CN106792465A - A kind of indoor fingerprint map constructing method based on mass-rent fingerprint - Google Patents

A kind of indoor fingerprint map constructing method based on mass-rent fingerprint Download PDF

Info

Publication number
CN106792465A
CN106792465A CN201611219485.9A CN201611219485A CN106792465A CN 106792465 A CN106792465 A CN 106792465A CN 201611219485 A CN201611219485 A CN 201611219485A CN 106792465 A CN106792465 A CN 106792465A
Authority
CN
China
Prior art keywords
fingerprint
grid
rent
mass
fitting
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
Application number
CN201611219485.9A
Other languages
Chinese (zh)
Other versions
CN106792465B (en
Inventor
王邦
叶炎珍
王忠思
刘文予
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
Original Assignee
Huazhong University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN201611219485.9A priority Critical patent/CN106792465B/en
Publication of CN106792465A publication Critical patent/CN106792465A/en
Application granted granted Critical
Publication of CN106792465B publication Critical patent/CN106792465B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • H04W4/029—Location-based management or tracking services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • 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
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Collating Specific Patterns (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

A kind of indoor fingerprint map constructing method based on mass-rent fingerprint, belong to the indoor positioning technologies based on fingerprint, solve the problems, such as the existing mass-rent fingerprint positions built existing for indoor fingerprint map based on mass-rent fingerprint mark that inaccurate, dimension is different and skewness caused by positional accuracy it is not high and computationally intensive, for communicating and radio network technique field.The present invention includes that grid division step, acquisition mass-rent fingerprint step, mass-rent fingerprint splitting step, mass-rent fingerprint quantity judge step, directly AP screenings step, construction grid fingerprint step and fingerprint surface fitting step.The present invention reduces fingerprint collecting workload, be conducive to improving positional accuracy, while reducing fingerprint contrast workload.

Description

A kind of indoor fingerprint map constructing method based on mass-rent fingerprint
Technical field
A kind of indoor positioning technologies the invention belongs to be based on fingerprint, and in particular to indoor fingerprint ground based on mass-rent fingerprint Figure construction method, for communicating and radio network technique field.
Background technology
With continuing to develop for mobile Internet, people are continuously increased for indoor location-based information service.It is indoor Location-based information service is mainly including parking stall lookup, logistics management, commercial promotions Information Push Service etc..At present Multiple indoor location technology is developed, is mainly included：WiFi positioning, bluetooth positioning, infrared positioning etc..Wherein based on WiFi Indoor positioning technologies have obtained extensive research, and its reason is that the WiFi signal of large scale deployment greatlys save basis The cost of facility, and present smart mobile phone can detect WiFi signal.
Indoor positioning technologies based on WiFi are broadly divided into two classes:Location technology based on range finding and the positioning based on fingerprint Technology.Location technology based on range finding is mainly using the polygon location technology based on propagation model range finding.However, in complicated room In interior environment, due to the complicated indoor arrangement such as separating and stopping, and the signal non line of sight that signal reflex scattering etc. is caused is passed Broadcast so that propagation model parameter is estimated to be forbidden very much, so that distance estimations error is larger, under causing positioning performance significantly Drop.
The research emphasis for being currently based on fingerprint location technology are constructed fingerprint and are set up fingerprint map based on WiFi signal. Location technology based on fingerprint is mainly made up of two stages：Offline fingerprint Map building stage and online equipment positioning stage. The offline fingerprint Map building stage builds indoor fingerprint ground generally by the fingerprint in professional survey crew measurement known location Figure.Online equipment positioning stage mainly compares the reference fingerprint in mobile phone real time fingerprint and fingerprint map, with the side based on probability Method or the method based on similarity mode are positioned.Location technology based on fingerprint can be divided into again traditional to be surveyed based on scene The location technology of survey and the location technology based on mass-rent fingerprint.Traditional location technology based on on-site land survey is by special survey Amount personnel carry out signal measurement to build indoor fingerprint map in the reference point of known coordinate.Although this technology has higher Positional accuracy, but this technology need specialty survey crew, time and effort consuming.
In recent years, some scholars propose the indoor positioning technologies based on mass-rent fingerprint, and its thought is mainly used to one As crowd carry out conscious or random measurement and originated as fingerprint, it is to avoid the process of special messenger's on-site land survey, moreover it is possible to keep The frequent renewal of mass-rent data, adapts to the change of environment.But it is new that the indoor positioning technologies based on mass-rent fingerprint bring some Problem, mainly includes：(1) mass-rent fingerprint positions mark is inaccurate.Either using mass-rent user actively mark by the way of or Using the passive notation methods of path matching, compared to the measurement of on-site land survey professional, the mark of mass-rent fingerprint positions all can There is larger error；(2) mass-rent fingerprint dimension is different.Because WiFi signal propagation distance is limited, may be in some functional areas Domain can receive more access point (AP, Access Point) signal and be merely able to receive less AP in other positions Signal, in addition, the quantity of AP signals that different user is received using different brands mobile phone is also differed, so as to cause to receive Mass-rent fingerprint there are different AP set and length；(3) mass-rent fingerprint skewness.Limitation and use due to indoor arrangement Family gathers the uncontrolled of behavior, so as to cause to receive the mass-rent fingerprint positions skewness for obtaining, some positions for easily reaching The place that there may be more mass-rent fingerprint and be difficult to reach comprises only less mass-rent fingerprint, or even some places do not have at all There is mass-rent fingerprint.
The content of the invention
The present invention provides a kind of indoor fingerprint map constructing method based on mass-rent fingerprint, solves existing based on mass-rent fingerprint Build the mass-rent fingerprint positions existing for indoor fingerprint map mark that inaccurate, dimension is different and skewness caused by positioning it is accurate Exactness problem not high and computationally intensive.
A kind of indoor fingerprint map constructing method based on mass-rent fingerprint provided by the present invention, including grid division step Suddenly mass-rent fingerprint step, mass-rent fingerprint splitting step, mass-rent fingerprint quantity, are obtained and judges step, directly AP screenings step, construction Grid fingerprint step and fingerprint surface fitting step：
(1) grid division step：
Plane right-angle coordinate is set up, planar target region is divided into what K was not overlapped each other according to its physical arrangement Functional area, and be the of substantially equal grid of size by each functional regional division, wherein, k-th functional regional division is J K () individual grid, the grid centre coordinate of j-th grid is designated as (Xj, Yj), j=1,2 ..., J (k), k=1,2 ..., K；K is for just Integer；
(2) mass-rent fingerprint step is obtained：
The existing WiFi signal in target area is gathered by way of run trace, frequency acquisition is 0.5~2Hz, walking Track limits walkable region in the target area, and the quantity of run trace should reach numf >=0.5 in target area, numf It is every square metre and includes mass-rent fingerprint quantity；Every run trace near linear and the walking that remains a constant speed substantially, and record every Starting point coordinate (the x of run traceb,yb) and terminate point coordinates (xe,ye), the fingerprint set l of the run tracetraj：ltraj=< (xb,yb),(xe,ye),(f1,f2,…,fT)>；
Wherein, t-th mass-rent fingerprint f in run tracet：T is sampling in run trace Mass-rent fingerprint quantity, rt2To receive the 2nd signal intensity of AP in t-th mass-rent fingerprint, below analogize；NfIt is t-th The quantity of AP is received in mass-rent fingerprint；According to the distribution situation of walkable region, the length of track is indefinite；According to difference Pedestrian's walking speed is different, and mass-rent fingerprint quantity is different on track；Due to AP limited coverage areas, received in each mass-rent fingerprint The number of AP be unequal；
To each bar run trace, by starting point coordinate (xb,yb) and terminate point coordinates (xe,ye) line segment on, by row Mass-rent fingerprint quantity in track is walked, an approximate coordinate is evenly distributed to each mass-rent fingerprint；In k-th functional area, i-th many Bag fingerprint fiCoordinate be designated as (xi, yi), i=1,2 ... I (k), I (k) they are the number comprising mass-rent fingerprint in k-th functional area Mesh；
(3) mass-rent fingerprint splitting step：
In same functional area, i-th mass-rent fingerprint f is calculatediTo j-th Euclidean distance at the grid center of grid dij：
Judge whether dij≤ R, be, to split Probability pijBy i-th mass-rent fingerprint fiThe grid of j-th grid is added to refer to Line supported collection GFjIn, otherwise, in grid fingerprint supported collection GFjIn be added without i-th mass-rent fingerprint fi, it is formulated as：GFj =GFj∪{fi}pij, dij≤ R, 90cm≤split threshold value R≤150cm；
A mass-rent fingerprint is split in multiple grids in this step the reason for be：On the one hand, received based on mass-rent mode The fingerprint position information mark that collection is obtained is inaccurate；On the other hand, even if part mass-rent fingerprint position information is labeled in correctly In grid, according to signal propagation characteristicses, the signal that the signal value received in certain position can represent its adjacent smaller area is special Levy；
(4) mass-rent fingerprint quantity judges step：
Judge in target area whether numf >=2, be to carry out step (5)；Otherwise carry out step (6)；
Even if numf >=2, due to mass-rent fingerprint skewness, the regional area that still some can not be reached does not exist mass-rent Fingerprint, grid fingerprint is obtained using step (5) and step (7)；As 0.5≤numf ＜ 2, obtained using step (6) and step (7) To grid fingerprint；
(5) AP screenings step：
For each grid of same functional area, judge whether split the mass-rent fingerprint for obtaining in its grid fingerprint supported collection Number >=Q, screening threshold value Q >=3, are to carry out AP screenings to the grid fingerprint supported collection, and construct grid fingerprint；Otherwise enter Row step (7)；
(6) grid fingerprint step is directly constructed：
For each grid of same functional area, the mass-rent obtained with the presence or absence of fractionation in its grid fingerprint supported collection is judged Fingerprint, is present, and grid fingerprint is directly constructed to the grid；Otherwise carry out step (7)；
(7) fingerprint surface fitting step：
For corresponding j-th grid of grid fingerprint supported collection, its grid centre coordinate is (Xj, Yj), it is neighbouring based on its Grid fingerprint, for each AP that neighbouring grid fingerprint is included, using the wireless of fingerprint surface fitting one local continuous of construction Electric map, the computation grid centre coordinate (X in the radio mapj, Yj) place each AP fitted signal intensity value, and will Its as the grid grid fingerprint；It is to screen step or directly construct grid fingerprint step by AP to obtain adjacent to grid fingerprint The grid fingerprint of the neighbouring grid for arriving.
In the step (3), Probability p is splitij=1, or
Wherein, dij≤ R, L be i-th mass-rent fingerprint according to threshold value R is split, be split to the quantity of neighbouring grid.
Described indoor fingerprint map constructing method, it is characterised in that：
In the step (5), for j-th grid, for its grid fingerprint supported collection GFjAP is carried out to screen and construct grid Lattice fingerprint includes following sub-step：
(5.1) the individual mass-rent fingerprint of M (j) therein will be split to, the RSS of one M (j) of construction × N (j) dimensions (receives signal Intensity, Received Signal Strength) matrix RM(j)×N(j)：
Wherein, rmnFor m-th mass-rent fingerprint receives n-th signal intensity of AP, m=1 ..., M (j), n=1 ..., N J number and the number of the AP for receiving that (), M (j) and N (j) represent mass-rent fingerprint in the grid fingerprint supported collection respectively；
If not receiving n-th signal of AP in m-th mass-rent fingerprint, r is mademn=0；Because the mass-rent in grid refers to Line gathers comprising different AP and length differs, therefore matrix RM(j)×N(j)It is sparse matrix；
(5.2) RSS matrixes R is calculatedM(j)×N(j)The variance V of the non-zero values matrix unit of middle each columnn：
Wherein,Represent the average of the signal intensity that n-th AP is received in the grid, VnAs n-th AP is in phase Answer the variance of the signal value for receiving in grid；
(5.3) V is judged whethern≤ σ, 0≤variance threshold values σ≤0.5 is then in RSS matrixes RM(j)×N(j)In, reject VnInstitute Corresponding row, otherwise retain corresponding row；Obtain the new RSS matrixes of M (j) × N1 (j) dimensions
Wherein, N1 (j) is to reject the AP numbers after corresponding AP, N1 (j) ＜ N (j)；
(5.4) j-th grid fingerprint of grid is constructedWherein, obtained in grid fingerprint A-th signal value of AP
Wherein, pmjRepresent the fractionation probability in m-th mass-rent fingerprint j-th grid fingerprint supported collection of grid of addition.
The reason for rejecting AP in this way in sub-step (5.3) be, on the one hand, the mass-rent for being split to same grid refers to The time that line comes from different physical locations and receives is different, according to signal propagation characteristic, the signal of same AP in grid Intensity level should be not completely equivalent in theory；If institute comprising the AP of the signal strength values of certain AP in a grid Have essentially equal in mass-rent fingerprint, i.e., the required variance yields for obtaining is smaller, then it is assumed that the AP in this grid without distinguish can, because This is rejected；On the other hand, it is if certain AP is only contained in one or fewer number of mass-rent fingerprint in grid, i.e., required The variance yields for obtaining is smaller, then it is assumed that AP receptances in this grid are relatively low, it may be possible to provide inaccurate location information, or even Be probably noise signal, therefore rejected, thus the purpose of AP screenings be reject AP without separating capacity and receptance compared with Low AP.
Described indoor fingerprint map constructing method, it is characterised in that in step (6), for j-th grid, direct structure Making grid fingerprint includes following sub-step：
(6.1) its its grid fingerprint supported collection GF will be split tojIn the individual mass-rent fingerprints of M (j), construct M (j) × N The RSS matrixes R of (j) dimensionM(j)×N(j)：
Wherein, rmnFor m-th mass-rent fingerprint receives n-th signal intensity of AP, m=1 ..., M (j), n=1 ..., N J number and the number of the AP for receiving that (), M (j) and N (j) represent mass-rent fingerprint in the grid fingerprint supported collection respectively；
If not receiving n-th signal of AP in m-th mass-rent fingerprint, r is mademn=0；Because the mass-rent in grid refers to Line gathers comprising different AP and length differs, therefore matrix RM(j)×N(j)It is sparse matrix；
(6.2) j-th grid fingerprint of grid is constructedWherein, for being obtained in grid fingerprint The n signal value of AP
Wherein, pmjRepresent the fractionation probability in m-th mass-rent fingerprint j-th grid fingerprint supported collection of grid of addition.
Described indoor fingerprint map constructing method, it is characterised in that step (6) includes following sub-step：
(6.1) construction fitting fingerprint supported collection C：
Centered on the grid, successively search whether it refers to adjacent to grid with grid by way of expanding outwardly Line, until the grid number with grid fingerprint reaches fit threshold S, S >=6, so as to the fitting fingerprint for obtaining the grid is supported Collect C, C is made up of the centre coordinate and its corresponding grid fingerprint of the grid with grid fingerprint；
(6.2) object function θ is built：
Wherein,It is binary polynomial signal intensity fitting functionIn g-th value of grid, table Show in fitting fingerprint supported collection C, the fitted signal intensity value of g-th grid, s-th AP；
Wherein, ωscdIt is fitting coefficient, Xg、YgIt is g-th horizontal, the ordinate, index c=1 ..., p at grid center；Index D=1 ..., q；To avoid over-fitting and reducing computation complexity, p, q=2；
For in g-th grid fingerprint of grid, s-th signal strength values of AP；| C | represents fitting fingerprint supported collection C The number of the middle grid that there is grid fingerprint；
(6.3) fitting coefficient ω is asked forscd：
Object function θ is asked on fitting coefficient ωscdPartial derivative, make partial derivative for 0, that is, cause that object function θ has Minimum value, obtains fitting coefficient ωscd：
Wherein, intermediate symbols
Intermediate symbols
Exponent e=1 ..., p, index h=1 ..., q；
(6.4) by the grid centre coordinate (X of the gridj, Yj) and fitting coefficient ωscdSubstitute into binary polynomial signal intensity Fitting functionTo ask for s-th fitted signal intensity value of AP in the gridThen grid of the grid Lattice fingerprint isWherein,S=1 ..., N2 (j).
In sub-step (5.4)In sub-step (6.2)In sub-step (7.4)Represent in corresponding sequence The signal value of a-th, n-th or s-th AP for receiving.
During the construction fitting fingerprint supported collection of sub-step 0, each grid has its 8 neighborhood grid, surrounds 8 neighborhood grids Outer layer be 16 neighborhood grids, surround 16 neighborhood grids outer layer be 24 neighborhood grids ..., it is so successively searched from inside to outside Whether neighbouring grid has grid fingerprint；The grid fingerprint obtained by using fingerprint surface fitting technology is not involved in constructing other Grid is fitted the process of fingerprint supported collection.Its reason is that the grid fingerprint that fitting is obtained is used adjacent to grid fingerprint by it Fingerprint surface fitting technology is obtained.And neighbouring grid fingerprint is obtained by mass-rent fingerprint supported collection, there is error in itself. If the grid fingerprint that fitting is obtained participates in constructing other grids fitting fingerprint supported collection, cumulative errors can be increasing.In addition, The neighbouring grid fingerprint chosen should be in same functional area with the grid for needing to be fitted, it is to avoid due to difference in functionality region Cause signal strength values to differ larger, be fitted inaccurate.
During the indoor fingerprint map built using the present invention, can enter using based on the Probabilistic Localization Methods of Bayes estimation Row positioning (is illustrated, the situation of 0.5≤numf ＜ 2 is similar, only AP quantity in grid fingerprint with the situation of numf >=2 It is different)：
After it experienced each step of the invention, each grid has corresponding grid fingerprint, j-th grid of grid Lattice fingerprint isOrUsing the letter of gaussian kernel function combination grid fingerprint Number intensityOrWith variance VaOr VsGaussian Profile is translated into, then obtains test fingerprint in j-th gridProbability：
Z=1 ..., N3, N3 represent the AP quantity that test fingerprint is received, when z-th AP and a-th AP or s-th AP are During same AP, above formula is just meaningful.
Wherein,OrRepresent in j-th grid, a or s AP signal strength values areOrIn resulting Gaussian Profile, the signal strength values for receiving areProbability；
Final choice probability P (Ft|Fj) maximum grid grid centre coordinate as the test fingerprint assessment position.
Wherein calculate probability P (Ft|Fj) during, FjWith FtIt is middle to include different AP set.Therefore specify, it is right In being present in FjIn and be not present in FtIn a or s AP, directly ignore its conditional probabilityOr Conversely, for being present in FtIn and be not present in FjIn z-th AP, its conditional probability is set to a less probability ValueOrIt is pmin=0.001.
The present invention is divided into K nonoverlapping functional area mutually according to the physical arrangement of target area first, and By the of substantially equal grid of each functional regional division size；The mass-rent fingerprint gathered using ruck, such as using walking The mode of track collects the collectable WiFi signal in target area, and carries out position mark to mass-rent fingerprint, for example, can use Path matching algorithm assigns approximate coordinate to each mass-rent fingerprint in track.Each mass-rent fingerprint is split to certain probability In one or more grids adjacent with its labeling position.For each grid, grid fingerprint supported collection is formed；And it is right Fingerprint carries out AP screenings in grid fingerprint supported collection, constructs grid fingerprint.For lack grid fingerprint supported collection or supported collection In containing less fingerprint quantity grid, using its adjacent to grid grid fingerprint, by fingerprint be fitted construct its grid fingerprint, It is fitted for example with fingerprint surface fitting technology and obtains grid fingerprint.
Using the indoor fingerprint map that the present invention builds, position assessment is carried out to test fingerprint using the method for probability fixed Position.
Compared with prior art, the present invention has following beneficial effect：
(1) fingerprint collecting workload is reduced：As a result of mass-rent fingerprint splitting step, fingerprint is split to multiple grids In, fingerprint quantity is increased, make it utilize the less mass-rent fingerprint there is preferable positioning result.
(2) be conducive to improving positional accuracy：As a result of mass-rent fingerprint splitting step, mass-rent fingerprint is split to many In individual grid, solve the problems, such as that mass-rent fingerprint positions mark is inaccurate；As a result of mass-rent fingerprint splitting step and refer to Line surface fitting step, is split and fingerprint fitting technique using fingerprint, solves the problems, such as fingerprint positions skewness；Due to adopting Step is screened with AP, AP screenings are carried out, the low AP of receptance, reduces the influence of noise signal in rejecting grid；Above three The combination of process greatly facilitates raising positional accuracy.
(3) fingerprint contrast workload is reduced：The indoor fingerprint map based on grid is set up, positioning stage needs the finger of contrast Line quantity is only related to the number of grid, is considerably less than the quantity of mass-rent fingerprint.Further, since employing AP screening steps, AP Screening reduces the computation complexity of fingerprint contrast.
Brief description of the drawings
Fig. 1 is schematic flow sheet of the invention；
Fig. 2 is the positioning scene figure of application example of the present invention；
Fig. 3 is the schematic diagram that a mass-rent fingerprint is split in the present invention multiple grids；
Fig. 4 is AP screening steps flow chart schematic diagrams；
Fig. 5 is fingerprint surface fitting steps flow chart schematic diagram；
During Fig. 6 is mean camber fingerprint fitting technique of the present invention, the schematic diagram of fitting fingerprint supported collection is obtained；
When Fig. 7 is using different mass-rent fingerprint numbers, different constructing plan average localization errors compare；
Fig. 8 is that different constructing plan position error cumulative distribution figures compare；
Fig. 9 is influence of the fingerprint mark error to different constructing plan average localization errors.
Specific embodiment
Below in conjunction with drawings and Examples, the present invention is described in more detail.
As shown in figure 1, the present invention includes grid division step, obtains mass-rent fingerprint step, mass-rent fingerprint splitting step, crowd Bag fingerprint quantity judges step, directly AP screenings step, construction grid fingerprint step and fingerprint surface fitting step.
As one embodiment of the present of invention：
(1) grid division step：
Set up plane right-angle coordinate, as shown in Fig. 2 by planar target region according to its physical arrangement be divided into 6 between teach Room and 1 corridor totally 7 functional areas not overlapped each other, wherein odd number classroom area is respectively 10.5 × 9.56m2, even number Number classroom area is respectively 10.5 × 7.76m2, corridor area is 32.6 × 3.62m2, cement wall thickness is between each functional area 0.3m, the gross area is about 717m2；And by each functional regional division be the of substantially equal grid of size, wherein, k-th function Region division is the individual grids of J (k), and the grid centre coordinate of j-th grid is designated as (Xj, Yj), j=1,2 ..., J (k), k=1, 2,…,7；
Such as, it is the grid that length and width are respectively about 0.6 meter, odd number by functional regional division in the scene of the present embodiment Classroom can be divided into 272 grids, and even number classroom can be divided into 221 grids, and corridor can be divided into 324 grids；
(2) mass-rent fingerprint step is obtained：
The existing WiFi signal in target area is gathered by way of run trace, frequency acquisition is 1Hz, run trace limit System in the target area walkable region (as shown in Fig. 2 walkable region mainly include between classroom inside corridor and classroom corridor, And without mass-rent fingerprint near seat in classroom, and run trace is to be randomly dispersed in walkable region, therefore, in target area Domain, mass-rent fingerprint positions skewness, some positions do not have mass-rent fingerprint at all), the quantity of run trace should reach target area Numf is about 10 and (in order to study influence of the mass-rent fingerprint quantity to positional accuracy, therefore have collected enough crowds in domain Bag fingerprint)；(in the present embodiment, walking speed is 1m/s, is received for every run trace near linear and the walking that remains a constant speed substantially The AP number changes scope for arriving is 100+~400+), and record every starting point coordinate (x of run traceb,yb) and terminating point Coordinate (xe,ye), the fingerprint set l of the run tracetraj：ltraj=<(xb,yb),(xe,ye),(f1,f2,…,fT)>；
Wherein, t-th mass-rent fingerprint f in run tracet：T is sampling in run trace Mass-rent fingerprint quantity, rt2To receive the 2nd signal intensity of AP in t-th mass-rent fingerprint, below analogize；NfIt is t-th The quantity of AP is received in mass-rent fingerprint；
In the corridor of Fig. 4, the fingerprint set l of the run traceAB：
lAB=<(xA,yA),(xB,yB),(f1,f2,…,f14)>,
Wherein, t-th mass-rent fingerprint f in run tracet：Run trace lABIn have 14 mass-rent fingerprints；
To each bar run trace, by starting point coordinate (xb,yb) and terminate point coordinates (xe,ye) line segment on, by row Mass-rent fingerprint quantity in track is walked, an approximate coordinate is evenly distributed to each mass-rent fingerprint；In k-th functional area, i-th many Bag fingerprint fiCoordinate be designated as (xi, yi), i=1,2 ... I (k), I (k) they are the number comprising mass-rent fingerprint in k-th functional area Mesh；
Carry out the collection of signal intensity as terminal device using MEIZU MX5 in testing.The fingerprint of collection is divided into two Part：A part is test fingerprint, and 725 test fingerprints are acquired altogether, and it is evenly distributed in the target at intervals of 1m × 1m In region, each test point sample within 20 seconds, and sampling per second is once；Another part is training fingerprint, is referred to for building interior Line map.Including the reference fingerprint positioned at walkable region that is obtained by on-site land survey, (1362, use ginseng to training fingerprint again The target of fingerprint is examined merely to increasing the quantity of fingerprint) and the mass-rent fingerprint (6830) that is obtained by track-wise.In Fig. 2 The point of black triangle represents grid fingerprint in classroom 412, and the black round dot in classroom 408 on curve is represented by track-wise The mass-rent fingerprint for obtaining, the pentagonal point of black represents the reference fingerprint obtained based on on-site land survey (using all in classroom 409 Reference fingerprint carry out contrast experiment).
(3) mass-rent fingerprint splitting step：
In same functional area, i-th mass-rent fingerprint f is calculatediTo j-th Euclidean distance at the grid center of grid dij：
Judge whether dij≤ R, be, to split Probability pijBy i-th mass-rent fingerprint fiThe grid of j-th grid is added to refer to Line supported collection GFjIn, otherwise, in grid fingerprint supported collection GFjIn be added without i-th mass-rent fingerprint fi, it is formulated as：GFj =GFj∪{fi}pij,dij≤ R, in the present embodiment, splits threshold value R and is set to 100cm；Split Probability pij=1；
As shown in figure 3, black round dot represents mass-rent fingerprint fi, black side's point represents grid center, calculate black round dot with Euclidean distance between black side's point, if be assigned to mass-rent fingerprint in the grid less than threshold value R is split by the Euclidean distance；
(4) mass-rent fingerprint quantity judges step：
Judge in target area whether numf >=2, be to carry out step (5)；Otherwise carry out step (6)；
(5) AP screenings step：
For each grid of same functional area, judge whether split the mass-rent fingerprint for obtaining in its grid fingerprint supported collection Number >=3, be AP screenings to be carried out to the grid fingerprint supported collection, and construct grid fingerprint；Otherwise carry out step (7)；
As shown in figure 4, in the step (5), for j-th grid, for its grid fingerprint supported collection GFjCarry out AP sieves Selecting and construct grid fingerprint includes following sub-step：
(5.1) the individual mass-rent fingerprint of M (j) therein, the RSS matrixes of one M (j) of construction × N (j) dimensions will be split to RM(j)×N(j)：
Wherein, rmnFor m-th mass-rent fingerprint receives n-th signal intensity of AP, m=1 ..., M (j), n=1 ..., N J number and the number of the AP for receiving that (), M (j) and N (j) represent mass-rent fingerprint in the grid fingerprint supported collection respectively；
If not receiving n-th signal of AP in m-th mass-rent fingerprint, r is mademn=0；Because the mass-rent in grid refers to Line gathers comprising different AP and length differs, therefore matrix RM(j)×N(j)It is sparse matrix；
(5.2) RSS matrixes R is calculatedM(j)×N(j)The variance V of the non-zero values matrix unit of middle each columnn：
Wherein,Represent the average of the signal intensity that n-th AP is received in the grid, VnAs n-th AP is in phase Answer the variance of the signal value for receiving in grid；
(5.3) V is judged whethern≤ σ, in the present embodiment, variance threshold values σ is set to 0, is then in RSS matrixes RM(j)×N(j) In, reject VnCorresponding row, otherwise retain corresponding row；Obtain the new RSS matrixes of M (j) × N1 (j) dimensions
Wherein, N1 (j) is to reject the AP numbers after corresponding AP, N1 (j) ＜ N (j)；
(5.4) j-th grid fingerprint of grid is constructedWherein, obtained in grid fingerprint A-th signal value of AP
Wherein, pmjRepresent the fractionation probability in m-th mass-rent fingerprint j-th grid fingerprint supported collection of grid of addition；
Table 1 gives AP quantity in each functional area received by average each fingerprint, performs AP screening processes institute The AP quantity of rejecting, and the ratio shared by the quantity of rejecting AP.As can be seen from Table 2, each functional area rejects the ratio of AP Rate is more than 25%.This procedure reduces the complexity of comparing calculation in position fixing process；
Table 1
APs Corridor 408 409 410 411 412 413
Average AP numbers 425.7 279.5 270.1 300.4 193.3 319.1 357.7
Reject AP 162.6 83.3 96.7 79.3 48.7 85.2 161.7
Reject ratio 0.382 0.298 0.358 0.264 0.252 0.267 0.452
(6) grid fingerprint step is directly constructed：
For each grid of same functional area, the mass-rent obtained with the presence or absence of fractionation in its grid fingerprint supported collection is judged Fingerprint, is present, and grid fingerprint is directly constructed to the grid；Otherwise carry out step (7)；
For j-th grid, directly constructing grid fingerprint includes following sub-step：
(6.1) its grid fingerprint supported collection GF will be split tojIn the individual mass-rent fingerprints of M (j), construct M (j) × N (j) The RSS matrixes R of dimensionM(j)×N(j)：
Wherein, rmnFor m-th mass-rent fingerprint receives n-th signal intensity of AP, m=1 ..., M (j), n=1 ..., N J number and the number of the AP for receiving that (), M (j) and N (j) represent mass-rent fingerprint in the grid fingerprint supported collection respectively；
If not receiving n-th signal of AP in m-th mass-rent fingerprint, r is mademn=0；Because the mass-rent in grid refers to Line gathers comprising different AP and length differs, therefore matrix RM(j)×N(j)It is sparse matrix；
(6.2) j-th grid fingerprint of grid is constructedWherein, for being obtained in grid fingerprint The n signal value of AP
Wherein, pmjRepresent the fractionation probability in m-th mass-rent fingerprint j-th grid fingerprint supported collection of grid of addition；
(7) fingerprint surface fitting step：
For corresponding j-th grid of grid fingerprint supported collection, its grid centre coordinate is (Xj, Yj), it is neighbouring based on its Grid fingerprint, for each AP that neighbouring grid fingerprint is included, using the wireless of fingerprint surface fitting one local continuous of construction Electric map, the computation grid centre coordinate (X in the radio mapj, Yj) place each AP fitted signal intensity value, and will Its as the grid grid fingerprint；It is to screen step or directly construct grid fingerprint step by AP to obtain adjacent to grid fingerprint The grid fingerprint of the neighbouring grid for arriving；
As shown in figure 5, step (7) includes following sub-step：
(7.1) construction fitting fingerprint supported collection C：
Centered on the grid, successively search whether it refers to adjacent to grid with grid by way of expanding outwardly Line, until the grid number with grid fingerprint reaches fit threshold S, in the present embodiment, fit threshold S is set to 6, so that To the grid fitting fingerprint supported collection C, C by the grid with grid fingerprint centre coordinate and its corresponding grid fingerprint structure Into；
As shown in fig. 6, numerical value 1 represents the grid has a grid fingerprint, numerical value 0 is represented in the grid without grid fingerprint, is needed Grid fingerprint is obtained using fingerprint surface fitting technology.For the grid of figure acceptance of the bid black square, refer to obtain fitting Line supported collection, first looks for whether there is grid fingerprint in the grid that nearest one layer of dotted line frame is included, if grid in these grids The quantity of lattice fingerprint reaches fit threshold, then stop searching, and the grid fingerprint obtained by lookup constitutes the fitting fingerprint of the grid Supported collection；Otherwise, seeking scope is expanded to the grid that following dotted line frame is included, continues previous action process；
(7.2) object function θ is built：
Wherein,It is binary polynomial signal intensity fitting functionIn g-th value of grid, table Show in fitting fingerprint supported collection C, the fitted signal intensity value of g-th grid, s-th AP；
Wherein, ωscdIt is fitting coefficient, Xg、YgIt is g-th horizontal, the ordinate, index c=1 ..., p at grid center；Index D=1 ..., q；To avoid over-fitting and reducing computation complexity, p, q=2；
For in g-th grid fingerprint of grid, s-th signal strength values of AP；| C | represents fitting fingerprint supported collection C The number of the middle grid that there is grid fingerprint；
(7.3) fitting coefficient ω is asked forscd：
Object function θ is asked on fitting coefficient ωscdPartial derivative, make partial derivative for 0, that is, cause that object function θ has Minimum value, obtains fitting coefficient ωscd：
Wherein, intermediate symbols
Intermediate symbols
Exponent e=1 ..., p, index h=1 ..., q；
(7.4) by the grid centre coordinate (X of the gridj, Yj) and fitting coefficient ωscdSubstitute into binary polynomial signal intensity Fitting functionTo ask for s-th fitted signal intensity value of AP in the gridThen grid of the grid Lattice fingerprint isWherein,S=1 ..., N2 (j).
Wherein, in sub-step (5.4)In sub-step (6.2)In sub-step (7.4)Represent in corresponding sequence The signal value of a-th, n-th or s-th AP received in row.
Split for the mass-rent fingerprint proposed in relatively of the invention, the property of AP screenings and fingerprint surface fitting these three steps Can, 6 kinds of schemes for building indoor fingerprint map are tested altogether, be respectively：
(a) without split+without screening+without fitting, on the basis of scheme, i.e., only include step of the invention (1) and step (2)；
(b) without split+without screening+fitting, i.e., only include step of the invention (1), step (2) and step (7)；
(c) fractionation+without screening+without fitting, i.e., only include step of the invention (1), step (2) and step (3)；
(d) fractionation+without screening+fitting, i.e., including step of the invention (1), step (2), step (3), step (6) and step Suddenly (7), it is adaptable in target area, the situation of 0.5≤numf ＜ 2；
E () splits+screening+fitting, i.e., including step of the invention (1), step (2), step (3), step (5) and step (7), it is adaptable in target area, the situation of numf >=2；；
On-site land survey is spaced 0.6 × 0.6m2
When Fig. 7 represents use different mass-rent fingerprint numbers, scheme (a), (b), (c), the comparing of (d) average localization error. It can be seen from figure 7 that scheme (c), (d) employ mass-rent fingerprint fractionation technology, it is average fixed for relative plan (a), (b) Level exactness tool improves a lot.It is also seen that mass-rent fingerprint splits technology with respect to fingerprint surface fitting technology performance from Fig. 7 More preferably, because, fitting fingerprint supported collection use grid fingerprint, there is certain error in itself, by fingerprint curved surface intend After conjunction, error can be bigger.It is the grid for being able to carry out AP screenings herein in Fig. 7, the reason for the performance for not describing AP screening schemes Premise be, it is necessary to ensure that each grid has a number of mass-rent fingerprint.
Fig. 8 represents scheme (a), (d), (e) and the position error cumulative distribution based on on-site land survey, and table 2 gives this Four kinds of average localization errors of scheme, 50% position error and 90% position errors.
Table 2
Average localization error (m) Averagely 50% 90%
On-site land survey is spaced 0.6 × 0.6m2 3.06 1.92 7.50
(a) without split+without screening+without fitting 1.96 1.20 4.63
(b) fractionation+without screening+fitting 1.65 1.02 3.65
C () splits+screening+fitting 1.48 1.01 3.16
Be can be seen that with reference to Fig. 8 and table 2, scheme (e) relative plan (a), (d) and the positioning performance based on on-site land survey have Larger raising.
Fig. 9 give fingerprint mark error to targeting scheme (a), (d), (e) average localization error influence.From Fig. 9 As can be seen that as the standard deviation of mark error increases, the average localization error of three kinds of schemes all increases, but scheme (d), E () change is relatively gentle, and the average localization error of scheme (e) is still minimum.Therefore, mass-rent fingerprint is split to multiple grid Go to reduce due to the inaccurate caused influence of fingerprint mark in lattice.

Claims (5)

1. a kind of indoor fingerprint map constructing method based on mass-rent fingerprint, including grid division step, acquisition mass-rent fingerprint step Suddenly, mass-rent fingerprint splitting step, mass-rent fingerprint quantity judge step, AP screenings step, directly construct grid fingerprint step and refer to Line surface fitting step, it is characterised in that：
(1) grid division step：
Plane right-angle coordinate is set up, planar target region is divided into the K function of not overlapping each other according to its physical arrangement Region, and be the of substantially equal grid of size by each functional regional division, wherein, k-th functional regional division is that J (k) is individual Grid, the grid centre coordinate of j-th grid is designated as (Xj, Yj), j=1,2 ..., J (k), k=1,2 ..., K；K is positive integer；
(2) mass-rent fingerprint step is obtained：
The existing WiFi signal in target area is gathered by way of run trace, frequency acquisition is 0.5~2Hz, run trace Walkable region in the target area is limited, the quantity of run trace should reach numf >=0.5 in target area, and numf is every Square metre include mass-rent fingerprint quantity；Every run trace near linear and the walking that remains a constant speed substantially, and record every walking Starting point coordinate (the x of trackb,yb) and terminate point coordinates (xe,ye), the fingerprint set l of the run tracetraj：ltraj=<(xb, yb),(xe,ye),(f1,f2,…,fT)>；
Wherein, t-th mass-rent fingerprint f in run tracet：T is the crowd of sampling in run trace Bag fingerprint quantity, rt2To receive the 2nd signal intensity of AP in t-th mass-rent fingerprint, below analogize；NfIt is t-th mass-rent The quantity of AP is received in fingerprint；
To each bar run trace, by starting point coordinate (xb,yb) and terminate point coordinates (xe,ye) line segment on, by walking rail Mass-rent fingerprint quantity in mark, an approximate coordinate is evenly distributed to each mass-rent fingerprint；In k-th functional area, i-th mass-rent refers to Line fiCoordinate be designated as (xi, yi), i=1,2 ... I (k), I (k) they are the number comprising mass-rent fingerprint in k-th functional area；
(3) mass-rent fingerprint splitting step：
In same functional area, i-th mass-rent fingerprint f is calculatediTo j-th Euclidean distance d at the grid center of gridij：
Judge whether dij≤ R, be, to split Probability pijBy i-th mass-rent fingerprint fiAdd j-th grid fingerprint branch of grid Support collection GFjIn, otherwise, in grid fingerprint supported collection GFjIn be added without i-th mass-rent fingerprint fi, it is formulated as：GFj=GFj ∪{fi}pij,dij≤ R, 90cm≤split threshold value R≤150cm；
(4) mass-rent fingerprint quantity judges step：
Judge in target area whether numf >=2, be to carry out step (5)；Otherwise carry out step (6)；
(5) AP screenings step：
For each grid of same functional area, judge whether the number of the mass-rent fingerprint for obtaining is split in its grid fingerprint supported collection Mesh >=Q, screening threshold value Q >=3, are to carry out AP screenings to the grid fingerprint supported collection, and construct grid fingerprint；Otherwise walked Suddenly (7)；
(6) grid fingerprint step is directly constructed：
For each grid of same functional area, judge that the mass-rent obtained with the presence or absence of fractionation in its grid fingerprint supported collection refers to Line, is directly to construct grid fingerprint to the grid；Otherwise carry out step (7)；
(7) fingerprint surface fitting step：
For corresponding j-th grid of grid fingerprint supported collection, its grid centre coordinate is (Xj, Yj), based on it adjacent to grid Fingerprint, for each AP that neighbouring grid fingerprint is included, a radio ground for local continuous is constructed using fingerprint surface fitting Figure, the computation grid centre coordinate (X in the radio mapj, Yj) place each AP fitted signal intensity value, and made It is the grid fingerprint of the grid；It screens step by AP adjacent to grid fingerprint or directly construction grid fingerprint step is obtained The grid fingerprint of neighbouring grid.
2. interior fingerprint map constructing method as claimed in claim 1, it is characterised in that：
In the step (3), Probability p is splitij=1, or
Wherein, dij≤ R, L be i-th mass-rent fingerprint according to threshold value R is split, be split to the quantity of neighbouring grid.
3. interior fingerprint map constructing method as claimed in claim 1 or 2, it is characterised in that：
In the step (5), for j-th grid, for its grid fingerprint supported collection GFjCarry out AP and screen and construct grid to refer to Line includes following sub-step：
(5.1) the individual mass-rent fingerprint of M (j) therein, the RSS matrixes R of one M (j) of construction × N (j) dimensions will be split toM(j)×N(j)：
Wherein, rmnFor m-th mass-rent fingerprint receives n-th signal intensity of AP, m=1 ..., M (j), n=1 ..., N (j), M J number and the number of the AP for receiving that () and N (j) represent mass-rent fingerprint in the grid fingerprint supported collection respectively；
If not receiving n-th signal of AP in m-th mass-rent fingerprint, r is mademn=0；Due to the mass-rent fingerprint bag in grid Gather containing different AP and length differs, therefore matrix RM(j)×N(j)It is sparse matrix；
(5.2) RSS matrixes R is calculatedM(j)×N(j)The variance V of the non-zero values matrix unit of middle each columnn：
V n = 1 M ( j ) &Sigma; m = 1 M ( j ) ( r m n - r n &OverBar; ) 2 , r m n &NotEqual; 0 ,
r n &OverBar; = 1 M ( j ) &Sigma; m = 1 M ( j ) r m n , r m n &NotEqual; 0 , n = 1 , ... , N ( j ) ,
Wherein,Represent the average of the signal intensity that n-th AP is received in the grid, VnAs n-th AP is in corresponding grid The variance of the signal value for receiving in lattice；
(5.3) V is judged whethern≤ σ, 0≤variance threshold values σ≤0.5 is then in RSS matrixes RM(j)×N(j)In, reject VnCorresponding Row, otherwise retain corresponding row；Obtain the new RSS matrixes of M (j) × N1 (j) dimensions
Wherein, N1 (j) is to reject the AP numbers after corresponding AP, N1 (j) ＜ N (j)；
(5.4) j-th grid fingerprint of grid is constructedWherein, a-th for being obtained in grid fingerprint The signal value of AP
r a j = &Sigma; m = 1 M ( j ) p m j &CenterDot; r m a &Sigma; m = 1 M ( j ) p m j , r m a &NotEqual; 0 , a = 1 , ... , N 1 ( j ) ;
Wherein, pmjRepresent the fractionation probability in m-th mass-rent fingerprint j-th grid fingerprint supported collection of grid of addition.
4. interior fingerprint map constructing method as claimed in claim 1 or 2, it is characterised in that in the step (6), for J-th grid, directly constructing grid fingerprint includes following sub-step：
(6.1) its grid fingerprint supported collection GF will be split tojIn the individual mass-rent fingerprints of M (j), one M (j) of construction × N (j) dimensions RSS matrixes RM(j)×N(j)：
Wherein, rmnFor m-th mass-rent fingerprint receives n-th signal intensity of AP, m=1 ..., M (j), n=1 ..., N (j), M J number and the number of the AP for receiving that () and N (j) represent mass-rent fingerprint in the grid fingerprint supported collection respectively；
If not receiving n-th signal of AP in m-th mass-rent fingerprint, r is mademn=0；Due to the mass-rent fingerprint bag in grid Gather containing different AP and length differs, therefore matrix RM(j)×N(j)It is sparse matrix；
(6.2) j-th grid fingerprint of grid is constructedWherein, n-th AP for being obtained in grid fingerprint Signal value
r n j = &Sigma; m = 1 M ( j ) p m j &CenterDot; r m n &Sigma; m = 1 M ( j ) p m j , r m n &NotEqual; 0 , n = 1 , ... , N ( j ) ;
Wherein, pmjRepresent the fractionation probability in m-th mass-rent fingerprint j-th grid fingerprint supported collection of grid of addition.
5. interior fingerprint map constructing method as claimed in claim 1 or 2, it is characterised in that step (7) includes following sub-step Suddenly：
(7.1) construction fitting fingerprint supported collection C：
Centered on the grid, successively search whether it has grid fingerprint adjacent to grid by way of expanding outwardly, directly Fit threshold S, S >=6, so as to obtain fitting fingerprint the supported collection C, C of the grid are reached to the grid number with grid fingerprint It is made up of the centre coordinate and its corresponding grid fingerprint of the grid with grid fingerprint；
(7.2) object function θ is built：
Wherein,It is binary polynomial signal intensity fitting functionIn g-th value of grid, represent In fitting fingerprint supported collection C, the fitted signal intensity value of g-th grid, s-th AP；
Wherein, ωscdIt is fitting coefficient, Xg、YgIt is g-th horizontal, the ordinate, index c=1 ..., p at grid center；Index d= 1,…,q；To avoid over-fitting and reducing computation complexity, p, q=2；
For in g-th grid fingerprint of grid, s-th signal strength values of AP；| C | is deposited in representing fitting fingerprint supported collection C In the number of the grid of grid fingerprint；
(7.3) fitting coefficient ω is asked forscd：
Object function θ is asked on fitting coefficient ωscdPartial derivative, make partial derivative for 0, that is, cause that object function θ has minimum Value, obtains fitting coefficient ωscd：
Wherein, intermediate symbols
Intermediate symbols
Exponent e=1 ..., p, index h=1 ..., q；
(7.4) by the grid centre coordinate (X of the gridj, Yj) and fitting coefficient ωscdSubstitute into the fitting of binary polynomial signal intensity FunctionTo ask for s-th fitted signal intensity value of AP in the gridThen the grid of the grid refers to Line isWherein,S=1 ..., N2 (j).
CN201611219485.9A 2016-12-26 2016-12-26 A kind of indoor fingerprint map constructing method based on crowdsourcing fingerprint Active CN106792465B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611219485.9A CN106792465B (en) 2016-12-26 2016-12-26 A kind of indoor fingerprint map constructing method based on crowdsourcing fingerprint

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611219485.9A CN106792465B (en) 2016-12-26 2016-12-26 A kind of indoor fingerprint map constructing method based on crowdsourcing fingerprint

Publications (2)

Publication Number Publication Date
CN106792465A true CN106792465A (en) 2017-05-31
CN106792465B CN106792465B (en) 2019-08-30

Family

ID=58926757

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611219485.9A Active CN106792465B (en) 2016-12-26 2016-12-26 A kind of indoor fingerprint map constructing method based on crowdsourcing fingerprint

Country Status (1)

Country Link
CN (1) CN106792465B (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107290715A (en) * 2017-07-18 2017-10-24 华中科技大学 It is a kind of that the indoor orientation method changed with fingerprint is calibrated based on fingerprint
CN108413975A (en) * 2018-03-15 2018-08-17 斑马网络技术有限公司 Ground picture capturing method, system, cloud processor and vehicle
CN108449709A (en) * 2018-03-16 2018-08-24 华中科技大学 A kind of indoor radio map constructing method based on crowdsourcing sample
CN108534779A (en) * 2018-03-09 2018-09-14 华中科技大学 One kind is corrected based on track and the improved indoor positioning map constructing method of fingerprint
CN108709557A (en) * 2018-05-18 2018-10-26 东南大学 Indoor map generation method based on multi-user's track fitting
CN108810817A (en) * 2018-05-18 2018-11-13 东南大学 Indoor map based on mobile crowdsourcing model generates and track encryption method
CN108919177A (en) * 2018-07-16 2018-11-30 华中科技大学 A kind of positioning map construction method based on virtual information source estimation and trajectory corrector
CN109059919A (en) * 2018-06-08 2018-12-21 华中科技大学 A kind of indoor orientation method based on crowdsourcing sample weighting surface fitting
CN110264154A (en) * 2019-05-28 2019-09-20 南京航空航天大学 A kind of crowdsourcing signal map constructing method based on self-encoding encoder
CN110530363A (en) * 2018-05-24 2019-12-03 北京智慧图科技有限责任公司 A kind of method that the AP crowdsourcing of building grade generates
CN110716512A (en) * 2019-09-02 2020-01-21 华电电力科学研究院有限公司 Environmental protection equipment performance prediction method based on coal-fired power plant operation data
CN111474516A (en) * 2020-04-17 2020-07-31 华中科技大学 Multi-level indoor positioning method and system based on crowdsourcing sample surface fitting
CN112068073A (en) * 2020-09-09 2020-12-11 中山大学 UWB positioning error correction method, UWB positioning system, device, and storage medium
CN112543938A (en) * 2020-09-29 2021-03-23 华为技术有限公司 Generation method and device of grid occupation map
CN113727273A (en) * 2021-08-19 2021-11-30 武汉大学 Personnel indoor semantic track reconstruction method based on wireless crowdsourcing data
WO2023005814A1 (en) * 2021-07-28 2023-02-02 华为技术有限公司 Construction method for indoor fingerprint map, and related device
CN115683121A (en) * 2022-12-30 2023-02-03 武汉大学 Method for generating multi-source ubiquitous positioning fingerprint based on measured track
CN117135573A (en) * 2023-04-14 2023-11-28 荣耀终端有限公司 Cell location updating method, server and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130144879A1 (en) * 2011-12-05 2013-06-06 Microsoft Corporation Trusting crowdsourced data with issued tags
US20140179341A1 (en) * 2012-12-24 2014-06-26 Jaroslaw J. Sydir Geo-location signal fingerprinting
CN104394588A (en) * 2014-11-15 2015-03-04 北京航空航天大学 Indoor positioning method based on Wi-Fi fingerprints and multi-dimensional scaling analysis
CN104462281A (en) * 2014-11-26 2015-03-25 杭州优体科技有限公司 Distributed type parallel surveying system for fingerprint positioning
CN104869639A (en) * 2015-05-29 2015-08-26 福建星网锐捷网络有限公司 Indoor positioning method and device
CN105242239A (en) * 2015-10-19 2016-01-13 华中科技大学 Indoor subarea positioning method based on crowdsourcing fingerprint clustering and matching
CN105263113A (en) * 2015-10-26 2016-01-20 深圳大学 Wi-Fi location fingerprint map building method and system based on crowd-sourcing

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130144879A1 (en) * 2011-12-05 2013-06-06 Microsoft Corporation Trusting crowdsourced data with issued tags
US20140179341A1 (en) * 2012-12-24 2014-06-26 Jaroslaw J. Sydir Geo-location signal fingerprinting
CN104394588A (en) * 2014-11-15 2015-03-04 北京航空航天大学 Indoor positioning method based on Wi-Fi fingerprints and multi-dimensional scaling analysis
CN104462281A (en) * 2014-11-26 2015-03-25 杭州优体科技有限公司 Distributed type parallel surveying system for fingerprint positioning
CN104869639A (en) * 2015-05-29 2015-08-26 福建星网锐捷网络有限公司 Indoor positioning method and device
CN105242239A (en) * 2015-10-19 2016-01-13 华中科技大学 Indoor subarea positioning method based on crowdsourcing fingerprint clustering and matching
CN105263113A (en) * 2015-10-26 2016-01-20 深圳大学 Wi-Fi location fingerprint map building method and system based on crowd-sourcing

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107290715A (en) * 2017-07-18 2017-10-24 华中科技大学 It is a kind of that the indoor orientation method changed with fingerprint is calibrated based on fingerprint
CN108534779A (en) * 2018-03-09 2018-09-14 华中科技大学 One kind is corrected based on track and the improved indoor positioning map constructing method of fingerprint
CN108413975A (en) * 2018-03-15 2018-08-17 斑马网络技术有限公司 Ground picture capturing method, system, cloud processor and vehicle
CN108449709A (en) * 2018-03-16 2018-08-24 华中科技大学 A kind of indoor radio map constructing method based on crowdsourcing sample
CN108810817B (en) * 2018-05-18 2020-10-27 东南大学 Indoor map generation and track encryption method based on mobile crowdsourcing mode
CN108709557A (en) * 2018-05-18 2018-10-26 东南大学 Indoor map generation method based on multi-user's track fitting
CN108810817A (en) * 2018-05-18 2018-11-13 东南大学 Indoor map based on mobile crowdsourcing model generates and track encryption method
CN108709557B (en) * 2018-05-18 2021-09-24 东南大学 Indoor map generation method based on multi-user track fitting
CN110530363B (en) * 2018-05-24 2022-08-19 北京智慧图科技有限责任公司 Building-level AP crowdsourcing generation method
CN110530363A (en) * 2018-05-24 2019-12-03 北京智慧图科技有限责任公司 A kind of method that the AP crowdsourcing of building grade generates
CN109059919A (en) * 2018-06-08 2018-12-21 华中科技大学 A kind of indoor orientation method based on crowdsourcing sample weighting surface fitting
CN108919177A (en) * 2018-07-16 2018-11-30 华中科技大学 A kind of positioning map construction method based on virtual information source estimation and trajectory corrector
CN108919177B (en) * 2018-07-16 2020-12-18 华中科技大学 Positioning map construction method based on virtual information source estimation and track correction
CN110264154A (en) * 2019-05-28 2019-09-20 南京航空航天大学 A kind of crowdsourcing signal map constructing method based on self-encoding encoder
CN110264154B (en) * 2019-05-28 2023-06-09 南京航空航天大学 Crowd-sourced signal map construction method based on self-encoder
CN110716512A (en) * 2019-09-02 2020-01-21 华电电力科学研究院有限公司 Environmental protection equipment performance prediction method based on coal-fired power plant operation data
CN111474516A (en) * 2020-04-17 2020-07-31 华中科技大学 Multi-level indoor positioning method and system based on crowdsourcing sample surface fitting
CN111474516B (en) * 2020-04-17 2022-01-11 华中科技大学 Multi-level indoor positioning method and system based on crowdsourcing sample surface fitting
CN112068073A (en) * 2020-09-09 2020-12-11 中山大学 UWB positioning error correction method, UWB positioning system, device, and storage medium
CN112068073B (en) * 2020-09-09 2023-09-01 中山大学 UWB positioning error correction method, UWB positioning system, device and storage medium
CN112543938A (en) * 2020-09-29 2021-03-23 华为技术有限公司 Generation method and device of grid occupation map
WO2023005814A1 (en) * 2021-07-28 2023-02-02 华为技术有限公司 Construction method for indoor fingerprint map, and related device
CN113727273B (en) * 2021-08-19 2022-04-26 武汉大学 Personnel indoor semantic track reconstruction method based on wireless crowdsourcing data
CN113727273A (en) * 2021-08-19 2021-11-30 武汉大学 Personnel indoor semantic track reconstruction method based on wireless crowdsourcing data
CN115683121A (en) * 2022-12-30 2023-02-03 武汉大学 Method for generating multi-source ubiquitous positioning fingerprint based on measured track
CN117135573A (en) * 2023-04-14 2023-11-28 荣耀终端有限公司 Cell location updating method, server and storage medium

Also Published As

Publication number Publication date
CN106792465B (en) 2019-08-30

Similar Documents

Publication Publication Date Title
CN106792465B (en) A kind of indoor fingerprint map constructing method based on crowdsourcing fingerprint
CN106205114B (en) A kind of Freeway Conditions information real time acquiring method based on data fusion
CN103945533B (en) Wireless real time position localization methods based on big data
KR102116824B1 (en) Positioning system based on deep learnin and construction method thereof
CN108109423B (en) Underground parking lot intelligent navigation method and system based on WiFi indoor positioning
WO2019062734A1 (en) Indoor positioning method and device based on wi-fi hot spots
CN104038901B (en) Indoor positioning method for reducing fingerprint data acquisition workload
CN106559749B (en) Multi-target passive positioning method based on radio frequency tomography
WO2017121168A1 (en) Cluster-based magnetic positioning method, device and system
CN106131958A (en) A kind of based on channel condition information with the indoor Passive Location of support vector machine
CN106102161A (en) Based on the data-optimized indoor orientation method of focusing solutions analysis
CN105137390A (en) Indoor positioning method based on AP with adjustable transmitted power
CN104270818A (en) Wireless positioning method for vehicles in park
CN104185275A (en) Indoor positioning method based on WLAN
CN103648164B (en) A kind of based on the difference time of advent and the wireless-sensor network distribution type localization method of Gossip algorithm
CN104200471A (en) SAR image change detection method based on adaptive weight image fusion
CN104540221A (en) WLAN indoor positioning method based on semi-supervised SDE algorithm
CN104519571A (en) Indoor positioning method based on RSS (Received Signal Strength)
CN104751185A (en) SAR image change detection method based on mean shift genetic clustering
CN104039008B (en) A kind of hybrid locating method
CN104394588A (en) Indoor positioning method based on Wi-Fi fingerprints and multi-dimensional scaling analysis
CN106600652A (en) Panorama camera positioning method based on artificial neural network
CN104200206A (en) Double-angle sequencing optimization based pedestrian re-identification method
CN106970379A (en) Based on distance-measuring and positioning method of the Taylor series expansion to indoor objects
CN106793078A (en) Bluetooth indoor orientation method based on RSSI correction value Dual positionings

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