Indoor positioning method and system based on multi-source signal fusion

Abstract

The invention relates to an indoor positioning method and system based on multi-source signal fusion, and the method comprises the steps: constructing a plurality of position fingerprint maps of a plurality of signal sources in a noiseless environment, and constructing a gradient distribution diagram after multi-source signal normalization according to the position fingerprint maps; determining one or more first signal sources for target indoor positioning and a plurality of second signal sources for auxiliary positioning according to the gradient distribution map and the plurality of position fingerprint maps; receiving signals of one or more first signal sources, and performing feature matching on the signal intensity of the signals and the fingerprint map of the corresponding position to obtain one or more estimated values of the target at the current position; and correcting the one or more estimated values by using a pedestrian trajectory calculation method and a filtering algorithm to obtain a final target position. According to the invention, the optimal signal source is determined through a plurality of fingerprint maps, and the indoor positioning method considering cost, time delay and precision is determined through related conditions and a correction method.

Description

technical field [0001] The invention belongs to the technical field of indoor positioning, and in particular relates to an indoor positioning method and system based on multi-source signal fusion. Background technique [0002] With the rapid development of communication technology and wireless sensing technology, as well as the increasing popularity and application of various intelligent terminals, people's demand for seamless location indoors and outdoors is increasing, and the complex indoor electromagnetic Indoor positioning technology presents challenges. On the other hand, location-based services (Location Based Service, LBS) are gradually changing people's lifestyles and work forms, such as positioning and navigation, social networking, precise advertising, public safety and emergency handling, etc. Among them, 70% to 90% of the location services required by public users are indoors. At the same time, the Global Navigation Satellite System (GNSS) in the outdoor enviro...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of low cost, low delay and high accuracy of indoor positioning that the existing technology cannot simultaneously meet, the first aspect of the present invention provides an indoor positioning method based on multi-source signal fusion, including: constructing multiple multiple position fingerprint maps of the signal source in a noise-free environment, and construct a normalized gradient distribution map of the multi-source signal based on it, and the multiple signal sources include at least magnetic field and millimeter wave; according to the gradient distribution map and multiple Position fingerprint map, determine one or more first signal sources for target indoor positioning, and multiple second signal sources for auxiliary positioning; receive signals from one or more first signal sources, and compare their signal strengths Perform feature matching with the corresponding location fingerprint map to obtain one or more estimated values ​​of the target at the current position; use pedestrian trajectory estimation method and filtering algorithm to correct the one or more estimated values ​​to obtain the final target position

Images