Enhanced land cover and land use information generation from satellite imagery and foursquare data
share
Volunteered Geographic Information (VGI) has been increasingly used in a variety of research studies over the recent years. Foursquare is one of the most commonly used sources of VGI. In this paper we investigate the possibility of using Foursquare data for inferring land use information from land cover classification of satellite imagery. Land cover is derived from satellite imagery by the application of supervised and unsupervised classification techniques. It is then integrated with Foursquare data, which comprises of land use information. The results of our study demonstrate that Foursquare data can be used for inferring up-to-date and reliable land use information from land cover classification of satellite imagery, to a reasonable extent. However the results also suggest that the use of Foursquare dataset as the only additional data source for inferring complete land use information is not a viable approach. But we believe that the combined use of multiple sources of VGI such as Foursquare data, OpenStreetMap data etc. together with remote sensing data would be an efficient way of generating comprehensive land use information.
READ FULL TEXT