Indoor positioning method, system and equipment based on signal three-dimensional fingerprint database and medium

Abstract

The invention discloses an indoor positioning method, system and device based on a signal three-dimensional fingerprint database and a medium. The method comprises the steps that an indoor space area is scanned, and motion data of the scanning device and signal data of all signal transmitters are recorded; performing three-dimensional mapping on the target area; calculating a three-dimensional coordinate of each signal data recording point as a reference point; dividing a target area into three-dimensional grids, and calculating a grid signal data mean value containing reference points as reference grid signal data; interpolation is carried out based on the signal data of other grids except the reference grid, and a three-dimensional fingerprint database is constructed; continuously monitoring signals at a fixed monitoring point, calculating signal data of each signal transmitter of the monitoring point, calculating corresponding coordinates, comparing the coordinates with true value coordinates, and updating the three-dimensional fingerprint database when the distance between the calculated coordinates and the true value coordinates exceeds a threshold value; and indoor positioning is completed by using the updated three-dimensional fingerprint database. According to the method, spatial three-dimensional positioning is supported, the three-dimensional fingerprint database is updated when necessary, the positioning precision is maintained, and cost waste is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of positioning and navigation, and in particular relates to an indoor positioning method, system, equipment and medium based on a signal three-dimensional fingerprint library. Background Art

[0002] RSSI (Received Signal Strength Indication) fingerprint matching is a commonly used method in wireless positioning technology. The RSSI fingerprint matching algorithm uses RSSI values ​​for location positioning. Its basic principle is to measure and record the RSSI values ​​of multiple wireless signal sources in a specific area (indoors) through a fixed receiver. These values ​​are stored together with the corresponding location information to form a fingerprint library (or fingerprint map). When positioning, the receiver will measure the RSSI value of the current location in real time, and match these values ​​with the data in the fingerprint library to estimate the current location.

[0003] RSSI fingerprint matching is an important means of achieving indoor positioning through signals such as WiFi and BLE (Bluetooth Low Energy). Wireless signals are transmitted through fixed signal transmitters (Access Points, AP) installed indoors, and the mobile terminal calculates the position through the received signal strength of each AP. This method requires the establishment of a signal fingerprint library in advance for matching during positioning. Each entry in the fingerprint library contains a set of RSSI values ​​and corresponding location coordinates. At present, a more accurate signal fingerprint library establishment method is to use SLAM (Simultaneous Localization and Mapping) technology to obtain the positioning position and record the signal strength through a mobile platform (such as a remote control car carrying a sensor) to generate a signal fingerprint library (Marcin Kolakowski. Automated Calibration of RSS Fingerprinting Based Systems Using a Mobile Robot and Machine Learning. Sensors 2021, 21 (18), 6270.). The current advantage of using a SLAM mobile platform for signal fingerprint collection is that the location accuracy of the collected data is high, but there are two disadvantages:

[0004] 1. Only the construction of two-dimensional fingerprint library is considered, and the construction of three-dimensional fingerprint library is not considered, which cannot be used for three-dimensional spatial positioning;

[0005] 2. There is no signal fingerprint library update mechanism. Changes in the fingerprint library caused by signal source aging and environmental changes will affect the positioning accuracy. Summary of the invention

[0006] The purpose of the present invention is to address the problems in the above-mentioned prior art and provide an indoor positioning method, system, device and medium based on a signal three-dimensional fingerprint library, which supports spatial three-dimensional positioning, monitors changes in fingerprint signals, updates the fingerprint library when necessary, maintains positioning accuracy, and avoids cost waste caused by unnecessary frequent updates.

[0007] In order to achieve the above object, the present invention has the following technical solutions:

[0008] In a first aspect, an embodiment provides an indoor positioning method based on a signal three-dimensional fingerprint library, including:

[0009] Scan the indoor space area and record the scanning device motion data and the signal data of each signal transmitter AP;

[0010] Build a three-dimensional map of the target area based on the motion data of the scanning device and the signal data of each signal transmitter AP;

[0011] Calculate the three-dimensional coordinates of each signal data recording point as a reference point based on the three-dimensional mapping of the target area;

[0012] Divide the target area into three-dimensional grids and calculate the mean value of grid signal data including reference points as reference grid signal data;

[0013] Interpolation is performed based on signal data of other grids other than the reference grid to construct a three-dimensional fingerprint library;

[0014] Continuously monitor the signal at a fixed monitoring point and calculate the signal data of each signal transmitter AP at the monitoring point, calculate the corresponding coordinates and compare them with the true value coordinates, and update the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold;

[0015] The updated three-dimensional fingerprint library is used to match the received signal strength indication RSSI value to complete indoor positioning.

[0016] As a preferred solution, when scanning an indoor space area and recording the motion data of the scanning device and the signal data of each signal transmitter AP, the scanning device uses an instant positioning and map construction SLAM mobile data acquisition platform equipped with a signal acquisition device. The signal acquisition device is an inertial navigation system IMU and a laser radar used in conjunction, and an additional signal receiver is used to collect and record signals.

[0017] As a preferred solution, the step of calculating the three-dimensional coordinates of each signal data recording point as a reference point based on the three-dimensional mapping of the target area includes:

[0018] Calculate the position coordinates of each set of signal data when it is recorded. Since the frequency of each sensor data is inconsistent, the recording time of a set of signal data is recorded as t, and the recording time of the adjacent lidar data is t1 and t2. The corresponding position coordinate calculation results are p1(x1, y1, z1) and p2(x2, y2, z2). The coordinates p(x, y, z) of this set of signal data are calculated according to the following formula:

[0019]

[0020] A reference point data set is obtained, where each reference point data contains three-dimensional coordinates and a signal value of each signal transmitter AP.

[0021] As a preferred solution, in the step of dividing the target area into three-dimensional grids and calculating the mean value of the grid signal data containing the reference points as the reference grid signal data, the mean value of the grid signal data containing the reference points is calculated according to the following formula:

[0022]

[0023] In the formula, k, V i They respectively represent the number of reference points falling into the grid and the signal vector corresponding to each reference point.

[0024] As a preferred solution, in the step of constructing a three-dimensional fingerprint library by interpolating signal data of other grids other than the reference grid:

[0025] The signal data at the grid p is calculated as follows:

[0026]

[0027] Where d(p,i) is the straight-line distance between the center point of grid p and the center point of reference grid i, V i is the signal value vector of reference grid i; after the signal data of all grids are calculated according to the formula, the construction of the three-dimensional fingerprint library is completed.

[0028] As a preferred solution, in the step of continuously monitoring the signal at a fixed monitoring point and calculating the signal data of each signal transmitter AP at the monitoring point, calculating the corresponding coordinates and comparing them with the true value coordinates, and updating the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold:

[0029] Fix signal monitoring tags at several locations in the target area and record the true value coordinates p of the signal monitoring tag locations i =(x i ,y i ,z i ), continuously receives signal data from each signal transmitter AP, and calculates the actual position p' through the three-dimensional fingerprint library i=(x' i ,y' i ,z' i ), if the distance between the calculated result and the true value is greater than the positioning accuracy requirement, that is, d(p i ,p' i )>d thr , then the three-dimensional fingerprint library is updated.

[0030] As a preferred solution, in the step of updating the three-dimensional fingerprint library, a data collection path for updating the three-dimensional fingerprint library is planned according to historical indoor positioning trajectory data, and data is recollected according to the updated data collection path to update the three-dimensional fingerprint library.

[0031] As a preferred solution, the steps of planning the data collection path for updating the three-dimensional fingerprint library according to the historical indoor positioning trajectory data are as follows:

[0032] Define the sampling step size;

[0033] Calculate the hottest positioning grid in the sampling step grid: the sampling step grid is a grid with the sampling step as the side length, the positioning grid is consistent with the constructed three-dimensional fingerprint library, calculate the number of positioning grids contained in a sampling step grid, and find the positioning grid with the most historical trajectory points in the corresponding number of positioning grids, that is, the hottest positioning grid; if no historical trajectory points fall into a sampling step grid, the positioning grid at the center of the corresponding sampling step grid is used as the hottest positioning grid;

[0034] Path planning: The hottest positioning grid in each sampling step grid is used as the waypoint, and the data collection path is obtained using the shortest path algorithm passing through the specified intermediate point.

[0035] In a second aspect, the embodiment provides an indoor positioning system based on a signal three-dimensional fingerprint library, including:

[0036] The data acquisition module is used to scan the indoor space area and record the motion data of the scanning device and the signal data of each signal transmitter AP;

[0037] A three-dimensional mapping module is used to construct a three-dimensional map of the target area based on the motion data of the scanning device and the signal data of each signal transmitter AP;

[0038] A reference point coordinate calculation module is used to calculate the three-dimensional coordinates of each signal data recording point as a reference point based on the three-dimensional mapping of the target area;

[0039] A reference grid determination module is used to divide the target area into three-dimensional grids and calculate the mean value of grid signal data containing reference points as reference grid signal data;

[0040] An interpolation module is used to interpolate signal data of other grids other than the reference grid to construct a three-dimensional fingerprint library;

[0041] The three-dimensional fingerprint library update module is used to continuously monitor the signal at a fixed monitoring point and calculate the signal data of each signal transmitter AP at the monitoring point, calculate the corresponding coordinates and compare them with the true value coordinates, and update the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold;

[0042] The indoor positioning module is used to use the updated three-dimensional fingerprint library to match the received signal strength indication RSSI value to complete indoor positioning.

[0043] As a preferred solution, when the data acquisition module scans the indoor space area and records the motion data of the scanning device and the signal data of each signal transmitter AP, the scanning device uses an instant positioning and map construction SLAM mobile data acquisition platform equipped with a signal acquisition device. The signal acquisition device is an inertial navigation system IMU and a laser radar used in conjunction, and an additional signal receiver is used to collect and record signals.

[0044] As a preferred solution, the reference point coordinate calculation module calculates the position coordinates when each set of signal data is recorded. Since the frequency of each sensor data is inconsistent, the recording time of a certain set of signal data is recorded as t, and the recording time of the adjacent laser radar data is t1 and t2, and the corresponding position coordinate calculation results are p1 (x1, y1, z1) and p2 (x2, y2, z2). The coordinates p (x, y, z) of this set of signal data are calculated according to the following formula:

[0045]

[0046] A reference point data set is obtained, where each reference point data contains three-dimensional coordinates and a signal value of each signal transmitter AP.

[0047] As a preferred solution, the reference grid determination module calculates the mean value of the grid signal data containing the reference point according to the following formula:

[0048]

[0049] In the formula, k, V i They respectively represent the number of reference points falling into the grid and the signal vector corresponding to each reference point.

[0050] As a preferred solution, the interpolation module calculates the signal data at a certain grid p outside the reference grid according to the following formula:

[0051]

[0052] Where d(p,i) is the straight-line distance between the center point of grid p and the center point of reference grid i, Vi is the signal value vector of reference grid i; after the signal data of all grids are calculated according to the formula, the construction of the three-dimensional fingerprint library is completed.

[0053] As a preferred solution, the three-dimensional fingerprint library update module fixes signal monitoring tags at several positions in the target area and records the true value coordinates p of the signal monitoring tag positions. i =(x i ,y i ,z i ), continuously receives signal data from each signal transmitter AP, and calculates the actual position p' through the three-dimensional fingerprint library i =(x' i ,y' i ,z' i ), if the distance between the calculated result and the true value is greater than the positioning accuracy requirement, that is, d(p i ,p' i )>d thr , then the three-dimensional fingerprint library is updated.

[0054] As a preferred solution, the indoor positioning system based on the signal three-dimensional fingerprint library also includes a data acquisition path update module, which is used to plan the data acquisition path for updating the three-dimensional fingerprint library according to the historical indoor positioning trajectory data, re-collect data according to the updated data acquisition path and realize the update of the three-dimensional fingerprint library.

[0055] As a preferred solution, the data acquisition path update module plans the data acquisition path for updating the three-dimensional fingerprint library according to the historical indoor positioning trajectory data, including:

[0056] Define the sampling step size;

[0057] Calculate the hottest positioning grid in the sampling step grid: the sampling step grid is a grid with the sampling step as the side length, the positioning grid is consistent with the constructed three-dimensional fingerprint library, calculate the number of positioning grids contained in a sampling step grid, and find the positioning grid with the most historical trajectory points in the corresponding number of positioning grids, that is, the hottest positioning grid; if no historical trajectory points fall into a sampling step grid, the positioning grid at the center of the corresponding sampling step grid is used as the hottest positioning grid;

[0058] Path planning: The hottest positioning grid in each sampling step grid is used as the waypoint, and the data collection path is obtained using the shortest path algorithm passing through the specified intermediate point.

[0059] In a third aspect, an embodiment provides an electronic device, including a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the indoor positioning method based on a signal three-dimensional fingerprint library.

[0060] In a fourth aspect, an embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the indoor positioning method based on the signal three-dimensional fingerprint library is implemented.

[0061] Compared with the prior art, the present invention has at least the following beneficial effects:

[0062] The present invention proposes a signal three-dimensional fingerprint library construction and updating method suitable for indoor positioning. According to the three-dimensional mapping of the target area, the three-dimensional coordinates of each signal data recording point are calculated as the reference point, the target area is divided into a three-dimensional grid and the grid signal data average containing the reference point is calculated as the reference grid signal data, and interpolation is performed based on other grid signal data outside the reference grid to construct a three-dimensional fingerprint library, which can support spatial three-dimensional positioning. By continuously monitoring the signal at a fixed monitoring point and calculating the signal data of each signal transmitter AP at the monitoring point, the corresponding coordinates are calculated and compared with the true value coordinates, and the three-dimensional fingerprint library is updated when the distance between the calculated coordinates and the true value coordinates exceeds a threshold. A quantitative indicator for whether the three-dimensional fingerprint library is updated is proposed, and the positioning accuracy can be maintained by updating the three-dimensional fingerprint library. In addition, according to the change of the monitored fingerprint signal, the fingerprint library is updated when necessary, which can avoid the cost waste caused by unnecessary frequent updates.

[0063] Furthermore, the indoor positioning method of the present invention is based on the signal three-dimensional fingerprint library, and adopts the real-time positioning and map construction SLAM mobile data acquisition platform equipped with a signal acquisition device as a scanning device. The initial three-dimensional fingerprint library construction data acquisition can be completed by manually remote-controlled drones, and subsequent fingerprint library updates can automatically plan paths for collection.

[0064] Furthermore, in the step of updating the three-dimensional fingerprint library, the indoor positioning method based on the signal three-dimensional fingerprint library of the present invention plans a data collection path for updating the three-dimensional fingerprint library according to historical indoor positioning trajectory data, re-collects data according to the updated data collection path and realizes the update of the three-dimensional fingerprint library. By planning the data collection path for updating the three-dimensional fingerprint library through the historical indoor positioning trajectory data, the local positioning accuracy of key areas (areas frequently passed by historical trajectories) can be improved.

[0065] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0067] Figure 1 A schematic diagram of a working scenario of an indoor positioning method based on a signal three-dimensional fingerprint library according to an embodiment of the present invention;

[0068] Figure 2 Flow chart of the indoor positioning method based on the signal three-dimensional fingerprint library according to the embodiment of the present invention;

[0069] In the attached figure: 101-SLAM mobile data acquisition platform; 102-signal transmitter AP; 103-signal receiver; 104-data gateway; 105-solution background. DETAILED DESCRIPTION

[0070] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0071] See also Figure 1 and Figure 2 In the working scenario of the indoor positioning method based on the signal three-dimensional fingerprint library of the embodiment of the present invention, the equipment that needs to be set up includes: SLAM mobile data acquisition platform 101, signal transmitter AP 102, signal receiver 103, data gateway 104 and solution background 105. Among them, the SLAM mobile data acquisition platform 101 is a mobile platform with SLAM mapping and positioning functions, and is equipped with a signal acquisition device for collecting reference point data of the signal fingerprint library. The signal transmitter AP102 has several positioning signal sources installed at a fixed position, such as WiFi, BLE (low-power Bluetooth), and UWB (Ultra-Wideband) signal sources. The signal receiver 103 is also a signal monitoring point, a signal receiving device installed at a fixed position, which is used to monitor the change of the signal in real time, and after calculation, it is used as an indicator of whether the fingerprint library is updated. The data gateway 104 is used to receive the data of the SLAM mobile data acquisition platform 101 and the signal monitoring point, and transmit it to the solution background 105 through the gateway for data processing. The solution background 105 is a computing unit that processes (maps and locates) the collected data.

[0072] The indoor positioning method based on the signal three-dimensional fingerprint library of the embodiment of the present invention includes the following steps:

[0073] S1, scan the indoor space area and record the scanning device motion data and the signal data of each signal transmitter AP (Access Points);

[0074] S2. Build a three-dimensional map of the target area based on the motion data of the scanning device and the signal data of each signal transmitter AP;

[0075] S3, calculating the three-dimensional coordinates of each signal data recording point as reference points (Reference Points, RP) based on the data collected in step S1 and the three-dimensional mapping of the target area in step S2;

[0076] S4, dividing the target area into three-dimensional grids, and calculating the mean value of the grid signal data including the reference point as the reference grid signal data;

[0077] S5, interpolating signal data of other grids other than the reference grid to construct a three-dimensional fingerprint library;

[0078] S6, continuously monitoring the signal at a fixed monitoring point and calculating the signal data of each signal transmitter AP at the monitoring point, calculating the corresponding coordinates and comparing them with the true value coordinates, and updating the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold;

[0079] S7. Use the updated three-dimensional fingerprint library to match the received signal strength indication RSSI value to complete indoor positioning.

[0080] In one possible implementation, in step S1, when scanning the indoor space area and recording the motion data of the scanning device and the signal data of each signal transmitter AP, the scanning device uses real-time positioning and mapping equipped with a signal acquisition device to build a SLAM mobile data acquisition platform. A typical signal acquisition device is an inertial navigation system IMU and a lidar used in conjunction, and an additional signal receiver is used to collect and record signals. The signal receiver should be careful not to be blocked by other components of the data acquisition platform so as to affect signal reception.

[0081] In a possible implementation, step S2 builds a map through real-time positioning and map construction on the SLAM mobile data acquisition platform, and records the data of each signal acquisition device (such as the data collected by the above-mentioned inertial navigation system IMU, laser radar, and signal receiver). The collected data is transmitted back to the solution background through the data gateway for mapping and positioning calculation. Among them, SLAM mapping and positioning are relatively mature technologies, and the embodiments are not repeated here. Please refer to "Laser SLAM laser radar + IMU multi-sensor fusion mapping: engineering landing project, from data reception to closed-loop detection to map optimization, complete and optimized code implementation and landing experience summary. https: / / blog.csdn.net / rkttkNkLY / article / details / 138197139 ”.

[0082] In a possible implementation, step S3 of calculating the three-dimensional coordinates of each signal data recording point as a reference point includes: calculating the position coordinates of each group of signal data when it is recorded. Since the frequency of each sensor data is inconsistent, the recording time of a group of signal data is recorded as t, and the recording time of the adjacent laser radar data is t1 and t2, and the corresponding position coordinate calculation results are p1 (x1, y1, z1) and p2 (x2, y2, z2). The coordinates p (x, y, z) of this group of signal data are calculated according to the following formula:

[0083]

[0084] A reference point data set is obtained, where each reference point data contains three-dimensional coordinates and a signal value of each signal transmitter AP.

[0085] The data structure of the reference point dataset is shown in the following table:

[0086] Serial number 3D Coordinates AP signal value 1 <![CDATA[(x1,y1,z1)]]> <![CDATA[{(mac1,v 1_1 ),(mac2,v 2_1 ),…,(mac n ,in n_1 )}]]> 2 <![CDATA[(x2,y2,z2)]]> <![CDATA[{(mac1,v 1_2 ),(mac2,v 2_2 ),…,(mac n ,in n_2 )}]]> … … … m <![CDATA[(x m ,y m ,z m )]]> <![CDATA[{(mac1,v 1_m ),(mac2,v 2_m ),…,(mac n ,in n_m )}]]>

[0087] In a possible implementation, step S4 divides the target area into a three-dimensional grid, such as a 10cm*10cm*10cm cubic grid. A grid containing at least one reference point is a reference grid, and the signal average value of the reference grid is:

[0088]

[0089] In the formula, k, V i They respectively represent the number of reference points falling into the grid and the signal vector corresponding to each reference point.

[0090] In a possible implementation, step S5 performs interpolation based on signal data of other grids other than the reference grid, for example, by using an inverse distance weighting (IDW) model.

[0091] The signal data at the grid p is calculated as follows:

[0092]

[0093] Where d(p,i) is the straight-line distance between the center point of grid p and the center point of reference grid i, V i is the signal value vector of reference grid i; after the signal data of all grids are calculated according to the formula, the construction of the three-dimensional fingerprint library is completed.

[0094] In a possible implementation, step S6 fixes signal monitoring tags at several locations within the target area and records the true value coordinates p of the signal monitoring tag locations. i =(x i ,y i ,z i ), continuously receives signal data from each signal transmitter AP, and calculates the actual position p' through the three-dimensional fingerprint library i =(x' i ,y' i ,z' i ), if the distance between the calculated result and the true value is greater than the positioning accuracy requirement, that is, d(p i ,p' i )>d thr , then the three-dimensional fingerprint library is updated. The positioning algorithm based on signal fingerprint is an existing technology, see "Zhu Qingshan, Wang Wei. Indoor positioning algorithm based on RSSI fingerprint map. Foreign Electronic Measurement Technology 39.10(2020):4." and "Dai Zhicheng, Li Xiaonian, Chen Zengzhao, et al. Variable weight indoor fingerprint positioning algorithm based on KNN algorithm [J]. Computer Engineering, 2019.", which will not be repeated here.

[0095] Since the accuracy of the local positioning result is related to the distribution of reference points in the three-dimensional fingerprint library, the closer to the reference point, the higher the positioning accuracy, and the farther from the reference point, the lower the positioning accuracy. Therefore, when the three-dimensional fingerprint library is updated, the areas and routes that people and equipment in the space often pass through can be obtained through historical positioning trajectory data, and the sampling path can be made to coincide with the behavior route as much as possible during path planning to improve positioning accuracy. In the step of updating the three-dimensional fingerprint library in the embodiment of the present invention, the data collection path for updating the three-dimensional fingerprint library is planned according to the historical indoor positioning trajectory data, and the data is re-collected according to the updated data collection path to realize the update of the three-dimensional fingerprint library. The specific steps of planning the data collection path for updating the three-dimensional fingerprint library are as follows:

[0096] (1) Define the sampling step length. To avoid excessive concentration of sampling points in long-term residence areas (where there are many historical trajectory points), a sampling step length (such as 1 m) is defined. In principle, sampling is not repeated within the sampling step length.

[0097] (2) Calculate the hottest positioning grid in the sampling step grid: The sampling step grid is a grid with the sampling step as the side length (1m*1m*1m in the example), and the positioning grid is consistent with the constructed three-dimensional fingerprint library (10cm*10cm*10cm in the example). Calculate the number of positioning grids contained in a sampling step grid (a sampling step grid in the example contains 1000 positioning grids), and find the positioning grid with the most historical trajectory points in the corresponding number of positioning grids, that is, the hottest positioning grid. If there is no historical trajectory point in a sampling step grid, the positioning grid at the center of the corresponding sampling step grid is used as the hottest positioning grid.

[0098] (3) Path planning: The hottest positioning grid in each sampling step grid is used as a waypoint, and the data collection path is obtained by using the shortest path algorithm passing through the specified intermediate point. The shortest path algorithm passing through the specified intermediate point is a prior art, which can be found in "Huang Shuli, Hu Dasha, Jiang Yuming. Shortest path algorithm passing through a specified set of intermediate nodes. Computer Engineering and Applications, 2015(11):41-46." and "Shortest path through a specified point. https: / / blog.csdn.net / aaa131420030415 / article / details / 128071960 ”, I will not go into details here.

[0099] The embodiment of the present invention is an indoor positioning method based on a signal three-dimensional fingerprint library. Signal monitoring tags are installed at fixed points to monitor signal changes in real time. The position coordinates of each tag are calculated through the constructed three-dimensional fingerprint library and the signal values ​​of each AP monitored by the tag; the distance between the calculated position coordinates of each tag and its true value coordinates is compared. If it is greater than a threshold, the three-dimensional fingerprint library is updated; when updating the three-dimensional fingerprint library, the sampling step is defined and the sampling step grid is divided accordingly; the hotspot positioning grid in each sampling step grid is calculated; and the path for updating the signal fingerprint library is calculated using the hotspot grid as a passing point. The present invention can maintain positioning accuracy through fingerprint library updates and avoid cost waste caused by unnecessary frequent updates. The sampling path for updating the three-dimensional fingerprint library is planned through historical trajectories to improve the local positioning accuracy of key areas (areas frequently passed by historical trajectories).

[0100] The embodiment of the present invention further proposes an indoor positioning system based on a signal three-dimensional fingerprint library, comprising:

[0101] The data acquisition module is used to scan the indoor space area and record the motion data of the scanning device and the signal data of each signal transmitter AP;

[0102] A three-dimensional mapping module is used to construct a three-dimensional map of the target area based on the motion data of the scanning device and the signal data of each signal transmitter AP;

[0103] A reference point coordinate calculation module is used to calculate the three-dimensional coordinates of each signal data recording point as a reference point based on the three-dimensional mapping of the target area;

[0104] A reference grid determination module is used to divide the target area into three-dimensional grids and calculate the mean value of grid signal data containing reference points as reference grid signal data;

[0105] An interpolation module is used to interpolate signal data of other grids other than the reference grid to construct a three-dimensional fingerprint library;

[0106] The three-dimensional fingerprint library update module is used to continuously monitor the signal at a fixed monitoring point and calculate the signal data of each signal transmitter AP at the monitoring point, calculate the corresponding coordinates and compare them with the true value coordinates, and update the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold;

[0107] The indoor positioning module is used to use the updated three-dimensional fingerprint library to match the received signal strength indication RSSI value to complete indoor positioning.

[0108] In one possible implementation, when the data acquisition module scans an indoor space area and records the motion data of the scanning device and the signal data of each signal transmitter AP, the scanning device uses an instant positioning and map construction SLAM mobile data acquisition platform equipped with a signal acquisition device. The signal acquisition device is an inertial navigation system IMU and a laser radar used in conjunction, and an additional signal receiver is used to collect and record signals.

[0109] In a possible implementation, the reference point coordinate calculation module calculates the position coordinates when each set of signal data is recorded. Since the frequency of each sensor data is inconsistent, the recording time of a certain set of signal data is recorded as t, and the recording times of the adjacent laser radar data are t1 and t2, and the corresponding position coordinate calculation results are p1 (x1, y1, z1) and p2 (x2, y2, z2). The coordinates p (x, y, z) of this set of signal data are calculated according to the following formula:

[0110]

[0111] A reference point data set is obtained, where each reference point data contains three-dimensional coordinates and a signal value of each signal transmitter AP.

[0112] Furthermore, the reference grid determination module calculates the mean value of the grid signal data including the reference point according to the following formula:

[0113]

[0114] In the formula, k, V i They respectively represent the number of reference points falling into the grid and the signal vector corresponding to each reference point.

[0115] In a possible implementation, the interpolation module calculates the signal data at a certain grid p outside the reference grid according to the following formula:

[0116]

[0117] Where d(p,i) is the straight-line distance between the center point of grid p and the center point of reference grid i, V i is the signal value vector of reference grid i; after the signal data of all grids are calculated according to the formula, the construction of the three-dimensional fingerprint library is completed.

[0118] In a possible implementation, the three-dimensional fingerprint library update module fixes signal monitoring tags at several locations in the target area and records the true value coordinates p of the signal monitoring tag locations. i =(x i ,y i ,z i ), continuously receives signal data from each signal transmitter AP, and calculates the actual position p' through the three-dimensional fingerprint library i =(x' i ,y' i ,z' i ), if the distance between the calculated result and the true value is greater than the positioning accuracy requirement, that is, d(p i ,p' i )>d thr , then the three-dimensional fingerprint library is updated.

[0119] In a possible implementation, the indoor positioning system based on the signal three-dimensional fingerprint library also includes a data acquisition path update module, which is used to plan the data acquisition path for updating the three-dimensional fingerprint library according to the historical indoor positioning trajectory data, re-collect data according to the updated data acquisition path and realize the update of the three-dimensional fingerprint library.

[0120] Furthermore, the data collection path update module plans the data collection path for updating the three-dimensional fingerprint library, including:

[0121] Define the sampling step size;

[0122] Calculate the hottest positioning grid in the sampling step grid: the sampling step grid is a grid with the sampling step as the side length, the positioning grid is consistent with the constructed three-dimensional fingerprint library, calculate the number of positioning grids contained in a sampling step grid, and find the positioning grid with the most historical trajectory points in the corresponding number of positioning grids, that is, the hottest positioning grid; if no historical trajectory points fall into a sampling step grid, the positioning grid at the center of the corresponding sampling step grid is used as the hottest positioning grid;

[0123] Path planning: The hottest positioning grid in each sampling step grid is used as the waypoint, and the data collection path is obtained using the shortest path algorithm passing through the specified intermediate point.

[0124] An embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the indoor positioning method based on the signal three-dimensional fingerprint library.

[0125] An embodiment of the present invention further proposes a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the indoor positioning method based on the signal three-dimensional fingerprint library is implemented.

[0126] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals. For ease of explanation, the above content only shows the part related to the embodiment of the present invention. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium is non-temporary and can be stored in a storage device formed by various electronic devices, which can realize the execution process recorded in the method of the embodiment of the present invention.

[0127] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An indoor positioning method based on a signal three-dimensional fingerprint library, characterized in that: include: Scan the indoor space area and record the scanning device motion data and the signal data of each signal transmitter AP; Build a three-dimensional map of the target area based on the motion data of the scanning device and the signal data of each signal transmitter AP; Calculate the three-dimensional coordinates of each signal data recording point as a reference point based on the three-dimensional mapping of the target area; Divide the target area into three-dimensional grids and calculate the mean value of grid signal data containing reference points as reference grid signal data; Interpolation is performed based on signal data of other grids other than the reference grid to construct a three-dimensional fingerprint library; Continuously monitor the signal at a fixed monitoring point and calculate the signal data of each signal transmitter AP at the monitoring point, calculate the corresponding coordinates and compare them with the true value coordinates, and update the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold; The updated three-dimensional fingerprint library is used to match the received signal strength indication RSSI value to complete indoor positioning.

2. The indoor positioning method based on the signal three-dimensional fingerprint library according to claim 1 is characterized in that: When scanning the indoor space area and recording the motion data of the scanning device and the signal data of each signal transmitter AP, the scanning device uses a real-time positioning and map construction SLAM mobile data acquisition platform equipped with a signal acquisition device. The signal acquisition device is an inertial navigation system IMU and a laser radar used in conjunction, and an additional signal receiver is attached to collect and record signals.

3. The indoor positioning method based on the signal three-dimensional fingerprint library according to claim 1 is characterized in that: The step of calculating the three-dimensional coordinates of each signal data recording point as a reference point based on the three-dimensional mapping of the target area comprises: Calculate the position coordinates of each set of signal data when it is recorded. Since the frequency of each sensor data is inconsistent, the recording time of a set of signal data is recorded as t, and the recording time of the adjacent lidar data is t1 and t2. The corresponding position coordinate calculation results are p1(x1, y1, z1) and p2(x2, y2, z2). The coordinates p(x, y, z) of this set of signal data are calculated according to the following formula: A reference point data set is obtained, where each reference point data contains three-dimensional coordinates and a signal value of each signal transmitter AP.

4. The indoor positioning method based on the signal three-dimensional fingerprint library according to claim 1 is characterized in that: In the step of dividing the target area into three-dimensional grids and calculating the mean value of the grid signal data containing the reference points as the reference grid signal data, the mean value of the grid signal data containing the reference points is calculated according to the following formula: In the formula, k, V i They respectively represent the number of reference points falling into the grid and the signal vector corresponding to each reference point.

5. The indoor positioning method based on the signal three-dimensional fingerprint library according to claim 4 is characterized in that: In the step of constructing a three-dimensional fingerprint library by interpolating signal data of other grids other than the reference grid: The signal data at the grid p is calculated as follows: Where d(p,i) is the straight-line distance between the center point of grid p and the center point of reference grid i, V i is the signal value vector of reference grid i; after the signal data of all grids are calculated according to the formula, the construction of the three-dimensional fingerprint library is completed.

6. The indoor positioning method based on the signal three-dimensional fingerprint library according to claim 1 is characterized in that: In the step of continuously monitoring the signal at a fixed monitoring point and calculating the signal data of each signal transmitter AP at the monitoring point, calculating the corresponding coordinates and comparing them with the true value coordinates, and updating the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold: Fix signal monitoring tags at several locations in the target area and record the true value coordinates p of the signal monitoring tag locations i =(x i ,y i ,z i ), continuously receives signal data from each signal transmitter AP, and calculates the actual position p' through the three-dimensional fingerprint library i =(x' i ,y' i ,z' i ), if the distance between the calculated result and the true value is greater than the positioning accuracy requirement, that is, d(p i ,p' i )>d thr , then the three-dimensional fingerprint library is updated.

7. The indoor positioning method based on the signal three-dimensional fingerprint library according to claim 1 is characterized in that: In the step of updating the three-dimensional fingerprint library, a data collection path for updating the three-dimensional fingerprint library is planned according to the historical indoor positioning trajectory data, and data is recollected according to the updated data collection path to update the three-dimensional fingerprint library.

8. The indoor positioning method based on the signal three-dimensional fingerprint library according to claim 7 is characterized in that: The steps of planning the data collection path for updating the three-dimensional fingerprint library according to the historical indoor positioning trajectory data are as follows: Define the sampling step size; Calculate the hottest positioning grid in the sampling step grid: the sampling step grid is a grid with the sampling step as the side length, the positioning grid is consistent with the constructed three-dimensional fingerprint library, calculate the number of positioning grids contained in a sampling step grid, and find the positioning grid with the most historical trajectory points in the corresponding number of positioning grids, that is, the hottest positioning grid; If no historical trajectory point falls into a certain sampling step grid, the positioning grid at the center of the corresponding sampling step grid is used as the hottest positioning grid; Path planning: The hottest positioning grid in each sampling step grid is used as the waypoint, and the data collection path is obtained using the shortest path algorithm passing through the specified intermediate point.

9. An indoor positioning system based on a signal three-dimensional fingerprint library, characterized in that: include: The data acquisition module is used to scan the indoor space area and record the motion data of the scanning device and the signal data of each signal transmitter AP; A three-dimensional mapping module is used to construct a three-dimensional map of the target area based on the motion data of the scanning device and the signal data of each signal transmitter AP; A reference point coordinate calculation module is used to calculate the three-dimensional coordinates of each signal data recording point as a reference point based on the three-dimensional mapping of the target area; A reference grid determination module is used to divide the target area into three-dimensional grids and calculate the mean value of grid signal data containing reference points as reference grid signal data; An interpolation module is used to interpolate signal data of other grids other than the reference grid to construct a three-dimensional fingerprint library; The three-dimensional fingerprint library update module is used to continuously monitor the signal at a fixed monitoring point and calculate the signal data of each signal transmitter AP at the monitoring point, calculate the corresponding coordinates and compare them with the true value coordinates, and update the three-dimensional fingerprint library when the distance between the calculated coordinates and the true value coordinates exceeds a threshold; The indoor positioning module is used to use the updated three-dimensional fingerprint library to match the received signal strength indication RSSI value to complete indoor positioning.

10. The indoor positioning system based on the signal three-dimensional fingerprint library according to claim 9 is characterized in that: When the data acquisition module scans the indoor space area and records the motion data of the scanning device and the signal data of each signal transmitter AP, the scanning device uses the real-time positioning and map construction SLAM mobile data acquisition platform equipped with a signal acquisition device. The signal acquisition device is an inertial navigation system IMU and a laser radar used in conjunction, and an additional signal receiver is used to collect and record signals.

11. The indoor positioning system based on the signal three-dimensional fingerprint library according to claim 9, characterized in that: The reference point coordinate calculation module calculates the position coordinates of each set of signal data when it is recorded. Since the frequency of each sensor data is inconsistent, the recording time of a set of signal data is recorded as t, and the recording time of the adjacent laser radar data is t1 and t2, and the corresponding position coordinate calculation results are p1 (x1, y1, z1) and p2 (x2, y2, z2). The coordinates p (x, y, z) of this set of signal data are calculated according to the following formula: A reference point data set is obtained, where each reference point data contains three-dimensional coordinates and a signal value of each signal transmitter AP.

12. The indoor positioning system based on the signal three-dimensional fingerprint library according to claim 9, characterized in that: The reference grid determination module calculates the mean value of the grid signal data containing the reference point according to the following formula: In the formula, k, V i They respectively represent the number of reference points falling into the grid and the signal vector corresponding to each reference point.

13. The indoor positioning system based on the signal three-dimensional fingerprint library according to claim 12, characterized in that: The interpolation module calculates the signal data at a certain grid p outside the reference grid according to the following formula: Where d(p,i) is the straight-line distance between the center point of grid p and the center point of reference grid i, V i is the signal value vector of reference grid i; after the signal data of all grids are calculated according to the formula, the construction of the three-dimensional fingerprint library is completed.

14. The indoor positioning system based on the signal three-dimensional fingerprint library according to claim 9, characterized in that: The three-dimensional fingerprint library update module fixes signal monitoring tags at several positions in the target area and records the true value coordinates p of the signal monitoring tag positions. i =(x i ,y i ,z i ), continuously receives signal data from each signal transmitter AP, and calculates the actual position p' through the three-dimensional fingerprint library i =(x' i ,y' i ,z' i ), if the distance between the calculated result and the true value is greater than the positioning accuracy requirement, that is, d(p i ,p' i )>d thr , then the three-dimensional fingerprint library is updated.

15. The indoor positioning system based on the signal three-dimensional fingerprint library according to claim 9, characterized in that: It also includes a data collection path update module, which is used to plan the data collection path for updating the three-dimensional fingerprint library according to the historical indoor positioning trajectory data, re-collect data according to the updated data collection path and realize the update of the three-dimensional fingerprint library.

16. The indoor positioning system based on the signal three-dimensional fingerprint library according to claim 15, characterized in that: The data acquisition path update module plans the data acquisition path updated by the three-dimensional fingerprint library according to the historical indoor positioning trajectory data, including: Define the sampling step size; Calculate the hottest positioning grid in the sampling step grid: the sampling step grid is a grid with the sampling step as the side length, the positioning grid is consistent with the constructed three-dimensional fingerprint library, calculate the number of positioning grids contained in a sampling step grid, and find the positioning grid with the most historical trajectory points in the corresponding number of positioning grids, that is, the hottest positioning grid; if no historical trajectory points fall into a sampling step grid, the positioning grid at the center of the corresponding sampling step grid is used as the hottest positioning grid; Path planning: The hottest positioning grid in each sampling step grid is used as the waypoint, and the data collection path is obtained using the shortest path algorithm passing through the specified intermediate point.

17. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the indoor positioning method based on a signal three-dimensional fingerprint library as claimed in any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the indoor positioning method based on the signal three-dimensional fingerprint library as described in any one of claims 1 to 8 is implemented.

Images