An indoor positioning method based on wireless graph compensation

Abstract

The present invention relates to an indoor positioning method based on wireless map compensation, which may include the following steps: for a certain indoor positioning application scenario, according to the general wireless signal model method, obtain the wireless map of each wireless signal in this scenario and store it in the positioning center; according to the fingerprint matching method, perform offline sampling on the wireless signals in this scenario to construct a fingerprint database in the positioning center; during online positioning, detect whether the fingerprint uploaded by the terminal to be located is complete. If it is not complete, first complete the incomplete fingerprint, and then perform retrieval and comparison in the fingerprint database based on the completed complete fingerprint. Otherwise, directly perform retrieval and comparison in the fingerprint database to obtain the positioning result.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor positioning, and particularly to an indoor positioning method based on wireless map compensation. Background Art

[0002] The methods for indoor positioning using wireless signals such as WIFI, BT, RFID, etc. are mainly divided into two categories: wireless signal model methods and fingerprint matching methods. For the fingerprint matching method, during the offline sampling stage, the wireless signal identifiers (usually the MAC addresses of wireless signal sources) collected at each sampling point and the corresponding signal strengths are used to form fingerprint vectors and entered into the central database. During online positioning applications, the fingerprints collected by the terminal to be located are uploaded to the positioning center and compared with the offline sampling data, and the position of the fingerprint with the highest similarity in the database is used as the positioning result. The accuracy of the fingerprint matching method is mainly affected by the completeness of offline sampling. The wireless signal model represents the indoor distribution of wireless signals using distribution models (such as the Keenan - Motley model, ITU - RP model, etc.). By training the model parameters with several sampling values, after calculating the model parameters, a wireless map of the entire wireless signal strength distribution in the space is obtained. During the positioning stage, the terminal receives the signal strength of the wireless signal source, and calculates the terminal position based on the wireless map. The positioning accuracy of the wireless signal model method is mainly affected by the degree of conformity between the wireless signal model and the actual signal strength distribution.

[0003] Both methods have their own advantages and disadvantages. The present invention proposes a fingerprint positioning method based on the fusion application of the two methods to obtain a more accurate positioning effect. When using the fingerprint matching method for positioning, it is hoped that the terminal to be located can search for all the wireless signals that can be received at the current position. Although different positioning terminals at the same position can often receive stronger signals, for weaker wireless signals, the reception results of different terminals or even the reception results of the same terminal at different times vary greatly. This is caused by the following two reasons:

[0004] 1. The performance differences of the hardware modules of the terminal to be located, so some devices can receive some weaker wireless signals while some devices cannot.

[0005] 2. The wireless signal itself has a certain degree of volatility, and the weaker wireless signal itself is at the critical value that can be received by the terminal receiving module. Therefore, signal fluctuations often cause it to be sometimes received and sometimes not received.

[0006] For positioning methods such as using wireless signal fingerprints, in order to improve positioning accuracy, obviously, it is desired that the receiving module of the terminal device to be positioned can receive all physically existing wireless signals. Only with relatively complete information collected can a more accurate positioning result be obtained. At the same time, due to the general requirement of real-time positioning, it is not possible to continuously sample at a location for a period of time to increase the completeness of wireless signal collection.

[0007] How to increase the completeness of weak signal collection for the terminal device to be positioned and improve positioning accuracy is the problem to be solved by the present invention. Summary of the Invention

[0008] The present invention aims to provide an indoor positioning method based on wireless map compensation to solve the above problems. For this purpose, the specific technical solutions adopted by the present invention are as follows:

[0009] An indoor positioning method based on wireless map compensation, the indoor positioning method includes the following steps:

[0010] For a certain indoor positioning application scenario, according to the general wireless signal model method, obtain the wireless map of each wireless signal in this scenario and store it in the positioning center;

[0011] According to the fingerprint matching method, perform offline sampling on the wireless signals in this scenario to construct a fingerprint database in the positioning center;

[0012] During online positioning, detect whether the fingerprint uploaded by the terminal to be positioned is complete. If it is not complete, first complete the incomplete fingerprint, and then perform retrieval and comparison in the fingerprint database according to the completed complete fingerprint. Otherwise, directly perform retrieval and comparison in the fingerprint database to obtain the positioning result.

[0013] Further, the offline sampling is specifically: use a wireless signal collector with sensitive receiving performance to collect wireless signal fingerprints at evenly spaced positions indoors.

[0014] Further, the specific process of completing the incomplete fingerprint is: the positioning center predicts the next positioning position P t-2 and P t-1 based on the consecutive positioning positions P of the terminal to be positioned in the previous two times; then according to the predicted next positioning position P t , retrieve all wireless signal identifiers and the RSS intensity value set R at this predicted position from the wireless maps of all wireless signals; then compare with the uploaded incomplete wireless fingerprint and R, and extract the wireless signals missing in the uploaded fingerprint and the corresponding RSS intensity values from R, and interpolate them into the uploaded fingerprint to form a complete fingerprint. t

[0015] Even further, the next positioning position Pt The prediction is carried out in the following way: Along the direction of the straight line from P t-2 to P t-1 in the straight line direction, extend from P t-1 Extend P t-2 to P t-1 and the distance can be obtained.

[0016] By adopting the above technical solution, the beneficial effects of the present invention are as follows: Through the fusion application of the wireless signal model method and the fingerprint matching method, the weak signals that cannot be collected by the positioning terminal are interpolated, the positioning information is improved, and a more accurate positioning effect can be obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To further illustrate the embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be combined with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are usually used to represent similar components.

[0018] Figure 1 is the flowchart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0019] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0020] As Figure 1 shown, an indoor positioning method based on wireless map compensation may include the following steps:

[0021] 100. For a certain indoor positioning application scenario, according to the general wireless signal model method, collect the wireless signals of this scenario, calculate the model parameters, obtain the wireless map of the wireless signals of this scenario, and store it in the positioning center. It should be understood that the specific implementation process of this step belongs to common knowledge and will not be elaborated here.

[0022] 102. According to the fingerprint matching method, use a wireless signal collector with more sensitive receiving performance to perform offline sampling on the wireless signals of this scenario, and construct a fingerprint database in the positioning center. It should be understood that the specific implementation process of this step belongs to common knowledge and will not be elaborated here. Since a wireless signal collector with more sensitive receiving performance is used, the fingerprint database is complete and can ensure accurate positioning results.

[0023] 104. During online positioning, it is detected whether the fingerprint uploaded by the terminal to be located is complete. If so, go to step 108; otherwise, go to step 106. Since the terminal to be located is an ordinary terminal, generally, a wireless signal fingerprint with weak signal loss and incompleteness is uploaded. Although this wireless fingerprint can directly perform matching calculations at the positioning center to obtain the positioning location, due to possible weak signal loss, it may affect the positioning accuracy calculated by the positioning center. Therefore, during online positioning, it is necessary to detect whether the fingerprint uploaded by the terminal to be located is complete.

[0024] 106. Complete the incomplete fingerprint. Specifically, the following process is adopted:

[0025] The positioning center predicts the next positioning position P t-2 and P t-1 based on the consecutive positioning positions P of the terminal to be located in the previous two times. t Specifically, the prediction method is as follows: Assume that the positioning request period is T seconds. Taking P t-2 to P t-1 as the direction and ((Pt1 - Pt2) / T) as the traveling speed, the position traveled for T seconds is the predicted position P t , that is, along the straight line direction from P t-2 to P t-1 , extend the distance from P t-1 to P t-2 to P t-1 to obtain the predicted position P t ;

[0026] Then, based on the predicted next positioning position P t , all wireless signal identifiers and the RSS intensity value set R at this predicted position are retrieved from the wireless map of all wireless signals;

[0027] Next, by comparing the uploaded incomplete wireless fingerprint with R, the wireless signals and the corresponding RSS intensity values missing in the uploaded fingerprint are extracted from R and interpolated into the uploaded fingerprint to form a complete fingerprint.

[0028] 108. Adopt the general fingerprint positioning method to retrieve and compare the fingerprint uploaded by the terminal to be located or the completed fingerprint in the fingerprint database to obtain the positioning result.

[0029] The method of the present invention, through the integrated application of the wireless signal model method and the fingerprint matching method, interpolates the weak signals that cannot be collected by the positioning terminal, improves the positioning information, and can achieve a more accurate positioning effect.

[0030] Although the present invention has been specifically shown and described in connection with preferred embodiments, those skilled in the art should understand that various changes in form and detail may be made to the present invention without departing from the spirit and scope of the present invention as defined by the appended claims, and all such changes are within the scope of protection of the present invention.

Claims

1. An indoor positioning method based on wireless graph compensation, characterized in that The indoor positioning method includes the following steps: For a certain indoor positioning application scenario, according to the general wireless signal model method, obtain the radio map of each wireless signal in this scenario and store it in the positioning center; According to the fingerprint matching method, perform offline sampling on the wireless signals in this scenario to construct a fingerprint database in the positioning center; During online positioning, detect whether the fingerprint uploaded by the terminal to be positioned is complete. If it is not complete, first complete the incomplete fingerprint, and then perform retrieval and comparison in the fingerprint database based on the completed complete fingerprint. Otherwise, directly perform retrieval and comparison in the fingerprint database to obtain the positioning result; Among them, completing the incomplete fingerprint includes: locating the center according to the consecutive positioning positions P of the terminal to be located at the previous two times t-2 and P t-1 to predict the next positioning position P t ; then, according to the predicted next positioning position P t , retrieve all wireless signal identifiers and the RSS intensity value set R of the predicted position from the wireless map of all wireless signals; then compare with the uploaded incomplete wireless fingerprint and R, extract the wireless signals missing from the uploaded fingerprint and the corresponding RSS intensity values from R, and interpolate them into the uploaded fingerprint to form a complete fingerprint; Among them, the next positioning position P t is predicted in the following way: Along the straight line direction from P t-2 to P t-1 extend P t-1 by the distance from P t-2 to P t-1 to obtain it.

2. The indoor positioning method according to claim 1, wherein The offline sampling is specifically as follows: Use a wireless signal collector with sensitive receiving performance to collect wireless signal fingerprints at evenly spaced positions indoors.

Images