Bluetooth indoor positioning method for improving PDR and RSSI fusion

Abstract

The invention relates to a Bluetooth indoor positioning method for improving PDR and RSSI fusion, and the method comprises the following steps: 1), constructing an RSSI positioning gray image set as a training set of a CNN positioning model, carrying out the RSSI positioning through employing the trained CNN positioning model, and obtaining an initial RSSI positioning result; (2) constructing an IMU data set according to walking data, collected by an IMU, of pedestrians, adopting a PDR algorithm for positioning, and obtaining an initial PDR positioning result; 3) correcting the initial PDR positioning result by adopting a PDR correction algorithm based on the stay duration; and 4) fusing the corrected PDR positioning result with the RSSI positioning result by using an EKF filter to obtain a final positioning result. Compared with the prior art, the method improves the problem of PDR error accumulation, improves the positioning precision, has higher system stability and universality, and can provide a more accurate positioning result for indoor personnel.

Description

technical field [0001] The invention relates to the field of indoor positioning technology, in particular to a Bluetooth indoor positioning method which improves the integration of PDR and RSSI. Background technique [0002] In today's life, GPS technology has become an indispensable part of our daily life. However, due to the weakened strength of satellite signals reaching the ground and only outdoor positioning, the current demand for indoor positioning is increasing, so it is suitable for indoor positioning and not PDR technology that requires external assistance has received a lot of attention. At the same time, the development of mobile Internet and smart phones has greatly promoted the development of Bluetooth indoor positioning technology, especially the newly launched Bluetooth 5.1 technology in recent years. The advantage of being able to transmit information to other devices has made Bluetooth indoor positioning more and more attention in various fields. [0003]...

AI Technical Summary

Problems solved by technology

[0003] In the existing research, most of the indoor positioning methods are based on the ranging method, using the time or energy information of signal transmission and reception to establish a corresponding mathematical model, and according to the geometric relationship between the positions, the distance between known nodes and unknown nodes is solved mathematically. However, in indoor scenarios, the distance between devices is short, the interference is complex, the signal propagation is affected by multipath effects, and the positioning accuracy is poor. In addition, PDR technology is another common technology for indoor navigation and positioning. Although it has small size and low cost Low autonomy and strong advantages, but due to the accumulation of errors, the positioning accuracy still needs to be further improved

Images