CN106793072A - A kind of indoor locating system fast construction method - Google Patents
A kind of indoor locating system fast construction method Download PDFInfo
- Publication number
- CN106793072A CN106793072A CN201611118893.5A CN201611118893A CN106793072A CN 106793072 A CN106793072 A CN 106793072A CN 201611118893 A CN201611118893 A CN 201611118893A CN 106793072 A CN106793072 A CN 106793072A
- Authority
- CN
- China
- Prior art keywords
- space
- indoor positioning
- target chamber
- located space
- similar
- 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
-
- 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
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/02—Systems for determining distance or velocity not using reflection or reradiation using radio waves
- G01S11/06—Systems for determining distance or velocity not using reflection or reradiation using radio waves using intensity measurements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
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)
Abstract
The present invention relates to a kind of indoor locating system fast construction method, comprise the following steps:Step a, sets the indoor positioning environment that located space in target chamber is based on WiFi signal intensity data;Step b, sets up similar indoor positioning locus fingerprint base collection;Step c, located space collection WiFi signal intensity data, constitutes located space location fingerprint storehouse in target chamber in target chamber;Step d, best knowledge matrix is determined using transfer learning method from the knowledge matrix of the location fingerprint storehouse collection in similar indoor positioning space.The method for using transfer learning in build process using indoor locating system fast construction method of the present invention, reduces the location fingerprint collection capacity of indoor locating system, greatly reduces the time cycle and human cost for building indoor locating system.Simultaneously in alignment system build process, the location fingerprint database data amount in effective indoor positioning space can be continued to increase, improve constantly new indoor locating system builds efficiency.
Description
Technical field
The present invention relates to indoor locating system, more particularly to a kind of building method of indoor locating system fast construction.
Background technology
In modern location technology, " last one kilometer " navigation that outdoor positioning technology completes after mission has derived room
Interior location technology.Existing indoor positioning technologies have great current demand in life of urban resident, adopt under normal circumstances
With the indoor locating system based on WiFi signal intensity, because it has the spies such as relatively low hardware cost, positioning precision higher
Put and receive extensive research application.However, the existing indoor locating system based on WiFi signal intensity is in build process
In, it is necessary to spend substantial amounts of human cost and the time cost to be used to gather location fingerprint data and constitute having for target located space
Effect location fingerprint storehouse, these problems largely limit the indoor locating system based on WiFi signal intensity in actual applications
The use of Rapid Popularization and large area.
The content of the invention
In view of the shortcomings of the prior art, indoor locating system is carried out using transfer learning technology the invention provides one kind
The building method of fast construction.
A kind of indoor locating system fast construction method, comprises the following steps:
Step a, sets the indoor positioning environment that located space in target chamber is based on WiFi signal intensity data;
Step b, sets up similar indoor positioning locus fingerprint base collection;
Step c, located space collection WiFi signal intensity data, constitutes located space position in target chamber in target chamber
Fingerprint base;
Step d, it is true from the knowledge matrix of the location fingerprint storehouse collection in similar indoor positioning space using transfer learning method
Determine best knowledge matrix.
Preferably, in step a, the method for setting the localizing environment of located space in target chamber comprises the following steps:
Step a1, N number of beacon region is divided into by located space in target chamber;
Step a2, located space sets M WiFi signal intensity sniffer in target chamber;
In stepb, the method for setting up similar indoor positioning locus fingerprint base collection comprises the following steps:
Step b1, source position fingerprint base collection is collected into by the location fingerprint database data in known indoor positioning space;
Step b2, the position as the similar indoor positioning space of located space in target chamber is selected from source position fingerprint base collection
Fingerprint base is put, and sets up into similar indoor positioning locus fingerprint base collection;
In step c, each beacon region L of located space from target chamberi(1≤i≤N) gathers WiFi signal intensity
Data, will be stored in database after data processing, and represent each data cell using a multi-component system, its method for expressing
It is as follows:
(RSS1, RSS2..., RSSM, Li)
Each data cell represents beacon region LiM Wifi signal strength data being collected into, wherein RSSj(1≤
J≤M) represent the WiFi signal intensity data that j-th WiFi signal intensity sniffer is received;By located space in target chamber
Location fingerprint is expressed as rt={ RSS1, RSS2..., RSSM, and a beacon region can correspond to multiple location fingerprints, if
Put RtIt is rtSet so that RtIt is located space location fingerprint storehouse in target chamber;
In step d, determine that the method for best knowledge matrix comprises the following steps:
Step d1, builds similar indoor positioning spatial knowledge matrix pool;
Step d2, calculates the optimal of located space in suitable target chamber from similar indoor positioning spatial knowledge matrix pool
Knowledge matrix.
Preferably, in stepb, similar indoor positioning space is there is provided equal number with located space in target chamber
The indoor positioning space of WiFi signal intensity sniffer;
In step c, in the default dimension space of target chamber, the WiFi signal intensity data chosen from each beacon region is adopted
The quantity for collecting point is 2 so that a beacon region can correspond to 2 location fingerprints, and WiFi signal is gathered in each collection point
Intensity data duration is 2 minutes.
Preferably, in step d1, the knowledge that K is WiFi signal intensity distribution in each similar indoor positioning space is set
Matrix, and the set that P is knowledge matrix K is set so that P is the knowledge matrix pond in similar indoor positioning space;For each
The WiFi signal intensity data in individual similar indoor positioning space, can calculate a knowledge matrix using below equation:
Tr () is represented and is sought the mark of matrix in formula, and the value that the value of B is set to 100, p is set to 2, Wherein RsIt is the location fingerprint storehouse in the similar indoor positioning space, N is at this
The quantitative value of the location fingerprint data collected in similar indoor positioning space;I is unit matrix;Y is RsMiddle position
The nuclear matrix of fingerprint and beacon region relation is put, Y (i, j)=1 represents RsInCorresponding LiIt is equal, while representingReceive
Combine in same beacon region, otherwise Y (i, j)=- 1;By the way that K=LL can be obtained after calculatingT, wherein L is knowledge matrix K processes
The matrix that singular value decomposition post processing is obtained, Q is the similar indoor positioning space corresponding with located space in a target chamber
Quantitative value, finally obtain P={ K1, K2..., KQ};
In step d2, K is settBest knowledge matrix corresponding to located space in target chamber, it is fixed from similar interior
The best knowledge matrix K of located space in suitable target chamber is calculated in bit space knowledge matrix pond PtMethod include following step
Suddenly:
Step d21, calculates each similar indoor positioning space similar to the location fingerprint storehouse of located space in target chamber
Property, computing formula is as follows:
Si=-(c1*MMDi+c2*Difi)
Wherein c1, c2∈ (0,1), and c1+c2=1, DifiIt is set to similar indoor positioning space and target indoor positioning
The difference of space beacon region quantity, MMDiIt is set to the location fingerprint in similar indoor positioning space and located space in target chamber
The Largest Mean difference in storehouse, the computing formula of Largest Mean difference is:
Wherein RsLocation fingerprint storehouse corresponding to similar indoor positioning space, RtCorresponding to located space in target chamber
Location fingerprint storehouse, location fingerprintWherein Ns, NtIt is Rs, RtColumns, represent location fingerprint quantity;
Step d22, calculates best knowledge matrix KtMethod it is as follows:
The location fingerprint storehouse degree of association in each similar indoor positioning space and located space in target chamber is calculated, calculates public
Formula is as follows:
Wherein knowledge matrix Ki∈ P, YtIt is RtThe nuclear matrix of middle location fingerprint and beacon region relation, YtThe table of (i, j)=1
Show RtInCorresponding LiIt is equal, while representingIt is collected in same beacon region, otherwise Yt(i, j)=- 1;Wherein make
Obtain degree of association DegreeiTake knowledge matrix K during maximumiIt is just best knowledge matrix Kt。
Preferably, the value of the quantity Q in similar indoor positioning space corresponding with located space in a target chamber is 10.
Preferably, in step d21, c is set1=0.8, c2=0.2.
Preferably, in step a1, located space in target chamber is divided into N number of equally distributed beacon region.
Preferably, WiFi signal intensity sniffer is wireless router.
Using indoor locating system fast construction method of the present invention, the interior based on WIFI signal intensity is reduced
The collection capacity of the offline finger print data of alignment system, using the method for transfer learning during system building, greatly reduces
Build time cycle and the human cost of indoor locating system.Simultaneously in alignment system build process, can continue to increase effectively
Indoor positioning space location fingerprint database data amount, improve constantly new indoor locating system builds efficiency.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the embodiment of the present invention.
Specific embodiment
Indoor locating system involved in the present invention includes WiFi signal intensity sniffer, wireless device and backstage clothes
Business device.WiFi signal intensity sniffer is set first in position fixing process and is in Monitor operational modes, wireless device is actively sent out
Wireless data link frame is sent, the wireless data link frame is then captured by WiFi signal intensity sniffer, and parse acquisition
The wireless device signal intensity data and the MAC Address related data of wireless device included in wireless data link frame, finally
The data of acquisition is enclosed by WiFi signal intensity sniffer be sent to background server after the MAC Address data of oneself and carry out
Reason, completes the indoor positioning work to wireless device., it is necessary to whole indoor generally before alignment system starts normal work
The location fingerprint data of localizing environment are acquired treatment, and wherein location fingerprint data contain certain point position in located space
WiFi signal intensity data, in order to improve positioning precision, common method often takes increase WiFi signal intensity collection point
The mode of quantity, and the data are carried out with a large amount of pointwise collections and the workload of processing data is very big, human cost is high, the cycle
It is long.The present invention indoors in the build process of alignment system using the method for transfer learning to the target chamber of there was only a small amount of collection point
The location fingerprint data of interior located space carry out aid in treatment, can fast and effectively complete building for alignment system, realize to nothing
The indoor positioning work of line equipment.
Wherein wireless device includes that those can be connected to all devices of network by WiFi WLANs, such as intelligent hand
The equipment such as machine, notebook computer, Intelligent bracelet or digital camera;And WiFi signal intensity sniffer can be operated in including all
The network equipment under Monitor operational modes, the operation network equipment in this mode can capture wireless data link frame, and city
Most of wireless routers can run under Monitor patterns on face.Now by specific embodiment to of the present invention one
Kind indoor locating system fast construction method is described in detail as follows:
Embodiment:
As shown in Figure 1, a kind of indoor locating system fast construction method based on WiFi signal intensity, specific method includes
The following steps:
Step a, sets the indoor positioning environment that located space in target chamber is based on WiFi signal intensity data, specific method
Comprise the following steps:
Step a1, N number of equally distributed beacon region, wherein each beacon region are divided into by located space in target chamber
Area is set to for 4 × 4m2Square area;
Step a2, located space sets M WiFi signal intensity sniffer in target chamber, here using wireless router
As WiFi signal intensity sniffer, and wireless router is set in Monitor operational modes, wireless data can be captured
The related data of isl frame.
Step b, sets up similar indoor positioning locus fingerprint base collection.It is empty in order to fast construction target indoor positioning
Between location fingerprint storehouse, improve located space position in target chamber using the location fingerprint storehouse for being capable of similar indoor positioning space
The locating effect of fingerprint base.Wherein similar indoor positioning space refers to have laid equal number WiFi with located space in target chamber
The indoor positioning space of signal intensity sniffer.The method for setting up similar indoor positioning locus fingerprint base collection includes following step
Suddenly:
Step b1, source position fingerprint base collection is collected into by the location fingerprint database data in known indoor positioning space;
Step b2, selects as the similar indoor positioning space of located space in target chamber from source position fingerprint base collection
Location fingerprint storehouse, and set up into similar indoor positioning locus fingerprint base collection.
Step c, located space collection WiFi signal intensity data, constitutes located space position in target chamber in target chamber
Fingerprint base, specific method is:
Each beacon region L of located space from target chamberi(1≤i≤N) gathers WiFi signal intensity data, by number
According to being stored in database after treatment, and each data cell is represented using a multi-component system, it is as follows:
(RSS1, RSS2..., RSSM, Li)
Each data cell represents beacon region LiM Wifi signal strength data being collected into, wherein RSSj(1≤
J≤M) j-th WiFi signal intensity data for receiving of WiFi signal intensity sniffer is represented, unit is dbM;By target chamber
The location fingerprint of interior located space is expressed as rt={ RSS1, RSS2..., RSSM, and a beacon region can be correspondingly more
Individual location fingerprint, sets RtIt is rtSet so that RtIt is the location fingerprint storehouse of located space in target chamber.
WiFi signal intensity data is gathered in located space in target chamber in order to reduce WiFi signal intensity sniffer
Time, the quantity of the WiFi signal intensity data collection point chosen from each beacon region is 2 so that a beacon region energy
2 location fingerprints are enough corresponded to, is 2 minutes in each collection point collection WiFi signal intensity data duration;To carry
Acquisition precision high, the quantity of the WiFi signal intensity data collection point that each beacon region is chosen is set to 4, now one
Beacon region can correspond to 4 location fingerprints.
Step d, it is true from the knowledge matrix of the location fingerprint storehouse collection in similar indoor positioning space using transfer learning method
Determine best knowledge matrix, improve located space locating effect in target chamber, positioning work is completed to aided positioning system;
For the location fingerprint storehouse collection in similar indoor positioning space, it is similar that system learns each using transfer learning method
The distributed knowledge of the WiFi signal intensity in indoor positioning space, and for the optimal distributed knowledge of located space selection in target chamber comes
Improve locating effect, determine that the method for best knowledge matrix comprises the following steps:
Step d1, builds similar indoor positioning spatial knowledge matrix pool, and specific method is as follows:
The knowledge matrix that K is WiFi signal intensity distribution in each similar indoor positioning space is set, and setting P is similar room
Interior located space knowledge matrix pond, and P is the set of knowledge matrix K;It is corresponding with located space in a target chamber to set Q
Similar indoor positioning space quantitative value;The WiFi signal intensity data in indoor positioning space similar for each, can
A knowledge matrix is calculated using below equation:
Tr () represents the mark for seeking matrix in formula, and B and p is two default constants, and B is set into 100, p is set to 2,Wherein RsIt is the location fingerprint storehouse in the similar indoor positioning space,The position that expression is collected into a beacon region in the similar indoor positioning space
Finger print data, N is the quantitative value of the location fingerprint data collected in the similar indoor positioning space.Y is RsMiddle location fingerprint
With the nuclear matrix of beacon region relation, Y (i, j)=1 represents RsInCorresponding LiIt is equal, while representingIt is collected in same
One beacon region, otherwise Y (i, j)=- 1.I is unit matrix.
A is symmetrical matrix, it is possible to A is expressed as into A=Vdiag (δ) V using feature decompositionT, wherein V is the feature of A
Vector, δ is the characteristic coefficient of A.Therefore, it is possible to obtain A+=Vdiag (δ+)VT, wherein δ+It is the corresponding non-negative vectors of δ, δ in A+
[i]=max (0, δ [i]).
Because being able to demonstrate that K is a positive semidefinite matrix of M × M, K can be expressed as with singular value decomposition (SVD):
K=LLT, wherein L is the matrix that knowledge matrix K is obtained by singular value decomposition post processing.
Further, two groups of positions in the location fingerprint storehouse R in similar indoor positioning space can be calculated according to below equation
Put fingerprint ri, rjBetween difference Value Data dK:
So the similar indoor positioning space corresponding with located space in target chamber for Q, can be calculated Q
Different knowledge matrix K, constitutes the knowledge matrix pond P in similar indoor positioning space to be selected:
P={ K1, K2..., KQ}
Here the value for setting Q is 10, that is, have 10 similar indoor positioning spaces corresponding with located space in target chamber.
Step d2, calculates the optimal of located space in suitable target chamber from similar indoor positioning spatial knowledge matrix pool
Knowledge matrix.
K is settBest knowledge matrix corresponding to located space in target chamber, from similar indoor positioning spatial knowledge square
The best knowledge matrix K of located space in suitable target chamber is calculated in battle array pond PtMethod comprise the following steps:
Step d21, calculates each similar indoor positioning space similar to the location fingerprint storehouse of located space in target chamber
Property, computing formula is as follows:
Si=-(c1*MMDi+c2*Difi)
Wherein c1, c2∈ (0,1), and c1+c2=1, c is set here1=0.8, c2=0.2.DifiIt is set to similar room
The difference of located space beacon region quantity, MMD in interior located space and target chamberiIt is set to similar indoor positioning space and mesh
The Largest Mean difference in the location fingerprint storehouse in indoor positioning space is marked, its computing formula is:
Wherein RsLocation fingerprint storehouse corresponding to similar indoor positioning space, RtCorresponding to located space in target chamber
Location fingerprint storehouse, location fingerprintWherein Ns, NtIt is Rs, RtColumns, represent location fingerprint quantity.
Step d22, the method for calculating best knowledge matrix is as follows:
The location fingerprint storehouse degree of association in each similar indoor positioning space and located space in target chamber is calculated, calculates public
Formula is as follows:
Wherein knowledge matrix Ki∈ P, YtIt is RtThe nuclear matrix of middle location fingerprint and beacon region relation, YtThe table of (i, j)=1
Show RtInCorresponding LiIt is equal, while representingIt is collected in same beacon region, otherwise Yt(i, j)=- 1.Wherein make
Obtain degree of association DegreeiTake knowledge matrix K during maximumiIt is just best knowledge matrix Kt。
Complete after step d, can just use the best knowledge matrix K determined in step dtInstruct to complete target indoor positioning
The alignment system fingerprint base in space is built, and accessory system completes the work of indoor positioning, and specific method is as follows:
R is settIt is a location fingerprint of located space in the real-time target chamber for obtaining, setsFor real time position refers to
Line rtWith location fingerprint in located space location fingerprint storehouse in target chamberDifference Value Data, using KNN algorithms, by comparing
Real time position fingerprint rtWith the difference of location fingerprint in located space location fingerprint storehouse in target chamberSet and causeIt is minimum
Location fingerprint corresponding to beacon region be estimation range Lt,Computing formula it is as follows:
WhereinL can be obtained using singular value decompositiont.Meanwhile, alignment system carries out reality using KNN algorithms
The calculating of Shi Dingwei, and arest neighbors flexible strategy k is set to 1.
In alignment system running, the new finger print data that will be obtained constitutes test data fingerprint base, when based on test
When the locating accuracy parameter of the alignment system in data fingerprint storehouse reaches the setting value for representing high position precision, number can will be tested
Source position fingerprint database collection is added according to fingerprint base.
Using indoor locating system fast construction method of the present invention, the interior based on WIFI signal intensity is reduced
The artificial collection capacity of the offline finger print data of alignment system, using the method for transfer learning during system building, drops significantly
Low time cycle and the human cost for building indoor locating system.Simultaneously in alignment system build process, can continue to increase
The location fingerprint database data amount in effective indoor positioning space, is continuously increased the finger print data that source position fingerprint database is concentrated,
That improves new indoor locating system builds efficiency.
The above embodiment of the present invention is only example to illustrate the invention, and is not to implementation of the invention
The restriction of mode.For those of ordinary skill in the field, other can also be made not on the basis of the above description
With the change and variation of form.Here cannot all of implementation method be exhaustive.It is every to belong to technical scheme institute
The obvious change amplified out changes row still in protection scope of the present invention.
Claims (8)
1. a kind of indoor locating system fast construction method, it is characterised in that comprise the following steps:
Step a, sets the indoor positioning environment that located space in target chamber is based on WiFi signal intensity data;
Step b, sets up similar indoor positioning locus fingerprint base collection;
Step c, located space collection WiFi signal intensity data, constitutes located space location fingerprint in target chamber in target chamber
Storehouse;
Step d, is determined most using transfer learning method from the knowledge matrix of the location fingerprint storehouse collection in similar indoor positioning space
Good knowledge matrix.
2. a kind of indoor locating system fast construction method according to claim 1, it is characterised in that in step a, if
The method for putting the localizing environment of located space in target chamber comprises the following steps:
Step a1, N number of beacon region is divided into by located space in target chamber;
Step a2, located space sets M WiFi signal intensity sniffer in target chamber;
In stepb, the method for setting up similar indoor positioning locus fingerprint base collection comprises the following steps:
Step b1, source position fingerprint base collection is collected into by the location fingerprint database data in known indoor positioning space;
Step b2, selects from source position fingerprint base collection and refers to as the position in the similar indoor positioning space of located space in target chamber
Line storehouse, and set up into similar indoor positioning locus fingerprint base collection;
In step c, each beacon region L of located space from target chamberi(1≤i≤N) gathers WiFi signal intensity data,
To be stored in database after data processing, and each data cell is represented using a multi-component system, its method for expressing is as follows:
(RSS1, RSS2..., RSSM, Li)
Each data cell represents beacon region LiM Wifi signal strength data being collected into, wherein RSSj(1≤j≤
M) the WiFi signal intensity data that j-th WiFi signal intensity sniffer of expression is received;By the position of located space in target chamber
Fingerprint representation is put for rt={ RSS1, RSS2..., RSSM, and a beacon region can correspond to multiple location fingerprints, set
RtIt is rtSet so that RtIt is located space location fingerprint storehouse in target chamber;
In step d, determine that the method for best knowledge matrix comprises the following steps:
Step d1, builds similar indoor positioning spatial knowledge matrix pool;
Step d2, calculates the best knowledge of located space in suitable target chamber from similar indoor positioning spatial knowledge matrix pool
Matrix.
3. a kind of indoor locating system fast construction method according to claim 2, it is characterised in that in stepb, phase
Like indoor positioning space it is with located space in target chamber there is provided the indoor positioning of equal number WiFi signal intensity sniffer
Space;
In step c, in located space in target chamber, from the WiFi signal intensity data collection point that each beacon region is chosen
Quantity be 2 so that a beacon region can correspond to 2 location fingerprints, each collection point gather WiFi signal intensity
Data duration is 2 minutes.
4. a kind of indoor locating system fast construction method according to any one of Claims 2 or 3, it is characterised in that
In step d1, K is set and is the knowledge matrix of WiFi signal intensity distribution in each similar indoor positioning space, and P is set
It is the set of knowledge matrix K so that P is the knowledge matrix pond in similar indoor positioning space;Indoor positioning similar for each
The WiFi signal intensity data in space, can calculate a knowledge matrix using below equation:
Tr () is represented and is sought the mark of matrix in formula, and the value that the value of B is set to 100, p is set to 2,Wherein RsIt is the location fingerprint storehouse in the similar indoor positioning space, N is at this
The quantitative value of the location fingerprint data collected in similar indoor positioning space;I is unit matrix:Y is RsMiddle position
The nuclear matrix of fingerprint and beacon region relation is put, Y (i, j)=1 represents RsInCorresponding LiIt is equal, while representingReceive
Combine in same beacon region, otherwise Y (i, j)=- 1;By the way that K=LL can be obtained after calculatingT, wherein L is knowledge matrix K processes
The matrix that singular value decomposition post processing is obtained, Q is the similar indoor positioning space corresponding with located space in a target chamber
Quantitative value, finally obtain P={ K1, K2..., KQ};
In step d2, K is settBest knowledge matrix corresponding to located space in target chamber, from similar indoor positioning space
The best knowledge matrix K of located space in suitable target chamber is calculated in the P of knowledge matrix pondtMethod comprise the following steps:
Step d21, calculates the location fingerprint storehouse similitude in each similar indoor positioning space and located space in target chamber, meter
Calculate formula as follows:
Si=-(c1*MMDi+c2*Difi)
Wherein c1, c2∈ (0,1), and c1+c2=1, DifiSimilar indoor positioning space is set to located space in target chamber
The difference of beacon region quantity, MMDiSimilar indoor positioning space is set to the location fingerprint storehouse of located space in target chamber
Largest Mean difference, the computing formula of Largest Mean difference is:
Wherein RsLocation fingerprint storehouse corresponding to similar indoor positioning space, RtPosition corresponding to located space in target chamber
Put fingerprint base, location fingerprintWherein Ns, NtIt is Rs, RtColumns, represent location fingerprint quantity;
Step d22, calculates best knowledge matrix KtMethod it is as follows:
The location fingerprint storehouse degree of association in each similar indoor positioning space and located space in target chamber is calculated, computing formula is such as
Under:
Wherein knowledge matrix Ki∈ P, YtIt is RtThe nuclear matrix of middle location fingerprint and beacon region relation, Yt(i, j)=1 represents RtInCorresponding LiIt is equal, while representingIt is collected in same beacon region, otherwise Yt(i, j)=- 1;Wherein so that association
Degree DegreeiTake knowledge matrix K during maximumiIt is just best knowledge matrix Kt。
5. a kind of indoor locating system fast construction method according to claim 4, it is characterised in that with a target chamber
The value of the quantity Q in the corresponding similar indoor positioning space of interior located space is 10.
6. a kind of indoor locating system fast construction method according to claim 5, it is characterised in that in step d21,
C is set1=0.8, c2=0.2.
7. a kind of indoor locating system fast construction method according to claim 6, it is characterised in that in step a1,
Located space in target chamber is divided into N number of equally distributed beacon region.
8. a kind of indoor locating system fast construction method according to claim 7, it is characterised in that WiFi signal intensity
Sniffer is wireless router.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611118893.5A CN106793072B (en) | 2016-12-08 | 2016-12-08 | Rapid building method of indoor positioning system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611118893.5A CN106793072B (en) | 2016-12-08 | 2016-12-08 | Rapid building method of indoor positioning system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106793072A true CN106793072A (en) | 2017-05-31 |
CN106793072B CN106793072B (en) | 2020-02-21 |
Family
ID=58881295
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611118893.5A Active CN106793072B (en) | 2016-12-08 | 2016-12-08 | Rapid building method of indoor positioning system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106793072B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109195123A (en) * | 2018-08-22 | 2019-01-11 | 普联技术有限公司 | The update method of finger print information, device, storage medium and system in indoor positioning |
CN109379695A (en) * | 2018-09-10 | 2019-02-22 | 北京西普阳光教育科技股份有限公司 | The method and machine readable storage medium of indoor positioning for LoRa network |
CN110087179A (en) * | 2019-03-26 | 2019-08-02 | 深圳先进技术研究院 | A kind of indoor positioning control method, system and electronic equipment |
CN110234085A (en) * | 2019-05-23 | 2019-09-13 | 深圳大学 | Based on the indoor location fingerprint to anti-migration network drawing generating method and system |
CN110380796A (en) * | 2019-07-12 | 2019-10-25 | 浙江云蝠电子科技有限公司 | The method for promoting WIFI positioning device anti-interference ability |
CN111368120A (en) * | 2020-05-28 | 2020-07-03 | 广东博智林机器人有限公司 | Target fingerprint database construction method and device, electronic equipment and storage medium |
CN111405461A (en) * | 2020-03-16 | 2020-07-10 | 南京邮电大学 | Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number |
US11808848B1 (en) | 2022-10-08 | 2023-11-07 | Zhejiang Deqing Zhilu Navigation Technology Co., LTD | Method, system and terminal for wide-area acoustic indoor positioning based on RF enhancement |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103139907A (en) * | 2013-02-04 | 2013-06-05 | 北京工业大学 | Indoor wireless positioning method by utilizing fingerprint technique |
CN103402256A (en) * | 2013-07-11 | 2013-11-20 | 武汉大学 | Indoor positioning method based on WiFi (Wireless Fidelity) fingerprints |
CN104105196A (en) * | 2013-04-09 | 2014-10-15 | 广东美晨通讯有限公司 | Positioning method and system based on radio frequency fingerprint |
CN105277917A (en) * | 2015-10-30 | 2016-01-27 | 湖南大学 | Dynamic fingerprint database indoor positioning method based on feedback mechanism |
-
2016
- 2016-12-08 CN CN201611118893.5A patent/CN106793072B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103139907A (en) * | 2013-02-04 | 2013-06-05 | 北京工业大学 | Indoor wireless positioning method by utilizing fingerprint technique |
CN104105196A (en) * | 2013-04-09 | 2014-10-15 | 广东美晨通讯有限公司 | Positioning method and system based on radio frequency fingerprint |
CN103402256A (en) * | 2013-07-11 | 2013-11-20 | 武汉大学 | Indoor positioning method based on WiFi (Wireless Fidelity) fingerprints |
CN105277917A (en) * | 2015-10-30 | 2016-01-27 | 湖南大学 | Dynamic fingerprint database indoor positioning method based on feedback mechanism |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109195123B (en) * | 2018-08-22 | 2020-10-30 | 普联技术有限公司 | Fingerprint information updating method, device, storage medium and system in indoor positioning |
CN109195123A (en) * | 2018-08-22 | 2019-01-11 | 普联技术有限公司 | The update method of finger print information, device, storage medium and system in indoor positioning |
CN109379695A (en) * | 2018-09-10 | 2019-02-22 | 北京西普阳光教育科技股份有限公司 | The method and machine readable storage medium of indoor positioning for LoRa network |
CN109379695B (en) * | 2018-09-10 | 2020-11-24 | 北京西普阳光教育科技股份有限公司 | Method and machine-readable storage medium for indoor positioning of LoRa network |
CN110087179A (en) * | 2019-03-26 | 2019-08-02 | 深圳先进技术研究院 | A kind of indoor positioning control method, system and electronic equipment |
CN110234085A (en) * | 2019-05-23 | 2019-09-13 | 深圳大学 | Based on the indoor location fingerprint to anti-migration network drawing generating method and system |
CN110234085B (en) * | 2019-05-23 | 2020-09-15 | 深圳大学 | Indoor position fingerprint map generation method and system based on anti-migration network |
CN110380796A (en) * | 2019-07-12 | 2019-10-25 | 浙江云蝠电子科技有限公司 | The method for promoting WIFI positioning device anti-interference ability |
CN110380796B (en) * | 2019-07-12 | 2022-03-25 | 浙江云蝠电子科技有限公司 | Method for improving anti-interference capability of WIFI positioning equipment |
CN111405461A (en) * | 2020-03-16 | 2020-07-10 | 南京邮电大学 | Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number |
CN111405461B (en) * | 2020-03-16 | 2021-10-08 | 南京邮电大学 | Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number |
CN111368120A (en) * | 2020-05-28 | 2020-07-03 | 广东博智林机器人有限公司 | Target fingerprint database construction method and device, electronic equipment and storage medium |
US11808848B1 (en) | 2022-10-08 | 2023-11-07 | Zhejiang Deqing Zhilu Navigation Technology Co., LTD | Method, system and terminal for wide-area acoustic indoor positioning based on RF enhancement |
Also Published As
Publication number | Publication date |
---|---|
CN106793072B (en) | 2020-02-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106793072A (en) | A kind of indoor locating system fast construction method | |
CN103747419B (en) | A kind of indoor orientation method based on signal strength difference and dynamic linear interpolation | |
CN103905992B (en) | Indoor positioning method based on wireless sensor networks of fingerprint data | |
CN109327797B (en) | Indoor positioning system of mobile robot based on WiFi network signal | |
CN102638863B (en) | Method for tracking moving targets in wireless sensor networks | |
CN104363654B (en) | Wireless sensor network tri-dimensional node positioning method based on Tunneling method | |
CN105142239B (en) | Wireless sense network mobile sink method of data capture based on data value dynamic estimation | |
CN105933932B (en) | The real-time fault diagnosis method and system of wireless sensor network under complex environment | |
CN105682224B (en) | A kind of distributed wireless fingerprint positioning method for exempting from off-line training | |
CN109068267B (en) | Indoor positioning method based on LoRa SX1280 | |
CN102638889A (en) | Indoor wireless terminal positioning method based on Bayes compression sensing | |
CN107197439A (en) | Wireless sensor network locating method based on matrix completion | |
CN110493717A (en) | A kind of non-ranging node fusion and positioning method suitable for concave domain | |
CN107423762A (en) | Semi-supervised fingerprinting localization algorithm based on manifold regularization | |
CN104053129A (en) | Wireless sensor network indoor positioning method and device based on sparse RF fingerprint interpolations | |
CN109886155A (en) | Man power single stem rice detection localization method, system, equipment and medium based on deep learning | |
CN113411213B (en) | Ad hoc network topology control method and cooperative monitoring method based on Internet of things | |
CN103702282B (en) | A kind of multiple types multiple target passive type localization method based on migration compressed sensing | |
CN107182032A (en) | Monitoring poisonous gas method based on sector models in wireless sensor network | |
Jia | Intelligent garden planning and design based on agricultural internet of things | |
CN106970379A (en) | Based on distance-measuring and positioning method of the Taylor series expansion to indoor objects | |
CN106211256A (en) | A kind of Unmanned Aerial Vehicle Data collection method based on data critical node | |
CN108769907A (en) | The indoor orientation method of fusion WiFi and iBeacon based on deep learning | |
CN113411766B (en) | Intelligent Internet of things comprehensive sensing system and method | |
Chekuri et al. | Automating wifi fingerprinting based on nano-scale unmanned aerial vehicles |
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 |