CN106793072B - Rapid building method of indoor positioning system - Google Patents
Rapid building method of indoor positioning system Download PDFInfo
- Publication number
- CN106793072B CN106793072B CN201611118893.5A CN201611118893A CN106793072B CN 106793072 B CN106793072 B CN 106793072B CN 201611118893 A CN201611118893 A CN 201611118893A CN 106793072 B CN106793072 B CN 106793072B
- Authority
- CN
- China
- Prior art keywords
- indoor positioning
- positioning space
- space
- similar
- target
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 239000011159 matrix material Substances 0.000 claims abstract description 69
- 238000010276 construction Methods 0.000 claims abstract description 17
- 238000013526 transfer learning Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000012805 post-processing Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000135164 Timea Species 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- 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 invention relates to a quick construction method of an indoor positioning system, which comprises the following steps: step a, setting an indoor positioning environment of a target indoor positioning space based on WiFi signal intensity data; b, establishing a similar indoor positioning spatial position fingerprint library set; step c, collecting WiFi signal intensity data in the target indoor positioning space to form a target indoor positioning space position fingerprint database; and d, determining the optimal knowledge matrix from the knowledge matrices of the position fingerprint library set of the similar indoor positioning space by adopting a transfer learning method. The rapid construction method of the indoor positioning system adopts the transfer learning method in the construction process, reduces the position fingerprint acquisition amount of the indoor positioning system, and greatly reduces the time period and labor cost for constructing the indoor positioning system. Meanwhile, in the construction process of the positioning system, the data volume of the position fingerprint database of the effective indoor positioning space can be continuously increased, and the construction efficiency of a new indoor positioning system is continuously improved.
Description
Technical Field
The invention relates to an indoor positioning system, in particular to a building method for quickly building the indoor positioning system.
Background
In modern positioning technologies, indoor positioning technologies are derived from "last mile" navigation after completion of an mission by outdoor positioning technologies. The existing indoor positioning technology has great practical requirements in urban resident life, and an indoor positioning system based on WiFi signal strength is adopted under the common condition, so that the indoor positioning technology is widely researched and applied due to the characteristics of low hardware cost, high positioning precision and the like. However, in the building process of the existing indoor positioning system based on WiFi signal strength, a large amount of labor cost and time cost are needed for collecting position fingerprint data and forming an effective position fingerprint database of a target positioning space, and these problems greatly limit the rapid popularization and large-area use of the indoor positioning system based on WiFi signal strength in practical application.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a building method for quickly building an indoor positioning system by adopting a transfer learning technology.
A quick construction method for an indoor positioning system comprises the following steps:
step a, setting an indoor positioning environment of a target indoor positioning space based on WiFi signal intensity data;
b, establishing a similar indoor positioning spatial position fingerprint library set;
step c, collecting WiFi signal intensity data in the target indoor positioning space to form a target indoor positioning space position fingerprint database;
and d, determining the optimal knowledge matrix from the knowledge matrices of the position fingerprint library set of the similar indoor positioning space by adopting a transfer learning method.
Preferably, in the step a, the method of setting the positioning environment of the target indoor positioning space includes the steps of:
a step 1, dividing the target indoor positioning space into N beacon areas;
step a2, arranging M WiFi signal strength sniffers in a target indoor positioning space;
in step b, the method for establishing the similar indoor positioning spatial position fingerprint library set comprises the following steps:
step b1, collecting the position fingerprint database data of the known indoor positioning space to a source position fingerprint database set;
b2, selecting a position fingerprint database of a similar indoor positioning space as a target indoor positioning space from the source position fingerprint database set, and constructing the similar indoor positioning space position fingerprint database set;
in step c, each beacon region L of the space is located from within the target roomi(i is more than or equal to 1 and less than or equal to N) WiFi signal intensity data are collected, the data are processed and stored in a database, and each data unit is represented by one tuple, and the representation method comprises the following steps:
(RSS1,RSS2,...,RSSM,Li)
each data unit represents a beacon region LiM Wifi Signal Strength data collected, wherein RSSj(j is more than or equal to 1 and less than or equal to M) represents WiFi signal strength data received by the jth WiFi signal strength sniffer; representing a location fingerprint of a target indoor positioning space as rt={RSS1,RSS2,...,RSSMR, and one beacon area can correspond to a plurality of location fingerprintstIs rtSuch that R istLocating a spatial location fingerprint library for a target room;
in step d, the method of determining the optimal knowledge matrix comprises the steps of:
step d1, constructing a similar indoor positioning space knowledge matrix pool;
and d2, calculating the optimal knowledge matrix suitable for the target indoor positioning space from the similar indoor positioning space knowledge matrix pool.
Preferably, in step b, the similar indoor positioning space is an indoor positioning space in which the same number of WiFi signal strength sniffers are set as the target indoor positioning space;
in step c, in the target indoor space, the number of WiFi signal strength data acquisition points selected from each beacon region is 2, so that one beacon region can correspond to 2 location fingerprints, and the duration of WiFi signal strength data acquisition at each acquisition point is 2 minutes.
Preferably, in step d1, K is set as a knowledge matrix of WiFi signal strength distribution in each similar indoor positioning space, and P is set as a set of knowledge matrices K, such that P is a knowledge matrix pool of similar indoor positioning spaces; for WiFi signal strength data for each similar indoor positioning space, a knowledge matrix can be calculated using the following formula:
tr (-) in the formula represents the trace of the matrix, B is set to 100, p is set to 2, wherein R issA location fingerprint database for the similar indoor positioning space, N being a quantitative value of location fingerprint data collected in the similar indoor positioning space;i is an identity matrix; y is RsA kernel matrix of the relation between the location fingerprint and the beacon region, where Y (i, j) ═ 1 denotes RsInCorresponding LiAre equal to, simultaneously representCollecting in the same beacon region, otherwise Y (i, j) ═ 1; after calculation, K is equal to LLTWherein, L is a matrix obtained by singular value decomposition post-processing of a knowledge matrix K, Q is a quantity value of a similar indoor positioning space corresponding to a target indoor positioning space, and finally P ═ K is obtained1,K2,...,KQ};
In step d2, K is settCalculating an optimal knowledge matrix K suitable for the target indoor positioning space from a similar indoor positioning space knowledge matrix pool P for the optimal knowledge matrix corresponding to the target indoor positioning spacetThe method comprises the following steps:
step d21, calculating the similarity of the location fingerprint database of each similar indoor location space and the target indoor location space, the calculation formula is as follows:
Si=-(c1*MMDi+c2*Difi)
wherein c is1,c2E (0, 1), and c1+c2=1,DifiSetting as the difference between the number of beacon regions of the similar indoor positioning space and the target indoor positioning space, MMDiSetting the maximum mean difference of the position fingerprint libraries of the similar indoor positioning space and the target indoor positioning space, wherein the calculation formula of the maximum mean difference is as follows:
wherein R issLocation fingerprint repository, R, corresponding to similar indoor location spacestLocation fingerprint library corresponding to target indoor location space, location fingerprintWherein N iss,NtIs Rs,RtThe number of columns representing the number of location fingerprints;
step d22, calculating the optimal knowledge matrix KtThe method comprises the following steps:
calculating the association degree of the position fingerprint database of each similar indoor positioning space and the target indoor positioning space, wherein the calculation formula is as follows:
wherein the knowledge matrix Ki∈P,YtIs RtKernel matrix of mid-position fingerprint to beacon region relation, Yt(i, j) ═ 1 denotes RtInCorresponding LiAre equal to, simultaneously representCollected in the same beacon area, otherwise Yt(i, j) ═ -1; wherein Degree of association is enabled to be DegreeiKnowledge matrix K when taking maximum valueiIs the optimal knowledge matrix Kt。
Preferably, the number Q of similar indoor positioning spaces corresponding to one target indoor positioning space has a value of 10.
Preferably, inIn step d21, c is set1=0.8,c2=0.2。
Preferably, in step a1, the target indoor positioning space is divided into N evenly distributed beacon regions.
Preferably, the WiFi signal strength sniffer is a wireless router.
By adopting the rapid construction method of the indoor positioning system, the acquisition amount of the offline fingerprint data of the indoor positioning system based on the WIFI signal strength is reduced, and the time period and the labor cost for constructing the indoor positioning system are greatly reduced by adopting the transfer learning method in the construction process of the system. Meanwhile, in the construction process of the positioning system, the data volume of the position fingerprint database of the effective indoor positioning space can be continuously increased, and the construction efficiency of a new indoor positioning system is continuously improved.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
The indoor positioning system comprises a WiFi signal strength sniffer, wireless equipment and a background server. In the positioning process, firstly, the WiFi signal strength sniffer is set to be in a Monitor operation mode, the wireless equipment actively sends a wireless data link frame, then the wireless data link frame is captured by the WiFi signal strength sniffer, wireless equipment signal strength data and MAC address related data of the wireless equipment contained in the acquired wireless data link frame are analyzed, finally, the acquired data are attached to the MAC address data of the wireless equipment by the WiFi signal strength sniffer and then sent to a background server for processing, and the indoor positioning work of the wireless equipment is completed. Generally, before a positioning system starts to work normally, position fingerprint data of the whole indoor positioning environment needs to be acquired and processed, wherein the position fingerprint data includes WiFi signal intensity data of a certain point in a positioning space. In the construction process of the indoor positioning system, the position fingerprint data of the target indoor positioning space with only a few acquisition points is subjected to auxiliary processing by adopting a transfer learning method, so that the construction of the positioning system can be quickly and effectively finished, and the indoor positioning work of the wireless equipment is realized.
The wireless devices comprise all devices which can be connected to a network through a WiFi wireless local area network, such as smart phones, notebook computers, smart bracelets or digital cameras and the like; the WiFi signal strength sniffer comprises all network equipment capable of operating in a Monitor operation mode, the network equipment operating in the mode can capture wireless data link frames, and most of wireless routers in the market can operate in the Monitor mode. The method for quickly building an indoor positioning system according to the present invention is described in detail by specific embodiments as follows:
example (b):
as shown in fig. 1, a method for quickly building an indoor positioning system based on WiFi signal strength specifically includes the following steps:
step a, setting an indoor positioning environment of a target indoor positioning space based on WiFi signal intensity data, wherein the specific method comprises the following steps:
step a1, dividing the target indoor positioning space into N uniformly distributed beacon regions, wherein each beacon region is set to be 4 x 4m in area2A square region of (a);
step a2, setting M WiFi signal strength sniffers in the target indoor positioning space, wherein a wireless router is used as the WiFi signal strength sniffer, and the wireless router is set to be in a Monitor operation mode, so that the wireless router can capture the relevant data of the wireless data link frame.
And b, establishing a similar indoor positioning spatial position fingerprint library set. In order to quickly build a position fingerprint library of a target indoor positioning space, the positioning effect of the target indoor positioning space position fingerprint library is improved by utilizing the position fingerprint library which can be similar to the indoor positioning space. The similar indoor positioning space refers to an indoor positioning space where the same number of WiFi signal strength sniffers are laid as the target indoor positioning space. The method for establishing the similar indoor positioning spatial position fingerprint library set comprises the following steps:
step b1, collecting the position fingerprint database data of the known indoor positioning space to a source position fingerprint database set;
and b2, selecting a position fingerprint database of a similar indoor positioning space as the target indoor positioning space from the source position fingerprint database set, and constructing the similar indoor positioning space position fingerprint database set.
Step c, collecting WiFi signal intensity data in the target indoor positioning space to form a target indoor positioning space position fingerprint database, wherein the specific method comprises the following steps:
locating each beacon region L of a space from within a target roomi(i is more than or equal to 1 and less than or equal to N) acquiring WiFi signal intensity data, processing the data, storing the processed data in a database, and representing each data unit by using a tuple as follows:
(RSS1,RSS2,...,RSSM,Li)
each data unit represents a beacon region LiM Wifi Signal Strength data collected, wherein RSSj(j is more than or equal to 1 and less than or equal to M) represents the received WiFi signal strength data of the jth WiFi signal strength sniffer, and the unit is dbM; representing a location fingerprint of a target indoor positioning space as rt={RSS1,RSS2,...,RSSMR, and one beacon area can correspond to a plurality of location fingerprintstIs rtSuch that R istA location fingerprint library of a space is located for a target room.
In order to reduce the time for the WiFi signal strength sniffer to collect WiFi signal strength data in a target indoor positioning space, the number of WiFi signal strength data collection points selected from each beacon area is 2, so that one beacon area can correspond to 2 position fingerprints, and the duration for collecting the WiFi signal strength data at each collection point is 2 minutes; if the acquisition precision is to be improved, the number of the WiFi signal strength data acquisition points selected in each beacon area is set to be 4, and at the moment, one beacon area can correspond to 4 position fingerprints.
D, determining an optimal knowledge matrix from knowledge matrices of the position fingerprint library set of the similar indoor positioning space by adopting a transfer learning method, improving the positioning effect of the target indoor positioning space and assisting a positioning system to complete positioning work;
for the position fingerprint library set of similar indoor positioning spaces, the system learns the distribution knowledge of the WiFi signal intensity of each similar indoor positioning space by adopting a transfer learning method, and selects the optimal distribution knowledge for the target indoor positioning space to improve the positioning effect, and the method for determining the optimal knowledge matrix comprises the following steps:
step d1, constructing a similar indoor positioning space knowledge matrix pool, wherein the specific method is as follows:
setting K as a knowledge matrix of WiFi signal intensity distribution in each similar indoor positioning space, setting P as a knowledge matrix pool of the similar indoor positioning spaces, and setting P as a set of the knowledge matrix K; setting Q as a quantity value of a similar indoor positioning space corresponding to a target indoor positioning space; for WiFi signal strength data for each similar indoor positioning space, a knowledge matrix can be calculated using the following formula:
where tr (-) denotes the trace of the matrix, B and p are two preset constants, B is set to 100, p is set to 2,wherein R issA location fingerprint library for the similar indoor location space,representing the location fingerprint data collected within a beacon region of the similar indoor positioning space, N being the magnitude of the location fingerprint data collected in the similar indoor positioning space. Y is RsA kernel matrix of the relation between the location fingerprint and the beacon region, where Y (i, j) ═ 1 denotes RsInCorresponding LiAre equal to, simultaneously representAnd collecting in the same beacon region, otherwise, Y (i, j) ═ 1.And I is an identity matrix.
A is a symmetric matrix, so it can be represented as a Vdiag (δ) V using eigen decompositionTWhere V is the eigenvector of A and δ is the eigen-coefficient of A. Thus can obtain A+=Vdiag(δ+)VTWherein δ+Is the non-negative vector corresponding to delta in A, delta+[i]=max(0,δ[i])。
Since K can be proven to be an M semi-positive definite matrix, K can be expressed by Singular Value Decomposition (SVD) as: k ═ LLTAnd L is a matrix obtained by performing singular value decomposition and post-processing on the knowledge matrix K.
Further, two sets of location fingerprints R in the location fingerprint library R of the similar indoor location space can be calculated according to the following formulai,rjDifference value data d betweenK:
Therefore, for Q similar indoor positioning spaces corresponding to the target indoor positioning space, Q different knowledge matrices K can be calculated to form a knowledge matrix pool P of the candidate similar indoor positioning space:
P={K1,K2,...,KQ}
the value of Q is set to 10 here, i.e., there are 10 similar indoor positioning spaces corresponding to the target indoor positioning space.
And d2, calculating the optimal knowledge matrix suitable for the target indoor positioning space from the similar indoor positioning space knowledge matrix pool.
Set up KtCalculating an optimal knowledge matrix K suitable for the target indoor positioning space from a similar indoor positioning space knowledge matrix pool P for the optimal knowledge matrix corresponding to the target indoor positioning spacetThe method comprises the following steps:
step d21, calculating the similarity of the location fingerprint database of each similar indoor location space and the target indoor location space, the calculation formula is as follows:
Si=-(c1*MMDi+c2*Difi)
wherein c is1,c2E (0, 1), and c1+c2Where c is set to 11=0.8,c2=0.2。DifiSetting as the difference between the number of beacon regions of the similar indoor positioning space and the target indoor positioning space, MMDiSetting the maximum mean difference of the position fingerprint libraries of the similar indoor positioning space and the target indoor positioning space, wherein the calculation formula is as follows:
wherein R issLocation fingerprint repository, R, corresponding to similar indoor location spacestLocation fingerprint library corresponding to target indoor location space, location fingerprintWherein N iss,NtIs Rs,RtThe number of columns representing the number of location fingerprints.
Step d22, the method for calculating the optimal knowledge matrix is as follows:
calculating the association degree of the position fingerprint database of each similar indoor positioning space and the target indoor positioning space, wherein the calculation formula is as follows:
wherein the knowledge matrix Ki∈P,YtIs RtKernel matrix of mid-position fingerprint to beacon region relation, Yt(i, j) ═ 1 denotes RtInCorresponding LiAre equal to, simultaneously representCollected in the same beacon area, otherwise Yt(i, j) — 1. Wherein Degree of association is enabled to be DegreeiKnowledge matrix K when taking maximum valueiIs the optimal knowledge matrix Kt。
After step d is completed, the optimal knowledge matrix K determined in step d can be usedtThe method is characterized by comprising the following steps of guiding to complete the construction of a positioning system fingerprint library of a target indoor positioning space and assisting a system to complete indoor positioning work, and specifically comprises the following steps:
set rtSetting for a position fingerprint of a target indoor positioning space acquired in real timeAs a real-time position fingerprint rtPosition fingerprint in target indoor positioning space position fingerprint libraryBy comparing the real-time position fingerprint r using the KNN algorithmtDifference with position fingerprint in target indoor positioning space position fingerprint libraryIs arranged such thatThe beacon region corresponding to the minimum location fingerprint is the predicted region Lt,The calculation formula of (a) is as follows:
whereinCan use singular value decomposition to obtain Lt. Meanwhile, the positioning system adopts a KNN algorithm to calculate real-time positioning, and sets the nearest neighbor weight k to be 1.
And in the operation process of the positioning system, the obtained new fingerprint data is combined into a test data fingerprint database, and when the positioning accuracy parameter of the positioning system based on the test data fingerprint database reaches a set value representing high positioning accuracy, the test data fingerprint database can be added into a source position fingerprint database set.
By using the rapid construction method of the indoor positioning system, the manual acquisition amount of the offline fingerprint data of the indoor positioning system based on the WIFI signal strength is reduced, and the time period and the labor cost for constructing the indoor positioning system are greatly reduced by adopting the transfer learning method in the construction process of the system. Meanwhile, in the setting-up process of the positioning system, the data volume of the position fingerprint database of an effective indoor positioning space can be continuously increased, the fingerprint data concentrated by the position fingerprint database is continuously increased, and the setting-up efficiency of a new indoor positioning system is improved.
The above examples of the present invention are merely illustrative of the present invention and are not intended to limit the embodiments of the present invention. Variations and modifications in other variations will occur to those skilled in the art upon reading the foregoing description. Not all embodiments are exhaustive here. All obvious changes and modifications of the present invention are within the scope of the present invention.
Claims (7)
1. A quick construction method for an indoor positioning system is characterized by comprising the following steps:
step a, setting an indoor positioning environment of a target indoor positioning space based on WiFi signal intensity data;
b, establishing a similar indoor positioning spatial position fingerprint library set;
step c, collecting WiFi signal intensity data in the target indoor positioning space to form a target indoor positioning space position fingerprint database;
d, determining an optimal knowledge matrix from knowledge matrices of the position fingerprint library set of the similar indoor positioning space by adopting a transfer learning method;
wherein, in the step a, the method for setting the positioning environment of the target indoor positioning space comprises the following steps:
a step 1, dividing the target indoor positioning space into N beacon areas;
step a2, arranging M WiFi signal strength sniffers in a target indoor positioning space;
in step b, the method for establishing the similar indoor positioning spatial position fingerprint library set comprises the following steps:
step b1, collecting the position fingerprint database data of the known indoor positioning space to a source position fingerprint database set;
b2, selecting a position fingerprint database of a similar indoor positioning space as a target indoor positioning space from the source position fingerprint database set, and constructing the similar indoor positioning space position fingerprint database set;
in step c, each beacon region L of the space is located from within the target roomi(i is more than or equal to 1 and less than or equal to N) WiFi signal intensity data are collected, the data are processed and stored in a database, and each data unit is represented by one tuple, and the representation method comprises the following steps:
(RSS1,RSS2,...,RSSM,Li)
each data unit represents a beacon region LiM Wifi Signal Strength data collected, wherein RSSj(j is more than or equal to 1 and less than or equal to M) represents WiFi signal strength data received by the jth WiFi signal strength sniffer; representing a location fingerprint of a target indoor positioning space as rt={RSS1,RSS2,...,RSSMR, and one beacon area can correspond to a plurality of location fingerprintstIs rtSuch that R istLocating a spatial location fingerprint library for a target room;
in step d, the method of determining the optimal knowledge matrix comprises the steps of:
step d1, constructing a similar indoor positioning space knowledge matrix pool;
and d2, calculating the optimal knowledge matrix suitable for the target indoor positioning space from the similar indoor positioning space knowledge matrix pool.
2. The method for quickly building an indoor positioning system according to claim 1, wherein in the step b, the similar indoor positioning space is an indoor positioning space in which the same number of WiFi signal strength sniffers as the target indoor positioning space are arranged;
in step c, in the target indoor positioning space, the number of WiFi signal strength data acquisition points selected from each beacon region is 2, so that one beacon region can correspond to 2 location fingerprints, and the duration of WiFi signal strength data acquisition at each acquisition point is 2 minutes.
3. The method for quickly building an indoor positioning system according to any one of claims 1 or 2, wherein in step d1, K is set as a knowledge matrix of WiFi signal intensity distribution in each similar indoor positioning space, and P is set as a set of knowledge matrices K, so that P is a knowledge matrix pool of similar indoor positioning spaces; for WiFi signal strength data for each similar indoor positioning space, a knowledge matrix can be calculated using the following formula:
tr (-) in the formula represents the trace of the matrix, B is set to 100, p is set to 2,wherein R issIs the same asA location fingerprint database of the indoor positioning space, wherein N is a quantity value of the location fingerprint data collected in the similar indoor positioning space;i is an identity matrix; y is RsA kernel matrix of the relation between the location fingerprint and the beacon region, where Y (i, j) ═ 1 denotes RsInCorresponding Li is equal and representsCollecting in the same beacon region, otherwise Y (i, j) ═ 1; after calculation, K is equal to LLTWherein, L is a matrix obtained by singular value decomposition post-processing of a knowledge matrix K, Q is a quantity value of a similar indoor positioning space corresponding to a target indoor positioning space, and finally P ═ K is obtained1,K2,...,KQ};
In step d2, K is settCalculating an optimal knowledge matrix K suitable for the target indoor positioning space from a similar indoor positioning space knowledge matrix pool P for the optimal knowledge matrix corresponding to the target indoor positioning spacetThe method comprises the following steps:
step d21, calculating the similarity of the location fingerprint database of each similar indoor location space and the target indoor location space, the calculation formula is as follows:
Si=-(c1*MMDi+c2*Difi)
wherein c is1,c2E (0, 1), and c1+c2=1,DifiSetting as the difference between the number of beacon regions of the similar indoor positioning space and the target indoor positioning space, MMDiSetting the maximum mean difference of the position fingerprint libraries of the similar indoor positioning space and the target indoor positioning space, wherein the calculation formula of the maximum mean difference is as follows:
wherein R issLocation fingerprint repository, R, corresponding to similar indoor location spacestLocation fingerprint library corresponding to target indoor location space, location fingerprintWherein N iss,NtIs Rs,RtThe number of columns representing the number of location fingerprints;
step d22, calculating the optimal knowledge matrix KtThe method comprises the following steps:
calculating the association degree of the position fingerprint database of each similar indoor positioning space and the target indoor positioning space, wherein the calculation formula is as follows:
wherein the knowledge matrix Ki∈P,YtIs RtKernel matrix of mid-position fingerprint to beacon region relation, Yt(i, j) ═ 1 denotes RtInCorresponding LiAre equal to, simultaneously representCollected in the same beacon area, otherwise Yt(i, j) ═ -1; wherein Degree of association is enabled to be DegreeiKnowledge matrix K when taking maximum valueiIs the optimal knowledge matrix Kt。
4. The method for quickly building an indoor positioning system according to claim 3, wherein the value of the number Q of similar indoor positioning spaces corresponding to one target indoor positioning space is 10.
5. The indoor positioning system rapid construction method according to claim 4, wherein in step d21, c is set1=0.8,c2=0.2。
6. The method for rapidly building an indoor positioning system according to claim 5, wherein in step a1, the target indoor positioning space is divided into N beacon regions which are uniformly distributed.
7. The method for quickly building an indoor positioning system according to claim 6, wherein the WiFi signal strength sniffer is a 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 CN106793072A (en) | 2017-05-31 |
CN106793072B true CN106793072B (en) | 2020-02-21 |
Family
ID=58881295
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611118893.5A Expired - Fee Related CN106793072B (en) | 2016-12-08 | 2016-12-08 | Rapid building method of indoor positioning system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106793072B (en) |
Families Citing this family (8)
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 |
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 |
CN110087179B (en) * | 2019-03-26 | 2020-07-21 | 深圳先进技术研究院 | Indoor positioning control method and system and electronic equipment |
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 |
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 |
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 |
CN111368120B (en) * | 2020-05-28 | 2020-09-15 | 广东博智林机器人有限公司 | Target fingerprint database construction method and device, electronic equipment and storage medium |
CN115604817B (en) | 2022-10-08 | 2023-05-02 | 浙江德清知路导航科技有限公司 | Wide-area audio indoor positioning method, system and terminal based on radio frequency 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 not_active Expired - Fee Related
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 |
Also Published As
Publication number | Publication date |
---|---|
CN106793072A (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106793072B (en) | Rapid building method of indoor positioning system | |
CN105792353B (en) | Crowd sensing type WiFi signal fingerprint assisted image matching indoor positioning method | |
CN106646338B (en) | A kind of quickly accurate indoor orientation method | |
CN107703480B (en) | Mixed kernel function indoor positioning method based on machine learning | |
CN105044662B (en) | A kind of fingerprint cluster multi-point joint indoor orientation method based on WIFI signal intensity | |
CN112165684B (en) | High-precision indoor positioning method based on joint vision and wireless signal characteristics | |
CN105223546B (en) | Indoor orientation method based on received signal strength and reference point locations double focusing class | |
CN109614935A (en) | Car damage identification method and device, storage medium and electronic equipment | |
CN105813194B (en) | Indoor orientation method based on fingerprint database secondary correction | |
CN105354841B (en) | A kind of rapid remote sensing image matching method and system | |
JP2021517284A (en) | Indoor positioning methods, indoor positioning systems, indoor positioning devices and computer readable media | |
CN104540221B (en) | WLAN indoor orientation methods based on semi-supervised SDE algorithms | |
CN109327797A (en) | Mobile robot indoor locating system based on WiFi network signal | |
CN108234927A (en) | Video frequency tracking method and system | |
CN110113560B (en) | Intelligent video linkage method and server | |
CN109756842B (en) | Wireless indoor positioning method and system based on attention mechanism | |
CN107274441B (en) | Wave band calibration method and system for hyperspectral image | |
CN108225332B (en) | Indoor positioning fingerprint map dimension reduction method based on supervision | |
CN117146739B (en) | Angle measurement verification method and system for optical sighting telescope | |
CN105005024A (en) | Compression sensing and positioning method | |
Qin et al. | A wireless sensor network location algorithm based on insufficient fingerprint information | |
US20240169584A1 (en) | Neural network-based pose estimation and registration method and device for heterogeneous images, and medium | |
CN116909208B (en) | Shell processing path optimization method and system based on artificial intelligence | |
CN113259883A (en) | Multi-source information fusion indoor positioning method for mobile phone user | |
CN113483661B (en) | Point cloud data acquisition method, device, equipment and storage medium |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200221 |