Fingerprint database and multi-sensor fused indoor positioning method, system and equipment

Abstract

The invention discloses a fingerprint database and multi-sensor fused indoor positioning method, system and device, and relates to the technical field of indoor positioning. The method comprises the following steps: acquiring a positioning result of a to-be-detected target in a fingerprint database; sensor data of a sensor network are obtained, forward information of a to-be-measured target is calculated based on the sensor data, and the sensor network at least comprises a gyroscope, a magnetic sensor and an acceleration sensor; calculating to obtain a course angle based on the sensor data, and calculating to obtain position information of the to-be-measured target based on the forward information and the course angle; and determining a target positioning result of the to-be-detected target based on the positioning result and the position information. By implementing the technical scheme provided by the invention, the indoor positioning precision can be improved.

Description

Technical Field

[0001] The present application relates to the field of indoor positioning technology, and in particular to an indoor positioning method, system and device based on fingerprint library and multi-sensor fusion. Background Art

[0002] Indoor positioning technology makes up for the shortcomings of satellite positioning indoors and is widely used in shopping mall navigation, hospital management, industrial safety, elderly care and other fields. It provides precise location services, optimizes navigation experience, improves efficiency and safety, and becomes an important cornerstone of digital transformation.

[0003] Indoor positioning technology is mainly divided into signal-based positioning methods or sensor-based positioning methods. However, in complex indoor structures, such as multi-story buildings or large shopping malls, relying on a single signal positioning method or sensor positioning, especially during long-term navigation, will cause positioning offset due to error accumulation problems, resulting in low indoor positioning accuracy. Summary of the invention

[0004] The present application provides a fingerprint library and multi-sensor fusion indoor positioning method, system and device, which can improve indoor positioning accuracy.

[0005] In a first aspect, the present application provides an indoor positioning method using a fingerprint library and multi-sensor fusion, the method comprising: Obtain the positioning result of the target to be tested in the fingerprint database; Acquire sensor data of a sensor network, and calculate the forward information of the target to be measured based on the sensor data, wherein the sensor network includes at least a gyroscope, a magnetic sensor, and an acceleration sensor; Calculating a heading angle based on the sensor data, and calculating position information of the target to be measured based on the forward information and the heading angle; A target positioning result of the target to be measured is determined based on the positioning result and the position information.

[0006] By adopting the above technical solution, the rough absolute position of the target device is first obtained by using the WiFi signal fingerprint matching algorithm, and then the data of the gyroscope, magnetometer and accelerometer are collected through the multi-sensor network installed on the target device. The target's forward distance and heading angle are calculated based on these sensor data to determine the target's relative position information. Finally, the fingerprint positioning result and the relative position calculated by the multi-sensor are fused, and the unscented Kalman filter algorithm is used to combine the advantages of the two positioning results to output the fused accurate target position. The advantages of WiFi signal fingerprint positioning in providing absolute position constraints and the advantages of multi-sensor PDR algorithm in providing continuous relative position are fully utilized. Through the coordination and data fusion of the two, the positioning system can not only use fingerprint positioning to obtain the initial position and correct the position drift, but also rely on PDR to provide continuous positioning state prediction, which significantly improves the indoor positioning accuracy.

[0007] Optionally, before obtaining the positioning result of the target to be measured in the fingerprint database, the method further includes: Grid the target indoor area to obtain multiple grid points; Taking each of the grid points as a reference point, and collecting signals at each of the reference points to obtain a signal strength corresponding to each of the reference points; A fingerprint database is constructed based on the signal strength corresponding to each of the reference points.

[0008] By adopting the above technical solution, the sampling workload can be effectively reduced by gridding the area for sampling. At the same time, it can represent the distribution of WiFi signals in the grid area. The constructed fingerprint database contains the WiFi hotspot signal characteristics of the target area. When the target device needs to be located, the measured online WiFi signal can be matched with the fingerprint information in the database to achieve efficient indoor positioning.

[0009] Optionally, obtaining the positioning result of the target to be measured in the fingerprint database includes: Collect WiFi signals of the target to be tested, and perform data preprocessing on the WiFi signals; Matching the preprocessed WiFi signal of the target to be detected with the fingerprint database to obtain a matching result; The positioning result of the target to be detected in the fingerprint database is determined based on the matching result.

[0010] By adopting the above technical solution, the collected signal can be preprocessed to filter out noise and improve the effective signal. Then the WiFi signal is matched with the fingerprint database to quickly and efficiently determine the similarity of the signal, and accurate positioning can be achieved using the fingerprint database.

[0011] Optionally, the calculating the forward information of the target to be detected based on the sensor data includes: Acquire the Y-axis acceleration collected by the acceleration sensor in the sensor data, wherein the Y-axis acceleration includes a maximum acceleration and a minimum acceleration; Substituting the maximum acceleration and the minimum acceleration into a preset first calculation formula to obtain the step length of the target to be measured, and using the step length as the forward information; The first calculation formula is: Among them, L is the step size, K is the step size model coefficient, a max is the maximum acceleration, a min is the minimum acceleration.

[0012] By adopting the above technical solution, by detecting the acceleration peak and valley characteristics of the accelerometer in the Y-axis direction during the walking process of the target, the maximum and minimum accelerations of the step cycle are extracted, and these two accelerations are brought into the first calculation formula, the step length of the target can be estimated in real time.

[0013] Optionally, the calculating the heading angle based on the sensor data includes: Acquire magnetic data collected by the magnetic sensor, acceleration data collected by the acceleration sensor, and gyroscope data collected by the gyroscope from the sensor data; Calculating a pitch angle and a yaw angle based on the acceleration data and the magnetic data; The heading angle is determined based on the magnetic data, the pitch and yaw angles, and the gyroscope data.

[0014] By adopting the above technical solution, the advantages of the magnetometer, accelerometer and gyroscope are comprehensively utilized to jointly solve the heading angle. First, the pitch angle and yaw angle of the device are calculated according to the data of the accelerometer and magnetometer. Then, these two angles are used as the initial azimuth, and the drift of the gyroscope is corrected by combining the magnetometer digital data. The azimuth angle is integrated through the gyroscope data to obtain the accurate heading angle.

[0015] Optionally, determining the heading angle based on the magnetic data, the pitch angle, the yaw angle, and the gyroscope data includes: Calculate an initial heading angle based on the magnetic data and the pitch angle and yaw angle; Calculate the rotation angles around the X-axis, Y-axis and Z-axis based on the gyroscope data; The rotation angle and the initial heading angle are fused to obtain the fused heading angle.

[0016] By adopting the above technical solution, the advantages of the magnetometer in providing accurate initial orientation and the gyroscope in continuously capturing rotational motion are fully utilized. By organically combining the two, real-time updating of the heading angle can be achieved, avoiding the error accumulation of relying solely on a single sensor.

[0017] Optionally, determining a target positioning result of the target to be measured based on the positioning result and the position information includes: The positioning result and the position information are fused based on an unscented Kalman filter, and the output result of the unscented Kalman filter is used as the target positioning result of the target to be measured.

[0018] By adopting the above technical solution, the unscented Kalman filter model is adopted, the fingerprint positioning result is used as the observation quantity, and the continuous position calculated by the inertial system is used as the state quantity. In the recursive filtering process, the state prediction and measurement update are repeated, and the optimal target positioning result after fusion is output in real time, providing high-precision and seamless positioning effect.

[0019] In a second aspect of the present application, a fingerprint library and a multi-sensor fusion indoor positioning system is provided, the system comprising: A positioning result acquisition module is used to obtain the positioning result of the target to be measured in the fingerprint database; A forward information acquisition module, used to acquire sensor data of a sensor network, and calculate the forward information of the target to be measured based on the sensor data, wherein the sensor network includes at least a gyroscope, a magnetic sensor, and an acceleration sensor; A position information calculation module, used to calculate the heading angle based on the sensor data, and calculate the position information of the target to be measured based on the forward information and the heading angle; A positioning result determination module is used to determine a target positioning result based on the positioning result and the position information.

[0020] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0021] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0022] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: This application first uses the WiFi signal fingerprint matching algorithm to obtain the rough absolute position of the target device, and then collects the data of the gyroscope, magnetometer and accelerometer through the multi-sensor network installed on the target device, and calculates the target's forward distance and heading angle based on these sensor data to determine the target's relative position information. Finally, the fingerprint positioning result and the relative position calculated by the multi-sensor are fused, and the unscented Kalman filter algorithm is used to combine the advantages of the two positioning results to output the fused accurate target position. The advantages of WiFi signal fingerprint positioning in providing absolute position constraints and the advantages of multi-sensor PDR algorithm in providing continuous relative position are fully utilized. Through the coordination and data fusion of the two, the positioning system can not only use fingerprint positioning to obtain the initial position and correct the position drift, but also rely on PDR to provide continuous positioning state prediction, which significantly improves the indoor positioning accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of an indoor positioning method using a fingerprint library and multi-sensor fusion provided in an embodiment of the present application; Figure 2 It is a schematic diagram of the principle of a Kalman filter optimization heading angle algorithm provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the principle of indoor positioning provided by an embodiment of the present application; Figure 4 It is a module schematic diagram of a fingerprint library and a multi-sensor fusion indoor positioning system provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0024] Description of reference numerals: 500, electronic device; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. DETAILED DESCRIPTION

[0025] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0027] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0028] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0029] Please refer to Figure 1 , a flowchart of an indoor positioning method of a fingerprint library and multi-sensor fusion is proposed. The method can be implemented by a computer program, can be implemented by a single-chip microcomputer, and can also be run on an indoor positioning system of a fingerprint library and multi-sensor fusion. The computer program can be integrated in a computer device, or can be run as an independent tool application. Specifically, the method includes steps 10 to 40, and the above steps are as follows: As an optional embodiment, before obtaining the positioning result of the target to be detected in the fingerprint database, a fingerprint database establishment process may also be included, which specifically includes the following steps: Step 001: Divide the target indoor area into grids to obtain multiple grid points.

[0030] Specifically, in order to construct a fingerprint database, the target indoor area needs to be processed first. The embodiment of the present application adopts a grid division method to divide the target area into multiple grids, and the center point of each grid is used as a sampling reference point. This is because for indoor environments, considering the propagation law of WiFi signals, the signals in the same grid area can be regarded as similar. The size of the grid is set according to the actual situation, usually set to about 1 meter × 1 meter, so as to obtain multiple grid points.

[0031] Step 002: Take each grid point as a reference point, and collect signals from each reference point to obtain the signal strength corresponding to each reference point.

[0032] Specifically, after completing the grid division of the indoor area, it is necessary to collect WiFi signals at the center point of each grid to build a fingerprint database. The center point of the grid is selected as the reference point because it can represent the distribution of WiFi signals in the corresponding grid area. For each reference point, a signal acquisition device (such as a smart phone) is used to collect signals from multiple WiFi hotspots (routers) multiple times, and the MAC address and signal strength value of each WiFi hotspot at each reference point are recorded. Repeat this process until enough valid signal samples are collected at each reference point. After preprocessing such as removing outliers, the average signal strength value of each WiFi hotspot at each reference point can be calculated.

[0033] Step 003: Construct a fingerprint database based on the signal strength corresponding to each reference point.

[0034] Specifically, in order to achieve indoor positioning based on WiFi signals, it is necessary to build a fingerprint database containing the WiFi signal characteristics of the entire target area. After obtaining the WiFi signal strength data of all reference points, the fingerprint database can be built. Specifically, the location coordinates of each reference point are combined with the MAC addresses and corresponding signal strength values ​​of the multiple WiFi hotspots it covers to form a feature vector as the fingerprint feature of the reference point. Then the feature vectors of all reference points are combined and stored in the database, and the reference points are indexed by the MAC address to form a fingerprint database. When the device to be located needs to be located, the WiFi hotspots and signal strengths scanned by it are first extracted to form an online signal vector. Then it is matched and compared with the fingerprint feature vectors of all reference points in the database. Usually, a machine learning algorithm is used to calculate the similarity between vectors, and finally determine which reference point vector the online signal vector is most similar to, and it can be considered that the device to be located is close to the position of this reference point.

[0035] Step 10: Obtain the positioning result of the target to be tested in the fingerprint database.

[0036] In the embodiment of the present application, the target to be detected refers to a mobile device or a person that needs to be located.

[0037] The fingerprint database in the embodiment of the present application refers to a database established by collecting WiFi signal features in the target area, which is used to match the signal of the target to be detected for positioning.

[0038] In the embodiment of the present application, the positioning result refers to the position information of the target to be measured obtained by matching the fingerprint database.

[0039] Specifically, in order to improve the accuracy of indoor positioning, it is necessary to first determine the rough position of the target to be measured through the fingerprint positioning algorithm. Specifically, the target area is first divided, the WiFi signal is collected at each grid point, and a fingerprint database containing the WiFi signal characteristics of each grid point is constructed. When positioning, the WiFi signal of the device to be located is first collected, and pre-processed by denoising and filtering. Then the processed signal is matched with the signal in the fingerprint database, and the most similar reference point is determined by the matching algorithm, that is, the positioning result of the target to be measured in the fingerprint database. This is because the indoor WiFi signal is relatively stable, and the fingerprint database can provide the approximate location information of the target to be measured.

[0040] Based on the above embodiment, as an optional embodiment, the step of obtaining the positioning result of the target to be detected in the fingerprint database may further include the following steps: Step 101: Collect the WiFi signal of the target to be measured, and perform data preprocessing on the WiFi signal.

[0041] Specifically, after the fingerprint database is established, when a target needs to be located, the first step is to collect the WiFi signal of the environment where the target is located. The WiFi module built into the mobile device (such as a mobile phone) of the target can be used to scan and obtain the signal strength of the surrounding WiFi hotspots. In order to improve the matching and positioning effect, the collected original WiFi signal needs to be preprocessed. First, remove the records with a signal strength of 0 to filter out unavailable WiFi information. Then take the average of the signal strengths of multiple hotspots to reduce the impact of instantaneous signal fluctuations. Then perform smoothing filtering, such as using Kalman filtering to smooth the signal value. Finally, other operations such as signal calibration and coordinate transformation can be performed to obtain a processed online signal fingerprint representing the distribution of WiFi signals at the target location.

[0042] Step 102: Match the preprocessed WiFi signal of the target to be tested with the fingerprint database to obtain a matching result.

[0043] Specifically, after preprocessing the collected target WiFi signal, the next step is to match it with the pre-built fingerprint database to determine the location of the target. During the matching process, the pre-processed online WiFi signal fingerprint is compared with all reference point fingerprints in the database in turn, and the similarity or distance measurement between the signal feature vectors is calculated and used as the matching result.

[0044] Step 103: Determine the positioning result of the target to be detected in the fingerprint database based on the matching result.

[0045] Specifically, the fingerprint matching result gives the reference point that is closest to the WiFi signal of the target to be tested, that is, the reference point with the highest similarity. Since the position coordinates of each reference point are known when the fingerprint database is constructed, the coordinates of the reference point can be used as the positioning result of the target to be tested in the fingerprint database according to the most similar reference point given in the matching result. This is equivalent to completing the fingerprint positioning process and giving a rough estimate of the target's location. The coordinates of this positioning result may not be highly accurate, but it provides a rough prior information of the target's location.

[0046] Step 20: Acquire sensor data of the sensor network, and calculate the forward information of the target to be measured based on the sensor data. The sensor network includes at least a gyroscope, a magnetic sensor, and an acceleration sensor.

[0047] Specifically, in order to achieve more accurate indoor positioning, the sensor network of the embodiment of the present application adopts a multi-sensor fusion solution in the PDR technology, which requires the integration of a multi-sensor module including a gyroscope, a magnetic sensor, and an acceleration sensor on a mobile device. During the positioning process, the acceleration sensor is used to collect three-axis linear acceleration data, and the user's step frequency, stride and other forward information can be calculated, that is, to determine how far the user has walked in one step, and thus calculate the relative displacement. In addition, the three-axis gyroscope can measure angular velocity, and the angle of rotation of the device in three directions can be obtained by integration. The magnetic sensor measures the earth's magnetic field and can obtain azimuth reference information. Combining these sensor data, the direction of movement and relative displacement of the device can be accurately determined. Compared with fingerprint positioning, it can provide continuous positioning data, and the two complement each other to improve positioning accuracy and continuity.

[0048] Based on the above embodiment, as an optional embodiment, the step of calculating the forward information of the target to be detected based on the sensor data may further include the following steps: Step 201: Acquire the Y-axis acceleration collected by the acceleration sensor in the sensor data, where the Y-axis acceleration includes the maximum acceleration and the minimum acceleration.

[0049] Step 202: Substitute the maximum acceleration and the minimum acceleration into a preset first calculation formula to obtain the step length of the target to be measured, and use the step length as the forward information.

[0050] Specifically, in a multi-sensor fusion positioning system, in order to calculate the user's forward distance, a key is to obtain the user's step length information. The embodiment of the present application adopts a step length estimation method based on an acceleration sensor. The acceleration sensor is installed on a mobile device on the user's body and can detect the acceleration change of the user's body in the vertical direction of the Y axis when the user walks. When the user completes a complete step cycle, the acceleration signal will fluctuate periodically on the Y axis, and the corresponding maximum acceleration and minimum acceleration can characterize the acceleration characteristics of a step. The system extracts the acceleration component in the Y-axis direction (vertically downward) from the collected data of the acceleration sensor, detects its peaks and troughs, and obtains the maximum acceleration a in the step cycle. max and minimum acceleration a min Then add a max and a min Substituting into the first calculation formula, we can estimate the step length L of each step of the user. The first calculation formula is: Among them, L is the step size, K is the step size model coefficient, a max is the maximum acceleration, a min The first calculation formula establishes the relationship between the step length and the peak-to-valley difference of acceleration, and k is the step length model coefficient, which is obtained by using the least squares method through multiple sets of experimental results. The calculated step length is the distance the user advances in the step cycle, that is, the user's forward information.

[0051] Step 30: Calculate the heading angle based on the sensor data, and calculate the position information of the target to be measured based on the forward information and the heading angle.

[0052] Specifically, after obtaining the target's forward information, that is, the step length, another key is to determine the user's walking direction, that is, the heading angle. The three-axis gyroscope can measure the angular velocity of the device in three-dimensional space. After processing, the azimuth change of the device at different times can be obtained, thereby calculating the azimuth integral within a time period, that is, the heading angle, and correcting the azimuth drift in conjunction with the magnetometer data. After obtaining the step length and heading angle of the user's movement, the user's real-time motion trajectory and current relative position can be calculated based on vector superposition. Assuming that the user's starting position is known, then for each step, the user's displacement distance can be determined based on the step length, and the direction of displacement can be determined in combination with the heading angle. The position information of the target to be measured can be updated through vector superposition, and the user's continuous motion trajectory can be obtained as time steps.

[0053] Based on the above embodiment, as an optional embodiment, the step of calculating the heading angle based on the sensor data may further include the following steps: Step 301: acquiring magnetic data collected by a magnetic sensor, acceleration data collected by an acceleration sensor, and gyroscope data collected by a gyroscope from sensor data.

[0054] Specifically, in the multi-sensor fusion indoor positioning system, magnetometers, accelerometers and gyroscopes are three key types of motion sensors used to collect different physical signals describing the motion state of the device. Among them: the magnetometer measures the strength and direction of the magnetic field in the environment, and can provide an absolute direction reference for correcting the direction angle calculation. The accelerometer measures the specific force generated during the movement, and can calculate parameters such as motion acceleration, velocity, and displacement, while the gyroscope measures the angular velocity of each axis, and can calculate the azimuth and direction changes of the device.

[0055] Step 302: Calculate the pitch angle and yaw angle based on the acceleration data and the magnetic data.

[0056] Specifically, the pitch angle and yaw angle are calculated by combining the data obtained by the magnetic sensor and the acceleration sensor. The calculation formula is as follows: Where θ is the pitch angle, is the yaw angle, A x , A y and A z The acceleration sensors measure the acceleration information on the x, y and z axes respectively, and g is the acceleration due to gravity.

[0057] Step 303: Determine the heading angle based on the magnetic data, the pitch angle, the yaw angle and the gyroscope data.

[0058] Specifically, the initial heading angle ω is calculated based on the magnetic data and the pitch angle and yaw angle m for: Among them, ω is the magnetic field information on each axis obtained by the sensor, through the heading angle ω m Combined with magnetic declination α d Correction is performed to calculate the azimuth information ω of the positive direction of the Y axis n , the formula is as follows: n =ω m +α d ; The rotation angles around the X-axis, Y-axis and Z-axis are calculated based on the gyroscope data. The formula is as follows: β = ξ·δt, where β is the angle of rotation of the sensor around the corresponding axis within δt, ξ is the angular velocity within δt, and δt is the time difference between the current moment and the previous moment obtained by the gyroscope. The rotation angle and the initial heading angle are fused to obtain the fused heading angle ω k+1 :ω k+1 =ω k ±ξ·δt+V k ·δt; where ω k+1 is the fused heading angle, v k is the increment of the angular velocity integral, v kThe Kalman filter is used to fuse the angles obtained by the magnetic field, gyroscope and accelerometer to reduce the cumulative error and improve the heading angle accuracy.

[0059] See also Figure 2 , is a schematic diagram of a Kalman filter optimization heading angle algorithm provided in an embodiment of the present application; like Figure 2 As shown, the magnetic data collected by the magnetic sensor, the acceleration data collected by the acceleration sensor, and the gyroscope data collected by the gyroscope are obtained from the sensor data, and then the pitch angle and the yaw angle are calculated according to the acceleration data and the magnetic data, and then the initial heading angle is calculated according to the pitch angle and the yaw angle, and the rotation angle around the X-axis, Y-axis, and Z-axis is calculated according to the gyroscope data, and the rotation angle and the initial heading angle are fused based on the Kalman filter to obtain the fused heading angle.

[0060] Step 40: Determine the target positioning result of the target to be measured based on the positioning result and the position information.

[0061] Specifically, the positioning result refers to the positioning result of the target to be measured in the fingerprint library obtained by matching the WiFi fingerprint positioning algorithm; the position information refers to the azimuth and displacement information of the device to be located relative to the initial point calculated based on the PDR multi-sensor algorithm.

[0062] It should be noted that the Pedestrian Dead Reckoning (PDR) algorithm uses sensor data such as accelerometers, gyroscopes, and magnetometers to track the user's gait and calculate their position. It can be positioned indoors without relying on signal coverage, and the positioning accuracy is high. However, the PDR algorithm is easily affected by the accumulation of sensor errors, resulting in a decrease in accuracy when used for a long time, and further improvement and optimization are still needed. In addition, the fingerprint library algorithm has been widely used and studied in the field of indoor positioning. There are many scenarios that meet the conditions of use, and the hardware cost of implementation is low. Existing equipment can be used to achieve location recognition by establishing and comparing fingerprint databases. However, this method requires a large number of fingerprint databases to support it, and may be affected by the quality and update frequency of the database.

[0063] Therefore, the embodiment of the present application proposes an indoor positioning method based on a fingerprint library and a multi-sensor fusion fingerprint library and multi-sensor fusion based on a fingerprint library and a PDR, and uses an unscented Kalman filter algorithm for fusion to achieve real-time high-precision positioning.

[0064] Specifically, after obtaining the fingerprint positioning result of the target to be positioned and the relative position information calculated by PDR, in order to fully integrate the advantages of both and improve the positioning accuracy, the embodiment of the present application adopts a multi-sensor data fusion method of unscented Kalman filtering.

[0065] The position information obtained by the PDR algorithm is used as the parameter of the state equation, and the model is as follows: Among them, x k and k is the position information of the target to be measured calculated by the PDR algorithm at time k, L is the step length of the target to be measured at time k, ω k is the heading angle information at time k, W k-1 is the system process noise.

[0066] The WiFi positioning information and the fused heading angle are used as parameters of the observation equation. The model is as follows: Among them, x k and k is the positioning result of the target under test at the time k, ω k ,ω k-1 is the heading angle information at time k and time k-1, ω k is the heading angle change at time k, V k-1 Observe the noise of the system.

[0067] Use unscented Kalman filter for fusion, and use the output of unscented Kalman filter as the positioning result. The unscented Kalman filter algorithm process is as follows: Calculate 2n+1 sampling points, the formula is as follows: Where n is the system state dimension, λ = γ 2 (n+κ)-n is the parameter for obtaining the sampling points. The discreteness of the sampling points is determined by the value of γ. κ is the parameter to be selected, and P is the state error covariance matrix.

[0068] Calculate the corresponding weights of the sampling points, the formula is as follows: Wherein, the subscripts m and c are the mean and covariance, respectively.

[0069] The prediction update equation is as follows: Among them, Q k is the process noise covariance matrix.

[0070] The observation update equation is as follows: Among them, R kis the measurement noise covariance matrix.

[0071] The result of the unscented Kalman filter output is used as the target positioning result of the current target to be measured. When the next step of positioning is performed, pre-positioning is performed according to the step heading angle. If the positioning result enters or leaves the range of the fingerprint database compared with the positioning result of the previous step, the positioning result of the fingerprint database is used as the observation input of this step.

[0072] See also Figure 3 , is a schematic diagram of the principle of indoor positioning provided by an embodiment of the present application; like Figure 3 As shown, first, the signal of the target to be measured is received online, and the signal is matched with the fingerprint database to obtain the positioning result of the target to be measured in the fingerprint database, then the relevant sensor data of the target to be measured is obtained from the sensor network, and the positioning is performed based on the PDR to obtain the position information, and finally the positioning result of the fingerprint database and the position information located by the PDR are fused based on the unscented Kalman filter to output the target positioning result.

[0073] See also Figure 4 , is a module schematic diagram of a fingerprint library and a multi-sensor fusion indoor positioning system provided in an embodiment of the present application. The fingerprint library and the multi-sensor fusion indoor positioning system may include: a positioning result acquisition module, a forward information acquisition module, a position information calculation module and a positioning result determination module, wherein: A positioning result acquisition module is used to obtain the positioning result of the target to be measured in the fingerprint database; A forward information acquisition module, used to acquire sensor data of a sensor network, and calculate the forward information of the target to be measured based on the sensor data, wherein the sensor network includes at least a gyroscope, a magnetic sensor, and an acceleration sensor; A position information calculation module, used to calculate the heading angle based on the sensor data, and calculate the position information of the target to be measured based on the forward information and the heading angle; A positioning result determination module is used to determine a target positioning result based on the positioning result and the position information.

[0074] Optionally, the positioning result acquisition module is also used to divide the target indoor area into grids to obtain multiple grid points; use each of the grid points as a reference point, and collect signals from each of the reference points to obtain the signal strength corresponding to each of the reference points; and build a fingerprint database based on the signal strength corresponding to each of the reference points.

[0075] Optionally, the positioning result acquisition module is also used to collect the WiFi signal of the target to be measured and perform data preprocessing on the WiFi signal; match the preprocessed WiFi signal of the target to be measured with the fingerprint database to obtain a matching result; and determine the positioning result of the target to be measured in the fingerprint database based on the matching result.

[0076] Optionally, the forward information acquisition module is further used to obtain the Y-axis acceleration collected by the acceleration sensor in the sensor data, where the Y-axis acceleration includes a maximum acceleration and a minimum acceleration; Substitute the maximum acceleration and the minimum acceleration into a preset first calculation formula to obtain the step length of the target to be measured, and use the step length as the forward information; the first calculation formula is: Among them, L is the step size, K is the step size model coefficient, a max is the maximum acceleration, a min is the minimum acceleration.

[0077] Optionally, the position information calculation module is further used to obtain magnetic data collected by the magnetic sensor, acceleration data collected by the acceleration sensor, and gyroscope data collected by the gyroscope in the sensor data; and calculate the pitch angle and yaw angle based on the acceleration data and the magnetic data; The heading angle is determined based on the magnetic data, the pitch and yaw angles, and the gyroscope data.

[0078] Optionally, the position information calculation module is also used to calculate the initial heading angle based on the magnetic data and the pitch angle and yaw angle; calculate the rotation angle around the X-axis, Y-axis and Z-axis based on the gyroscope data; fuse the rotation angle and the initial heading angle to obtain the fused heading angle. Optionally, the positioning result determination module is also used to fuse the positioning result and the position information based on an unscented Kalman filter, and use the output result of the unscented Kalman filter as the target positioning result of the target to be measured.

[0079] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0080] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a fingerprint library and a multi-sensor fusion indoor positioning method of the above-mentioned embodiment. The specific execution process can be found in the specific description of the above-mentioned embodiment, which will not be repeated here.

[0081] Please refer to Figure 5 The application also discloses an electronic device. Figure 5 The electronic device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0082] The communication bus 502 is used to realize the connection and communication between these components.

[0083] The user interface 503 may include a display screen (Display) and a camera (Camera), and the optional user interface 503 may also include a standard wired interface and a wireless interface.

[0084] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0085] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0086] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. Refer to Figure 5 The memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a fingerprint library and a multi-sensor fusion indoor positioning method.

[0087] exist Figure 5 In the electronic device 500 shown, the user interface 503 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 501 can be used to call the application program of the indoor positioning method of a fingerprint library and multi-sensor fusion stored in the memory 505. When executed by one or more processors 501, the electronic device 500 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0088] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0092] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0093] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0094] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A fingerprint library and multi-sensor fusion indoor positioning method, characterized in that: The method comprises: Obtain the positioning result of the target to be tested in the fingerprint database; Acquire sensor data of a sensor network, and calculate the forward information of the target to be measured based on the sensor data, wherein the sensor network includes at least a gyroscope, a magnetic sensor, and an acceleration sensor; Calculating a heading angle based on the sensor data, and calculating position information of the target to be measured based on the forward information and the heading angle; A target positioning result of the target to be measured is determined based on the positioning result and the position information.

2. The indoor positioning method based on fingerprint library and multi-sensor fusion according to claim 1 is characterized in that: Before obtaining the positioning result of the target to be measured in the fingerprint database, the method further includes: Grid the target indoor area to obtain multiple grid points; Taking each of the grid points as a reference point, and collecting signals at each of the reference points to obtain a signal strength corresponding to each of the reference points; A fingerprint database is constructed based on the signal strength corresponding to each of the reference points.

3. The indoor positioning method based on fingerprint library and multi-sensor fusion according to claim 1 is characterized in that: The obtaining of the positioning result of the target to be measured in the fingerprint database includes: Collect WiFi signals of the target to be tested, and perform data preprocessing on the WiFi signals; Matching the preprocessed WiFi signal of the target to be detected with the fingerprint database to obtain a matching result; The positioning result of the target to be detected in the fingerprint database is determined based on the matching result.

4. The indoor positioning method based on fingerprint library and multi-sensor fusion according to claim 1, characterized in that: The calculating the forward information of the target to be detected based on the sensor data includes: Acquire the Y-axis acceleration collected by the acceleration sensor in the sensor data, wherein the Y-axis acceleration includes a maximum acceleration and a minimum acceleration; Substituting the maximum acceleration and the minimum acceleration into a preset first calculation formula to obtain the step length of the target to be measured, and using the step length as the forward information; The first calculation formula is: Among them, L is the step size, K is the step size model coefficient, a max is the maximum acceleration, a min is the minimum acceleration.

5. The indoor positioning method based on fingerprint library and multi-sensor fusion according to claim 1, characterized in that: The calculating the heading angle based on the sensor data includes: Acquire magnetic data collected by the magnetic sensor, acceleration data collected by the acceleration sensor, and gyroscope data collected by the gyroscope from the sensor data; Calculating a pitch angle and a yaw angle based on the acceleration data and the magnetic data; The heading angle is determined based on the magnetic data, the pitch and yaw angles, and the gyroscope data.

6. The indoor positioning method based on fingerprint database and multi-sensor fusion according to claim 5 is characterized in that: The determining the heading angle based on the magnetic data, the pitch angle, the yaw angle and the gyroscope data comprises: Calculate an initial heading angle based on the magnetic data and the pitch angle and yaw angle; Calculate the rotation angles around the X-axis, Y-axis and Z-axis based on the gyroscope data; The rotation angle and the initial heading angle are fused to obtain the fused heading angle.

7. The indoor positioning method based on fingerprint database and multi-sensor fusion according to claim 1, characterized in that: The determining the target positioning result of the target to be measured based on the positioning result and the position information includes: The positioning result and the position information are fused based on an unscented Kalman filter, and the output result of the unscented Kalman filter is used as the target positioning result of the target to be measured.

8. An indoor positioning system based on fingerprint database and multi-sensor fusion, characterized in that: The system comprises: A positioning result acquisition module is used to obtain the positioning result of the target to be measured in the fingerprint database; A forward information acquisition module, used to acquire sensor data of a sensor network, and calculate the forward information of the target to be measured based on the sensor data, wherein the sensor network includes at least a gyroscope, a magnetic sensor, and an acceleration sensor; A position information calculation module, used to calculate the heading angle based on the sensor data, and calculate the position information of the target to be measured based on the forward information and the heading angle; A positioning result determination module is used to determine a target positioning result based on the positioning result and the position information.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

Images