Abstract
Since the introduction of Google Street View, a part of Google Maps, vehicles equipped with roof-mounted mobile cameras have methodically captured street-level images of entire cities. The worldwide Street View coverage spans over 10 countries in four different continents. This service is freely available to anyone with an internet connection. While this is seen as a valuable service, the images are taken in public spaces, so they also contain license plates, faces, and other information information deemed sensitive from a privacy standpoint. Privacy concerns have been expressed by many, in particular in European countries. As a result, Google has introduced a system that automatically blurs faces in Street View images. However, many identifiable features still remain on the un-blurred person. In this paper, we propose an automatic method to remove entire pedestrians from Street View images in urban scenes. The resulting holes are filled in with data from neighboring views. A compositing method for creating “ghost-free” mosaics is used to minimize the introduction of artifacts. This yields Street View images as if the pedestrians had never been there. We present promising results on a set of images from cities around the world.