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 one or more processors, for each given mobile device of the first set of mobile devices a user trajectory based on the set of inertial navigation signals received from the given mobile device in order to provide a set of user trajectories for the mobile devices of the first set of mobile devices; identifying paths associated with the number of user trajectories by applying a smoothing algorithm to each user trajectory of the set of user trajectories, wherein each identified path comprises a set of turns traveled between a first position and a second position on the map; selecting a candidate path of the identified paths based on a number of turns in the set of turns in the candidate path; determining a score for each given path of the identified paths based on a similarity of the given path to the candidate path; selecting at least one path from the identified paths that scores above a pre-determined threshold; and generating, using the one or more processors, map information based on the at least one selected path that identifies walkable areas of the indoor space around constraints of the plurality of constraints of the map.