Wifi and geomagnetism fused indoor positioning system and method based on HMM (Hidden Markov Model)

Abstract

The invention discloses a wifi and geomagnetism fused indoor positioning system and method based on an HMM (Hidden Markov Model). The method comprises the following steps: matching a wifi signal acquired by a mobile terminal in real time with a pre-established wifi fingerprint library to obtain a local position area; initializing the position in the area to obtain an initial probability distribution matrix; obtaining a state transition probability matrix by using a position relationship of label points in the local position area; and fusing a geomagnetic signal with a pre-established geomagnetic fingerprint library to obtain an observation probability matrix, and estimating the position of a user according to a forward algorithm. When the user is positioned in the local position area determined by the wifi signal, the current real-time geomagnetic signal is used to update the observation probability matrix, and the position of the user is estimated by the observation probability matrixand the state transition matrix; otherwise, the wifi signal is introduced to re-establish the local position area, and the initial probability distribution matrix, the state transition probability matrix and the observation probability matrix are updated according to the preceding method. According to the wifi and geomagnetism fused indoor positioning method based on the provided by the invention, various information is effectively fused, and the positioning accuracy of the system is improved.

Description

technical field [0001] The invention relates to an indoor positioning system and a positioning method, in particular to an indoor positioning system and a positioning method based on HMM wifi and geomagnetic fusion. Background technique [0002] With the rapid development of the economy, various high-rise buildings have sprung up, people's indoor activity space is expanding and the indoor terrain is becoming more and more complex. There is an increasing need for indoor positioning. When looking for a specific item in a shopping mall, looking for a friend who came from afar in the airport, or looking for a car in the parking lot, people need a clear location for guidance. GPS positioning technology can play a very good role in outdoor positioning, but in an indoor environment, GPS signals are blocked by buildings, and it is difficult for mobile terminals to receive GPS signals. [0003] There are many technologies based on indoor positioning, including infrared positioning ...

AI Technical Summary

Problems solved by technology

In the inertial navigation technology, the inertial sensor has a better positioning effect in a short time, but it is easy to accumulate errors for a long time, resulting in a sharp drop in positioning accuracy

In the geomagnetic positioning technology, the magnetic field signal is stable, the anti-interference ability is strong, and the local characteristics are obvious. However, when the positioning space is large, the geomagnetic signals at different positions may have similar situations, resulting in a decrease in the positioning accuracy based only on the geomagnetic signal.

Directly using the wifi network widely deployed in public places for positioning can reduce the cost of positioning, but wifi is easily affected by multipath effects, signal attenuation and human body blocking, resulting in a relatively low accuracy of single wifi positioning technology

[0004] A single indoor positioning technology can no longer meet people's needs for location, and the combination of multiple positioning technologies has become the mainstream direction of indoor positioning. Therefore, how to effectively combine multiple information to achieve accurate positioning is an exploratory problem.

At present, the filter-based fusion positioning method is mainly particle filter. This method needs to accurately estimate the user's step size and direction during the particle state transition process. However, the step size of different users is diverse and the walking direction is random. Can it be effectively estimated? The step size and direction affect the positioning results

Images