Estrazione rapida di strade mediante segmentazione di immagini telerilevate da satellite integrabili in Open Street Map per situazioni di emergenza

During the Haiti earthquake on 12.01.2010 and the Nepal earthquake on 25/04/2015 proved to be very useful the work of the volunteers that integrate the free Open Street Map (OSM) creating maps of the roads on site, useful in case of emergency, thus supporting the humanitarian organizations.
Though away from the site of interest, with such crowdsourcing they can contribute to the efforts of mapping inaccessible or little known regions by tracing images from aerial photographs or satellite images, in some cases made available free of charge.
The objective of this research, still in progress, is to experience the opportunity to obtain very quickly the road, pulling automatically or semi-automatically from the satellite data.
The methodology used is the Object Based Image Analysis, which operates a segmentation of the whole image, in this case by setting parameters such as shape and color easily distinguishing roads from rivers, then making it possible a fast exporting of data obtained to Open Street Map. This migration process to OSM is automated so is much more rapid and efficient than manual integration, inhomogeneous and subject to many variables.
The results obtained so far are encouraging and suggest continuing the search for rapid techniques for the integration of maps to be used for humanitarian emergencies.