Integration of open-source tools for object-based monitoring of urban targets

The constant increase in population in conjunction with unplanned and irregular urban growth, typical problems in developing countries, can promote a rapid increase in population density and related public infrastructure demand that may be hard to bear with the available economic resources. Efficient monitoring of urban development is thus a key instrument for planners and public policy makers that have to cope with this scenario. This work aims at developing a tool to aid monitoring urban growth from very-high
resolution remote sensing images, focussing on the integration of available open-source software and the application of OBIA methods. Specifically, we created a method for detection of urban, land use/land cover classes based on the integration of the InterIMAGE and the Orange Canvas software packages. The image interpretation model for the particular application was constructed with the aid of dataflow building blocks (widgets) for data analysis, structured in the visual programming environment of Orange Canvas. The Classification Tree and the Classification Tree Graph widgets were used to design a decision tree that was later translated in InterIMAGE Decision Rules. The study was conducted over an image from the GeoEye-1 sensor, covering a central area of the city of Goianésia, in the Midwestern region of Brazil. Ten land use/land cover classes were the target of the supervised classification. The results obtained in the experiments confirm that the integration of the two open-source packages can provide for accurate remote sensing image analysis, while facilitating data exploration and the construction of automatic image interpretation models.