CROWD-SOURCING INDOOR LOCATIONS

摘要

Aspects of the present disclosure provide techniques for constructing a scalable model of an indoor space using crowd-sourced inertial navigation system (INS) signals from mobile devices. By tracking INS signals from a number of participating users, the user's trajectories can be estimated as they move their mobile devices indoors. The estimated trajectories can be scored against similar routes taken by other users. Routes with the highest scores are then laid out over a map of the indoor space to identify areas most often traveled to and from landmarks and distances between the landmarks.

主权项

1. A method, comprising:
identifying a map of an indoor space, the map being based on a plurality of constraints; receiving inertial navigation signals from a first set of mobile devices moving through the indoor space, where the inertial navigation signals represent a direction and speed of movement of the mobile devices; calculating, using a processor, a number of user trajectories based on the received set of inertial navigation signals; identifying paths associated with the number of user trajectories, wherein each path comprises a number of turns traveled between a first position and a second position on the map; determining a score for each of the identified paths based on a similarity of a given path to the number of user trajectories; selecting at least one path from the identified paths that scores above a pre-determined threshold; and generating, using the processor, map information based on at least one selected path that identifies walkable areas of the indoor space.