification has attracted significant attention as a method for land cover mapping. This method consists of two steps: segmentation and classification. In this research, we will develop a new approach based on image processing techniques to be utilized in the OB classification method for the analysis of urban growth. In this approach, we propose a multi-phase segmentation for the segmentation step and a rule-based method for the classification step. Besides speeding up the process of OB classification, the accuracy of the final preliminary results is another advantage of the proposed approach. Moreover, for collecting RS images, a two-zoom level data collection is adopted using an open source RGB RS database. An important application of analyzing RS images is the detection of non-authorized communities formation around water reservoirs. Therefore, in our preliminary experiments, we selected three different regions around Guarapiranga reservoir in Sao Paulo, Brazil, for collecting our RS images.