Looking into the world on Google Maps with view direction estimated photos

In this paper, we present a novel system, named ViewFocus, to explore the world on Google Maps by leveraging and mining the large amount of user-uploaded geo-tagged photos. Compared with current available online geolocation-oriented photo exploring websites, such as Flickr and Panoramio, ViewFocus is characterized with its ability of supporting precise exploration of specific places or viewing angles of interests on the map with the view direction filtered photos. To achieve this goal, we present a practical solution to estimate the view directions of photos via fast visual search, robust object matching and camera reconstruction techniques, and geo-registers the directions on the map. Thus, the proposed system allows users to (1) select the places they are interested in and then focus their exploration and (2) walk freely through the map and view what can be seen along their eyes with the automatically returned precise set of photos of the target places/angles, by filtering out photos that are pointing to other directions. The evaluations and user study validate the effectiveness of the proposed system.