CN107318084B - Fingerprint positioning method and device based on optimal similarity - Google Patents
Fingerprint positioning method and device based on optimal similarity Download PDFInfo
- Publication number
- CN107318084B CN107318084B CN201610264145.1A CN201610264145A CN107318084B CN 107318084 B CN107318084 B CN 107318084B CN 201610264145 A CN201610264145 A CN 201610264145A CN 107318084 B CN107318084 B CN 107318084B
- Authority
- CN
- China
- Prior art keywords
- similarity
- fingerprint
- reference points
- point
- fingerprint reference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a fingerprint positioning method and a fingerprint positioning device based on optimal similarity, which relate to the technical field of mobile positioning, and the method comprises the following steps: performing Euclidean distance matching processing and similarity matching processing on the signal characteristics of the to-be-positioned points and the signal characteristics of position fingerprint reference points in a position fingerprint database, and determining a plurality of optimal similarity position fingerprint reference points which are closest to the to-be-positioned points; and calculating the position coordinates of the to-be-positioned point by using the determined plurality of optimal similarity position fingerprint reference points. The Euclidean distance and the similarity between the signal characteristics of the to-be-positioned point and the signal characteristics of the position fingerprint reference points in the position fingerprint database are calculated, so that the position fingerprint reference points optimally similar to the to-be-positioned point are determined, the diversity error of the matching result is eliminated, and the positioning precision is improved.
Description
Technical Field
The invention relates to the technical field of mobile positioning, in particular to a fingerprint positioning method and device based on optimal similarity.
Background
With the development of the mobile internet, people will have higher and higher demands for positioning and navigation functions. Outdoor Positioning technologies represented by a Global Positioning System (GPS) and the beidou have been widely used, but in complex indoor or closed environments, such as large waiting rooms, large meeting places, stadiums, large office buildings, underground mines and other scenes, the Positioning still cannot be performed due to serious signal shielding and attenuation. However, the communication network needs to satisfy the hot spot coverage at any time and any place for these complicated indoor environments, so that the communication system base station can be used for indoor positioning.
In order to realize mobile positioning, various technical schemes are proposed at present, and typical schemes include gyroscope-based positioning, triangulation positioning and fingerprint positioning. The gyroscope-based positioning has the problem of error accumulation and cannot be used for a long time. Positioning systems based on time measurement generally require multiple base stations to be strictly time-synchronized and require high-precision time-of-arrival measurement of wireless signals, which is not supported by current base station equipment. Fingerprint positioning does not need to know the position of a base station and an accurate channel model, so the fingerprint positioning has great advantages over triangulation positioning in the aspects of implementation and positioning performance.
The fingerprint positioning refers to that the Signal characteristics of an RSS Signal are extracted by testing Received Signal Strength (RSS) signals of all reference points in a positioning area, the Signal characteristics and the position coordinates of the corresponding reference points are stored in a position fingerprint database, then the Signal characteristics of a point to be positioned are obtained by the same method, and the estimated position of the point to be positioned is obtained by matching according to a certain matching algorithm and the position fingerprint database. The method commonly used includes Nearest neighbor method (NNSS), K-Nearest neighbor algorithm (KNNSS), and the like.
However, in the NNSS algorithm or the KNNSS algorithm, the reference fingerprint is selected by calculating the distance between the signal strength vector of the point to be located and the signal strength vectors of all the sample points in the fingerprint library, and the signal strength of the fingerprint does not change linearly with the distance, so that the quality of the selected reference fingerprint is difficult to ensure, the accuracy and stability of the location result are affected, and the accuracy of the location result is seriously affected.
Disclosure of Invention
The technical problem solved by the technical scheme provided by the embodiment of the invention is how to improve the fingerprint positioning precision.
The fingerprint positioning method based on the optimal similarity provided by the embodiment of the invention comprises the following steps:
performing Euclidean distance matching processing and similarity matching processing on the signal characteristics of the to-be-positioned points and the signal characteristics of position fingerprint reference points in a position fingerprint database, and determining a plurality of optimal similarity position fingerprint reference points which are closest to the to-be-positioned points;
and calculating the position coordinates of the to-be-positioned point by using the determined plurality of optimal similarity position fingerprint reference points.
Preferably, the signal feature is a received signal strength vector, and the step of determining a plurality of optimal similarity position fingerprint reference points closest to the to-be-located point includes:
respectively carrying out Euclidean distance matching processing on the received signal intensity vector of the point to be located and the received signal intensity vector of the position fingerprint reference point in the position fingerprint database, and determining N position fingerprint reference points with the minimum Euclidean distance;
and respectively carrying out similarity matching processing on the received signal strength vector of the point to be located and the received signal strength vectors of the N position fingerprint reference points, and determining N position fingerprint reference points with the maximum similarity as optimal similarity position fingerprint reference points, wherein N is more than or equal to 2 and less than or equal to N, and N is more than or equal to 3.
Preferably, the step of determining the n position fingerprint reference points with the maximum similarity as the optimal similarity position fingerprint reference points includes:
calculating the similarity of the received signal strength vectors between the to-be-positioned point and the N position fingerprint reference points respectively to obtain N similarities;
and sequencing the obtained N similarities to determine the maximum N similarities and N position fingerprint reference points corresponding to the N similarities.
Preferably, the similarity calculation is performed using a cosine similarity algorithm or a modified cosine similarity algorithm or a Pearson similarity algorithm.
Preferably, the step of calculating the position coordinates of the point to be located by using the determined plurality of optimal similarity position fingerprint reference points includes:
and weighting the position coordinates of the plurality of determined optimal similarity position fingerprint reference points to obtain the position coordinates of the to-be-positioned point.
According to an embodiment of the present invention, there is provided a storage medium storing a program for implementing the above fingerprint location method based on optimal similarity.
The fingerprint positioning device based on the optimal similarity provided by the embodiment of the invention comprises:
the optimal similarity fingerprint determining module is used for carrying out Euclidean distance matching processing and similarity matching processing on the signal characteristics of the to-be-positioned points and the signal characteristics of position fingerprint reference points in the position fingerprint database, and determining a plurality of optimal similarity position fingerprint reference points which are closest to the to-be-positioned points;
and the position determining module for the position to be positioned is used for calculating the position coordinates of the position to be positioned by utilizing the determined plurality of optimal similarity position fingerprint reference points.
Preferably, the signal feature is a received signal strength vector, the optimal similarity fingerprint determining module performs euclidean distance matching on the received signal strength vector of the to-be-located point and the received signal strength vector of the position fingerprint reference point in the position fingerprint database, determines N position fingerprint reference points with the minimum euclidean distance, performs similarity matching on the received signal strength vector of the to-be-located point and the received signal strength vectors of the N position fingerprint reference points, and determines N position fingerprint reference points with the maximum similarity as optimal similarity position fingerprint reference points, where N is greater than or equal to 2 and less than or equal to N, and N is greater than 3.
Preferably, the optimal similarity fingerprint determination module calculates similarities of received signal strength vectors between the to-be-located point and the N location fingerprint reference points respectively to obtain N similarities, and determines the N largest similarities and the N location fingerprint reference points corresponding to the N similarities by sorting the N similarities.
Preferably, the optimal similarity fingerprint determination module performs similarity calculation by using a cosine similarity algorithm or a modified cosine similarity algorithm or a Pearson similarity algorithm.
Preferably, the module for determining the position of the point to be located obtains the position coordinate of the point to be located by performing weighting processing on the position coordinates of the plurality of determined fingerprint reference points of the optimal similarity positions.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
by calculating the Euclidean distance and the similarity between the signal characteristics of the to-be-positioned point and the signal characteristics of the position fingerprint reference points in the position fingerprint database, the position fingerprint reference point which is optimally similar to the to-be-positioned point can be selected, the diversity error of the matching result is eliminated, and the positioning precision is improved.
Drawings
FIG. 1 is a first block diagram of a fingerprint location method based on optimal similarity according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a first structure of a fingerprint locating device based on optimal similarity according to an embodiment of the present invention;
fig. 3 is a second block diagram of a positioning method provided by the embodiment of the invention;
fig. 4 is a flowchart of a positioning method provided in an embodiment of the present invention;
FIG. 5 is a schematic plan view of a mall provided in accordance with an embodiment of the present invention;
fig. 6 is a schematic diagram of a second structure of a fingerprint positioning device according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described below are only for the purpose of illustrating and explaining the present invention, and are not to be construed as limiting the present invention.
Fig. 1 is a first block diagram of a fingerprint locating method based on optimal similarity according to an embodiment of the present invention, as shown in fig. 1, the steps include:
step S101: and performing Euclidean distance matching processing and similarity matching processing on the signal characteristics of the to-be-positioned point and the signal characteristics of the position fingerprint reference points in the position fingerprint database, and determining a plurality of optimal similarity position fingerprint reference points which are closest to the to-be-positioned point.
The signal characteristics are received signal strength vectors (i.e., signal strength vectors, which are power information).
Specifically, first, Euclidean distance matching processing is performed on the received signal intensity vector of the point to be located and the received signal intensity vector of the position fingerprint reference point in the position fingerprint database, and N position fingerprint reference points with the minimum Euclidean distance are determined. Then, similarity matching processing is carried out on the received signal intensity vector of the point to be located and the received signal intensity vectors of the N position fingerprint reference points respectively, N position fingerprint reference points with the maximum similarity are determined to serve as the optimal similarity position fingerprint reference points, furthermore, the similarity of the received signal intensity vectors between the point to be located and the N position fingerprint reference points is calculated respectively, a cosine similarity algorithm or a modified cosine similarity algorithm or a Pearson similarity algorithm can be adopted, so that N similarities are obtained, and the N position fingerprint reference points with the maximum similarity and the N corresponding similarity are determined by sequencing the obtained N similarities. Wherein N is more than or equal to 2 and less than or equal to N, N is more than 3, and N and N are positive integers.
Wherein the location fingerprint database is a pre-established database in an off-line situation, the database comprising a fingerprint of each location fingerprint reference point (i.e. reference point or reference fingerprint point or sample point), the fingerprint comprising the location and signal characteristics of the location fingerprint reference point.
Step S102: and calculating the position coordinates of the to-be-positioned point by using the determined plurality of optimal similarity position fingerprint reference points.
Specifically, the position coordinates of the to-be-positioned point are obtained by weighting the position coordinates of the determined optimal similarity position fingerprint reference points.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by hardware that is related to instructions of a program, and the program may be stored in a computer-readable storage medium, and when executed, includes steps S101 to S102. The storage medium may be ROM/RAM, magnetic disk, optical disk, etc.
Fig. 2 is a schematic view of a first structure of a fingerprint positioning device based on optimal similarity according to an embodiment of the present invention, and as shown in fig. 2, the fingerprint positioning device includes an optimal similarity fingerprint determining module and a to-be-positioned point position determining module.
The optimal similarity fingerprint determining module is used for carrying out Euclidean distance matching processing and similarity matching processing on the signal characteristics of the to-be-positioned point and the signal characteristics of the position fingerprint reference points in the position fingerprint database, and determining a plurality of optimal similarity position fingerprint reference points which are closest to the to-be-positioned point. Specifically, the signal feature is the received signal strength vector, the optimal similarity fingerprint determining module performs Euclidean distance matching processing on the received signal strength vector of the point to be located and the received signal strength vector of the position fingerprint reference point in the position fingerprint database respectively to determine N position fingerprint reference points with the minimum Euclidean distance, and the received signal strength vector of the point to be located and the received signal strength vector of the fingerprint reference points of N positions are respectively processed by similarity matching, the similarity calculation can be carried out by adopting a cosine similarity calculation method or a modified cosine similarity calculation method or a Pearson similarity calculation method to obtain N similarities, and sequencing the N similarity degrees, determining the N maximum similarity degrees and N position fingerprint reference points corresponding to the N similarity degrees, and taking the N position fingerprint reference points as the optimal similarity position fingerprint reference points. Wherein N is more than or equal to 2 and less than or equal to N, N is more than 3, and N and N are positive integers.
And the position determining module of the position to be positioned is used for calculating the position coordinate of the position to be positioned by utilizing the determined plurality of optimal similarity position fingerprint reference points. Specifically, the position determining module for the position to be located obtains the position coordinates of the position to be located by performing weighting processing on the position coordinates of the determined fingerprint reference points of the plurality of optimal similarity positions.
Fig. 3 is a second block diagram of the positioning method according to the embodiment of the present invention, and as shown in fig. 3, the steps include:
step S201: an offline fingerprint database (i.e., a fingerprint database or a location fingerprint database) is constructed.
Step S202: and matching the characteristic information (namely signal characteristics) of the to-be-positioned point with the data in the fingerprint database by Euclidean distance.
And obtaining a plurality of reference fingerprint point data with the minimum Euclidean distance through Euclidean distance matching.
Step S203: and performing similarity matching on the feature information of the to-be-positioned point and the reference fingerprint point data with the minimum Euclidean distance.
And obtaining a plurality of fingerprint points with the maximum similarity through similarity matching.
Step S204: and applying a weighted nearest neighbor algorithm to the fingerprint points with the maximum similarity to estimate the final position of the point to be located.
Therefore, the fingerprint positioning method based on the optimal similarity provided by the embodiment of the invention comprises the following steps: firstly, an off-line fingerprint database is constructed; secondly, matching Euclidean distances by utilizing the characteristic information of the to-be-positioned points and the characteristic information in the fingerprint database, and taking N fingerprints with the minimum Euclidean distances as a new fingerprint database; and then, carrying out similarity solution by using the characteristic information of the to-be-positioned point and the new fingerprint library to obtain n fingerprints with the maximum similarity, and finally applying a weighting algorithm such as WKNNSS (weighted KNNSS) to the n fingerprints to obtain a final positioning result. The implementation comprises a stage of constructing an offline fingerprint database and a stage of online positioning, and specifically comprises the following steps:
stage one: and constructing an offline fingerprint database.
Arranging M base stations in a positioning environment, setting K reference points in a positioning area, sampling the received signal power of each base station at each reference point, and combining the reference point position and power information to form a fingerprint, wherein the ith fingerprint is expressed as follows: [ xi, yi, zi, p1i,p2i,...,pMi]。
Wherein xi, yi, zi are the position information of the ith reference point, p1i,p2i,...,pMiAnd the receiving power of the M base stations to the signal of the user equipment at the ith reference point position at the moment of fingerprint library establishment, namely the receiving power of the signal from the M base stations received by the user equipment at the ith reference point position at the moment of fingerprint library establishment. The value of i ranges from 1 to K.
And a second stage: on-line positioning
Step 1: signal strength vector R received from M base stations at a point to be positionedx＝[p1,p2,...,pM]M valid signal strength values are found, wherein M is a positive integer smaller than M and larger than 2.
Step 2: and performing Euclidean distance matching on the signal intensity vector received by the point to be positioned and the corresponding signal intensity vector in the fingerprint library, and obtaining N fingerprints with the minimum Euclidean distance by solving the Euclidean distance between the signal intensity vector received by the point to be positioned and the corresponding signal intensity vector in the fingerprint library, wherein N is a positive integer greater than 3.
The euclidean distance is calculated using the following formula:
wherein, PxjRepresents the received signal strength, P, of the jth base station of the point to be positionedjiThe signal strength vector of the jth base station received by the ith reference point is shown, and m represents the number of effective signal strengths. Qi represents the euclidean distance of the signal strength from the ith reference point to the point to be located.
And step 3: and (3) carrying out similarity solving on the signal intensity vectors of the N fingerprints obtained in the step (2) and the signal intensity vector of the to-be-positioned point in sequence. The similarity calculation method can select cosine similarity, Pearson correlation coefficient or modified cosine similarity, etc.
Taking cosine similarity as an example, the following formula is used for calculation:
wherein P isxRepresenting the signal strength vector, P, of the point to be locatediRepresents the signal strength vector of the ith fingerprint in the N fingerprints, | | | represents the modulo operation,<*>denotes inner product calculation, CosSim (P)x,Pi) And expressing the cosine similarity coefficient of the point to be located and the ith fingerprint point. The larger the cosine similarity coefficient, the greater the correlation between the two.
And 4, step 4: and sequencing the N cosine similarity coefficients from large to small, and selecting the first N large values of the cosine similarity coefficients, wherein the N fingerprints corresponding to the N cosine similarity coefficients are the N fingerprint points closest to the point to be positioned.
And 5: and applying a WKNNSS algorithm to the n fingerprint points to obtain a final positioning result. The calculation formula is as follows:
in the formula, xk、yk、zkIs the coordinate information of the kth matching fingerprint. Weight wkObtained by a weighted neighbor method, and the formula is as follows:
where ε is a very small real constant to avoid the case where the denominator is 0. QkAnd expressing the Euclidean distance from the Kth reference point to the signal strength of the point to be positioned.
Fig. 4 is a flowchart of a positioning method according to an embodiment of the present invention, and as shown in fig. 4, the steps include:
step S301: and setting sample points in the fingerprint positioning area.
Step S302: and (3) the received signal power information of the sample points relative to each base station in the sampling area.
Step S303: and combining the position information and the received power information of the sample points to form a fingerprint database.
Step S304: and selecting the received signal strength information of a plurality of base stations related to the point to be positioned.
Step S305: and performing Euclidean distance matching on the power information of the to-be-positioned point and the power information of each fingerprint in the fingerprint library, and selecting a plurality of fingerprint points with the minimum Euclidean distance.
Step S306: and solving the cosine similarity of the fingerprint points selected in the step and the to-be-positioned points, and selecting a plurality of corresponding fingerprint points with the smallest and positive cosine similarity.
Step S307: the position of the terminal is estimated from several candidate points using a specific algorithm (e.g., WKNNSS).
Steps S301 to S303 are steps of an offline fingerprint database construction phase, and steps S304 to S307 are steps of an online positioning phase.
Because the reference fingerprint is selected only by the magnitude of the signal intensity vector in the existing fingerprint method, the quality of the selected N fingerprints is difficult to ensure, and the accuracy and the stability of the positioning result are further influenced. Especially, when vectors formed by signal strengths obtained by different base stations have symmetry, the matching results of the to-be-positioned points in the samples have diversity, which sample point is the closest point to the to-be-positioned point cannot be distinguished, and fingerprints with large actual physical position errors may exist in the selected N reference fingerprints, so that the positioning error fluctuation is large, the positioning accuracy is seriously affected, and the user experience is poor. This embodiment will further describe the technical method provided by the present invention in detail with reference to fig. 5. The following specific embodiments are merely illustrative of the invention and are not intended to limit the scope of the invention.
Fig. 5 is a schematic plan view of a certain mall provided in the embodiment of the present invention, and as shown in fig. 5, 6 Access Points (APs) or base stations are arranged in the mall of 12 meters by 60 meters.
Example 1 fingerprint location based on intensity and orientation
Stage one: constructing an offline fingerprint database
Arranging 6 APs (access points) in a 12-meter by 60-meter mall, arranging 50 reference points in the mall, sampling the received signal power of each AP at each reference point, and combining the position of the reference point and the power information to form a fingerprint, wherein the ith fingerprint is represented as follows: [ xi, yi, zi, p1i,p2i,...,pMi]. Wherein xi, yi, zi are the position information of the ith reference point, p1i,p2i,...,pMiAnd establishing a database for the fingerprint database for 6 base stations, and determining the receiving power of the signal of the user equipment at the ith reference point position. i ranges from 1 to 50.
And a second stage: on-line positioning
Step 1: received signal strength vector R from a point to be positionedx＝[p1,p2,...,pM]Find m-3 valid signal strength values, the valid signal strength gate valve is determined by the shop environment, here set to-100 dBm.
Step 2: and solving the signal intensity vector received by the point to be positioned and carrying out Euclidean distance matching with the corresponding signal intensity vector in the fingerprint database to obtain 6 fingerprints with the minimum Euclidean distance. The euclidean distance is calculated using the following formula:
wherein, PxjRepresents the received signal strength, P, of the jth AP of the point to be positionedjiThe signal strength vector of the jth AP received by the ith reference point is shown, and m represents the number of effective signal strengths. Qi represents the euclidean distance of the signal strength from the ith reference point to the point to be located.
And step 3: and (3) sequentially carrying out cosine similarity algorithm solving on the signal intensity vectors of the 6 fingerprints with the minimum Euclidean distance obtained in the step (2) and the signal intensity vector of the to-be-positioned point. The cosine similarity is calculated by the following formula:
wherein, PxRepresenting the signal strength vector, P, of the point to be locatediRepresents the signal strength vector of the ith fingerprint of the 6 fingerprints, | | | represents the modulo operation,<*>denotes inner product calculation, CosSim (P)x,Pi) And expressing the cosine similarity coefficient of the point to be located and the ith fingerprint point. The larger the cosine similarity coefficient, the greater the correlation between the two.
And 4, step 4: and sequencing the 6 cosine similarity coefficients from large to small, selecting the first 3 large values of the cosine similarity coefficients, wherein 3 fingerprints corresponding to the 3 cosine similarity coefficients are the 3 fingerprint points closest to the point to be positioned.
And 5: and applying a WKNNSS algorithm to the 3 fingerprint points to obtain a final positioning result (x, y, z), wherein the calculation formula is as follows:
in the formula, xk、yk、zkIs the coordinate information of the kth matching fingerprint. Weight wkObtained by a weighted neighbor method, and the formula is as follows:
where ε is a very small real constant to avoid the case where the denominator is 0.
Example 2 fingerprint location based on optimal similarity
Stage one: constructing an offline fingerprint database
Arranging 6 base stations (M) in a 12-meter by 60-meter market, arranging 50 reference points (K) in the market, sampling the signal power of the 6 base stations received by the current reference point at each reference point, and combining the position of the reference point and the power information to form a fingerprint, wherein the ith fingerprint is expressed as follows: [ xi, yi, zi, p1i,p2i,...,pMi]. Where xi, yi, zi are the location information of the ith reference point, p1i,p2i,...,pMiThe user equipment for the ith point receives the signal power of 6 base stations. i ranges from 1 to 50.
And a second stage: on-line positioning
Step 1: receiving signal strength vectors R of 6 base stations from user equipment of a point to be positionedx＝[p1,p2,...,pM]Where m is found to be the effective signal strength value of 3 base stations, the effective signal strength gate valve is determined by the mall environment, here set to-98 dBm.
Step 2: and solving the signal intensity vector received by the point to be positioned and carrying out Euclidean distance matching with the corresponding signal intensity vector in the fingerprint database to obtain 6 fingerprints with the minimum Euclidean distance. The euclidean distance is calculated using the following formula:
wherein, PxjRepresents the received signal strength, P, of the jth base station of the point to be positionedjiThe signal strength vector of the jth base station received by the ith reference point is shown, and m represents the number of effective signal strengths. Qi represents the euclidean distance of the signal strength from the ith reference point to the point to be located.
And step 3: and (3) sequentially carrying out Pearson similarity algorithm solving on the signal intensity vectors of the 6 fingerprints with the minimum Euclidean distance obtained in the step (2) and the signal intensity vector of the point to be positioned. The Pearson similarity is calculated by the following formula:
wherein, PxRepresenting the signal strength vector, P, of the point to be locatediRepresenting the signal strength vector of the ith fingerprint of the 6 fingerprints,
representing the average of the signal strength vectors with anchor points,
represents the average of the signal strength vectors of the ith fingerprint, | | x | represents the modulo operation,<*>representing the inner product calculation, Corr (P)x,Pi) And representing the Pearson similarity coefficient of the point to be located and the ith fingerprint point. The greater the Pearson similarity coefficient, the greater the correlation between the two.
And 4, step 4: and sequencing the 6 Pearson similarity coefficients from large to small, selecting the first 3 large values of the cosine similarity coefficients, wherein 3 fingerprints corresponding to the 3 cosine similarity coefficients are the 3 fingerprint points closest to the point to be positioned.
And 5: and applying a WKNNSS algorithm to the 3 fingerprint points to obtain a final positioning result (x, y, z), wherein the calculation formula is as follows:
in the formula, xk、yk、zkIs the coordinate information of the kth matching fingerprint. Weight wkObtained by a weighted neighbor method, and the formula is as follows:
where ε is a very small real constant to avoid the case where the denominator is 0.
The embodiment of the invention can eliminate the positioning matching diversity error caused by the symmetry of the signal strength vectors measured by different base stations and improve the positioning precision.
Example 3:
according to the fingerprint positioning method provided in the above embodiment, the embodiment of the present invention further provides a device for applying the above fingerprint positioning method determined based on the optimal similarity.
Fig. 6 is a schematic diagram of a second structure of a fingerprint positioning device according to an embodiment of the present invention, as shown in fig. 6, including:
the off-line fingerprint database building module is used for building a fingerprint database, M base stations are distributed in a positioning environment, K reference points are set in a positioning area, the received signal power of each base station or terminal relative to each base station is sampled at each reference point, and the reference point position and the power information are combined to form a fingerprint.
And the receiving selection module is used for receiving the actually measured data reported by the user equipment and screening out effective data.
And the matching module is used for performing Euclidean distance calculation on the actually measured data and the fingerprint database data by the positioning server and finding out the first N fingerprints with the minimum Euclidean distance.
And the determining module is used for performing similarity calculation on the measured data and the N fingerprint data by the positioning server and selecting N optimal similarity fingerprints.
And the positioning module is used for obtaining a positioning result of the user equipment by the positioning server according to the selected optimal similarity fingerprint information by using a WKNNSS method.
The receiving selection module, the matching module and the determining module jointly realize the function of the optimal similarity fingerprint determining module, and the positioning module realizes the function of the position determining module to be positioned.
The fingerprint positioning can be divided into two modes of uplink fingerprint positioning and downlink fingerprint positioning by using the mobile network base station, wherein the uplink fingerprint positioning refers to that the UE transmits a reference signal, and the plurality of base stations measure the power of the signal transmitted by the UE to form a fingerprint to be matched and positioned with the fingerprint stored in the database in advance. The downlink fingerprint positioning refers to that the UE receives and measures the strength of the transmitted signals of a plurality of base stations to form fingerprints to be matched and positioned with the fingerprints stored in a database in advance. The invention jointly determines the optimal similarity of the fingerprint and the measured data to position based on the RSS size and direction, has high positioning precision, and is suitable for up-down fingerprint positioning and down-down fingerprint positioning because the wireless channel has symmetry.
In summary, the embodiments of the present invention have the following technical effects:
by calculating the Euclidean distance and the similarity between the actually measured data of the user and the fingerprint data in the fingerprint database, the correlation between the reference fingerprint and the to-be-positioned point is ensured in the data size and direction, the reference fingerprint optimally similar to the to-be-positioned point can be selected, the diversity error of the matching between the fingerprint point and the to-be-positioned point is eliminated, and the positioning precision is improved.
Although the present invention has been described in detail hereinabove, the present invention is not limited thereto, and various modifications can be made by those skilled in the art in light of the principle of the present invention. Thus, modifications made in accordance with the principles of the present invention should be understood to fall within the scope of the present invention.
Claims (8)
1. A fingerprint positioning method based on optimal similarity comprises the following steps:
respectively carrying out Euclidean distance matching processing on the received signal intensity vector of the point to be located and the received signal intensity vector of the position fingerprint reference point in the position fingerprint database, and determining N position fingerprint reference points with the minimum Euclidean distance from the point to be located;
similarity matching processing is carried out on the received signal intensity vector of the to-be-positioned point and the received signal intensity vectors of the N position fingerprint reference points with the minimum Euclidean distance, and the N position fingerprint reference points with the maximum similarity to the to-be-positioned point are determined from the N position fingerprint reference points with the minimum Euclidean distance to serve as the optimal similarity position fingerprint reference points, wherein N is more than or equal to 2 and less than or equal to N, and N is more than or equal to 3;
and calculating the position coordinates of the to-be-positioned point by using the n optimal similarity position fingerprint reference points.
2. The method according to claim 1, wherein the step of determining the n position fingerprint reference points with the maximum similarity as the optimal similarity position fingerprint reference points comprises:
calculating the similarity of the received signal strength vectors between the to-be-positioned point and the N position fingerprint reference points respectively to obtain N similarities;
and sequencing the obtained N similarities to determine the maximum N similarities and N position fingerprint reference points corresponding to the N similarities.
3. The method according to claim 1 or 2, wherein the similarity calculation is performed using a cosine similarity algorithm or a modified cosine similarity algorithm or a Pearson similarity algorithm.
4. The method according to claim 1, wherein the step of calculating the position coordinates of the point to be located using the determined plurality of optimal similarity position fingerprint reference points comprises:
and weighting the position coordinates of the plurality of determined optimal similarity position fingerprint reference points to obtain the position coordinates of the to-be-positioned point.
5. An optimal similarity-based fingerprint positioning device, comprising:
the optimal similarity fingerprint determining module is used for respectively carrying out Euclidean distance matching processing on the received signal intensity vector of the point to be positioned and the received signal intensity vector of the position fingerprint reference point in the position fingerprint database, and determining N position fingerprint reference points with the minimum Euclidean distance from the point to be positioned; similarity matching processing is carried out on the received signal intensity vector of the to-be-positioned point and the received signal intensity vectors of the N position fingerprint reference points with the minimum Euclidean distance, and the N position fingerprint reference points with the maximum similarity to the to-be-positioned point are determined from the N position fingerprint reference points with the minimum Euclidean distance to serve as the optimal similarity position fingerprint reference points, wherein N is more than or equal to 2 and less than or equal to N, and N is more than or equal to 3;
and the position determining module of the position to be positioned is used for calculating the position coordinate of the position to be positioned by using the n optimal similarity position fingerprint reference points.
6. The apparatus according to claim 5, wherein the optimal similarity fingerprint determination module calculates similarities of received signal strength vectors between the to-be-located point and the N location fingerprint reference points, respectively, to obtain N similarities, and determines the N largest similarities and the N location fingerprint reference points corresponding to the N similarities by sorting the obtained N similarities.
7. The apparatus of claim 5 or 6, the optimal similarity fingerprint determination module to perform similarity calculation using a cosine similarity algorithm or a modified cosine similarity algorithm or a Pearson similarity algorithm.
8. The device of claim 5, wherein the module for determining the position of the to-be-located point obtains the position coordinates of the to-be-located point by weighting the position coordinates of the determined fingerprint reference points of the optimal similarity positions.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610264145.1A CN107318084B (en) | 2016-04-26 | 2016-04-26 | Fingerprint positioning method and device based on optimal similarity |
| PCT/CN2017/070501 WO2017185828A1 (en) | 2016-04-26 | 2017-01-06 | Fingerprint positioning method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610264145.1A CN107318084B (en) | 2016-04-26 | 2016-04-26 | Fingerprint positioning method and device based on optimal similarity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107318084A CN107318084A (en) | 2017-11-03 |
| CN107318084B true CN107318084B (en) | 2021-01-26 |
Family
ID=60160669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610264145.1A Active CN107318084B (en) | 2016-04-26 | 2016-04-26 | Fingerprint positioning method and device based on optimal similarity |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107318084B (en) |
| WO (1) | WO2017185828A1 (en) |
Families Citing this family (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110320493B (en) * | 2018-03-30 | 2023-11-14 | 北京百度网讯科技有限公司 | Indoor positioning method, device, electronic equipment and computer storage medium |
| CN108680940B (en) * | 2018-05-17 | 2020-08-28 | 中国科学院微电子研究所 | Auxiliary positioning method and device for automatic driving vehicle |
| CN109001674B (en) * | 2018-05-31 | 2022-09-02 | 中国矿业大学 | WiFi fingerprint information rapid acquisition and positioning method based on continuous video sequence |
| CN108834053B (en) * | 2018-06-20 | 2021-03-12 | 北京邮电大学 | Positioning method, device and equipment |
| CN108802678A (en) * | 2018-07-23 | 2018-11-13 | 深圳市欧辰技术有限公司 | A kind of method and apparatus of equipment positioning |
| EP3864426A1 (en) * | 2018-10-12 | 2021-08-18 | Inventio AG | System and method for position determination in a building |
| CN111460088A (en) * | 2019-01-22 | 2020-07-28 | 阿里巴巴集团控股有限公司 | Similar text retrieval method, device and system |
| CN111654843B (en) * | 2019-03-04 | 2024-04-30 | 深圳光启空间技术有限公司 | Method and system for automatically updating fingerprint database, wifi positioning method and system |
| CN110490268A (en) * | 2019-08-26 | 2019-11-22 | 山东浪潮人工智能研究院有限公司 | A kind of feature matching method of the improvement nearest neighbor distance ratio based on cosine similarity |
| CN110515036A (en) * | 2019-09-02 | 2019-11-29 | 上海图聚智能科技股份有限公司 | Localization method, device, electronic equipment and storage medium |
| CN111464945B (en) * | 2020-04-07 | 2023-03-14 | 广州起妙科技有限公司 | Positioning method and system of terminal equipment |
| CN111726860B (en) * | 2020-06-09 | 2022-04-08 | 北京无限向溯科技有限公司 | Positioning method, device, equipment and storage medium based on POI space distance |
| CN112230243B (en) * | 2020-10-28 | 2022-04-08 | 西南科技大学 | Indoor map construction method for mobile robot |
| CN112415472A (en) * | 2020-11-20 | 2021-02-26 | Oppo（重庆）智能科技有限公司 | Indoor positioning method and device, electronic equipment and storage medium |
| CN112383873A (en) * | 2020-11-26 | 2021-02-19 | 上海五航航空技术有限公司 | Indoor positioning system and positioning method thereof |
| CN112714493B (en) * | 2020-12-29 | 2023-03-24 | 北京工业大学 | Object position positioning method and positioning system |
| CN112860718B (en) * | 2021-02-03 | 2022-07-08 | 腾讯科技（深圳）有限公司 | Subway station fingerprint database updating method and device, computer equipment and storage medium |
| CN113203984B (en) * | 2021-04-25 | 2023-03-24 | 华中科技大学 | Multi-user-end online cooperative positioning system |
| CN113259837B (en) * | 2021-04-29 | 2023-02-10 | 西安电子科技大学 | Indoor positioning method based on angle estimation and fingerprint positioning algorithm |
| CN113613167B (en) * | 2021-08-05 | 2022-07-12 | 广东工业大学 | Indoor positioning method and device based on transfer learning |
| CN113723234B (en) * | 2021-08-17 | 2023-07-07 | 中铁第四勘察设计院集团有限公司 | Fingerprint passive perception positioning method, device and storage medium |
| CN113852911B (en) * | 2021-09-26 | 2024-05-07 | 桂林电子科技大学 | Fusion positioning method based on fingerprint library and PDR calculation and fingerprint library updating method |
| CN114002646A (en) * | 2021-11-02 | 2022-02-01 | 陈予朋 | Artificial intelligence-based livestock individual real-time tracking method |
| CN114423076B (en) * | 2021-12-27 | 2024-03-22 | 深圳云天励飞技术股份有限公司 | Fingerprint data generation method and device, electronic equipment and storage medium |
| CN114495306B (en) * | 2022-01-12 | 2024-01-26 | 武汉美和易思数字科技有限公司 | Classroom sign-in method and system based on distance measurement |
| CN115278524A (en) * | 2022-07-29 | 2022-11-01 | 广东电网有限责任公司 | Positioning method, device, equipment and storage medium of sensor network node |
| CN116233747B (en) * | 2023-03-09 | 2023-12-22 | 江苏亨鑫科技有限公司 | BLE positioning method and device based on transfer learning and fingerprint library updating |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268483A (en) * | 2013-05-31 | 2013-08-28 | 沈阳工业大学 | Method for recognizing palmprint acquired in non-contact mode in open environment |
| CN103533650A (en) * | 2013-10-28 | 2014-01-22 | 哈尔滨工业大学 | Cosine-similarity-based indoor positioning method capable of improving positioning precision |
| CN103596267A (en) * | 2013-11-29 | 2014-02-19 | 哈尔滨工业大学 | Fingerprint map matching method based on Euclidean distances |
| CN103634902A (en) * | 2013-11-06 | 2014-03-12 | 上海交通大学 | Novel indoor positioning method based on fingerprint cluster |
| CN103796305A (en) * | 2014-02-11 | 2014-05-14 | 上海交通大学 | Indoor positioning method based on Wi-Fi position fingerprint |
| WO2015099738A1 (en) * | 2013-12-26 | 2015-07-02 | Intel Corporation | Method and apparatus for cross device automatic calibration |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9491731B2 (en) * | 2011-04-13 | 2016-11-08 | Telefonaktiebolaget L M Ericsson | Positioning in a cellular communication network |
| CN103476115B (en) * | 2013-09-22 | 2016-03-23 | 中国地质大学（武汉） | A kind of Wi-Fi fingerprint positioning method based on AP collection similarity |
| CN103596266B (en) * | 2013-11-26 | 2017-06-27 | 无锡市中安捷联科技有限公司 | A kind of human testing and method, the apparatus and system of positioning |
| CN105224961B (en) * | 2015-11-04 | 2018-05-11 | 中国电子科技集团公司第四十一研究所 | A kind of infrared spectrum feature extracting and matching method of high resolution |
-
2016
- 2016-04-26 CN CN201610264145.1A patent/CN107318084B/en active Active
-
2017
- 2017-01-06 WO PCT/CN2017/070501 patent/WO2017185828A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268483A (en) * | 2013-05-31 | 2013-08-28 | 沈阳工业大学 | Method for recognizing palmprint acquired in non-contact mode in open environment |
| CN103533650A (en) * | 2013-10-28 | 2014-01-22 | 哈尔滨工业大学 | Cosine-similarity-based indoor positioning method capable of improving positioning precision |
| CN103634902A (en) * | 2013-11-06 | 2014-03-12 | 上海交通大学 | Novel indoor positioning method based on fingerprint cluster |
| CN103596267A (en) * | 2013-11-29 | 2014-02-19 | 哈尔滨工业大学 | Fingerprint map matching method based on Euclidean distances |
| WO2015099738A1 (en) * | 2013-12-26 | 2015-07-02 | Intel Corporation | Method and apparatus for cross device automatic calibration |
| CN103796305A (en) * | 2014-02-11 | 2014-05-14 | 上海交通大学 | Indoor positioning method based on Wi-Fi position fingerprint |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107318084A (en) | 2017-11-03 |
| WO2017185828A1 (en) | 2017-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107318084B (en) | Fingerprint positioning method and device based on optimal similarity | |
| Li et al. | A feature-scaling-based $ k $-nearest neighbor algorithm for indoor positioning systems | |
| Seow et al. | Non-line-of-sight localization in multipath environments | |
| Kaemarungsi et al. | Modeling of indoor positioning systems based on location fingerprinting | |
| CN103402258B (en) | Wi-Fi (Wireless Fidelity)-based indoor positioning system and method | |
| CN106912105B (en) | Three-dimensional positioning method based on PSO _ BP neural network | |
| EP1575325B1 (en) | Estimating the location of inexpensive wireless terminals by using signal strength measurements | |
| CN110045324B (en) | Indoor positioning fusion method based on UWB and Bluetooth technology | |
| Tarrio et al. | A new positioning technique for RSS-based localization based on a weighted least squares estimator | |
| Fang et al. | Calibration-free approaches for robust Wi-Fi positioning against device diversity: A performance comparison | |
| CN103618997B (en) | Indoor positioning method and device based on signal intensity probability | |
| TW201329486A (en) | Positioning method | |
| CN103476116A (en) | Anti-NLoS error locating method based on location unit quality and multi-algorithm data fusion | |
| KR101709411B1 (en) | Method for positioning based on weighted triangulation and method for indoor positioning using the same | |
| Gholoobi et al. | RSS based localization using a new WKNN approach | |
| WO2022214002A1 (en) | Indoor positioning method and indoor positioning apparatus | |
| Maung et al. | Comparative study of RSS-based indoor positioning techniques on two different Wi-Fi frequency bands | |
| Kanaris et al. | Improving RSS fingerprint-based localization using directional antennas | |
| Kodippili et al. | Integration of fingerprinting and trilateration techniques for improved indoor localization | |
| CN113068127B (en) | Positioning method of NB-IoT terminal | |
| CN108650629B (en) | Indoor three-dimensional positioning algorithm based on wireless communication base station | |
| CN106792516B (en) | 3-D positioning method based on radio communication base station | |
| KR100524180B1 (en) | Position tracking method of a mobile phone using cell position and receiving/pre-measured radio wave characteristic information | |
| Jeon et al. | An adaptive AP selection scheme based on RSS for enhancing positioning accuracy | |
| KR20140119333A (en) | Method and Apparatus for Location Determination to Improve the accuracy of the location |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |