Indoor-positioning-oriented position fingerprint library building and dynamic updating method

Abstract

The invention discloses an indoor-positioning-oriented position fingerprint library building and dynamic updating method. At the off-line stage, firstly, an initial position fingerprint library is built by a Gaussian process regression method; at the on-line stage, when a client to be positioned sends the current collected RSS observing value to a server side, the server side estimates the currentposition of the client by a fingerprint matching algorithm according to fingerprint information in the position fingerprint library, and returns the current position to the client; if a carrier of the current client equipment is a crowdsourcing participant of position fingerprint library updating, the RSS observing value when the client passes through a section of path is recorded; the information and initial position estimation and pedestrian dead reckoning results are sent to the server; then, the server side operates an on-line marginalized particle extension Gaussian process algorithm; the position fingerprint library is updated in an on-linemode. The recursive real-time updating of the position fingerprint library at the on-line stage is realized; the fingerprint precision is high.

Description

technical field [0001] The invention belongs to the technical field of indoor positioning, and in particular relates to a method for constructing and dynamically updating a location fingerprint library for indoor positioning. Background technique [0002] The traditional fingerprint library construction method is realized by site survey (Site Survey), that is, RSS collection is carried out by specialized personnel in a large number of indoor locations, which consumes a lot of manpower and time. The positioning accuracy of the fingerprint database established by this approach will gradually decrease as time goes by, that is, the effectiveness of the fingerprint database will decrease. To this end, the researchers proposed the following types of improvement methods: [0003] 1. Model-based fingerprint estimation method. [0004] By using multiple signal propagation models, predicting RSS observations at different locations (rather than collecting them manually), forming fing...

AI Technical Summary

Problems solved by technology

[0010] First of all, in the existing fingerprint library construction method based on crowdsourcing, the noise contained in the location label obtained by PDR or other estimation methods is not considered, and the accuracy of the fingerprint established accordingly is affected to a certain extent.

[0011] Secondly, the existing fingerprint library update method only adopts a simple replacement strategy, that is, replaces the old fingerprint with a new one, which on the one hand causes the size of the fingerprint library to change, and on the other hand does not make full use of the useful information of the old fingerprint.

[0012] Thirdly, the existing fingerprint library construction and update methods do not take into account the asynchronous characteristics of the arrival of new fingerprints or crowdsourced fingerprints, but adopt a one-time overall generation strategy, which has high computational costs and large delays.

Images