CN109739830A - A kind of location fingerprint database fast construction method based on crowdsourcing data - Google Patents
A kind of location fingerprint database fast construction method based on crowdsourcing data Download PDFInfo
- Publication number
- CN109739830A CN109739830A CN201910149853.4A CN201910149853A CN109739830A CN 109739830 A CN109739830 A CN 109739830A CN 201910149853 A CN201910149853 A CN 201910149853A CN 109739830 A CN109739830 A CN 109739830A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- landmark
- data
- implicit
- path
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 9
- 230000004992 fission Effects 0.000 claims abstract description 19
- 239000002245 particle Substances 0.000 claims abstract description 16
- 238000005516 engineering process Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 44
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 12
- 230000005855 radiation Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 abstract description 3
- 230000001186 cumulative effect Effects 0.000 abstract 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The invention discloses a kind of location fingerprint database fast construction method based on crowdsourcing data, library is built in S1, the fission based on PDR, particle filter and ground constraint diagram；S2, the PDR accumulated error that non-explicit landmark point region is corrected based on MDS.The present invention is based on fission modes and setting path effective time threshold value to construct location fingerprint database, and combines implicit landmark point to correct PDR cumulative errors using MDS, meanwhile, short distance location fingerprint correlation model is constructed based on weighting multidimensional WiFi numerical characteristics；The cumulative errors of sensor can be reduced with rapid build location fingerprint database compared with the existing technology, improve the matching precision of position and fingerprint, efficiently solve and frequently bother user in the prior art, position and the low problem of fingerprint matching precision.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a position fingerprint database rapid construction method based on crowdsourcing data.
Background
The existing method for constructing the position fingerprint database based on crowdsourcing comprises two methods: one is a display crowdsourcing mode, and the method is characterized in that relatively accurate position fingerprint information can be obtained, but the user can be disturbed frequently, so that the experience of the user is reduced, and data can be polluted when the user does not operate accurately, so that the practical popularization and application are hindered; the other mode is an implicit crowdsourcing mode, the method can avoid the phenomenon that a user is frequently disturbed, but the matching problem of the position and the fingerprint needs to be considered, and the existing position fingerprint database construction method based on the implicit crowdsourcing can only roughly match the position and the fingerprint.
The existing method for constructing the position fingerprint database based on PDR and implicit crowdsourcing can realize the matching problem of positions and fingerprints, and can quickly construct a relatively complete position fingerprint database. However, the PDR has a large accumulated error, so that the matching precision of the position and the fingerprint is not high, the matching precision of a partial area can be improved by correcting the PDR accumulated error by adopting the characteristic landmark points, but the number of the characteristic landmark points is limited, and the matching precision cannot be effectively improved.
Disclosure of Invention
The invention aims to provide a method for quickly constructing a position fingerprint database based on crowdsourcing data aiming at the defects in the prior art, so as to solve the problems that users are frequently disturbed and the matching precision of positions and fingerprints is low in the prior art.
In order to achieve the purpose, the invention adopts the technical scheme that:
a position fingerprint database rapid construction method based on crowdsourcing data comprises the following steps:
s1, creating a library based on the fission of the PDR, the particle filter and the map constraint, wherein the steps comprise
S11, training a short-distance position fingerprint correlation model;
s12, constructing an indoor map;
s13, marking explicit landmark points and collecting fingerprint data of corresponding positions;
s14, judging whether the crowdsourcing path data is enabled;
s15, associating fingerprints and position points based on PDR, particle filtering and map constraint multiple conditions;
s16, setting an effective time threshold of a crowdsourcing path, and if the accumulated error of the sensor data is within a tolerable range within the effective time threshold, entering step S15, otherwise, failing the crowdsourcing path, and entering step S17;
s17, sequentially building a library based on the fission mode;
s2, correcting the PDR accumulated error of the non-explicit landmark region based on the MDS, wherein the steps comprise
S21, calculating an implicit landmark point area range based on the fingerprint similarity;
s22, counting common paths among the implicit landmark point areas;
s23, searching a relatively effective crowdsourcing path;
s24, redrawing a new path between the implicit landmark point areas;
s25, calculating the relative coordinates of the implicit landmark point area;
s26, accurately calculating the absolute coordinates of the implicit landmark point area based on MDS;
and S27, correcting the PDR accumulated error of the non-explicit landmark region.
Preferably, the method for training the short-range location fingerprint correlation model in step S11 includes:
a1, modeling based on multi-dimensional WiFi numerical characteristic fingerprint distance;
and A2, training a short-distance position fingerprint correlation model.
Preferably, the method for modeling the step a1 based on the multidimensional WiFi numerical characteristic fingerprint distance is as follows:
a11, constructing a relative fingerprint consisting of relative subsequences;
a12, calculating the similarity of the relative subsequence pairs;
a13, calculating the similarity of the fingerprint relative subsequence pairs in the relative fingerprint pairs, and obtaining a similarity matrix of the relative fingerprint pairs by adopting traversal calculation;
and A14, searching for the best matching relative fingerprint pair in the similarity matrix by adopting a dynamic programming algorithm.
Preferably, the training method of the short-distance position fingerprint association model in the step a2 is as follows:
a21, acquiring crowd-sourced data around the known landmark points;
a22, extracting fingerprint data of the landmark point radiation area according to the fingerprint similarity;
a23, calculating the fingerprint distance of the fingerprint data of the landmark point radiation area;
and A24, determining a short-distance position fingerprint correlation model based on the MDS.
Preferably, the method for determining whether the crowdsourcing path data is enabled in step S14 is as follows:
when only explicit landmark point data exists in the database, setting that when a user walks to the vicinity of the explicit landmark point, the crowdsourcing path starts to be effective, and calculating the physical coordinates of the initial position point when the crowdsourcing path starts to be effective by using a short-distance position fingerprint correlation model;
and judging whether the user has walked around the explicit landmark point according to the similarity of the WiFi fingerprint.
Preferably, the method for associating fingerprints and location points based on PDR, particle filtering and map constraint multiple conditional constraints in step S15 is:
combining multiple technologies of PDR, particle filtering and map constraint to construct a position fingerprint database;
deducing the pedestrian step number, step length and course according to the built-in sensor data of the smart phone to obtain a user walking path, obtain the physical coordinates of data acquisition points on the crowdsourcing path, and obtain the matching of the position and the fingerprint;
and obtaining an accurate crowdsourcing path by adopting a particle filtering and map constraint dual constraint condition.
Preferably, the step S17 is to sequentially create the library based on the fission mode segmentation, and the method includes:
when fingerprint data of non-explicit position points are established in the position fingerprint database, effective initial positions of crowdsourcing path data of other users are around any known position point, and the database is established based on a fission mode;
and each fingerprint point on the position fingerprint database after the fission mode library is built corresponds to a rough physical coordinate.
Preferably, step S21 includes setting a threshold σ of fingerprint similaritysimSimilarity of fingerprint exceeds sigmasimThe small area where the position point of (2) is located is taken as an implicit landmark point area;
step S22 includes numbering the continuous paths to obtain the number of paths passing through two landmark areas simultaneously;
step S23 includes selecting the path with the minimum fluctuation of magnetometer data as the effective path between two landmark point areas in the common path between the two implicit landmark point areas;
step S24 includes redrawing a new path between the implicit landmark regions according to the acceleration sensor and magnetometer sensor data of the effective path between the implicit landmark regions;
step S25 includes calculating coordinates of each implicit landmark region relative to the explicit landmark points in turn, starting from the explicit landmark nodes.
Preferably, the method for accurately calculating the absolute coordinates of the implicit landmark region based on the MDS in step S26 is as follows:
constructing a relative distance matrix D according to the relative coordinates of each implicit landmark point area and each explicit landmark point,
wherein d isijI is the relative distance between the explicit landmark point, the implicit landmark point, and the center position point, i is 1,2,3, …, m; j is 1,2,3 …, m;
setting the central position point as an origin, calculating relative coordinates of the explicit and implicit landmark points and the origin according to the MDS, and updating the original relative coordinates of the implicit landmark points;
and solving the actual physical coordinates of each implicit landmark point according to the actual physical coordinates of the explicit landmark points.
Preferably, the method for correcting the PDR accumulated error of the non-explicit landmark region in step S27 is as follows:
and taking each implicit landmark point as a new starting point of a crowdsourcing path passing around the point, drawing a new crowdsourcing path according to the information of the subsequent part of original path passing through the point, correcting the accumulated error of the PDR, and improving the matching precision of the position and the fingerprint.
The position fingerprint database rapid construction method based on crowdsourcing data provided by the invention has the following beneficial effects:
the method comprises the steps of constructing a position fingerprint database based on a fission mode and a set path effective time threshold, correcting a PDR accumulated error by adopting an MDS and combining an implicit landmark point, and constructing a short-distance position fingerprint correlation model based on weighted multidimensional WiFi numerical characteristics; compared with the prior art, the method can quickly establish the position fingerprint database, reduce the accumulated error of the sensor, improve the matching precision of the position and the fingerprint, and effectively solve the problems that the user is frequently disturbed and the matching precision of the position and the fingerprint is low in the prior art.
Drawings
Fig. 1 is a flowchart of a method for quickly constructing a location fingerprint database based on crowdsourcing data.
FIG. 2 is a flow chart of training a short-range location fingerprint correlation model.
FIG. 3 is a schematic diagram of a fission-based library construction.
Fig. 4 is a diagram illustrating the calculation of relative coordinates of an implicit landmark region.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
According to an embodiment of the application, referring to fig. 1, a method for quickly constructing a position fingerprint database based on crowdsourcing data according to the present scheme includes:
s1, creating a library based on the fission of the PDR, the particle filter and the map constraint, wherein the steps comprise:
s11, training a short-distance position fingerprint correlation model;
referring to fig. 2, step S11 specifically includes the following two steps
A1, modeling based on multi-dimensional WiFi numerical characteristic fingerprint distance;
and A2, training a short-distance position fingerprint correlation model.
The specific method for modeling based on the multidimensional WiFi numerical characteristic fingerprint distance in the step A1 comprises the following steps:
a11, constructing a relative fingerprint consisting of relative subsequences;
is provided with two groups of fingerprintsAndexpanding the rss value of each AP in the fingerprint by a group of rss vectors to form a relative subsequenceWhere i, j ∈ {1, …, Nn}. The relative fingerprint is composed of the relative subsequences:and
a12, calculating the similarity of the relative subsequence pairs;
two different sets of relative fingerprintsAndform a fingerprint pairAre respectively atAndtaking fingerprint opponent subsequencesAndwherein j ∈ {1, …, Nn}，i∈{1,…,NmI.e. thatRelative subsequence pairs forming fingerprintsObtaining relative fingerprint centering based on multidimensional WiFi numerical characteristic weighted statisticsDegree of similarity ofCan be expressed as:
wherein, wiIs a weighting coefficient (0 ≦ wi≤1，i＝1,2,3,4)，Is the rss level matching cost,is thatThe coefficient of the spearman correlation between N and N is NmAnd NnThe total number of all the non-identical APs in the system,is thatThe number of the APs is the total number of the APs,is thatNumber of unrelated APs in (a).
A13, calculating the similarity of the fingerprint relative subsequence pairs in the relative fingerprint pairs, and obtaining a similarity matrix of the relative fingerprint pairs by adopting traversal calculation;
the similarity matrix of the relative fingerprint pair represents the similarity matrix of the relative fingerprint pairIn the middle, byA matrix of formations; first calculateMiddle fingerprint relative subsequence pairDegree of similarity ofBy traversing the calculationInThe similarity of the two can be obtainedSimilarity matrix of
Wherein,
a14, searching and searching the best matching relative fingerprint pair in the similarity matrix by adopting a dynamic programming algorithm;
obtaining a similarity matrixThereafter, the search is performed using a dynamic programming algorithmIn thatSearching for the best matching path C; according to the best matching path C of two relative fingerprint pairs, the similarity (or fingerprint distance) of the fingerprint pair obtained by accumulation is as follows:
the method for constructing the relative fingerprint distance can reduce the influence of equipment heterogeneity on the positioning result.
The specific method for training the short-distance position fingerprint association model in the step A2 comprises the following steps:
a21, acquiring crowd-sourced data around the known landmark points;
arranging some known landmark points on an indoor area to be positioned and acquiring coordinates and rss information of corresponding positions, and simultaneously recording a walking path by using a PDR (product data record) by using user handheld equipment for acquiring rss data around the landmark points; in the process, in order to avoid the problem of device heterogeneity existing in the training process, the mobile phone device for collecting data at the known landmark point is consistent with the mobile phone device used by the user for collecting crowdsourcing data near the known landmark point, and the data are crowdsourcing data collected specially for training the short-distance estimation model instead of crowdsourcing data in the real library building process.
A22, extracting fingerprint data of the landmark point radiation area according to the fingerprint similarity;
and fingerprint data of the landmark point radiation area is extracted according to the fingerprint similarity, and the fingerprint similarity can be calculated according to the rss Euclidean distance between the fingerprints because the influence of equipment heterogeneity is avoided during the acquisition of training data.
A23, calculating the fingerprint distance of the fingerprint data of the landmark point radiation area;
dividing the extracted fingerprint data around the landmark points according to the same crowdsourcing path to form training data; the training data comprises pairwise matched data acquisition points, the matched data acquisition points are located on the same crowdsourcing path, and the relative physical distance and the fingerprint data are known. Calculating the relative fingerprint distance between each matched data acquisition point by using a fingerprint distance model to form a relative fingerprint distance matrix Dwifi。
A24, determining short-distance position fingerprint correlation model based on MDS
The short-distance position fingerprint correlation model is derived from fingerprint characteristics and can be used for estimating the actual physical distance. The model can deduce the physical coordinate information of one point according to the fingerprint information between two points and the physical coordinate information of the other point.
Short range location fingerprintThe correlation model is further obtained on the basis of the fingerprint distance model, and the optimal weight value w is more than or equal to 0 through trainingi1 ≦ (i ≦ 1,2,3,4) to obtain the model; from the relative fingerprint distance matrix D by MDS (Multidimensional scaling analysis, MDS) algorithmwifiGenerating relative coordinates among the data acquisition points, obtaining a relative distance L between the data acquisition points according to the relative coordinates, obtaining a physical relative distance d between the data acquisition points by a PDR (product data Rate), and assuming that d and L are approximately in a proportional relation of d ═ kL, wherein the formula contains w is more than or equal to 0 and less than or equal to wiThe method comprises the following steps of obtaining an optimal unknown parameter by a least square method LS (least square) to obtain a short-distance position fingerprint correlation model, wherein the same crowdsourcing path position point data is used as training data of the least square method, and finally, the accuracy of the model is verified by adopting the accurate data of known landmark points to obtain the error of the model.
S12, constructing an indoor map;
and drawing a corresponding plane map of the area to be positioned according to a certain proportion for the constraint condition of particle filtering, and further improving the matching precision of the position and the fingerprint in the library building process.
S13, marking explicit landmark points and collecting fingerprint data of corresponding positions;
explicit landmark nodes are generally located in areas where pedestrians easily pass, such as specific physical location points, corridor intersection positions, stairway positions, and area entrances. Before crowdsourcing and establishing a library, physical coordinates and fingerprint data of explicit landmark points are collected in advance and stored in a position fingerprint database.
S14, judging whether the crowdsourcing path data is enabled;
because PDR has large accumulated errors, the reliability of the collected crowdsourcing data is low if it is not corrected for a long time. In order to obtain relatively accurate crowdsourcing data, when only explicit landmark point data exists in the database, the crowdsourcing path is set to start to be effective when a user walks to the vicinity of the explicit landmark point, and the physical coordinates of the starting position point of the crowdsourcing path when the crowdsourcing path starts to be effective are calculated by using the short-distance position fingerprint correlation model. And judging whether the user has walked around the explicit landmark point according to the WiFi fingerprint similarity (shown in formula 2).
S15, associating fingerprints and position points based on PDR, particle filtering and map constraint multiple conditions;
and after the crowdsourcing path starts to be effective, combining multiple technologies of PDR, particle filtering and map constraint to construct a position fingerprint database. Deducing the step number, step length and course of the pedestrian according to data of built-in sensors (a gyroscope, a magnetometer and an accelerometer sensor) of the smart phone to obtain a walking path of the user;
the physical coordinates of the initial position point when the crowdsourcing path starts to be effective are known, so that the physical coordinates of the data acquisition point on the crowdsourcing path can be obtained, and the matching between the position and the fingerprint is obtained; meanwhile, a more accurate crowdsourcing path is obtained by adopting a particle filtering and map constraint dual constraint condition.
S16, setting an effective time threshold of a crowdsourcing path, and if the accumulated error of the sensor data is within a tolerable range within the effective time threshold, entering step S15, otherwise, failing the crowdsourcing path, and entering step S17;
since the sensor has an accumulated error, in order to reduce the accumulated error, a sensor accumulated error time threshold is trained in advance, generally about 5-10 minutes, and within the time threshold, the sensor data accumulated error belongs to a tolerable range. And when the time threshold is exceeded, the crowdsourcing path is invalid, and the acquired data is not stored in the position fingerprint database.
S17, sequentially building a library based on the fission mode;
referring to fig. 3, the fission mode refers to a series of effective path location points from a known location point, which can be used as effective starting location points of a crowdsourcing path passing through the points. When the fingerprint data of the non-explicit location points is established in the location fingerprint database, the valid starting location of the crowd-sourced path data of other users can be the periphery of any known location point (including the explicit location point and the valid crowd-sourced path segment). After the database is built in a fission mode, each fingerprint point on the position fingerprint database corresponds to a rough physical coordinate.
Step S2, correcting PDR accumulated error of the non-explicit landmark region based on MDS, which includes the steps of:
s21, calculating an implicit landmark point area range based on the fingerprint similarity;
the implicit landmark point is calculated by the crowdsourcing path, and the intersection position of a plurality of crowdsourcing paths can be used as an implicit landmark point. Therefore, after more crowdsourcing paths are collected on the area to be positioned, more implicit landmark points can be calculated. Since the similarity of fingerprints around the same position point is high, a threshold value sigma of the similarity of fingerprints can be setsimAnd a small area where the position point with the fingerprint similarity exceeding the threshold is located is taken as an implicit landmark point area, such as the area V in fig. 3. In order to reduce the influence of the heterogeneity, the fingerprint similarity can be calculated after the relative fingerprint of the fingerprint is calculated.
S22, counting common paths among the implicit landmark point areas;
the quantity of the crowdsourcing paths passing through each landmark point (including an implicit landmark point and an explicit landmark point) is not necessarily the same, and the number of the paths passing through two landmark point areas simultaneously is obtained by numbering the continuous paths.
S23, searching a relatively effective crowdsourcing path;
the accumulated errors of the crowdsourcing paths are different, and one path with the smallest accumulated error needs to be selected from the common paths among the landmark point areas.
The magnetometer sensors are relatively stable for a long time and are easily influenced by the magnetic field of the mobile phone in a short time, and the gyroscope sensors have large accumulated errors for a long time and are accurate in a short time, so that a path with the minimum fluctuation of magnetometer data can be selected as an effective path between two landmark point areas in a common path between the two implicit landmark point areas.
S24, redrawing a new path between the implicit landmark point areas;
and re-drawing a new path between the implicit landmark areas according to the data of the acceleration sensor and the magnetometer sensor of the effective path between the implicit landmark areas.
S25, calculating the relative coordinates of the implicit landmark point area;
the physical coordinates of the explicit landmark points are accurately known, and the coordinates of each implicit landmark point area relative to the explicit landmark points are calculated sequentially from the explicit landmark nodes. The process is as follows: if a crowdsourcing path passes through an explicit landmark and an implicit landmark area at the same time, the coordinates of the implicit landmark area can be calculated, and further the coordinates of other implicit landmark areas connected with the crowdsourcing path of the implicit landmark area can be calculated.
Referring to fig. 4, the explicit landmark point and the implicit landmark point A, E are connected by a path, coordinates of A, E two points can be obtained according to the PDR algorithm and the explicit landmark point coordinates, while the implicit landmark point B is connected with the a path, coordinates of the B point can be obtained according to coordinates of the a point, and so on, coordinates of other implicit landmark points connected by a path can be obtained.
S26, accurately calculating the absolute coordinates of the implicit landmark point area based on MDS;
constructing a relative distance matrix D according to the relative coordinates of each implicit landmark point area and each explicit landmark point, assuming that the number of the explicit landmark points and the implicit landmark points connected by the crowdsourcing path is m-1, and calculating the central position point of the m-1 landmark pointsCalculating relative distance d between position points (including explicit landmark points, implicit landmark points and central position points) according to coordinatesijWhere i 1,2, 3., m, j 1,2, 3., m is the relative distance matrix:
and setting the central position point as an origin, calculating the relative coordinates of the explicit and implicit landmark points and the origin according to the MDS, and updating the original relative coordinates of the implicit landmark points. And further accurately solving the actual physical coordinates of each implicit landmark point according to the actual physical coordinates of the explicit landmark points. Because the original relative coordinates of the implicit landmark points are calculated according to a single path, the error is possibly large, and the implicit landmark points can be corrected mutually according to an MDS algorithm, so that the coordinate error of the implicit landmark points is reduced.
And S27, correcting the PDR accumulated error of the non-explicit landmark region.
And each implicit landmark point is taken as a new starting point of a crowdsourcing path passing around the point, and a new crowdsourcing path is drawn according to the information of the subsequent part of the original path passing through the point, so that the accumulated error of the PDR is further corrected, and the matching precision of the position and the fingerprint is improved.
The method comprises the steps of constructing a position fingerprint database based on a fission mode and a set path effective time threshold, correcting a PDR accumulated error by adopting an MDS and combining an implicit landmark point, and constructing a short-distance position fingerprint correlation model based on weighted multidimensional WiFi numerical characteristics; compared with the prior art, the method can quickly establish the position fingerprint database, reduce the accumulated error of the sensor, improve the matching precision of the position and the fingerprint, and effectively solve the problems that the user is frequently disturbed and the matching precision of the position and the fingerprint is low in the prior art.
While the embodiments of the invention have been described in detail in connection with the accompanying drawings, it is not intended to limit the scope of the invention. Various modifications and changes may be made by those skilled in the art without inventive step within the scope of the appended claims.
Claims (10)
1. A position fingerprint database rapid construction method based on crowdsourcing data is characterized by comprising the following steps:
s1, creating a library based on the fission of the PDR, the particle filter and the map constraint, wherein the steps comprise
S11, training a short-distance position fingerprint correlation model;
s12, constructing an indoor map;
s13, marking explicit landmark points and collecting fingerprint data of corresponding positions;
s14, judging whether the crowdsourcing path data is enabled;
s15, associating fingerprints and position points based on PDR, particle filtering and map constraint multiple conditions;
s16, setting an effective time threshold of a crowdsourcing path, and if the accumulated error of the sensor data is within a tolerable range within the effective time threshold, entering step S15, otherwise, failing the crowdsourcing path, and entering step S17;
s17, sequentially building a library based on the fission mode;
s2, correcting the PDR accumulated error of the non-explicit landmark region based on the MDS, wherein the steps comprise
S21, calculating an implicit landmark point area range based on the fingerprint similarity;
s22, counting common paths among the implicit landmark point areas;
s23, searching a relatively effective crowdsourcing path;
s24, redrawing a new path between the implicit landmark point areas;
s25, calculating the relative coordinates of the implicit landmark point area;
s26, accurately calculating the absolute coordinates of the implicit landmark point area based on MDS;
and S27, correcting the PDR accumulated error of the non-explicit landmark region.
2. The method for rapidly building a position fingerprint database based on crowdsourced data as claimed in claim 1, wherein the method for training the short-distance position fingerprint correlation model in step S11 comprises:
a1, modeling based on multi-dimensional WiFi numerical characteristic fingerprint distance;
and A2, training a short-distance position fingerprint correlation model.
3. The method for rapidly building a position fingerprint database based on crowdsourced data as claimed in claim 2, wherein the step a1 is based on multidimensional WiFi numerical characteristic fingerprint distance modeling method:
a11, constructing a relative fingerprint consisting of relative subsequences;
a12, calculating the similarity of the relative subsequence pairs;
a13, calculating the similarity of the fingerprint relative subsequence pairs in the relative fingerprint pairs, and obtaining a similarity matrix of the relative fingerprint pairs by adopting traversal calculation;
and A14, searching for the best matching relative fingerprint pair in the similarity matrix by adopting a dynamic programming algorithm.
4. The method for rapidly building a position fingerprint database based on crowdsourced data as claimed in claim 2, wherein the step a2 is a method for training a short-distance position fingerprint correlation model, comprising the steps of:
a21, acquiring crowd-sourced data around the known landmark points;
a22, extracting fingerprint data of the landmark point radiation area according to the fingerprint similarity;
a23, calculating the fingerprint distance of the fingerprint data of the landmark point radiation area;
and A24, determining a short-distance position fingerprint correlation model based on the MDS.
5. The method for quickly building a position fingerprint database based on crowdsourcing data according to claim 1, wherein the step S14 is to determine whether crowdsourcing path data is enabled by:
when only explicit landmark point data exists in the database, setting that when a user walks to the vicinity of the explicit landmark point, the crowdsourcing path starts to be effective, and calculating the physical coordinates of the initial position point when the crowdsourcing path starts to be effective by using a short-distance position fingerprint correlation model;
and judging whether the user has walked around the explicit landmark point according to the similarity of the WiFi fingerprint.
6. The method for rapidly building a location fingerprint database based on crowdsourced data as claimed in claim 1, wherein the step S15 is based on PDR, particle filtering and map constraint to associate fingerprints and location points under multiple conditions:
combining multiple technologies of PDR, particle filtering and map constraint to construct a position fingerprint database;
deducing the pedestrian step number, step length and course according to the built-in sensor data of the smart phone to obtain a user walking path, obtain the physical coordinates of data acquisition points on the crowdsourcing path, and obtain the matching of the position and the fingerprint;
and obtaining an accurate crowdsourcing path by adopting a particle filtering and map constraint dual constraint condition.
7. The method for rapidly building the position fingerprint database based on the crowdsourcing data according to claim 1, wherein the step S17 is implemented by sequentially building the database based on the fission mode segmentation:
when fingerprint data of non-explicit position points are established in the position fingerprint database, effective initial positions of crowdsourcing path data of other users are around any known position point, and the database is established based on a fission mode;
and each fingerprint point on the position fingerprint database after the fission mode library is built corresponds to a rough physical coordinate.
8. The method for rapidly building a position fingerprint database based on crowdsourced data as claimed in claim 1, wherein the step S21 includes setting a threshold σ of fingerprint similaritysimSimilarity of fingerprint exceeds sigmasimThe small area where the position point of (2) is located is taken as an implicit landmark point area;
step S22 includes numbering the continuous paths to obtain the number of paths passing through two landmark regions at the same time;
the step S23 includes sequentially selecting, from the common paths between the two implicit landmark regions, a path with the minimum fluctuation of magnetometer data as an effective path between the two landmark regions;
step S24 includes redrawing a new path between the implicit landmark regions according to the acceleration sensor and magnetometer sensor data of the effective path between the implicit landmark regions;
the step S25 includes sequentially calculating coordinates of each implicit landmark region relative to the explicit landmark points from the explicit landmark nodes.
9. The method for rapidly building a position fingerprint database based on crowdsourced data as claimed in claim 1, wherein the step S26 is based on the method of accurately calculating absolute coordinates of the implicit landmark region by MDS as follows:
constructing a relative distance matrix D according to the relative coordinates of each implicit landmark point area and each explicit landmark point,
wherein d isijRelative distances between explicit landmark points, implicit landmark points and center location points,
i＝1,2,3，…，m；j＝1,2,3…，m；
setting the central position point as an origin, calculating relative coordinates of the explicit and implicit landmark points and the origin according to the MDS, and updating the original relative coordinates of the implicit landmark points;
and solving the actual physical coordinates of each implicit landmark point according to the actual physical coordinates of the explicit landmark points.
10. The method for rapidly building a position fingerprint database based on crowdsourced data as claimed in claim 1, wherein the step S27 is to correct PDR accumulated errors of non-explicit landmark regions by:
and taking each implicit landmark point as a new starting point of a crowdsourcing path passing around the point, drawing a new crowdsourcing path according to the information of the subsequent part of original path passing through the point, correcting the accumulated error of the PDR, and improving the matching precision of the position and the fingerprint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910149853.4A CN109739830B (en) | 2019-02-28 | 2019-02-28 | Position fingerprint database rapid construction method based on crowdsourcing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910149853.4A CN109739830B (en) | 2019-02-28 | 2019-02-28 | Position fingerprint database rapid construction method based on crowdsourcing data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109739830A true CN109739830A (en) | 2019-05-10 |
| CN109739830B CN109739830B (en) | 2021-01-26 |
Family
ID=66368775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910149853.4A Active CN109739830B (en) | 2019-02-28 | 2019-02-28 | Position fingerprint database rapid construction method based on crowdsourcing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109739830B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110351666A (en) * | 2019-07-31 | 2019-10-18 | 燕山大学 | A kind of ambiguous method of elimination wireless fingerprint map |
| CN111735458A (en) * | 2020-08-04 | 2020-10-02 | 西南石油大学 | Navigation and positioning method of petrochemical inspection robot based on GPS, 5G and vision |
| CN113899368A (en) * | 2021-09-15 | 2022-01-07 | 武汉大学 | Pedestrian course correction method based on indoor fingerprint point topological relation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106714110A (en) * | 2017-01-19 | 2017-05-24 | 深圳大学 | Auto building method and system of Wi-Fi position fingerprint map |
| CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
| CN105263113B (en) * | 2015-10-26 | 2018-08-21 | 深圳大学 | A kind of WiFi location fingerprints map constructing method and its system based on crowdsourcing |
| US20180348334A1 (en) * | 2017-06-02 | 2018-12-06 | Apple Inc. | Compressing radio maps |
| CN109005503A (en) * | 2018-08-13 | 2018-12-14 | 电子科技大学 | A kind of fusion and positioning method based on WiFi and PDR |
-
2019
- 2019-02-28 CN CN201910149853.4A patent/CN109739830B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105263113B (en) * | 2015-10-26 | 2018-08-21 | 深圳大学 | A kind of WiFi location fingerprints map constructing method and its system based on crowdsourcing |
| CN106714110A (en) * | 2017-01-19 | 2017-05-24 | 深圳大学 | Auto building method and system of Wi-Fi position fingerprint map |
| US20180348334A1 (en) * | 2017-06-02 | 2018-12-06 | Apple Inc. | Compressing radio maps |
| CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
| CN109005503A (en) * | 2018-08-13 | 2018-12-14 | 电子科技大学 | A kind of fusion and positioning method based on WiFi and PDR |
Non-Patent Citations (4)
| Title |
|---|
| H. LEPPAKOSKI, J. COLLIN, J. TAKALA: "Pedestrian Navigation Based on Inertial Sensors，Indoor Map, and WLAN Signals", 《JOURNAL OF SIGNAL PROCESSING SYSTEMS》 * |
| 周瑞: "基于粒子滤波和地图匹配的融合室内定位", 《电子科技大学学报》 * |
| 宋红丽: "基于航位推算的室内定位系统研究与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 梁溪: "基于智能手机的室内定位关键技术研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110351666A (en) * | 2019-07-31 | 2019-10-18 | 燕山大学 | A kind of ambiguous method of elimination wireless fingerprint map |
| CN110351666B (en) * | 2019-07-31 | 2020-08-25 | 燕山大学 | Method for eliminating ambiguity of wireless fingerprint map |
| CN111735458A (en) * | 2020-08-04 | 2020-10-02 | 西南石油大学 | Navigation and positioning method of petrochemical inspection robot based on GPS, 5G and vision |
| CN113899368A (en) * | 2021-09-15 | 2022-01-07 | 武汉大学 | Pedestrian course correction method based on indoor fingerprint point topological relation |
| CN113899368B (en) * | 2021-09-15 | 2023-06-23 | 武汉大学 | Pedestrian course correction method based on indoor fingerprint point topological relation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109739830B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109298389B (en) | Indoor pedestrian combination pose estimation method based on multi-particle swarm optimization | |
| CN110856112B (en) | Crowd-sourcing perception multi-source information fusion indoor positioning method and system | |
| CN111199564B (en) | Indoor positioning method and device of intelligent mobile terminal and electronic equipment | |
| CN105813194B (en) | Indoor orientation method based on fingerprint database secondary correction | |
| CN109739830B (en) | Position fingerprint database rapid construction method based on crowdsourcing data | |
| CN107688665B (en) | Automatic indoor map construction method and device and storage medium | |
| CN108534779B (en) | Indoor positioning map construction method based on track correction and fingerprint improvement | |
| KR101751731B1 (en) | Location tracking system and method | |
| CN109413578B (en) | Indoor positioning method based on fusion of WIFI and PDR | |
| US20160371394A1 (en) | Indoor localization using crowdsourced data | |
| WO2020224305A1 (en) | Method and apparatus for device positioning, and device | |
| Du et al. | CRCLoc: A crowdsourcing-based radio map construction method for WiFi fingerprinting localization | |
| CN107621263B (en) | Geomagnetic positioning method based on road magnetic field characteristics | |
| CN109668563B (en) | Indoor-based track processing method and device | |
| CN108632761A (en) | A kind of indoor orientation method based on particle filter algorithm | |
| CN104197934B (en) | A kind of localization method based on earth magnetism, apparatus and system | |
| CN110360999A (en) | Indoor orientation method, indoor locating system and computer-readable medium | |
| CN104320759B (en) | Based on fixedly target indoor locating system fingerprint base construction method | |
| Wu et al. | Efficient indoor localization based on geomagnetism | |
| CN111970633A (en) | Indoor positioning method based on WiFi, Bluetooth and pedestrian dead reckoning fusion | |
| CN110579207A (en) | Indoor positioning system and method based on combination of geomagnetic signals and computer vision | |
| Kwak et al. | Magnetic field based indoor localization system: A crowdsourcing approach | |
| Wang et al. | An adaptive indoor positioning method using multisource information fusion combing Wi-Fi/MM/PDR | |
| Tan et al. | Implicit multimodal crowdsourcing for joint RF and geomagnetic fingerprinting | |
| Ding et al. | OGI-SLAM2: A hybrid map SLAM framework grounded in inertial-based SLAM |
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 |