CN107318084A - A kind of fingerprint positioning method and device based on optimal similarity - Google Patents
A kind of fingerprint positioning method and device based on optimal similarity Download PDFInfo
- Publication number
- CN107318084A CN107318084A CN201610264145.1A CN201610264145A CN107318084A CN 107318084 A CN107318084 A CN 107318084A CN 201610264145 A CN201610264145 A CN 201610264145A CN 107318084 A CN107318084 A CN 107318084A
- Authority
- CN
- China
- Prior art keywords
- similarity
- point
- determined
- fingerprint
- reference point
- 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.)
- Granted
Links
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 the fingerprint positioning method based on optimal similarity and device, it is related to mobile positioning technique field, methods described includes：The signal characteristic of fingerprint reference point in position in the signal characteristic of point to be determined and location fingerprint database is subjected to Euclidean distance matching treatment and similarity mode processing, it is determined that the multiple optimal similarity location fingerprint reference points closest with the point to be determined；Using identified multiple optimal similarity location fingerprint reference points, the position coordinates of the point to be determined is calculated.By the Euclidean distance and similarity of the signal characteristic and the signal characteristic of position fingerprint reference point in location fingerprint database that calculate point to be determined, it is determined that to the optimal similar location fingerprint reference point in point to be determined, the diversity error of matching result is eliminated, positioning precision is improved.
Description
Technical field
It is more particularly to a kind of based on optimal similarity the present invention relates to mobile positioning technique field
Fingerprint positioning method and device.
Background technology
With the development of mobile Internet, people will increasingly to the demand of positioning and navigation feature
It is high.With global positioning system (Global Positioning System, GPS) and the Big Dipper
Extensive use has been obtained for the outdoor positioning technology of representative, but in complicated interior or closed-loop
Under border, such as large-scale waiting room, large-scale meeting-place, gymnasium, large-scale office building, underground mine
Scene, because signal blocks decay is serious, still can not be positioned.But communication network is multiple to these
Miscellaneous indoor environment is, it is necessary to meet focus covering anywhere or anytime, it is possible to utilize communication system
System base station carries out indoor positioning.
To realize running fix, multiple technologies scheme is currently suggested, is based on than more typical
The positioning of gyroscope, triangle polyester fibre and fingerprint location.There is error value product in the positioning based on gyroscope
Tired problem, it is impossible to use for a long time.Alignment system based on time measurement typically requires multiple bases
Standing strict time synchronization and needs to carry out high-precision measurements of arrival time, mesh to wireless signal
Preceding base station equipment is not supported.Fingerprint location need not know the position of base station and accurate channel mould
Type, therefore in specific implementation and positioning performance, all has larger excellent relative to triangle polyester fibre
More property.
Fingerprint location refers to the received signal strength by all reference points in test position fix region
(Received Signal Strength, RSS) signal and the signal spy for extracting RSS signals
Levy, signal characteristic is stored in location fingerprint data together with the position coordinates of corresponding reference point
Storehouse, then obtains the signal characteristic of point to be determined using same method, according to certain matching
Algorithm and location fingerprint database are matched, so as to obtain the estimated position of point to be determined.Often
Method have arest neighbors method (Nearest neighbor in signal Space, NNSS),
K- nearest neighbor algorithms (KNNSS) etc..
However, either NNSS algorithms or KNNSS algorithms, its principle are all by calculating
The signal strength values vector of the signal intensity vector of point to be determined and all sample points in fingerprint base
Distance selection reference fingerprint, and the signal intensity size of fingerprint is with apart from linear change,
It is difficult to ensure that the quality for the reference fingerprint selected, and then influence the degree of accuracy of positioning result and steady
It is qualitative so that the precision of positioning result receives serious influence.
The content of the invention
The technical problem that the technical scheme provided according to embodiments of the present invention is solved is how to improve
Fingerprint location precision.
The fingerprint positioning method based on optimal similarity provided according to embodiments of the present invention, bag
Include：
By fingerprint reference point in position in the signal characteristic of point to be determined and location fingerprint database
Signal characteristic carry out Euclidean distance matching treatment and similarity mode processing, it is determined that with it is described undetermined
The closest multiple optimal similarity location fingerprint reference points in site；
Using identified multiple optimal similarity location fingerprint reference points, calculate described to be positioned
The position coordinates of point.
Preferably, the signal characteristic is received signal strength vector, described determination with it is described
The step of closest multiple optimal similarity location fingerprint reference points in point to be determined, includes：
By in location fingerprint database described in the received signal strength vector sum of the point to be determined
The received signal strength vector of location fingerprint reference point carries out Euclidean distance matching treatment respectively, really
Determine the minimum N number of location fingerprint reference point of Euclidean distance；
By N number of location fingerprint reference described in the received signal strength vector sum of the point to be determined
The received signal strength vector of point carries out similarity mode processing respectively, determines similarity maximum
N location fingerprint reference point as optimal similarity location fingerprint reference point, wherein,
2≤n≤N,N>3。
Preferably, n maximum location fingerprint reference point of described determination similarity is as optimal
The step of similarity location fingerprint reference point, includes：
It is strong to the reception signal between the point to be determined and N number of location fingerprint reference point
The similarity of degree vector is respectively calculated, and obtains N number of similarity；
By being ranked up to resulting N number of similarity, it is determined that maximum n similarity and
N location fingerprint reference point of the correspondence n similarity.
Preferably, cosine similarity algorithm or amendment cosine similarity algorithm or Pearson are utilized
Similarity algorithm carries out Similarity Measure.
Preferably, it is described to utilize identified multiple optimal similarity location fingerprint reference points, meter
The step of position coordinates for calculating the point to be determined, includes：
Entered by the position coordinates to identified multiple optimal similarity location fingerprint reference points
Row weighting is handled, and obtains the position coordinates of the point to be determined.
The storage medium provided according to embodiments of the present invention, it stores above-mentioned based on most for realizing
The program of the fingerprint positioning method of excellent similarity.
The fingerprint location device based on optimal similarity provided according to embodiments of the present invention, bag
Include：
Optimal similarity fingerprint determination module, for the signal characteristic of point to be determined and position to be referred to
The signal characteristic of position fingerprint reference point carries out Euclidean distance matching treatment and phase in line database
Like degree matching treatment, it is determined that the multiple optimal similarity positions closest with the point to be determined
Fingerprint reference point；
Point to be determined position determination module, for utilizing identified multiple optimal similarity positions
Fingerprint reference point, calculates the position coordinates of the point to be determined.
Preferably, the signal characteristic is received signal strength vector, and the optimal similarity refers to
Line determining module is by location fingerprint number described in the received signal strength vector sum of the point to be determined
Euclidean distance matching is carried out respectively according to the received signal strength vector of fingerprint reference point in position in storehouse
Processing, determines the minimum N number of location fingerprint reference point of Euclidean distance, and by the point to be determined
Received signal strength vector sum described in N number of location fingerprint reference point received signal strength to
Amount carries out similarity mode processing respectively, determines n maximum location fingerprint reference point of similarity
As optimal similarity location fingerprint reference point, wherein, 2≤n≤N, N>3.
Preferably, the optimal similarity fingerprint determination module is to the point to be determined and the N
The similarity of received signal strength vector between individual location fingerprint reference point is respectively calculated,
N number of similarity is obtained, by being ranked up to resulting N number of similarity, it is determined that maximum
N location fingerprint reference point of n similarity and the correspondence n similarity.
Preferably, the optimal similarity fingerprint determination module is using cosine similarity algorithm or repaiies
Sine and cosine similarity algorithm or Pearson similarity algorithms carry out Similarity Measure.
Preferably, the point to be determined position determination module passes through to identified multiple optimal phases
Processing is weighted like the position coordinates of degree location fingerprint reference point, the point to be determined is obtained
Position coordinates.
Technical scheme provided in an embodiment of the present invention has the advantages that：
Joined by the signal characteristic for calculating point to be determined with location fingerprint in location fingerprint database
The Euclidean distance and similarity of the signal characteristic of examination point, can select optimal similar to point to be determined
Location fingerprint reference point, eliminate matching result diversity error, improve positioning precision.
Brief description of the drawings
Fig. 1 is the fingerprint positioning method provided in an embodiment of the present invention based on optimal similarity
First block diagram；
Fig. 2 is the fingerprint location device provided in an embodiment of the present invention based on optimal similarity
First structure schematic diagram；
Fig. 3 is the second block diagram of localization method provided in an embodiment of the present invention；
Fig. 4 is the flow chart of localization method provided in an embodiment of the present invention；
Fig. 5 is certain market floor map provided in an embodiment of the present invention；
Fig. 6 is the second structural representation of fingerprint location device provided in an embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing to a preferred embodiment of the present invention will be described in detail, it will be appreciated that
Preferred embodiment described below is merely to illustrate and explain the present invention, and is not used to limit this
Invention.
Fig. 1 is the fingerprint positioning method provided in an embodiment of the present invention based on optimal similarity
First block diagram, as shown in figure 1, step includes：
Step S101：Position in the signal characteristic of point to be determined and location fingerprint database is referred to
The signal characteristic of line reference point carries out Euclidean distance matching treatment and similarity mode processing, it is determined that
Closest multiple optimal similarity location fingerprint reference points with point to be determined.
Above-mentioned signal characteristic is that (i.e. signal intensity vector, is power letter to received signal strength vector
Breath).
Specifically, first by the received signal strength vector sum location fingerprint data of point to be determined
The received signal strength vector of position fingerprint reference point is carried out at Euclidean distance matching respectively in storehouse
Reason, determines the minimum N number of location fingerprint reference point of Euclidean distance.Then connecing point to be determined
The received signal strength vector of collection of letters intensity vector and N number of location fingerprint reference point enters respectively
The processing of row similarity mode, determines n maximum location fingerprint reference point of similarity as optimal
Similarity location fingerprint reference point, furtherly, is referred to point to be determined and N number of location fingerprint
The similarity of received signal strength vector between point is respectively calculated, and can use cosine phase
Like degree algorithm or amendment cosine similarity algorithm or Pearson similarity algorithms, so as to obtain N
Individual similarity, by being ranked up to resulting N number of similarity, it is determined that n maximum phase
Like n location fingerprint reference point of n similarity of degree and correspondence.Wherein, 2≤n≤N, N>3,n
It is positive integer with N.
Wherein, location fingerprint database is the database pre-established in off-line case, the number
Each location fingerprint reference point (i.e. reference point or reference fingerprint point or sample point) is included according to storehouse
Fingerprint, the fingerprint includes position and the signal characteristic of the location fingerprint reference point.
Step S102：Utilize identified multiple optimal similarity location fingerprint reference points, meter
Calculate the position coordinates of point to be determined.
Specifically, the position to identified multiple optimal similarity location fingerprint reference points is passed through
Put coordinate and be weighted processing, obtain the position coordinates of point to be determined.
It will appreciated by the skilled person that realize whole in above-described embodiment method or
Part steps can be by program to instruct the hardware of correlation to complete, program can store
In computer read/write memory medium, the program upon execution, including step S101 to walk
Rapid S102.Wherein, storage medium can be ROM/RAM, magnetic disc, CD etc..
Fig. 2 is the fingerprint location device provided in an embodiment of the present invention based on optimal similarity
First structure schematic diagram, as shown in Fig. 2 including optimal similarity fingerprint determination module and undetermined
Site location determining module.
Optimal similarity fingerprint determination module is used to refer to the signal characteristic of point to be determined and position
The signal characteristic of position fingerprint reference point carries out Euclidean distance matching treatment and phase in line database
Like degree matching treatment, it is determined that the multiple optimal similarity location fingerprints closest with point to be determined
Reference point.Specifically, signal characteristic is received signal strength vector, optimal similarity fingerprint
Determining module is by position in the received signal strength vector sum location fingerprint database of point to be determined
The received signal strength vector of fingerprint reference point carries out Euclidean distance matching treatment respectively, determines Europe
The minimum N number of location fingerprint reference point of formula distance, and by the received signal strength of point to be determined to
The received signal strength vector of amount and N number of location fingerprint reference point carries out similarity mode respectively
Processing, can be similar using cosine similarity algorithm or amendment cosine similarity algorithm or Pearson
Spend algorithm and carry out Similarity Measure, obtain N number of similarity, N number of similarity is ranked up,
It is determined that n location fingerprint reference point of maximum n similarity of n similarity and correspondence, and
It regard n location fingerprint reference point as optimal similarity location fingerprint reference point.Wherein,
2≤n≤N,N>3, n and N is positive integer.
Point to be determined position determination module, for utilizing identified multiple optimal similarity positions
Fingerprint reference point, calculates the position coordinates of point to be determined.Specifically, point to be determined position is true
Cover half block passes through the position coordinates to identified multiple optimal similarity location fingerprint reference points
Processing is weighted, the position coordinates of point to be determined is obtained.
Fig. 3 is the second block diagram of localization method provided in an embodiment of the present invention, as shown in figure 3,
Step includes：
Step S201：Build offline fingerprint database (i.e. fingerprint base or location fingerprint database).
Step S202：By in the characteristic information (i.e. signal characteristic) of point to be determined and fingerprint base
Data carry out Euclidean distance matching.
Matched by Euclidean distance, obtain the minimum several reference fingerprint point datas of Euclidean distance.
Step S203：By the characteristic information of point to be determined and the minimum several ginsengs of above-mentioned Euclidean distance
Examine fingerprint point data and carry out similarity mode.
By similarity mode, the maximum several fingerprint points of similarity are obtained.
Step S204：To several fingerprint point application weighting nearest neighbor algorithms that above-mentioned similarity is maximum
Estimate point to be determined final position.
It can be seen that, the fingerprint positioning method bag provided in an embodiment of the present invention based on optimal similarity
Include：Offline fingerprint database is built first；Secondly using point to be determined characteristic information with it is above-mentioned
Characteristic information in fingerprint base carries out Euclidean distance matching, by N number of fingerprint that Euclidean distance is minimum
It is used as new fingerprint base；Then entered using the characteristic information and above-mentioned new fingerprint base of point to be determined
Row similarity is solved, and obtains n maximum fingerprint of similarity, finally fingerprint application to n such as
WKNNSS (Weighted KNNSS) weighting algorithm tries to achieve final positioning result.During implementation
Including building offline fingerprint database stage and tuning on-line stage, specifically include：
Stage one：Build offline fingerprint database.
M base station is laid in localizing environment, K reference point is set in localization region, every
The received signal power of each base station of sampling at one reference point, reference point locations and power are believed
Breath joint constitutes fingerprint, and i-th of fingerprint representation is as follows：[xi,yi,zi,p1i,p2i,...,pMi]。
Wherein, xi, yi, zi are the positional information of i-th of reference point, p1i,p2i,...,pMiFor M base
Stand and build receiving power of the storehouse moment to i-th of reference point locations user equipment signal in fingerprint base,
It is individual from M that the user equipment for building i-th of reference point locations of storehouse moment in fingerprint base is received
The receiving power of the signal of base station.I span is 1 to K.
Stage two：Tuning on-line
Step 1：The signal intensity vector R that M base station is received at point to be determinedx
=[p1,p2,...,pM] in find out the effective signal strength values of m, m be less than M and more than 2 just
Integer.
Step 2：The signal intensity vector letter corresponding with fingerprint base received to point to be determined
Number intensity vector carries out Euclidean distance matching, by ask the signal intensity that point to be determined is received to
The Euclidean distance of amount signal intensity vector corresponding with fingerprint base, obtains Euclidean distance minimum
N number of fingerprint, N is the positive integer more than 3.
Euclidean distance is calculated using equation below：
Wherein, PxjRepresent the signal intensity that j-th of point to be determined base station is received, PjiRepresent the
I reference point receives the signal intensity vector of j-th of base station, and m represents valid signal strengths
Number.Qi represents i-th of reference point to the Euclidean distance of the signal intensity of point to be determined.
Step 3：N number of fingerprint that step 2 is obtained signal intensity vector successively with it is to be positioned
The signal intensity vector of point carries out similarity solution.Similarity algorithm may be selected cosine similarity,
Pearson correlation coefficient or amendment cosine similarity etc..
By taking cosine similarity as an example, calculated by equation below：
Wherein PxRepresent the signal intensity vector of point to be determined, PiRepresent in N number of fingerprint i-th
The signal intensity vector of fingerprint, | | * | | modulus computing is represented,<*>Expression asks inner product to calculate,
CosSim(Px,Pi) represent the cosine similarity coefficient of point to be determined and i-th of fingerprint point.Cosine phase
Bigger like degree coefficient, the correlation of the two is bigger.
Step 4：N number of cosine similarity coefficient is sorted from big to small, cosine phase is selected
Like n big values before degree coefficient, the corresponding n fingerprint of n cosine similarity coefficient is
The n fingerprint point nearest from point to be determined.
Step 5：Final positioning knot is tried to achieve to above-mentioned n fingerprint point application WKNNSS algorithms
Really.Calculation formula is as follows：In formula,
xk、yk、zkIt is the coordinate information of k-th of matching fingerprint.Weight wkObtained by weighting nearest neighbour method,
Formula is as follows：
ε is a very small real constant in formula, for avoiding the situation that denominator is 0.QkTable
Show k-th reference point to the Euclidean distance of the signal intensity of point to be determined.
Fig. 4 is the flow chart of localization method provided in an embodiment of the present invention, as shown in figure 4, step
Suddenly include：
Step S301：In fingerprint location region, sample point is set.
Step S302：The received signal power information of relatively each base station of sample point in sample area.
Step S303：The positional information of sample point and receiving power information consolidation are constituted into fingerprint
Storehouse.
Step S304：Select the received signal strength information of the related some base stations in point to be determined.
Step S305：By the power information of each fingerprint in the power information and fingerprint base of point to be determined
Carry out Euclidean distance matching, several minimum fingerprint points of selection Euclidean distance.
Step S306：The fingerprint point selected above-mentioned steps carries out cosine similarity with point to be determined
Solve, selection cosine similarity is just and several minimum corresponding fingerprint points.
Step S307：It is somebody's turn to do using special algorithm (such as WKNNSS) by the estimation of some candidate points
The position of terminal.
Wherein step S301 to step S303 is the step of offline fingerprint base builds the stage, step
The step of S304 to step S307 is the tuning on-line stage.
Because existing fingerprint method only selects reference fingerprint by signal intensity vector magnitude, very
It is difficult to ensure the quality for N number of fingerprint that card is selected, and then influences the degree of accuracy and stably of positioning result
Property.Particularly when the vector for the signal intensity composition that different base station is obtained has symmetry, sample
Matching result in this with respect to point to be determined can have diversity, it is impossible to differentiate which sample point
It is, apart from the closest point in point to be determined, reality to be there may be in the N number of reference fingerprint selected
The larger fingerprint of border physical location error so that position error fluctuation it is larger, positioning precision by
Have a strong impact on, the experience property of user is very poor.The skill that the present embodiment combination Fig. 5 is provided the present invention
Art method is described in further detail.Following embodiments be merely to illustrate the present invention and
It is not used in limitation the scope of the present invention.
Fig. 5 is certain market floor map provided in an embodiment of the present invention, as shown in figure 5,
In one 12 meters * 60 meters of market lay 6 access points (Access Point, AP) or
Base station.
Fingerprint location of the embodiment 1. based on intensity and direction
Stage one：Build offline fingerprint database
M=6 AP is laid in one 12 meters * 60 meters of market, K=50 is laid in market
The each AP of sampling received signal power at individual reference point, each reference point, by reference point
Position and power information joint constitute fingerprint, and i-th of fingerprint representation is as follows：
[xi,yi,zi,p1i,p2i,...,pMi].Wherein, xi, yi, zi are the positional information of i-th of reference point,
p1i,p2i,...,pMiThe storehouse moment is built to i-th of reference point locations user in fingerprint base for 6 base stations
The receiving power of device signal.I span is 1 to 50.
Stage two：Tuning on-line
Step 1：The signal intensity vector R received from point to be determinedx=[p1,p2,...,pM] in look for
Go out m=3 effective signal strength values, valid signal strengths gate valve is determined by market environment, this
Place is set to -100dBm.
Step 2：Seek the signal intensity vector letter corresponding with fingerprint base that point to be determined is received
Number intensity vector carries out Euclidean distance matching, obtains 6 minimum fingerprints of Euclidean distance.Utilize
Equation below calculates Euclidean distance：
Wherein, PxjRepresent the signal intensity that j-th of point to be determined AP is received, PjiRepresent i-th
Individual reference point receives j-th of AP signal intensity vector, and m represents valid signal strengths
Number.Qi represents i-th of reference point to the Euclidean distance of the signal intensity of point to be determined.
Step 3：The signal intensity of 6 minimum fingerprints of Euclidean distance that step 2 is obtained to
Amount carries out cosine similarity Algorithm for Solving with the signal intensity vector of point to be determined successively.Cosine phase
Calculated like degree by equation below：
Wherein, PxRepresent the signal intensity vector of point to be determined, PiRepresent in 6 fingerprints i-th
The signal intensity vector of fingerprint, | | * | | modulus computing is represented,<*>Expression asks inner product to calculate,
CosSim(Px,Pi) represent the cosine similarity coefficient of point to be determined and i-th of fingerprint point.Cosine phase
Bigger like degree coefficient, the correlation of the two is bigger.
Step 4：6 cosine similarity coefficients are sorted from big to small, cosine phase is selected
Like 3 big values before degree coefficient, corresponding 3 fingerprints of 3 cosine similarity coefficients are
The 3 fingerprint points nearest from point to be determined.
Step 5：Final positioning knot is tried to achieve to above-mentioned 3 fingerprints point application WKNNSS algorithms
Really (x, y, z), calculation formula is as follows：
In formula, xk、yk、zkIt is the coordinate information of k-th of matching fingerprint.Weight wkBy weighting neighbour
Method is obtained, and formula is as follows：
In formula, ε is a very small real constant, for avoiding the situation that denominator is 0.
Fingerprint location of the embodiment 2. based on optimal similarity
Stage one：Build offline fingerprint database
M=6 base station is laid in one 12 meters * 60 meters of market, K=50 is laid in market
Current reference point of being sampled at individual reference point, each reference point receives the signal work(of 6 base stations
Reference point locations and power information joint are constituted fingerprint, i-th of fingerprint representation is as follows by rate：
[xi,yi,zi,p1i,p2i,...,pMi].Wherein xi, yi, zi are the positional information of i-th of reference point,
p1i,p2i,...,pMiThe signal power of 6 base stations is received for i-th point of user equipment.I's
Span is 1 to 50.
Stage two：Tuning on-line
Step 1：The signal intensity vector R of 6 base stations is received from point to be determined user equipmentx
=[p1,p2,...,pM] in find out the valid signal strengths value for receiving m=3 base station, useful signal
Intensity gate valve is determined by market environment, and -98dBm is set to herein.
Step 2：Seek the signal intensity vector letter corresponding with fingerprint base that point to be determined is received
Number intensity vector carries out Euclidean distance matching, obtains 6 minimum fingerprints of Euclidean distance.Utilize
Equation below calculates Euclidean distance：
Wherein, PxjRepresent the signal intensity that j-th of point to be determined base station is received, PjiRepresent the
I reference point receives the signal intensity vector of j-th of base station, and m represents valid signal strengths
Number.Qi represents i-th of reference point to the Euclidean distance of the signal intensity of point to be determined.
Step 3：The signal intensity of 6 minimum fingerprints of Euclidean distance that step 2 is obtained to
Amount carries out Pearson similarity algorithm solutions with the signal intensity vector of point to be determined successively.
Pearson similarities are calculated by equation below：
Wherein, PxRepresent the signal intensity vector of point to be determined, PiRepresent in 6 fingerprints i-th
The signal intensity vector of fingerprint,The average value with setpoint signal intensity vector is represented,Table
Show the average value of the signal intensity vector of i-th of fingerprint, | | * | | modulus computing is represented,<*>Represent
Inner product is asked to calculate, Corr (Px,Pi) represent the Pearson phases of point to be determined and i-th of fingerprint point
Like degree coefficient.Pearson coefficient of similarity is bigger, and the correlation of the two is bigger.
Step 4：6 Pearson coefficient of similarity are sorted from big to small, selection is remaining
3 big values before string coefficient of similarity, corresponding 3 fingerprints of 3 cosine similarity coefficients
3 fingerprint points as from point to be determined recently.
Step 5：Final positioning knot is tried to achieve to above-mentioned 3 fingerprints point application WKNNSS algorithms
Really (x, y, z), calculation formula is as follows：
In formula, xk、yk、zkIt is the coordinate information of k-th of matching fingerprint.Weight wkBy weighting neighbour
Method is obtained, and formula is as follows：
ε is a very small real constant in formula, for avoiding the situation that denominator is 0.
It is symmetrical that the embodiment of the present invention can eliminate the signal intensity vector measured by different base station
Property caused by position matching diversity error, improve positioning precision.
Embodiment 3：
According to the fingerprint positioning method provided in above-mentioned embodiment, the embodiment of the present invention is also provided
The device of the above-mentioned fingerprint positioning method determined based on optimal similarity of application.
Fig. 6 is the second structural representation of fingerprint location device provided in an embodiment of the present invention, such as
Shown in Fig. 6, including：
Offline fingerprint database builds module, i.e., offline fingerprint database module, for fingerprint base
Foundation, in localizing environment lay M base station, localization region setting K reference point,
Reception signal of each base station or the terminal of being sampled at each reference point relative to each base station
Reference point locations and power information joint are constituted fingerprint by power.
Selecting module is received, for receiving the measured data of user equipment to report and filtering out effectively
Data.
Matching module, for location-server measured data and fingerprint base data are carried out it is European away from
From calculating, the minimum top n fingerprint of Euclidean distance is found out.
Determining module, it is similar with the progress of N number of finger print data to measured data for location-server
Degree is calculated, n optimal similarity fingerprints of selection.
Locating module, for location-server according to the optimal similarity finger print information profit selected
The positioning result of user equipment is obtained with WKNNSS methods.
Wherein, reception selecting module, matching module and determining module realize optimal similar jointly
The function of fingerprint determination module is spent, locating module realizes the work(of point to be determined position determination module
Energy.
Fingerprint location is carried out using mobile network base station, up fingerprint location and descending finger can be divided into
Line positions two ways, and up fingerprint location refers to UE transmitted reference signals, and multiple base stations are surveyed
UE institutes transmission signal power is measured, fingerprint is constituted and the fingerprint being pre-stored in database is carried out
Matching positioning.Descending fingerprint location refer to UE receive and measure multiple base stations transmission signal it is strong
Degree, constitutes fingerprint of the fingerprint with being pre-stored in database and carries out matching positioning.Base of the present invention
Combine the optimal similarity of determination fingerprint and measured data to be determined in RSS size and Orientations
Position, positioning precision is high, because wireless channel has a symmetry, therefore above and below the present invention is applied to
Fingerprint location is also applied for descending fingerprint location.
To sum up, embodiments of the invention have following technique effect：
By calculating the Euclidean distance of user's measured data and finger print data in fingerprint base and similar
Degree, while ensure that from size of data and direction related between reference fingerprint and point to be determined
Property, can select to the optimal similar reference fingerprint in point to be determined, eliminate fingerprint point with it is undetermined
The diversity error of site matching, improves positioning precision.
Although the present invention is described in detail above, the invention is not restricted to this, this skill
Art art personnel can carry out various modifications according to the principle of the present invention.Therefore, it is all according to
The modification that the principle of the invention is made, all should be understood to fall into protection scope of the present invention.
Claims (10)
1. a kind of fingerprint positioning method based on optimal similarity, including：
By fingerprint reference point in position in the signal characteristic of point to be determined and location fingerprint database
Signal characteristic carry out Euclidean distance matching treatment and similarity mode processing, it is determined that with it is described undetermined
The closest multiple optimal similarity location fingerprint reference points in site；
Using identified multiple optimal similarity location fingerprint reference points, calculate described to be positioned
The position coordinates of point.
2. according to the method described in claim 1, the signal characteristic is received signal strength
Vector, the described determination multiple optimal similarity positions closest with the point to be determined refer to
The step of line reference point, includes：
By in location fingerprint database described in the received signal strength vector sum of the point to be determined
The received signal strength vector of location fingerprint reference point carries out Euclidean distance matching treatment respectively, really
Determine the minimum N number of location fingerprint reference point of Euclidean distance；
By N number of location fingerprint reference described in the received signal strength vector sum of the point to be determined
The received signal strength vector of point carries out similarity mode processing respectively, determines similarity maximum
N location fingerprint reference point as optimal similarity location fingerprint reference point, wherein,
2≤n≤N, N ＞ 3.
3. method according to claim 2, the maximum n of described determination similarity is individual
The step of location fingerprint reference point is as optimal similarity location fingerprint reference point includes：
It is strong to the reception signal between the point to be determined and N number of location fingerprint reference point
The similarity of degree vector is respectively calculated, and obtains N number of similarity；
By being ranked up to resulting N number of similarity, it is determined that maximum n similarity and
N location fingerprint reference point of the correspondence n similarity.
4. method according to claim 3, remaining using cosine similarity algorithm or amendment
String similarity algorithm or Pearson similarity algorithms carry out Similarity Measure.
5. according to the method described in claim 1, described utilize identified multiple optimal phases
Include like the step of spending location fingerprint reference point, the position coordinates of the calculating point to be determined：
Entered by the position coordinates to identified multiple optimal similarity location fingerprint reference points
Row weighting is handled, and obtains the position coordinates of the point to be determined.
6. a kind of fingerprint location device based on optimal similarity, including：
Optimal similarity fingerprint determination module, for the signal characteristic of point to be determined and position to be referred to
The signal characteristic of position fingerprint reference point carries out Euclidean distance matching treatment and phase in line database
Like degree matching treatment, it is determined that the multiple optimal similarity positions closest with the point to be determined
Fingerprint reference point；
Point to be determined position determination module, for utilizing identified multiple optimal similarity positions
Fingerprint reference point, calculates the position coordinates of the point to be determined.
7. device according to claim 6, the signal characteristic is received signal strength
Vector, the optimal similarity fingerprint determination module is by the received signal strength of the point to be determined
The received signal strength vector of position fingerprint reference point in location fingerprint database described in vector sum
Euclidean distance matching treatment is carried out respectively, determines the minimum N number of location fingerprint reference of Euclidean distance
Point, and N number of location fingerprint described in the received signal strength vector sum of the point to be determined is referred to
The received signal strength vector of point carries out similarity mode processing respectively, determines similarity maximum
N location fingerprint reference point as optimal similarity location fingerprint reference point, wherein,
2≤n≤N, N ＞ 3.
8. device according to claim 7, the optimal similarity fingerprint determination module
To the received signal strength between the point to be determined and N number of location fingerprint reference point to
The similarity of amount is respectively calculated, and obtains N number of similarity, by resulting N number of phase
It is ranked up like degree, it is determined that n maximum similarity and n of the correspondence n similarity
Location fingerprint reference point.
9. device according to claim 8, the optimal similarity fingerprint determination module
Utilize cosine similarity algorithm or amendment cosine similarity algorithm or Pearson similarity algorithms
Carry out Similarity Measure.
10. device according to claim 6, the point to be determined position determination module is led to
Cross and the position coordinates of identified multiple optimal similarity location fingerprint reference points is weighted
Processing, obtains the position coordinates of the point to be determined.
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 true CN107318084A (en) | 2017-11-03 |
| CN107318084B 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) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108680940A (en) * | 2018-05-17 | 2018-10-19 | 中国科学院微电子研究所 | Auxiliary positioning method and device for automatic driving vehicle |
| 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 |
| CN108834053A (en) * | 2018-06-20 | 2018-11-16 | 北京邮电大学 | A kind of localization method, device and equipment |
| 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 |
| 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 |
| CN112230243A (en) * | 2020-10-28 | 2021-01-15 | 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 |
| CN112823289A (en) * | 2018-10-12 | 2021-05-18 | 因温特奥股份公司 | System and method for location determination in a building |
| CN113259837A (en) * | 2021-04-29 | 2021-08-13 | 西安电子科技大学 | Indoor positioning method based on angle estimation and fingerprint positioning algorithm |
| CN113723234A (en) * | 2021-08-17 | 2021-11-30 | 中铁第四勘察设计院集团有限公司 | Passive sensing and positioning method and device for fingerprint and storage medium |
| CN114002646A (en) * | 2021-11-02 | 2022-02-01 | 陈予朋 | Artificial intelligence-based livestock individual real-time tracking method |
Families Citing this family (15)
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN113613167B (en) * | 2021-08-05 | 2022-07-12 | 广东工业大学 | Indoor positioning method and device based on transfer learning |
| 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 |
| 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 |
|---|---|---|---|---|
| EP2698015B1 (en) * | 2011-04-13 | 2021-07-14 | Telefonaktiebolaget LM Ericsson (publ) | 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 |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108680940A (en) * | 2018-05-17 | 2018-10-19 | 中国科学院微电子研究所 | Auxiliary positioning method and device for automatic driving vehicle |
| CN108834053A (en) * | 2018-06-20 | 2018-11-16 | 北京邮电大学 | A kind of localization 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 |
| CN112823289A (en) * | 2018-10-12 | 2021-05-18 | 因温特奥股份公司 | System and method for location 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 |
| 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 |
| CN112230243A (en) * | 2020-10-28 | 2021-01-15 | 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 |
| CN113259837A (en) * | 2021-04-29 | 2021-08-13 | 西安电子科技大学 | Indoor positioning method based on angle estimation and fingerprint positioning algorithm |
| CN113723234A (en) * | 2021-08-17 | 2021-11-30 | 中铁第四勘察设计院集团有限公司 | Passive sensing and positioning method and device for fingerprint and storage medium |
| 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 |
| CN114002646A (en) * | 2021-11-02 | 2022-02-01 | 陈予朋 | Artificial intelligence-based livestock individual real-time tracking method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017185828A1 (en) | 2017-11-02 |
| CN107318084B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107318084A (en) | A kind of fingerprint positioning method and device based on optimal similarity | |
| CN103957505B (en) | A kind of action trail detection and analysis and service provider system and method based on AP | |
| CN103379619B (en) | A kind of localization method and system | |
| CN105043380A (en) | Indoor navigation method based on a micro electro mechanical system, WiFi (Wireless Fidelity) positioning and magnetic field matching | |
| CN103369466B (en) | A kind of map match assists indoor orientation method | |
| CN106574975A (en) | Trajectory matching using peripheral signal | |
| CN103167606B (en) | Based on the WLAN indoor orientation method of rarefaction representation | |
| CN104320759B (en) | Based on fixedly target indoor locating system fingerprint base construction method | |
| CN107277772A (en) | A kind of wireless access independent positioning method and device, computer-readable recording medium | |
| CN103200667A (en) | A method of positioning, an electronic device using the method, and a positioning system thereof | |
| CN107071902A (en) | One kind is based on mixed filtering and Power Exponent Mapping WIFI indoor orientation methods | |
| CN104581945B (en) | The WLAN indoor orientation methods of semi-supervised APC clustering algorithms based on distance restraint | |
| CN109029429A (en) | Multi-categorizer overall situation dynamic fusion localization method based on WiFi and earth magnetism fingerprint | |
| CN103888979B (en) | Indoor positioning method based on wireless local area network | |
| Kwak et al. | Magnetic field based indoor localization system: A crowdsourcing approach | |
| CN106954190A (en) | A kind of WIFI indoor orientation methods based on index mapping domain | |
| CN105444755B (en) | Indoor orientation method based on space noise signal | |
| CN108632763A (en) | A kind of indoor positioning weighting k nearest neighbor method based on WiFi fingerprints | |
| CN106291609A (en) | A kind of RTK precision assessment method | |
| Wang et al. | Study on improvement of fingerprint matching algorithm in wireless LAN based indoor positioning system | |
| CN106792533A (en) | Multidrop topology based on WiFi and the position measuring and calculating of pedestrian's boat approaches localization method | |
| CN114608560A (en) | Passive combined indoor positioning system and method based on intelligent terminal sensor | |
| CN104619017B (en) | Indoor locating system WiFi access point deployment scheme based on map auxiliary | |
| CN107872873A (en) | Internet-of-things terminal localization method and device | |
| Shao et al. | DePos: Accurate orientation-free indoor positioning with deep convolutional neural networks |
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 |