| Computer Vision |

Tasty City
Photo Geolocation using Street and Restaurant Data

Team: Tianyu Su, Zhuangyuan Fan

Supervisor: Prof. William T. Freeman,

Prof. Antonio Torralba, Prof. Phillip Isola

‚Äč

# Computer Vision, Deep Learning, Mapping

In computer vision, the photo geolocation problem has been usually approached at a global scale or regional

scale. In this project, we derive knowledge from urban studies and present a classification based method looking into neighborhood scale photo geotagging.

 

We subdivide Boston Chinatown into multiple geographic cells and train a deep network using 20K google street view images labeled with local restaurant density and street speed limit. We show that this multitask model could output a probability distribution over a couple of cells in the neighborhood.