Estimating geographic information from an image is an excellent, difficult high-level computer vision problem whose time has come. The emergence of vast amounts of geographically-calibrated image data is a great reason for computer vision to start looking globally — on the scale of the entire planet! In this paper, we propose a simple algorithm for estimating a distribution over geographic locations from a single image using a purely data-driven scene matching approach. For this task, we will leverage a dataset of over 6 million GPS-tagged images from the Internet. We represent the estimated image location as a probability distribution over the Earth’s surface. We quantitatively evaluate our approach in several geolocation tasks and demonstrate encouraging performance (up to 30 times better than chance). We show that geolocation estimates can provide the basis for numerous other image understanding tasks such as population density estimation, land cover estimation or urban/rural classification.

En somme, l’ordinateur compare une photo avec les photos de Flickr et détermine l’origine géographique possible de cette dernière à partir des données géographiques des photographies les plus ressemblantes. Très habile. Et c’est une belle illustration du principe qui fait que le quantitatif, à un certain degré, devient du qualitatif (quoique cela mériterait un large débat et que l’on s’y arrête exprès).

Source : IM2GPS: estimating geographic information from a single image.