Moving beyond the map: automated landmark based pedestrian guidance using street level panoramas

  • Authors:

  • Jason Wither;Carmen E. Au;Raymond Rischpater;Radek Grzeszczuk

  • Affiliations:

  • Microsoft, Sunnyvale, California, United States;Microsoft, Sunnyvale, California, United States;Microsoft, Sunnyvale, California, United States;Microsoft, Sunnyvale, California, United States

  • Venue:
  • Proceedings of the 15th international conference on Human-computer interaction with mobile devices and services
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the past people have used very different forms of directions depending on how those directions were acquired. If a person is giving another person directions in a familiar area, he will frequently use landmarks to describe the route [10]. If the person gets the route from a personal navigation system though, it will be displayed on a map and make use of street names for the directions. In this paper we present a system to automatically give landmark based navigation to pedestrians by using panoramic imagery to both find salient landmarks along a route automatically, and to present those landmarks to a pedestrian navigator in an immersive and intuitive manner. Our system primarily uses automatically detected business signs as landmarks, and currently works in a half dozen cities around the world. We have also evaluated our system and found that people can effectively navigate solely using landmark enhanced panoramas of decision points along the route.