Extracting Touristic Information from Online Image Collections

摘要

In this paper, we present a GeographicaludInformation Retrieval system, which aims to automaticallyudextract and analyze touristic information from photos ofudonline image collections (in our case of study Flickr). Ourudsystem collect all the photos, and the related information,udthat are associated to a specific city. We then use GoogleudMaps service to geolocate the retrieved photos, and finallyudwe analyze geo-referenced data to obtain our goals: 1)uddetermining and locating the most interesting places of theudcity, i.e. the most visited locations, and 2) reconstructingudtouristic routes of the users visiting the city. Information isudfiltered by using a set of constraints, which we apply to selectudonly the users that reasonably are tourists visiting the city.udTests were performed on an Italian city, Palermo, that is richudin artistic and touristic attractions, but preliminary testsudshowed that our technique could successfully be applied toudany city in the world with a reasonable number of touristicudlandmarks.