Walking down a Different Path

Abstract

For a traveler to enjoy a trip in a city, one important factor is the diversity of sceneries and facilities along the route. Current navigation systems can provide the shortest route between two points, as well as scenic or safe routes. However, diversity is largely ignored in existing works. In this paper, we present a system that provides diversity-based route recommendation. It measures visual-based diversity and facility-based diversity with information extracted from publicly available data such as Google Street View images and FourSquare venues. As we will show, the current prototype system is able to provide diversity-based route recommendation for city areas in San Fransisco and Kyoto.