Mapping the world's photos

TLDR

The study aims to develop methods for organizing a large geotagged photo collection from Flickr. The authors combine text, image, and geospatial analyses, using spatial popularity to build a relational structure and classification models that predict photo locations from visual, textual, and temporal cues. The combined visual and temporal features enhance photo location prediction over text alone, enabling effective organization of the collection and revealing global patterns of popular cities and landmarks.

Abstract

We investigate how to organize a large collection of geotagged photos, working with a dataset of about 35 million images collected from Flickr. Our approach combines content analysis based on text tags and image data with structural analysis based on geospatial data. We use the spatial distribution of where people take photos to define a relational structure between the photos that are taken at popular places. We then study the interplay between this structure and the content, using classification methods for predicting such locations from visual, textual and temporal features of the photos. We find that visual and temporal features improve the ability to estimate the location of a photo, compared to using just textual features. We illustrate using these techniques to organize a large photo collection, while also revealing various interesting properties about popular cities and landmarks at a global scale.