CN103889053B - Automatic establishing method of self-growing-type fingerprint - Google Patents

Abstract

The invention discloses an automatic establishing method of a self-growing-type fingerprint, and relates to position fingerprint locating technologies. The automatic establishing method aims to solve the problem that a large amount of workload is needed in fingerprint establishing and maintaining in the fingerprint locating process. The offline part of the method comprises the steps that a seed zone is established, a fingerprint of a current service area is determined, RSS estimation is conducted on corresponding reference points according to user position prediction results and RSS values uploaded by the online part, a fingerprint is updated, and after the fingerprint grows to a certain degree, the fingerprint of the current service area is determined again. The online part of the method comprises the steps that a receiver at a user-side collects RSS vectors; a user conducts fingerprint locating by using the fingerprints provided by the offline part; the position of the user is predicted by using the filtering algorithm; whether the user leaves the service area or not is judged. By means of the automatic establishing method, the workload needing to be consumed in a fingerprint locating system in the fingerprint establishing process is greatly reduced, the establishing speed of the fingerprint is increased and is beneficial for popularization and application of the fingerprint locating technologies in the commercialization aspect.

Description

A kind of autonomous method for building up of fingerprint image from growth formula

Technical field

The present invention relates to a kind of fingerprint image method for building up, it is related to Indoor Position Techniques Based on Location Fingerprint.

Background technology

The enforcement of location fingerprint positioning can be generally divided into two stages：First stage is training/off-line phase, main work Work is the signal characteristic parameter of collection required location region each reference mode position, such as signal strength, multipath phase angle component work( Rate etc., one group of finger print information is corresponded to a specific position forming position fingerprint database.Second stage is positioning/online rank Section, measures the parameter of receipt signal using receiver, to be determined using matching algorithm and which group data match in data base, Thus drawing the physical location of user.When using location fingerprint localization method, positioning experiment flow chart such as Fig. 2 institute of classics Show：Wherein, (RP₁,RP₂,…,RP_n) represent the 1 to n-th reference point, RSSi_j(i=1,…,n;J=1 ..., T) represent i-th The j-th RSS signal phasor measuring at individual reference point.(TP₁,TP₂,…,TP_m) represent the 1 to m-th reference point.In positioning In stage, WLAN alignment system, based on Radio Map, carries out space in the wlan client needing to be positioned The real-time sampling of signal, and the mobile computing environment data transmission environment transmission using WLAN and calculating sampled data.Calculate Process mainly carries out search and the positioning of locus by the search and matching algorithm applying specific signal space, and it is right to draw The position prediction result of sampled data, completes the positioning of locus.Under practical situation, building has different physical dimensions And internal structure, in order to simplify the task of training stage, the selection of reference point generally requires suitably to be selected according to building structure.? Reference point is approximate meet and be uniformly distributed under conditions of, the effect of distance of neighboring reference point positioning precision, and with reference point Increase, positioning precision is higher.During fingerprint location, the foundation of fingerprint image and maintenance process need to put into extensive work amount, this It is the main technical barrier in terms of commercialization of fingerprint location technology.

Content of the invention

It is an object of the invention to provide a kind of growth autonomous method for building up of formula fingerprint image certainly uploading data based on user, with Solve the problems, such as that the foundation of fingerprint image and maintenance process need to put into extensive work amount during fingerprint location, thus impact refers to The application of stricture of vagina location technology.

The present invention is to solve above-mentioned technical problem to adopt the technical scheme that：

A kind of from grow formula the autonomous method for building up of fingerprint image, described from growth formula the autonomous method for building up of fingerprint image press with Lower step is realized：

Step one, offline part

Step one（One）, set up " seed zone "：

Measure a basic fingerprint image, referred to as " seed zone " in the key position of building；Wherein, described in being in User in seed zone can carry out fingerprint location；

Step one（Two）, determine current service area fingerprint image：

Current service area fingerprint image includes " seed zone " and uploads the calculated ginseng of data according to online certain customers end The when real growth district extending that examination point is formed；Described upload data refers to customer location coordinate and field intensity corresponding with this position Value, i.e. RSS vector；And current service area fingerprint image is supplied to the user side of online part；

Step one（Three）, fingerprint image growth detailed process：

Upload, according to online part, the customer location coming up to predict the outcome and RSS value, RSS is carried out to corresponding reference point RP Estimation, updates fingerprint image, and fingerprint image grows, and after fingerprint image grows to a certain extent, jumps into step 2 and redefines current clothes Business area fingerprint image；

Described customer location uploads information and is shown below：

A=(RSS_a1,RSS_a2,RSS_a3,…,RSS_aP,X_a,Y_a)

RSS in formula_axRepresent the RSS value of x-th AP uploading, X_a, Y_aThe coordinate of the receipts machine estimated location respectively reporting Information；The span of x is 1～P, and P is the total number of AP in localizing environment；

Described to corresponding reference point（RP）The process carrying out RSS estimation is as follows：

To a large amount of fresh informations A uploading, try to achieve reference point locations (Xi, Y to be estimated_j) and all estimated locations (Xa, Ya the two-dimensional distance D between)_dis_ a, and recorded；

$D_{\mathrm{dis}\_}a=\sqrt{{(X_a-X_i)}^2+{(Y_a-Y_j)}^2}$

Then system is that each reference point to be restored finds out K nearest therewith estimated distance：D_dis_a₁、D_dis_a₂、 D_dis_a₃、…、D_dis_a_K, and by RSS vector corresponding in fresh information is averaged with the RSS vector to obtain reference point；

${{\mathrm{RSS}}_{\mathrm{ijp}}}^{\′}=\underset{k=1}{\overset{K}{\mathrm{\Σ}}}{\mathrm{RSS}}_{a_{k}p}/K---\left(1\right)$

In formula, p represents No. AP, RSS_ijp' represent (i, j) number p-th AP of reference point RSS value estimated value, the value of p is Between 1～P；Weigh Maturity Tr being resumed reference point by such as following formula：

$\mathrm{Tr}=\frac{\underset{i=1}{\overset{K}{\mathrm{\Σ}}}{D}_{\mathrm{dis}\_}{a}_i}{K}---\left(2\right)$

Work as Tr<Tr_thWhen it is believed that reference point is ripe enough, can add in fingerprint image use；Wherein, Tr_thIt is with reference to thresholding；

Step 2, online part

Step 2（One）, user side receiver collection RSS vector；

Step 2（Two）, user use offline part step one（Two）The fingerprint image providing carries out fingerprint location；

Step 2（Three）, using filtering algorithm predict customer location；

Step 2（Four）, judge whether user leaves service area；Described service area refers to current time fingerprint map combining Region；

Step 2（Five）, if it is, uploading RSS and current location, for the step one of offline part（Three）Carry out fingerprint Figure growth operation；Otherwise, then return execution step two（One）, until user leaves step 2（Four）Described service area.

The key position of building described in step one refers to the region that artificial abortion is larger or concentrates.

Step one（Three）Described in when fingerprint image growth refer to a certain extent Maturity function Tr be less than its threshold T r_th When current finger print figure.

The invention has the beneficial effects as follows：

The use of the inventive method greatly reduces fingerprint image in fingerprint location system and sets up the work that process needs to expend Amount.The small range fingerprint image that the inventive method passes through to pre-build provides the user initial positioning service, and binding site is predicted Algorithm, updating the data of collecting of user is uploaded onto the server, the such data of Server Consolidation, when real expand covering of fingerprint image Lid scope, need not set up large-scale fingerprint image in early stage, the inventive method improves the construction speed of fingerprint image, be conducive to referring to Popularization and application in terms of commercialization for the stricture of vagina location technology.

Brief description

Fig. 1 is the workflow block diagram from growing system for the fingerprint image based on the inventive method；Fig. 2 is in prior art WLAN fingerprint location system flow schematic diagram；Fig. 3 is the system data storage organization figure realizing the inventive method, and Fig. 4 is system Workflow diagram（What depositor group stored is the RSS vector of K renewal point data and updates the distance apart from this reference point for the point D_dis_a_x）；Fig. 5 is the emulation experiment environment map using the inventive method；The simulation experiment result figure of Fig. 6 the inventive method, Fig. 6 In：

Fig. 6 a shows 5000 users fingerprint image recovery after this scene, and in figure abscissa represents the X of experimental situation Axial coordinate, in figure vertical coordinate represents the Y-axis coordinate of experimental situation, and unit is rice；

Fig. 6 b shows 10000 users fingerprint image recovery after this scene, and in figure abscissa represents the X of experimental situation Axial coordinate, in figure vertical coordinate represents the Y-axis coordinate of experimental situation, and unit is rice；

Fig. 6 c shows 20000 users fingerprint image recovery after this scene, and in figure abscissa represents the X of experimental situation Axial coordinate, in figure vertical coordinate represents the Y-axis coordinate of experimental situation, and unit is rice；

Fig. 6 d shows 50000 users fingerprint image recovery after this scene, and in figure abscissa represents the X of experimental situation Axial coordinate, in figure vertical coordinate represents the Y-axis coordinate of experimental situation, and unit is rice；

Fig. 6 e shows 100000 users fingerprint image recovery after this scene, and in figure abscissa represents experimental situation X-axis coordinate, in figure vertical coordinate represents the Y-axis coordinate of experimental situation, and unit is rice；

Fig. 6 f shows 200000 users fingerprint image recovery after this scene, and in figure abscissa represents experimental situation X-axis coordinate, in figure vertical coordinate represents the Y-axis coordinate of experimental situation, and unit is rice.

Specific embodiment：

Specific embodiment one：As shown in Fig. 1,3 and 4, a kind of fingerprint image from growth formula described in present embodiment is certainly Main method for building up is realized according to the following steps：

Step one, offline part

Step one（One）, set up " seed zone "：

Measure a basic fingerprint image in the key position of building（Initial fingerprint figure）, referred to as " seed zone "； Wherein, the user being in described seed zone can carry out fingerprint location；

Step one（Two）, determine current service area fingerprint image：

Current service area fingerprint image includes " seed zone " and uploads the calculated ginseng of data according to online certain customers end Examination point（From growing extension reference point）The when real growth district extending being formed；Described upload data refers to customer location coordinate And field intensity value corresponding with this position（RSS vector）；And current service area fingerprint image is supplied to the user side of online part；

Current service area is identical with seed zone when starting, and increases with fingerprint image afterwards, positioning service area can gradually expand；

Step one（Three）, fingerprint image growth detailed process：

Upload, according to online part, the customer location coming up to predict the outcome and RSS value, to corresponding reference point（RP）Carry out RSS estimates, updates fingerprint image, and fingerprint image grows, and after fingerprint image grows to a certain extent, jumps into step 2 and redefines currently Service area fingerprint image；

Described customer location uploads information and is shown below：

A=(RSS_a1,RSS_a2,RSS_a3,…,RSS_aP,X_a,Y_a)

RSS in formula_axRepresent the RSS value of x-th AP uploading, X_a, Y_aThe coordinate of the receipts machine estimated location respectively reporting Information；The span of x is 1～P, and P is the total number of AP in localizing environment；

Described to corresponding reference point（RP）The process carrying out RSS estimation is as follows：

To a large amount of fresh informations A uploading, try to achieve reference point locations (Xi, Y to be estimated_j) and all estimated locations (Xa, Ya the two-dimensional distance D between)_dis_ a, and recorded；

$D_{\mathrm{dis}\_}a=\sqrt{{(X_a-X_i)}^2+{(Y_a-Y_j)}^2}$

Then system is that each reference point to be restored finds out K nearest therewith estimated distance：D_dis_a₁、D_dis_a₂、 D_dis_a₃、…、D_disa_K, and by RSS vector corresponding in fresh information is averaged with the RSS vector to obtain reference point；

${{\mathrm{RSS}}_{\mathrm{ijp}}}^{\&prime;}=\underset{k=1}{\overset{K}{\mathrm{\&Sigma;}}}{\mathrm{RSS}}_{a_{k}p}/K---\left(1\right)$

In formula, p represents No. AP, RSSi_jp' represent (i, j) number p-th AP of reference point RSS value estimated value, the value of p is Between 1～P；Weigh Maturity Tr being resumed reference point by such as following formula：

$\mathrm{Tr}=\frac{\underset{i=1}{\overset{K}{\mathrm{\&Sigma;}}}{D}_{\mathrm{dis}\_}{a}_i}{K}---\left(2\right)$

Work as Tr<Tr_thWhen it is believed that reference point is ripe enough, can add in fingerprint image use；Wherein, Tr_thIt is with reference to thresholding, Obtained by emulation is carried out to corresponding indoor environment；

Step 2, online part

Step 2（One）, user side receiver collection RSS vector；

Step 2（Two）, user use offline part step one（Two）The fingerprint image providing carries out fingerprint location；

Step 2（Three）, using filtering algorithm predict customer location；

Step 2（Four）, judge whether user leaves service area；Described service area refers to current time fingerprint map combining Region；

Step 2（Five）, if it is, uploading RSS and current location, for the step one of offline part（Three）Carry out fingerprint Figure growth operation；Otherwise, then return execution step two（One）, until user leaves step 2（Four）Described service area.

Specific embodiment two：The key position of present embodiment building described in step one refer to artificial abortion larger or The region concentrated.

It is such as gate entry, elevator entrance, turning, passageway, outlet or staircase, in the key position of building（As Entrance, turning etc.）Measure one region is less but fingerprint image that quality is higher, referred to as " seed zone ", user is in this region Interior can carry out fingerprint location.

Specific embodiment three：Present embodiment is in step one（Three）Described in when fingerprint image growth refer to a certain extent Maturity function Tr is less than its threshold T r_thWhen current finger print figure.

Can also judge according to uploading the degree of closeness that data point is with corresponding RP point whether corresponding RP is accurate enough, Whether can add in fingerprint image.

Embodiment：

Step 1, setting seed zone：

Algorithm passes through the key position in building（As entrance, turning etc.）Measure one region is less but quality is higher Fingerprint image, referred to as " seed zone ", user can carry out fingerprint location in this region.

Step 2, customer location prediction：

For moving user, due to the regular hour shared by data processing during fingerprint location so that logical Crossed the position calculating for user in the position in a upper moment, and not real time position.And just leave " seed zone " in user When, still can obtain the positional information of itself by position prediction algorithm, gather corresponding RSS vector simultaneously.

Step 3, user data upload：

Receiver is to server upload location information and its corresponding RSS vector.

Step 4, estimation reference point：

Repeat step 2 arrives step 3, until when the renewal sampled point in a certain region is enough, server can pass through They calculate the reference point in this region.

Step 5, the assessment of reference point Maturity

Whether space distribution situation according to reporting of user data and signal characteristic space distribution situation, judge this reference point Estimation is accurate enough.

Step 6, fingerprint image expand：

Reference point ripe enough is added in fingerprint image, repeat step 2 arrives step 5, constantly expands fingerprint map combining.

Operator carries out offline part, and user uses online portion, and both sides are synchronously carried out, and the continuous uploading position of user is believed Breath and RSS, server is with regard to constantly carrying out the expansion of fingerprint image.

During realizing, position prediction process can select particle filter, kalman filter method.Reference point RSS is estimated The method of meter can adopt KNN algorithm.

Whole fingerprint image is saved as the matrix of a M × N by system in realizing, each element of matrix has the depth to be The depositor group of K+1 is constituted, and each depositor group is made up of P+1 depositor, as shown in Figure 3.

As shown in FIG., front K depositor group storage is the K RSS vector updating point data and a renewal point distance This reference point apart from D_dis_a_x.Last depositor group internal memory is that the reference point RSS vector sum finally calculating becomes Ripe degree Tr.

$\mathrm{Tr}=\frac{\underset{i=1}{\overset{K}{\mathrm{\&Sigma;}}}{D}_{\mathrm{dis}\_}{a}_i}{K}$

Its workflow is as shown in 4 figures；Tr_thFor the threshold value whether judgement reference point is ripe.

Emulation experiment and its effect

For feasibility in user movement environment for the verification algorithm, carry out corresponding emulation experiment herein.Empty in emulation Intend the hall of a 30m × 50m, as shown in Figure 5.

Seed zone is 10m × 10m size, as shown in figure dash area.Grand entrance is wide 3 meters.Experimental result such as 6 figure institute Show, in figure shows the relation between the number of users and the area of fingerprint map combining passing through in environment.In this experiment, offline The reference point quantity of part collection is reduced at 100 points it is seen that this method can be effectively reduced fingerprint image foundation from 1500 points During workload.

Claims (2)

1. a kind of from growth formula the autonomous method for building up of fingerprint image it is characterised in that：The described fingerprint image from growth formula is independently built Cube method is realized according to the following steps：

Step one, offline part

Step one (one), foundation " seed zone "：

Measure a basic fingerprint image, referred to as " seed zone " in the key position of building；Wherein, it is in described seed User in area can carry out fingerprint location；

Step one (two), determine current service area fingerprint image：

Current service area fingerprint image includes " seed zone " and uploads the calculated reference point of data according to online certain customers end The growth district of the real-time extension being formed；Described upload data refers to customer location coordinate and field intensity value corresponding with this position, I.e. RSS vector；And current service area fingerprint image is supplied to the user side of online part；

Step one (three), the detailed process of fingerprint image growth：

Upload, according to online part, the customer location coming up to predict the outcome and RSS value, RSS is carried out to corresponding reference point RP and estimates Calculate, update fingerprint image, fingerprint image grows, after fingerprint image grows to a certain extent, jump into step 2 and redefine current service Area's fingerprint image；Fingerprint image growth refers to that Maturity function Tr is less than its threshold T r to a certain extent_thWhen current finger print figure；

Described customer location uploads information and is shown below：

A=(RSS_a1,RSS_a2,RSS_a3,…,RSS_aP,X_a,Y_a)

RSS in formula_axRepresent the RSS value of x-th AP uploading, X_a, Y_aThe coordinate information of the data estimation position respectively reporting, AP is WAP；The span of x is 1～P, and P is the total number of AP in localizing environment；

The described process that corresponding reference point RP is carried out with RSS estimation is as follows：

To a large amount of fresh informations A uploading, try to achieve reference point locations (X to be estimated_i,Y_j) and all estimated location (X_a,Y_a) between Two-dimensional distance D_dis_ a, and recorded；

$D_{dis}\_a=\sqrt{{(X_a-X_i)}^2+{(Y_a-Y_j)}^2}$

Then system is that each reference point to be restored finds out K nearest therewith estimated distance：D_dis_a₁、D_dis_a₂、D_dis_ a₃、…、D_dis_a_K, and by RSS vector corresponding in fresh information is averaged with the RSS vector to obtain reference point；

${{\mathrm{RSS}}_{ijp}}^{\&prime;}=\underset{k=1}{\overset{K}{\mathrm{\&Sigma;}}}{\mathrm{RSS}}_{a_{k}p}/K---\left(1\right)$

In formula, p represents No. AP, RSS_ijp' represent (i, j) number p-th AP of reference point RSS value estimated value, the value of p is 1～P Between；

Weigh Maturity Tr being resumed reference point by such as following formula：

$Tr=\frac{\underset{i=1}{\overset{K}{\mathrm{\&Sigma;}}}{D}_{dis}\_a_i}{K}---\left(2\right)$

Work as Tr<Tr_thWhen it is believed that reference point is ripe enough, can add in fingerprint image use；Wherein, Tr_thIt is with reference to thresholding；

Step 2, online part

Step 2 (one), the receiver collection RSS vector of user side；

Step 2 (two), user carry out fingerprint location using the fingerprint image that the step one (two) of offline part provides；

Step 2 (three), using filtering algorithm predict customer location；

Step 2 (four), judge whether user leaves service area；Described service area refers to the region of current time fingerprint map combining；

If it is, uploading RSS and current location, the step one (three) for offline part carries out fingerprint image life to step 2 (five) Long operation；Otherwise, then return execution step two (), until user leaves the service area described in step 2 (four).

2. the autonomous method for building up of fingerprint image from growth formula according to claim 1 is it is characterised in that described in step one The key position of building refers to the region that artificial abortion is larger or concentrates.