Discussing the Potential of Crowdsourced Geographic Information for Urban Areas Monitoring Using the Panoramio Initiative: A Case Study in Rome, Italy

During the last decade, Crowdsourced Geographic Information or Volunteered Geographic Information has attracted the attention of the research community to explore this vast amount of data and extract useful information for various applications. Among these, geotagged photos shared publicly online have been explored as potential source for Land Use/Cover (LULC) mapping creation and validation. In this work, we performed an evaluation of the adequacy of the geotagged photos available from the Panoramio initiative for monitoring LULC in urban areas, with a study conducted in the urban area of Rome, Italy. We investigated the temporal distribution of the photos for the time range 2007–2013 with different resolution (year, season and month) as well as the spatial distribution in the study area. Then, we evaluated the representativeness of the Panoramio dataset for each LULC class by using the Urban Atlas database as a reference and computing the number and density of photos per square km for each class. Finally we discussed the main limitations of the dataset for LULC monitoring in urban areas and we proposed alternative approaches useful to overcome some of the identified limitations.