CN109413578B - Indoor positioning method based on fusion of WIFI and PDR - Google Patents

Abstract

The invention discloses an indoor positioning method based on fusion of WIFI and PDR, relates to the technical field of indoor positioning of WIFI signals and pedestrian dead reckoning, and solves the technical problem of providing an indoor positioning method with high measurement precision, which comprises the following steps: (1) establishing a WIFI offline fingerprint database; (2) clustering the training samples to obtain clustering samples and corresponding categories; (3) obtaining a positioning coordinate through a weighted K nearest neighbor algorithm; (4) updating the state and the position by fusing PDR positioning; (5) using the fusion result as a correction source for the PDR; (6) and acquiring a correction factor correction PDR result through the evaluation parameters. The method shortens the WIFI positioning time, improves the positioning accuracy, has the characteristics of high positioning accuracy and low software computation amount, and meets the real-time positioning requirement on the premise of ensuring the positioning accuracy.

Description

Indoor positioning method based on fusion of WIFI and PDR

Technical Field

The invention relates to the technical field of indoor positioning of WIFI signals and pedestrian dead reckoning, in particular to an indoor positioning method based on fusion of WIFI and PDR.

Background

Statistically, 80% of a person's lifetime stays indoors, but GPS cannot be operated indoors. Industries such as trip navigation, intelligent manufacturing, intelligent service and the like also wait for people to review the value of indoor positions again. Indoor positioning technology has also become more and more important in recent years as a key to open an indoor location service door. The current mature indoor positioning comprises technologies such as ultrasonic positioning, UWB positioning, inertial navigation positioning, Radio Frequency Identification (RFID) positioning, Bluetooth positioning and WIFI positioning. Compared with other indoor wireless positioning technologies, WIFI has unique advantages, WIFI hotspots are distributed in all corners and building areas of a city, due to the ubiquitous nature of the WIFI, the deployment cost is low, hardware is easy to install, the WIFI is easy to combine with a smart phone for positioning, the coverage area is wide, the positioning accuracy is high, the WIFI is easy to achieve, and the WIFI hotspot is a research hotspot of the indoor positioning technology rapidly.

In the positioning process by utilizing the WIFI fingerprint, due to the complex indoor environment, the WIFI signal is easy to interfere, the signal intensity is easy to generate large-amplitude jump, and an area which cannot be covered by the WIFI signal exists, so that the WIFI positioning deviation is large. Therefore, indoor positioning by using the WIFI technology alone cannot meet the needs of people.

Utilize intelligent terminal to carry out indoor location in-process, because motion sensor such as gyroscope, acceleration sensor, electron compass are generally furnished with to mobile terminal, this makes mobile terminal's inertial navigation technique have better popularization nature, has advantages such as difficult environmental impact, stability height. However, the electronic compass is easily interfered by the environment, so that the course angle is deviated, the walking distance error is caused by the gait judgment error and the step length estimation error, the inertial system cannot be accurately positioned for a long time due to the accumulated error, and how to effectively eliminate the accumulated error becomes the key for solving the problem.

The invention CN 106610292A in china discloses an indoor positioning method combining WIFI and dead reckoning (PDR), which obtains an initial position of a target to be measured by using a WIFI positioning subsystem, and after obtaining the initial position of the target to be measured, two positioning subsystems in the system, namely the WIFI positioning subsystem and the PDR positioning subsystem, respectively output the position of the target to be measured. The system adopts a time window utility function to effectively and linearly weight the coordinates output by the WIFI positioning subsystem and the coordinates output by the PDR-based positioning subsystem, and after weighting, processing is carried out through Kalman filtering to obtain global positioning coordinates of mixed WIFI and PDR. The PDR fusion calibration is not considered in the positioning of the method, and due to the instability of WIFI positioning and the accumulated error of PDR positioning, the obtained positioning coordinate precision is still less accurate.

China CN 107302754A discloses a WIFI and PDR based indoor positioning simple method, which judges the motion state of a pedestrian through acceleration measured by an acceleration sensor by setting an initial position and a step length, carries out a WIFI positioning method through RSSI values, collects RSSI values of a plurality of reference nodes, calculates the current position by using an improved algorithm when the RSSI values are detected to exceed a threshold value, and carries out PDR positioning to carry out dead reckoning on the indoor pedestrian to obtain position estimation by taking the current position as an actual position value. The PDR initial position is self-positioning, calibration is not considered, and due to the instability of WIFI positioning and the accumulated error of PDR positioning, the accuracy of the obtained positioning coordinate is still less accurate.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides an indoor positioning method with high measurement precision.

In order to solve the technical problems, the technical scheme adopted by the invention is an indoor positioning method based on the fusion of WIFI and PDR, and the method comprises the following steps:

(1) establishing a WIFI offline fingerprint database: arranging M AP nodes for transmitting WIFI hotspots in a positioning area, dividing the positioning area into N nodes, calculating the actual position of each node, acquiring the RSSI of the signal strength from each AP node in the N nodes to obtain an RSSI training sample, corresponding the RSSI training sample to the actual position of the RSSI training sample, and establishing a fingerprint database I; the fingerprint data set I is represented as:

I＝{(r₁,o₁),(r₂,o₂),...,(r_i,o_i),...,(r_N,o_N)} (1)

wherein, the vector r_i＝(r_i1,r_i2,...,r_iM)∈R^MRepresents RSSI, r from M APs_i1Is RSSI, r from the 1 st WIFI hotspot_iMFor RSSI of Mth AP, position vector o_i＝(x,y)∈R²Is represented by r_iThe position corresponding to the vector, x is the x-axis coordinate of the position, y is the y-axis coordinate of the position, and the RSSI vector r of the RSSI training sample_iAnd a position vector o_iAre known, i ═ 1, 2.. N;

(2) clustering training samples to obtain cluster samplesThis and corresponding categories: clustering the fingerprint database I through a K-means algorithm, and dividing the fingerprint database I into V classes { c₁,c₂,.c_v..c_VEach class center vector is defined as { C }₁,C₂,...C_VDividing RSSI training samples in the fingerprint database into V classes respectively to obtain a clustering sample data set:

L＝{(r₁,c_v1),(r₂,c_v2),...(r_i,c_vi),...,(r_N,c_vN)} (2)，

wherein r is_i＝(r_i1,r_i2,...,r_iM)∈R^MIndicates the RSSI of the M APs,

indicates the V category to which it belongs, c_vClass is trained by p RSSI samples { r_v1,r_v2,...,r_vpComposition of, for all c_vC is obtained by averaging RSSI-like training samples_vClass center vector

(3) Obtaining positioning coordinates through a weighted K nearest neighbor algorithm: acquiring real-time RSSI samples on line, finding out a class most similar to the acquired real-time RSSI samples, predicting attribute values of the real-time RSSI samples acquired on line through K nearest neighbor samples, and weighting positions corresponding to the K RSSI training samples to acquire position coordinates of the RSSI training samples; the real-time RSSI sample obtained online is denoted as T ═ r ((r)_j1,r_j2,...,r_jM) (x, y)), where the real-time RSSI samples r taken online are r_j＝(r_j1,r_j2,...,r_jM)∈R^MThe location vector o ═ (x, y) represents the location information of the online acquired real-time RSSI samples, where the online acquired RSSI vector is known and the location vector (x, y) is unknown;

first, r vector and V class center RSSI vectors { C are calculated₁,C₂,...C_VThe similarity of the r vector, r, is determined_j1,r_j2,...,r_jMRSSI vector with the ith class center

The cosine similarity of (a) is defined as:

similarly, calculating the similarity between the r vector and the RSSI vectors of other categories, and obtaining V cosine similarities { Sim after V times of calculation₁,Sim₂,...,Sim_VIn which the category c corresponding to the maximum similarity is_vIs the most similar class to the r vector;

determining the most similar class c_vK samples r most similar to the r vector_K1,r_K2,.r_Ki..,r_KKSimilarity is respectively Sim_K1,Sim_K2,...,Sim_KK,

(x_K1,y_K1)，(x_K2,y_K2),...,(x_KK,y_KK) Represents the corresponding coordinates, (r)_i1,r₁₂,...r_iM) Representing the most similar sample r selected_KiCorresponding RSSI samples, normalization processing similarity, defining the weight affecting the positioning result as { w }_K1,w_K2,...,w_KK}；

Weighting the sample coordinates to obtain the position coordinates of the on-line acquired RSSI:

x＝w_K1x_K1+w_K2x_K2+...+w_KKx_KK(6)，

y＝w_K1y_K1+w_K2y_K2+...+w_KKy_KK(7)，

(4) updating the state and the position by fusing PDR positioning: system model X for constructing pedestrian walking_kThe initial position coordinates of the PDR positioning are obtained through WIFI positioning, the WIFI positioning and the PDR positioning are fused to obtain an error threshold value, a walking step length is obtained through an acceleration sensor, the orientation angle variation after walking is obtained through a gyroscope arranged in the intelligent terminal, and a measurement equation Z is used_kUpdating the state information and the position information;

the pedestrian walking system model X_kThe following were used:

wherein the number of steps of walking is represented by k, and the position information after walking is represented by x_k,y_kIs represented by theta_kDenotes the azimuth angle after k steps, W_k-1The representation of the noise is represented by,

the step length model is adopted to match the result of the acceleration sensor for the step length average value, the step length is set to be 60cm,

is the orientation angle variation; measurement equation Z_kAs follows:

wherein x is_k,y_kRepresenting a positioning result obtained through WIFI positioning; s_kRepresenting the average pedestrian walking step, obtained from the acceleration sensor results, Δ θ_kThe orientation angle variation of the pedestrian after walking can be acquired through a built-in gyroscope of the intelligent terminal, and theta_kRepresenting the orientation angle of the pedestrian after walking; v_kRepresenting noise.

(5) Using the fusion result as a correction source for the PDR;

setting PDR deviation threshold_pdrAnd if the deviation exceeds a set threshold value,correcting the positioning result to obtain a WIFI and PDR fusion positioning result, and using the WIFI and PDR fusion result as a correction source of the PDR, which is shown in a formula (9);

(6) acquiring a correction factor correction PDR result through the evaluation parameters;

obtaining an evaluation parameter by using data in an interval time period, namely [0, T ] time, wherein the evaluation parameter is shown in formula (13) and formula (14), obtaining a correction factor by the evaluation parameter, and the correction factor is shown in formula (15), and correcting the PDR result, wherein the specific process is as follows:

indicating the positioning result after positioning by fusion,

representing the PDR individual positioning result, wherein the PDR individual positioning result is obtained by the following formula

y₂＝y₁+S₁₂cosθ₁(10)，

x₂＝x₁+S₁₂sin θ₁(11)，

(x₁,x₂) Is PDR initial position, (x)₂,y₂) Coordinates are positioned for the PDR, the displacement S is obtained by matching a step length model with an acceleration sensor, the step length of the pedestrian is 60cm, the direction angle theta is obtained by the sensor and a gyroscope,

the positioning result difference is as follows:

given a [0, K ] time, the accumulated error is expressed as:

the characteristic is used as a correction factor for PDR positioning, and the correction principle is as follows:

if the error C is accumulated_xAnd C_yThe absolute value is E [0, sigma ]₁]The positioning error is negligible and does not need to be corrected;

if the error C is accumulated_xAnd C_yAbsolute value ∈ [ σ ]₁,σ₂]The error evaluation requirement is met, and the positioning result is corrected;

if the error C is accumulated_xAnd C_yAbsolute value ∈ [ σ ]₂,∞]The error evaluation requirement is not met, the WIFI positioning error is large, the fusion positioning is carried out again,

because the PDR positioning result has accumulated error, the correction information is not corresponding, the correction capability is too weak, the correction scale factor alpha is set to represent the proportional relation between the error of the current time and the error of the previous time, and [0, K ] is used for solving the problem of the error of the PDR positioning result]Represents a time period, C_N＝αC_kExpressing a proportional relation, smoothing a correction process in the M time period by the following formula, and solving the problem of mutation of the positioning result:

wherein j is ∈ [1, M ].

Compared with the prior art, the invention has the beneficial effects that:

the K-means algorithm is combined with the K nearest neighbor method, so that the WIFI positioning time is shortened, and the positioning precision is improved. And (5) utilizing the WIFI positioning result and the PDR to fuse and position, and correcting the positioning factor of the system by using the correction factor. The method has the characteristics of high positioning precision and low software computation, and realizes real-time requirements on the premise of ensuring the positioning precision.

Drawings

FIG. 1 is a flow chart of a method of the present invention;

fig. 2 is a fusion structure diagram of WIFI positioning and PDR positioning.

Detailed Description

The following further describes the embodiments of the present invention with reference to the drawings, but the present invention is not limited thereto.

Fig. 1 shows an indoor positioning method based on WIFI and PDR fusion, which includes the following steps:

(1) establishing a WIFI offline fingerprint database: arranging M AP nodes for transmitting WIFI hotspots in a positioning area, dividing the positioning area into N nodes, calculating the actual position of each node, acquiring the RSSI of the signal strength from each AP node in the N nodes to obtain an RSSI training sample, corresponding the RSSI training sample to the actual position of the RSSI training sample, and establishing a fingerprint database I; the fingerprint data set I is represented as:

I＝{(r₁,o₁),(r₂,o₂),...,(r_i,o_i),...,(r_N,o_N)} (1)，

wherein, the vector r_i＝(r_i1,r_i2,...,r_iM)∈R^MRepresents RSSI, r from M APs_i1Is RSSI, r from the 1 st WIFI hotspot_iMFor RSSI of Mth AP, position vector o_i＝(x,y)∈R²Is represented by r_iThe position corresponding to the vector, x is the x-axis coordinate of the position, y is the y-axis coordinate of the position, and the RSSI vector r of the RSSI training sample_iAnd a position vector o_iAre known, i ═ 1, 2.. N;

(2) clustering the training samples to obtain clustering samples and corresponding categories: clustering the fingerprint database I through a K-means algorithm, and dividing the fingerprint database I into V classes { c₁,c₂,.c_v..c_VEach class center vector is defined as { C }₁,C₂,...C_VDividing RSSI training samples in the fingerprint database into V classes respectively to obtain a clustering sample data set:

L＝{(r₁,c_v1),(r₂,c_v2),...(r_i,c_vi),...,(r_N,c_vN)} (2)，

wherein r is_i＝(r_i1,r_i2,...,r_iM)∈R^MIndicates the RSSI of the M APs,

indicates the V category to which it belongs, c_vClass is trained by p RSSI samples { r_v1,r_v2,...,r_vpComposition of, for all c_vC is obtained by averaging RSSI-like training samples_vClass center vector

(3) Obtaining positioning coordinates through a weighted K nearest neighbor algorithm: acquiring real-time RSSI samples on line, finding out a class most similar to the acquired real-time RSSI samples, predicting attribute values of the real-time RSSI samples acquired on line through K nearest neighbor samples, and weighting positions corresponding to the K nearest neighbor training samples to acquire position coordinates of the real-time RSSI samples; the real-time RSSI sample obtained from the line is denoted as T ═ r ((r)_j1,r_j2,...,r_jM) (x, y)), where the real-time RSSI samples r taken online are defined by r_j＝(r_j1,r_j2,...,r_jM)∈R^MIndicating RSSI for M APs received online, a location vector o ═ x, y indicating location information for real-time RSSI samples acquired online, where the RSSI vector acquired online is known and the location vector (x, y) is unknown,

first, r vector and V class center RSSI vectors { C are calculated₁,C₂,...C_VThe similarity of the r vector, r, is determined_j1,r_j2,...,r_jMRSSI vector with the ith class center

The cosine similarity of (a) is defined as:

similarly, calculating the similarity between the r vector and the RSSI vectors of other categories, and obtaining V cosine similarities { Sim after V times of calculation₁,Sim₂,...,Sim_VIn which the category c corresponding to the maximum similarity is_vIs the most similar class to the r vector;

determiningMost similar class c_vK samples r most similar to the r vector_K1,r_K2,..r_Ki.,r_KKSimilarity is respectively Sim_K1,Sim_K2,...,Sim_KK,

(x_K1,y_K1)，(x_K2,y_K2),...,(x_KK,y_KK) Represents the corresponding coordinates, (r)_i1,r₁₂,...r_iM) Representing the most similar sample r selected_KiCorresponding RSSI samples, normalization processing similarity, defining the weight affecting the positioning result as { w }_K1,w_K2,...,w_KK}；

Weighting the sample coordinates to obtain the position coordinates of the on-line acquired RSSI:

x＝w_K1x_K1+w_K2x_K2+...+w_KKx_KK(6)，

y＝w_K1y_K1+w_K2y_K2+...+w_KKy_KK(7)，

(4) updating the state and the position by fusing PDR positioning: system model X for constructing pedestrian walking_kThe initial position coordinates of the PDR positioning are obtained through WIFI positioning, the WIFI positioning and the PDR positioning are fused to obtain an error threshold value, a walking step length is obtained through an acceleration sensor, the orientation angle variation after walking is obtained through a gyroscope arranged in the intelligent terminal, and a measurement equation Z is used_kAnd updating state information and position information, wherein the system model of the pedestrian walking is as follows:

wherein the number of steps of walking is represented by k, and the position information after walking is represented by x_k,y_kIs represented by theta_kDenotes the azimuth angle after k steps, W_k-1The representation of the noise is represented by,

is the step length average value, is obtained by an acceleration sensor,

for the variation of the orientation angle, measure the equation Z_kAs follows:

wherein x is_k,y_kRepresenting a positioning result obtained through WIFI positioning; s_kRepresenting the average walking step length of the pedestrian, obtained by an acceleration sensor, Delta theta_kRepresenting the variation of the orientation angle of the pedestrian after walking, and obtaining the variation through a built-in gyroscope of the intelligent terminal_kRepresenting the orientation angle of the pedestrian after walking; v_kRepresenting noise;

(5) using the fusion results as a correction source for PDR: setting PDR deviation threshold_pdrIf the deviation exceeds a set threshold value, correcting the positioning result to obtain a WIFI and PDR fusion positioning result, and using the WIFI and PDR fusion result as a PDR correction source, referring to a formula (9);

(6) obtaining correction factor corrected PDR results by evaluating parameters: obtaining evaluation parameters by using data in interval time periods, namely [0, T ] time, wherein the evaluation parameters are shown in formulas (13) and (14), and obtaining correction factors and correction factors by the evaluation parameters, namely formula (15), and correcting the PDR result; the specific process is as follows:

indicating the positioning result after positioning by fusion,

representing the PDR individual positioning result, the PDR individual positioning is obtained by the following formula,

y₂＝y₁+S₁₂cos θ₁(10)，

x₂＝x₁+S₁₂sin θ₁(11)，

(x₁,x₂) Is PDR initial position, (x)₂,y₂) Coordinates are positioned for the PDR, the displacement S is obtained by matching a step length model with an acceleration sensor, the step length of the pedestrian is 60cm, the direction angle theta is obtained by the sensor and a gyroscope,

the positioning result difference is as follows:

given a [0, K ] time, the accumulated error is expressed as:

the characteristic is used as a correction factor for PDR positioning, and the correction principle is as follows:

if the error C is accumulated_xAnd C_yThe absolute value is E [0, sigma ]₁]The positioning error is negligible and does not need to be corrected;

if the error C is accumulated_xAnd C_yAbsolute value ∈ [ σ ]₁,σ₂]The error evaluation requirement is met, and the positioning result is corrected;

if the error C is accumulated_xAnd C_yAbsolute value ∈ [ σ ]₂,∞]If the error evaluation requirement is not met, the WIFI positioning error is large, and fusion positioning is carried out again;

because the PDR positioning result has the problems of accumulated error and the like, the correction information is not corresponding, the correction capability is too weak, and the correction scale factor alpha is set to represent the proportional relation between the error of the current time and the error of the previous time, [0, K]Represents a time period, C_N＝αC_kPresentation ratioFor example, the correction process within the M time period is smoothed by the following formula to solve the problem of abrupt change in localization result:

wherein j is ∈ [1, M ].

Fig. 2 shows a fusion structure of WIFI positioning and PDR positioning, where an initial position coordinate of PDR positioning is obtained through WIFI positioning, and an error threshold is obtained by fusing WIFI positioning and PDR positioning; using a WIFI and PDR fusion result as a PDR correction source, setting a PDR deviation threshold, and correcting a positioning result if the deviation exceeds the set threshold; and acquiring an evaluation parameter by using the data of the interval time period, acquiring a correction factor by the evaluation parameter, and correcting the PDR result.

Compared with the prior art, the invention has the beneficial effects that:

the K-means algorithm is combined with the K nearest neighbor method, so that the WIFI positioning time is shortened, and the positioning precision is improved. And (5) utilizing the WIFI positioning result and the PDR to fuse and position, and correcting the positioning factor of the system by using the correction factor. The method has the characteristics of high positioning precision and low software computation, and realizes real-time requirements on the premise of ensuring the positioning precision.

The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention.

Claims (2)

1. An indoor positioning method based on WIFI and PDR fusion is characterized by comprising the following steps:

(1) establishing a WIFI offline fingerprint database: arranging M APs for transmitting WIFI hotspots in a positioning area, dividing the positioning area into N nodes, calculating the actual position of each node, acquiring the signal strength RSSI from each AP in the N nodes to obtain an RSSI training sample, corresponding the RSSI training sample to the actual position of the RSSI training sample, and establishing a fingerprint database I;

(2) clustering the training samples to obtain clustering samples and corresponding categories: clustering the fingerprint database I through a K-means algorithm, and dividing the fingerprint database I into V classes { c₁,c₂,.c_v..c_VEach class center vector is defined as { C }₁,C₂,...C_VDividing RSSI training samples in the fingerprint database into V classes respectively to obtain a clustering sample data set:

L＝{(r₁,c_v1),(r₂,c_v2),...(r_i,c_vi),...,(r_N,c_vN)} (2)，

wherein r is_i＝(r_i1,r_i2,...,r_iM)∈R^MRSSI of M APs, their corresponding categories

Indicates the V category to which it belongs, c_vClass is trained by p RSSI samples { r_v1,r_v2,...,r_vpComposition of, for all c_vC is obtained by averaging RSSI-like training samples_vClass center vector

(3) Obtaining positioning coordinates through a weighted K nearest neighbor algorithm: acquiring real-time RSSI samples on line, finding out a class which is most similar to the acquired real-time RSSI samples in a fingerprint database I, predicting attribute values of the real-time RSSI samples acquired on line through K nearest neighbor samples, and weighting positions corresponding to the K nearest neighbor samples to acquire position coordinates of the K nearest neighbor samples; the real-time RSSI sample obtained online is denoted as T ═ r ((r)_j1,r_j2,...,r_jM) (x, y)), where the real-time RSSI samples r taken online are defined by r_j＝(r_j1,r_j2,...,r_jM)∈R^MIndicating RSSI of M APs received online, and a location vector o ═ x, y indicating location information of real-time RSSI samples acquired online, where the RSSI vector acquired online is known and the location vector (x, y) is unknown;

first, r vector and V class center RSSI vectors { C are calculated₁,C₂,...C_VThe similarity of the r vector, r, is determined_j1,r_j2,...,r_jMRSSI vector with the ith class center

The cosine similarity of (a) is defined as:

similarly, calculating the similarity between the r vector and the RSSI vectors of other categories, and obtaining V cosine similarities { Sim after V times of calculation₁,Sim₂,...,Sim_VIn which the category c corresponding to the maximum similarity is_vIs the most similar class to the r-vector,

determining the most similar class c_vK samples r most similar to the r vector_K1,r_K2,.r_Ki..,r_KKSimilarity is respectively Sim_K1,Sim_K2,...,Sim_KK,

(x_K1,y_K1)，(x_K2,y_K2),...,(x_KK,y_KK) Represents the corresponding coordinates, (r)_i1,r₁₂,...r_iM) Representing the most similar sample r selected_KiCorresponding RSSI samples, normalization processing similarity, defining the weight affecting the positioning result as { w }_K1,w_K2,...,w_KK}，

Weighting the sample coordinates to obtain the position coordinates of the on-line acquired RSSI:

x＝w_K1x_K1+w_K2x_K2+...+w_KKx_KK(6)，

y＝w_K1y_K1+w_K2y_K2+...+w_KKy_KK(7)，

(4) updating the state and the position by fusing PDR positioning;

system model X for constructing pedestrian walking_kAcquiring initial position coordinates of PDR positioning through WIFI positioning, acquiring an error threshold by fusing the WIFI positioning and the PDR positioning, acquiring a walking step length through an acceleration sensor, acquiring the variation of an orientation angle after walking through a gyroscope arranged in an intelligent terminal, and updating state information and position information by using a measurement equation;

(5) using the fusion results as a correction source for PDR: setting PDR deviation threshold_pdrIf the deviation exceeds a set threshold value, correcting the positioning result to obtain a WIFI and PDR fusion positioning result, and using the WIFI and PDR fusion result as a PDR correction source, referring to a formula (9);

(6) obtaining correction factor corrected PDR results by evaluating parameters: obtaining an evaluation parameter by using data in an interval time period, namely [0, T ] time, wherein the evaluation parameter is shown in formula (13) and formula (14), obtaining a correction factor by the evaluation parameter, and the correction factor is shown in formula (15), and correcting the PDR result, wherein the specific process is as follows:

indicating the positioning result after positioning by fusion,

representing the PDR individual positioning result, which is obtained by the following formula,

y₂＝y₁+S₁₂cosθ₁(10)，

x₂＝x₁+S₁₂sinθ₁(11)，

(x₁,x₂) Is PDR initial position, (x)₂,y₂) The coordinates are located for the PDR,the displacement S is obtained by matching the step length model with an acceleration sensor, the step length of the pedestrian is selected to be 60cm, and the direction angle theta is obtained through the sensor and a gyroscope;

the positioning result difference is as follows:

given a [0, K ] time, the accumulated error is expressed as:

the characteristic is used as a correction factor for PDR positioning, and the correction principle is as follows:

if the error C is accumulated_xAnd C_yThe absolute value is E [0, sigma ]₁]The positioning error is negligible and does not need to be corrected;

if the error C is accumulated_xAnd C_yAbsolute value ∈ [ σ ]₁,σ₂]The error evaluation requirement is met, and the positioning result is corrected;

if the error C is accumulated_xAnd C_yAbsolute value ∈ [ σ ]₂,∞]If the error evaluation requirement is not met, the WIFI positioning error is large at the moment, fusion positioning is carried out again, a correction scale factor alpha is set to represent the proportional relation between the error of the current time and the error of the previous time, and [0, K ]]Represents a time period, C_N＝αC_kExpressing a proportional relation, smoothing a correction process in the M time period by the following formula, and solving the problem of mutation of the positioning result:

wherein j belongs to [1, M ], and the system model of pedestrian walking is as follows:

wherein the number of steps of walking is represented by k, and the position information after walking is represented by x_i,y_iIs represented by theta_kDenotes the azimuth angle after k steps, W_k-1The representation of the noise is represented by,

the step length is the average value, the result of the acceleration sensor is matched through a step length model, the step length is selected to be 60cm,

is the orientation angle variation; the measurement equation is as follows:

wherein x is_k,y_kRepresenting a positioning result obtained through WIFI positioning; s_kRepresenting the average walking step length of the pedestrian, obtained by an acceleration sensor, Delta theta_kRepresenting the variation of the orientation angle of the pedestrian after walking, and obtaining the variation through a built-in gyroscope of the intelligent terminal_kRepresenting the orientation angle of the pedestrian after walking; v_kRepresenting noise.

2. The WIFI and PDR fusion based indoor positioning method according to claim 1, wherein in step (1), the number set of training samples is represented as:

I＝{(r₁,o₁),(r₂,o₂),...,(r_i,o_i),...,(r_N,o_N)} (1)

wherein, the vector r_i＝(r_i1,r_i2,...,r_iM)∈R^MRepresents the RSSI vector, r, from M APs_i1Is RSSI, r from the 1 st WIFI hotspot_iMFor RSSI of Mth AP, position vector o_i＝(x,y)∈R²Is represented by r_iThe position corresponding to the vector, x isThe x-axis coordinate of the position, y is the y-axis coordinate of the position, and the RSSI vector r of the training sample_iAnd a position vector o_iAre known, i ═ 1, 2.. N.

Images