A New Tool for Information Extraction and Mining from Satellite Imagery Available from Google Maps Engine

The wealth of satellite imagery available in web mapping service applications such as Google Maps, which now provides high-resolution satellite images from many locations around the Earth, has opened the appealing perspective of performing information extraction and mining tasks via the Google Maps application programming interface (API). In fact, the introduction of Google's mapping engine (the Google Maps service is free for non-commercial use) has prompted a worldwide interest in satellite imagery exploitation. In this paper, we present a new tool for information extraction and mining from satellite images available Google Maps. Our main focus in this work will be on describing the interface and how the user can interact with the tool. The functionalities included in the tool comprise the possibility to perform unsupervised classification of image portions selected by the user (at the maximum zoom level) using ISODATA and K-Means classifiers, followed by spatial post-processing based on majority voting. Selected regions in the classified portion can then be used to train a more sophisticated classifier able to map larger image areas in a manner transparent to the user. Several examples of use, focused on the analysis of different locations around the Iberian Peninsula and comprising different types of information extraction case studies (vegetation, semi-arid environments, urban areas, etc.) are illustrated and thoroughly described.