A positioning method and device based on geomagnetic field and LoRa

Abstract

The application relates to the field of LoRa and deep learning fusion, and specifically provides a positioning method and device based on a geomagnetic field and LoRa, which comprises multiple LoRa fixed stations, one LoRa mobile station, a geomagnetic field sensor and a central processor, the LoRa fixed stations are placed in multiple corners of a building to be positioned, the LoRa mobile station, the geomagnetic field sensor and the central processor are placed on a target to be positioned. Compared with the prior art, the application realizes full coverage and high precision of positioning in the building by fusing a LoRa signal and geomagnetic information. Traditional geomagnetic fields are matched in a point-to-point mode, the collected geomagnetic data is unfolded according to a specified rule to form a time sequence, and the time sequence is matched, the LoRa positioning excludes the ambiguity solution of geomagnetic positioning, and is fused with the geomagnetic positioning information.

Description

TECHNICAL FIELD

[0001] The application relates to the field of LoRa and deep learning fusion, and specifically provides a positioning method and device based on a geomagnetic field and LoRa. BACKGROUND

[0002] Indoor positioning and navigation has become a core problem of navigation and location services, and is of great significance to smart cities, auxiliary robots, personal navigation, emergency rescue and other fields; more than 70% of modern people spend time indoors, and with the rapid development of urbanization and urbanization, urban "valleys" and large and closed indoor spaces are increasing, which puts forward unprecedented huge requirements for indoor positioning, and establishing an indoor seamless positioning system has great significance to the society.

[0003] At present, one kind of indoor positioning technology is based on Bluetooth, wifi, UWB and other signals to realize positioning, constructs a hidden Markov model, and realizes indoor positioning through the use of position fingerprint information, establishes an RSSI fingerprint library of a positioning area, and calculates the maximum possible trajectory of continuous motion based on a hidden Markov positioning model, but the penetration of these signals is poor, the coverage is small, and many base stations need to be arranged to realize some positioning effect, so it is not suitable for use in complex high-rise buildings;

[0004] Another kind is inertial navigation technology based on inertial devices, which has no signal transmission problem and can be used continuously anywhere, but its problem is that the self-error cannot be corrected, and the cumulative error will be very large after long-time work, finally leading to unusable positioning results. The existing geomagnetic positioning technology generally matches a point with a plane, which is easy to produce ambiguous solutions. SUMMARY

[0005] The application is aimed at the deficiencies of the prior art, and provides a positioning method based on a geomagnetic field and LoRa.

[0006] The further technical task of the application is to provide a positioning device based on a geomagnetic field and LoRa, which is reasonable in design and safe and suitable for use.

[0007] The technical scheme adopted by the application to solve the technical problems is:

[0008] A positioning method based on a geomagnetic field and LoRa, comprising a plurality of LoRa fixed sites, a LoRa mobile site, a geomagnetic field sensor and a central processor, the LoRa fixed sites are placed in a plurality of corners of a building to be positioned, the LoRa mobile site, the geomagnetic field sensor and the central processor are placed on a target to be positioned.

[0009] Further, the specific steps are:

[0010] S1, collect the plane magnetic field and LoRa signal strength data in the region to be positioned;

[0011] S2, stretch the plane data to form a linear sequence;

[0012] S3, construct a local matching library through the linear sequence after stretching;

[0013] S4, the movable LoRa station carried by the object to be positioned communicates with each LoRa fixed station to obtain an approximate position;

[0014] S5, select nearby data in the matching library in S3 through the approximate position in step S4 to construct a local matching library;

[0015] S6, compare the time sequence received in real time with the data in the matching library to obtain an accurate position.

[0016] Further, in step S1, the matching library is constructed, the plane magnetic field and LoRa signal strength value in the region to be positioned are collected by carrying the collection region, after the collection route collects the entire region data, the plane data is converted into a one-dimensional time sequence, and all data is saved as a complete matching library.

[0017] Further, in step S2, the movable LoRa station carried by the object to be positioned communicates with each LoRa fixed station to obtain a fuzzy position by calculating the distance after communicating the communication time.

[0018] Further, in step S3, according to the position obtained in step S2, the data in the matching library within a distance near the position is extracted as a local matching library.

[0019] Further, in step S4, the real-time magnetic field and signal strength value are collected by setting a time window for a period of time, and the data is taken as a time sequence, which is compared with the local matching library through the LSTM deep learning algorithm to obtain an accurate position.

[0020] Further, the original plane magnetic field is stretched to form a time sequence, and the strength value of the LoRa signal is added to form a matching library, and then the time sequence collected within a certain period of time is matched with the data in the matching library to obtain a more accurate result.

[0021] A positioning device based on a geomagnetic field and LoRa, comprising at least one memory and at least one processor;

[0022] The at least one memory is used to store machine-readable programs;

[0023] The at least one processor is configured to invoke the machine-readable program to execute a positioning method based on geomagnetic field and LoRa.

[0024] Compared with existing technologies, the positioning method and device based on the geomagnetic field and LoRa of the present invention have the following outstanding advantages:

[0025] This invention can send information to multiple fixed stations simultaneously. Upon receiving the information, each fixed station quickly sends back a message. The mobile station determines its distance to each fixed station by the time it sends and receives the messages, thus determining its own location. Simultaneously, the LoRa mobile station can continuously monitor the signal strength of each fixed station. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Appendix Figure 1 This is a flowchart illustrating a positioning method based on the Earth's magnetic field and LoRa.

[0028] Appendix Figure 2 This is a schematic diagram of geomagnetic stretching as a time series in a positioning method based on the geomagnetic field and LoRa. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to specific embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] The following is a preferred embodiment:

[0031] like Figure 1 As shown, this embodiment of a positioning method based on geomagnetic field and LoRa includes multiple LoRa fixed stations, a LoRa mobile station, a geomagnetic field sensor and a central processing unit. The LoRa fixed stations are placed in multiple corners of the building to be located, and the LoRa mobile station, geomagnetic field sensor and central processing unit are placed on the target to be located.

[0032] The specific steps are as follows:

[0033] S1. Build the matching library;

[0034] Within the area requiring positioning, this device is used to collect geomagnetic and LoRa signal strength values. The collection route follows... Figure 2 As shown, after the data collection for the entire region is completed, the data is converted into a one-dimensional time series according to the diagram, and all the data is saved as a complete matching library.

[0035] S2. The mobile LoRa station carried by the object being located communicates with each fixed LoRa station.

[0036] The movable LoRa station carried by the object being located communicates with each fixed LoRa station. After obtaining the communication time, the distance is calculated, and a fuzzy location is obtained and recorded.

[0037] S3. Construct a local matching library;

[0038] Based on the location obtained in step S2, the data in the matching library within 5 meters of that location is extracted as a local matching library.

[0039] S4. By comparison, the accurate location is determined;

[0040] By setting a 3-second time window to collect real-time geomagnetic field and signal strength values, and using this data as a time series, the accurate location is obtained by comparing it with a local matching library through an LSTM deep learning algorithm.

[0041] The original planar geomagnetic field is stretched to form a time series, and the intensity value of the LoRa signal is added to form a matching library. Then, the time series collected within a certain period of time is matched with the data in the matching library to obtain a more accurate result.

[0042] Figure 1 For simplicity, the geomagnetic and LoRa signal strengths are collected along the arrows in the positioning area. The collection interval is related to the required accuracy; for higher accuracy, the distance between each vertical line needs to be shorter. After collection, the data is converted into a time series. During matching, data over a short period is first collected in real time, and then matched with data in the time series database using an LSTM deep learning algorithm.

[0043] After matching the corresponding points, the two-dimensional positions are restored by reverse processing during the stretching of the time series.

[0044] To improve the real-time performance of the system, it is necessary to increase the speed of deep learning operations. Therefore, reducing the size of the matching library becomes the most convenient method.

[0045] A fuzzy position is obtained by means of signal transceiving, so in the matching process, according to the obtained fuzzy position, the time sequence near the position is taken as the matching library, so that the data amount of matching is greatly reduced, thereby improving the overall operation speed.

[0046] The LoRa mobile station has multiple channels and can simultaneously send information to multiple fixed stations, and the fixed stations quickly return a message after receiving the information, and the mobile station determines the distance between each fixed station by the time of message transceiving, the positions of the fixed stations are calibrated in advance, and the position information of the mobile station is determined through the distance relationship. Meanwhile, the LoRa mobile station can obtain the signal strength of each fixed station at any time.

[0047] A positioning device based on a geomagnetic field and LoRa, comprising: at least one memory and at least one processor;

[0048] The at least one memory is used to store a machine-readable program.

[0049] The at least one processor is used to call the machine-readable program and execute a positioning method based on a geomagnetic field and LoRa.

[0050] The above specific embodiments are only specific cases of the present application, and the patent protection scope of the present application includes but is not limited to the above specific embodiments, any appropriate changes or replacements made by any person skilled in the art to the positioning method and device based on a geomagnetic field and LoRa according to the claims of the present application, and any changes or replacements shall fall within the patent protection scope of the present application.

[0051] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A positioning method based on the geomagnetic field and LoRa, characterized in that, It includes multiple LoRa fixed stations, one LoRa mobile station, a geomagnetic field sensor, and a central processing unit. The LoRa fixed stations are placed in multiple corners of the building to be located, and the LoRa mobile station, geomagnetic field sensor, and central processing unit are placed on the target to be located. The specific steps are as follows: S1. Collect geomagnetic and LoRa signal strength data of the plane within the area to be located; A matching library is constructed. Within the area to be located, the geomagnetic and LoRa signal strength values ​​within the collection area are carried. After the data collection route is completed, the planar data is converted into a one-dimensional time series, and all data is saved as the complete matching library. S2. Stretch the planar data to form a linear sequence; The movable LoRa station carried by the object being located communicates with each fixed LoRa station. After obtaining the communication time, the distance is calculated to obtain a fuzzy location, and the fuzzy location is recorded. S3. Construct a local matching library using the stretched linear sequence; Based on the location obtained in step S2, data from the matching library within a certain distance of the location is extracted as a local matching library. S4. The mobile LoRa station carried by the object being located communicates with each fixed LoRa station to obtain its approximate location. By setting a time window for a certain period of time to collect real-time geomagnetic field and signal strength values, and using this data as a time series, the accurate location is obtained by comparing it with a local matching library through an LSTM deep learning algorithm. The original planar geomagnetic field is stretched to form a time series, and the intensity value of the LoRa signal is added to form a matching library. Then, the time series collected within a certain period of time is matched with the data in the matching library to obtain a more accurate result. S5. Based on the approximate location in step S4, select nearby data from the matching library in S3 to construct a local matching library; S6. By comparing the received time series data with the data in the matching library in real time, the accurate location is obtained.

2. A positioning device based on the Earth's magnetic field and LoRa, characterized in that, include: At least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is configured to invoke the machine-readable program to execute the method of claim 1.

Images