A Multi-floor Indoor Localization Method Based on Radial Basis Function Network

Abstract

The present invention relates to a multi-floor indoor positioning method based on a radial basis function network, comprising: 1) obtaining a signal strength vector of an observation point, and inputting the trained first radial basis function network to estimate the floor where the observation point is located; ) input the signal strength vector of the observation point into the trained second radial basis function network corresponding to the floor where it is located, and estimate the plane position coordinates of the observation point; the construction process of the first and second radial basis function networks includes: Set several reference points and wireless access points on each floor, record the location fingerprint of each reference point, and build a location fingerprint sample database; use the reference points as hidden nodes to build the first radial basis function network and the second corresponding to each floor. Radial Basis Function Network; the network is trained using a database of location fingerprint samples. Compared with the prior art, the present invention has the advantages of high positioning accuracy, strong robustness and the like.

Description

technical field [0001] The invention relates to an indoor positioning method, in particular to a multi-floor indoor positioning method based on a radial basis function network. Background technique [0002] The wide application of mobile intelligent terminals and the rapid popularization and large-scale application of wireless networks make the application demand for Location Based Services (LBS) show a rapid and substantial growth trend. field. Among them, reliable and efficient positioning technology is the premise and key to realize LBS. [0003] Outdoors, the Global Navigation Satellite System (GNSS) is used in various occasions where positioning service information is required. The generation and development of GNSS basically solved the problem of positioning in the outdoor open space, and it has been widely used in the fields of military, transportation, resources and environment, agriculture, animal husbandry and fishery, surveying and mapping, as well as people's d...

AI Technical Summary

Problems solved by technology

[0006] One is that the data in the fingerprint database is insufficient, because on-site surveying and mapping in the offline stage often consumes a lot of manpower and material resources. In practical applications, the data collected at each reference point may be very small. In this case, most probabilistic algorithms may be Invalid, because if there is not enough data, the construction of the signal strength vector RSSI (Received SignalStrength Index) probability distribution model cannot be completed;

[0007] The second is the data deviation of the fingerprint library. Due to the limitation of low-cost sensors, this deviation is not only due to the volatility of the received RSSI, but also to the low precision of the position calibration of the reference point, so the deviation on the electronic map is usually unavoidable ;

[0008] The third is the time-varying nature of the fingerprint database. In theory, the RSSI fingerprint will change with the indoor environment, so the database should be updated regularly to ensure the positioning accuracy. However, the time, money and labor costs required to update the electronic map high

Images