CN112714493A - Object position positioning method and positioning system - Google Patents

Object position positioning method and positioning system Download PDF

Info

Publication number
CN112714493A
CN112714493A CN202011593423.0A CN202011593423A CN112714493A CN 112714493 A CN112714493 A CN 112714493A CN 202011593423 A CN202011593423 A CN 202011593423A CN 112714493 A CN112714493 A CN 112714493A
Authority
CN
China
Prior art keywords
reference points
signal strength
calculating
module
weight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011593423.0A
Other languages
Chinese (zh)
Other versions
CN112714493B (en
Inventor
何泾沙
许甜
朱娜斐
吴霜
邓万航
他永君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing University of Technology
Original Assignee
Beijing University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing University of Technology filed Critical Beijing University of Technology
Priority to CN202011593423.0A priority Critical patent/CN112714493B/en
Publication of CN112714493A publication Critical patent/CN112714493A/en
Application granted granted Critical
Publication of CN112714493B publication Critical patent/CN112714493B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0252—Radio frequency fingerprinting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Remote Sensing (AREA)
  • Probability & Statistics with Applications (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention discloses an object position positioning method and a positioning system, wherein the positioning method comprises an off-line stage and an on-line stage, and the off-line stage comprises the following steps: deploying reference points, and collecting signal strength values of all APs at each reference point; establishing a position fingerprint database according to the signal strength values of all APs acquired at all the reference points and the physical position coordinates of the corresponding reference points; the online phase comprises: measuring a signal strength value of each AP at an object to be located; matching the measured signal intensity value of the object to be positioned with a position fingerprint database; and obtaining the physical position coordinates of the object to be positioned according to the matching result. By the technical scheme of the invention, the error of the final positioning result caused by the instability of the AP signal is effectively reduced, and the positioning precision of the indoor object position is improved.

Description

Object position positioning method and positioning system
Technical Field
The invention relates to the technical field of indoor positioning, in particular to an object position positioning method and an object position positioning system.
Background
The position fingerprint method is a main method for researching indoor positioning technology, and mainly determines the physical position of an object to be positioned by calculating the similarity of position fingerprints between the position of the object to be positioned and a reference point. A "location fingerprint" is a fingerprint that associates a location in the physical environment with a particular location, a location corresponding to a unique fingerprint. The location fingerprint may be of various types, and any feature that is helpful in distinguishing locations may be used as a location fingerprint, such as the multipath structure of the communication signal at a location, whether an access point or base station is detected at a location, the received signal strength of the signal from a base station detected at a location, the round trip time or delay of the signal during communication at a location, as a location fingerprint, or a combination thereof. The present invention uses the physical location coordinates of a location and its signal strength value under each Wireless Access Point (AP) as the location fingerprint of the location, and the following description describes the AP in the WiFi wlan as the infrastructure for spatial arrangement.
The basic principle of location by the position fingerprint method is that fingerprint information of all sampling points is collected in an off-line stage and is recorded into a position fingerprint database; and in the online stage, the acquired information of the point to be located is matched with the position fingerprint in the fingerprint database to obtain the coordinate of the point to be located.
The matching algorithm in the online stage is one of the main factors influencing the indoor positioning accuracy. At present, the matching algorithm of the online stage includes a nearest neighbor algorithm, a K neighbor algorithm, and a weighted K neighbor algorithm. The positioning principle of the nearest neighbor method is as follows: the method comprises the steps of firstly collecting signal intensity values of all APs at a point to be positioned, then calculating Euclidean distances between the point to be positioned and all reference points by utilizing the AP signal intensity, and selecting a position coordinate of the reference point with the minimum Euclidean distance as a final physical position coordinate of the point to be positioned. The K-nearest neighbor algorithm is that after the nearest neighbor algorithm calculates the Euclidean distances between the to-be-positioned point and each reference point, all the Euclidean distances are sorted from small to large, K (K >1) reference points with the minimum Euclidean distances are selected, and the physical position coordinates of the K reference points are averaged in each dimension to serve as the final physical position coordinate of the to-be-positioned point. The weighted K-nearest neighbor algorithm is based on the K-nearest neighbor algorithm, different weight values of K nearest neighbor reference points selected finally are calculated by using Euclidean distances in consideration of different influences of reference points with different Euclidean distances between the reference points and a point to be positioned on a positioning result, then the weight values of the Euclidean distances are added into the calculation of positioning coordinates, and finally the physical position coordinates of the point to be positioned are obtained.
The influence of Euclidean distances between different reference points and a point to be positioned on positioning precision is not considered in the nearest neighbor algorithm and the K neighbor algorithm, while the influence of the Euclidean distances on the positioning precision is considered in the weighted K neighbor algorithm, the final positioning result is weighted by adopting Euclidean distance normalization processing, and the great influence of the fluctuation of AP signals on the positioning result is not considered. In an actual indoor scene, the environment is very complex, the shielding of walls and obstacles can influence the mobile terminal on the reception of signals, the signals collected by the terminal fluctuate due to the large flow of indoor personnel, and the stability of each AP signal is different for different positions.
Disclosure of Invention
Aiming at the problems, the invention provides an object position positioning method and an object position positioning system, which are characterized in that a weighted K nearest neighbor algorithm improved based on discrete coefficients is applied to carry out position matching in an online stage, the discrete coefficients are used for calculating the weight of each AP signal intensity, the weight of an AP signal is added into a position fingerprint matching algorithm, the error caused by the instability of the AP signal to the final positioning result is effectively reduced, and the positioning precision of the indoor object position is improved.
In order to achieve the above object, the present invention provides an object position positioning method, which includes an off-line stage and an on-line stage, wherein the off-line stage includes: deploying reference points, and collecting signal strength values of all APs at each reference point; establishing a position fingerprint database according to the signal strength values of all APs acquired at all the reference points and the physical position coordinates of the corresponding reference points; the online phase comprises: measuring a signal strength value of each AP at an object to be located; matching the measured signal intensity value of the object to be positioned with the position fingerprint database; and obtaining the physical position coordinates of the object to be positioned according to the matching result.
In the foregoing technical solution, preferably, the process of measuring the signal strength value of each AP at the object to be located specifically includes: and measuring the signal strength value of each AP for preset times at the position of the object to be positioned, and constructing a matrix according to the measurement results of the predicted times for all the APs.
In the foregoing technical solution, preferably, the process of matching the measured signal strength value of the object to be located with the location fingerprint database specifically includes: calculating a discrete coefficient of an AP according to a standard deviation and an average value of signal strength value measurement results for a certain AP preset times; calculating the weight of the corresponding AP signal strength value according to the discrete coefficient of each AP; calculating to obtain Euclidean distance of a corresponding AP after weighting by a discrete coefficient according to the weight of a certain AP signal intensity value, the average value of signal intensity value measurement results of preset times of the current AP and the signal intensity value of the corresponding AP measured by a certain reference point; calculating distance weight factors of corresponding reference points according to the Euclidean distances from a preset number of reference points with the Euclidean distances from small to large to the Euclidean distances of the object to be positioned; and calculating the physical position coordinates of the object to be positioned according to the distance weight factors of the reference points with the preset number and the object to be positioned.
In the foregoing technical solution, preferably, the specific process of calculating the weight corresponding to the AP signal strength value according to the discrete coefficient of each AP includes: according to the discrete coefficient V of ith AP in n APsiCalculating the reciprocal of the discrete coefficient by the discrete coefficient V according to equation (1)iIs a reciprocal number meterCalculating to obtain the weight W of the ith AP signal strength valuei：
Figure BDA0002869290700000031
In the foregoing technical solution, preferably, the euclidean distance D after weighting the discrete coefficients of the corresponding AP is obtained by calculating according to the weight of a certain AP signal strength value, the average value of the signal strength value measurement results of the preset number of times of the current AP, and the signal strength value of the corresponding AP measured by a certain reference pointjThe concrete formula of (1) is as follows:
Figure BDA0002869290700000032
wherein, WiIs the weight, avr, of the ith AP signal strength valueiIs the average of the m signal strength values, rssi, of the ith AP acquired at the object to be locatedjiFor the signal strength value of the ith AP measured at the jth reference point in the location fingerprint database, DjAnd the weighted Euclidean distance between the object to be positioned and the jth reference point.
In the above technical solution, preferably, the specific process of calculating the distance weight factor of the corresponding reference point according to the euclidean distances from the reference points of the preset number of reference points with the euclidean distances from small to large to the euclidean distances of the object to be positioned includes: sorting the weighted Euclidean distances between the object to be positioned and each reference point from small to large; selecting the first k reference points with the weighted Euclidean distance from small to large, and calculating the distance weight factor of each reference point in the k reference points according to the formula (2):
Figure BDA0002869290700000033
wherein, ω isiDistance weighting factor for the ith reference point, DiDiscrete coefficient-based method between ith reference point of k nearest neighbor reference points and object to be positionedWeighted euclidean distance.
In the above technical solution, preferably, the specific formula for obtaining the physical position coordinate of the object to be positioned by calculating according to the distance weighting factor between the reference points in the preset number and the object to be positioned is as follows:
Figure BDA0002869290700000041
wherein (x)i，yi) The physical position coordinates of the ith reference point in the k nearest neighbor reference points in the position fingerprint database.
In the above technical solution, preferably, the signal strength value of each AP measured at the reference point is subjected to data preprocessing and then input to the location fingerprint database, and the signal strength value of each AP measured at the object to be located is subjected to data preprocessing and then matched with the location fingerprint database.
The invention also provides an object position positioning system, which applies the object position positioning method provided by any one of the above technical schemes, and comprises the following steps: an offline system and an online system; the off-line system comprises an off-line signal measurement module and a database construction module, wherein the off-line signal measurement module is used for collecting signal intensity values of all APs at deployed reference points, and the database construction module is used for establishing a position fingerprint database according to the collected signal intensity values and physical position coordinates of the reference points; the online system comprises an online signal measuring module, a data matching module and a coordinate determining module; the online signal measurement module is used for measuring the signal strength value of each AP at an object to be positioned; the data matching module is used for matching the measured signal intensity value of the object to be positioned with the position fingerprint database; and the coordinate determination module determines the physical position coordinate of the object to be positioned according to the matching result of the data matching module.
In the above technical solution, preferably, the data matching module includes a discrete coefficient calculation sub-module, a weight calculation sub-module, a weighted euclidean distance calculation sub-module, a distance weight factor calculation sub-module, and a physical coordinate calculation sub-module; the discrete coefficient calculation submodule is used for calculating the discrete coefficient of the AP according to the standard deviation and the average value of the signal intensity value measurement results for a certain AP preset times; the weight calculation submodule is used for calculating the weight of the corresponding AP signal strength value according to the discrete coefficient of each AP; the weighted Euclidean distance calculation submodule is used for calculating to obtain the Euclidean distance of the corresponding AP after the corresponding AP is weighted by the discrete coefficient according to the weight of a certain AP signal intensity value, the average value of the signal intensity value measurement results of the preset times of the current AP and the signal intensity value of the corresponding AP measured by a certain reference point; the distance weight factor calculation submodule is used for calculating distance weight factors of corresponding reference points according to the Euclidean distances between a preset number of reference points with the Euclidean distances from small to large and the object to be positioned; and the physical coordinate calculation submodule is used for calculating the physical position coordinate of the object to be positioned according to the distance weight factors of the reference points with the preset number and the object to be positioned.
Compared with the prior art, the invention has the beneficial effects that: the position matching in the online stage is carried out by applying a weighted K nearest neighbor algorithm improved based on discrete coefficients, the weight of each AP signal intensity is calculated by using the discrete coefficients, and the weight of the AP signal is added into a position fingerprint matching algorithm, so that the error of the final positioning result caused by the instability of the AP signal is effectively reduced, and the positioning precision of the indoor object position is improved.
Drawings
FIG. 1 is a schematic overall flow chart of an object position locating method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a position distribution of a reference point and an object to be positioned in an experimental area according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a VWKNN algorithm according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of an object position locating system according to one embodiment of the present disclosure;
fig. 5 is a schematic block diagram of a data matching module according to an embodiment of the present invention.
In the drawings, the correspondence between each component and the reference numeral is:
1. an off-line system; 11. an off-line signal measurement module; 12. a database construction module; 2. an online system; 21. an online signal measurement module; 22. a data matching module; 23. a coordinate determination module; 31. a discrete coefficient calculation submodule; 32. a weight calculation submodule; 33. a weighted Euclidean distance calculation submodule; 34. a distance weight factor calculation submodule; 35. and a physical coordinate calculation submodule.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
as shown in fig. 1, the object position locating method provided by the present invention includes an offline stage and an online stage, wherein the offline stage includes: deploying reference points, and collecting signal strength values of all APs at each reference point; establishing a position fingerprint database according to the signal strength values of all APs acquired at all the reference points and the physical position coordinates of the corresponding reference points; the online phase comprises: measuring a signal strength value of each AP at an object to be located; matching the measured signal intensity value of the object to be positioned with a position fingerprint database; and obtaining the physical position coordinates of the object to be positioned according to the matching result.
In the embodiment, on the basis of existing Wi-Fi facilities in a room, reasonable reference points are set in a designated area, position fingerprint information of each reference point is respectively collected at each reference point position, a position fingerprint database is established, then position fingerprint information of the position of an object to be positioned is collected, and a new position fingerprint matching algorithm based on discrete coefficient improvement is adopted to match the position fingerprint information of the object to be positioned with data in the position fingerprint database, so that physical position coordinate information of the object to be positioned is obtained. The method improves the indoor positioning precision and has wide application prospect. The location fingerprint matching algorithm based on discrete coefficient improvement is hereinafter referred to as a VWKNN algorithm, and the VWKNN algorithm is calculated by taking the weight of each AP signal into consideration on the basis of a weighted K-nearest neighbor algorithm.
As shown in fig. 2, first, reference points are deployed in an offline stage, and AP signal strength values of each reference point are collected to establish a location fingerprint database. Specifically, an indoor area may be selected and the x axis and the y axis may be customized, and the reference points may be deployed in an equally spaced manner, preferably, the reference point deployment is performed at an interval of 1m in this embodiment.
Further, preferably, the process of measuring the signal strength value of each AP at the object to be located specifically includes: and measuring the signal strength value of each AP for preset times at the position of the object to be positioned, and constructing a matrix according to the measurement results of the predicted times for all the APs. For example, assuming that there are n AP signal sources, m measurements are performed on each AP at a point to be located, resulting in a matrix of m rows and n columns:
Figure BDA0002869290700000061
as shown in fig. 3, in the foregoing embodiment, preferably, the process of matching the measured signal strength value of the object to be located with the location fingerprint database specifically includes: calculating a discrete coefficient of an AP according to a standard deviation and an average value of signal strength value measurement results for a certain AP preset times; calculating the weight of the corresponding AP signal strength value according to the discrete coefficient of each AP; calculating to obtain Euclidean distance of a corresponding AP after weighting by a discrete coefficient according to the weight of a certain AP signal intensity value, the average value of signal intensity value measurement results of preset times of the current AP and the signal intensity value of the corresponding AP measured by a certain reference point; calculating distance weight factors of corresponding reference points according to the Euclidean distances between a preset number of reference points and an object to be positioned from small to large; and calculating the physical position coordinate of the object to be positioned according to the distance weight factors of the reference points with the preset number and the object to be positioned.
Wherein, according to the calculation formula of discrete coefficient, the discrete coefficient V of the ith AP is calculatedi，ViThe calculation formula of (2) is as follows:
Figure BDA0002869290700000071
wherein σiIs the standard deviation, avr, of the m measurements of the ith AP signaliIs the average of m measurements of the ith AP signal.
Wherein, the standard deviation sigmaiThe calculation formula of (a) is as follows:
Figure BDA0002869290700000072
average value avriThe calculation formula of (a) is as follows:
Figure BDA0002869290700000073
in the foregoing embodiment, preferably, after calculating the dispersion coefficient of each AP, the specific process of calculating the weight of the corresponding AP signal strength value according to the dispersion coefficient of each AP includes: according to the discrete coefficient V of ith AP in n APsiCalculating the reciprocal of the discrete coefficient by the discrete coefficient V according to equation (1)iCalculating to obtain the weight W of the ith AP signal intensity valueiComprises the following steps:
Figure BDA0002869290700000074
in the above-described embodimentsPreferably, the euclidean distance D weighted by the discrete coefficient of the corresponding AP is calculated according to the weight of the signal intensity value of the certain AP, the average value of the signal intensity value measurement results of the preset number of times of the current AP, and the signal intensity value of the corresponding AP measured by the certain reference pointjThe concrete formula of (1) is as follows:
Figure BDA0002869290700000075
wherein, WiIs the weight, avr, of the ith AP signal strength valueiIs the average of the m signal strength values, rssi, of the ith AP acquired at the object to be locatedjiIs the signal intensity value of the ith AP measured at the jth reference point in the location fingerprint database, DjIs the weighted Euclidean distance between the object to be positioned and the jth reference point.
The mean value of the signal strength measured m times by each AP is different, so that the dispersion degree of the sample data of each AP can be better reflected by using the dispersion coefficient of each AP. The AP with large dispersion coefficient has large signal intensity value fluctuation and weaker stability; and the AP with small dispersion coefficient has small signal intensity value fluctuation and strong stability. When the similarity between the to-be-positioned point and the reference point is represented by using the weighted Euclidean distance improved based on the discrete coefficient, in the calculation process of the weight, the reciprocal of the discrete coefficient is used for calculation, so that the weight factor of the AP with a large discrete coefficient can be smaller, and the error caused by the instability of the AP signal to the final positioning result can be effectively reduced.
In the above embodiment, preferably, the specific process of calculating the distance weight factor of the corresponding reference point according to the euclidean distances between the reference points with the preset number of reference points and the object to be positioned from small to large in the euclidean distances includes: sorting the weighted Euclidean distances between the object to be positioned and each reference point from small to large; selecting the first k reference points with the weighted Euclidean distance from small to large, and calculating the distance weight factor of each reference point in the k reference points according to the formula (2):
Figure BDA0002869290700000081
wherein, ω isiDistance weighting factor for the ith reference point, DiAnd the Euclidean distance between the ith reference point in the k nearest neighbor reference points and the object to be positioned is weighted based on the discrete coefficient.
Specifically, when the VWKNN algorithm calculates the euclidean distance, the discrete coefficients are used for weighting, so that k reference points which are found by the matching algorithm and are nearest to the point to be positioned are more accurate. Firstly, acquiring a signal intensity value for each AP signal source m times at a point to be positioned, calculating a weighted Euclidean distance between the point to be positioned and each reference point through a discrete coefficient weighted Euclidean distance formula, sequencing the calculated weighted Euclidean distances from small to large, selecting k reference points with the minimum weighted Euclidean distance, respectively calculating a distance weight factor of each reference point in the k reference points, and finally calculating a physical position coordinate of the point to be positioned.
In the foregoing embodiment, preferably, the specific formula for obtaining the physical position coordinate of the object to be positioned by calculating according to the distance weighting factor between the reference points in the preset number and the object to be positioned is as follows:
Figure BDA0002869290700000082
wherein (x)i，yi) The physical location coordinates of the ith reference point in the k nearest neighbor reference points in the location fingerprint database.
In the object location positioning method proposed in the above embodiment, the physical location of each reference point and the signal strength value of each AP at the reference point are combined to serve as a location fingerprint of the reference point to uniquely identify the reference point, using that the different AP signal strength values at different reference points are different and unique. Therefore, the indoor position of an object can be positioned by utilizing Wi-Fi under the condition of not adding extra equipment according to local conditions. The position fingerprints of the object position and the position fingerprints of the reference points are compared to find out the position fingerprint information of the K reference points with the highest similarity to the position fingerprints of the object position to be positioned, and then the weight of the AP signals calculated through the discrete coefficients is taken into account in the calculation of the final physical position coordinates, so that the final physical position of the object is obtained.
In the above embodiment, preferably, the position fingerprint database is input after the signal strength values of the APs measured at the reference point are subjected to data preprocessing, and the signal strength values of each AP measured at the object to be positioned are subjected to data preprocessing and then are matched with the position fingerprint database.
As shown in fig. 4, the present invention further provides an object position locating system, which applies the object position locating method provided in any of the above embodiments, including: an offline system 1 and an online system 2; the offline system 1 comprises an offline signal measurement module 11 and a database construction module 12, wherein the offline signal measurement module 11 is used for collecting signal intensity values of all APs at deployed reference points, and the database construction module 12 is used for establishing a position fingerprint database according to the collected signal intensity values and physical position coordinates of the reference points; the online system 2 comprises an online signal measuring module 21, a data matching module 22 and a coordinate determining module 23; the online signal measurement module 21 is configured to measure a signal strength value of each AP at an object to be located; the data matching module 22 is used for matching the measured signal intensity value of the object to be positioned with the position fingerprint database; the coordinate determination module 23 determines the physical position coordinates of the object to be positioned according to the matching result of the data matching module 22.
As shown in fig. 5, in the above embodiment, preferably, the data matching module 22 includes a discrete coefficient calculation sub-module 31, a weight calculation sub-module 32, a weighted euclidean distance calculation sub-module 33, a distance weight factor calculation sub-module 34, and a physical coordinate calculation sub-module 35; the discrete coefficient calculation submodule 31 is configured to calculate a discrete coefficient of an AP according to a standard deviation and an average value of signal strength value measurement results for a preset number of times for the AP; the weight calculation submodule 32 is configured to calculate a weight corresponding to the AP signal strength value according to the discrete coefficient of each AP; the weighted euclidean distance calculating sub-module 33 is configured to calculate, according to a weight of a certain AP signal intensity value, an average value of signal intensity value measurement results of preset times of the current AP, and a signal intensity value of a corresponding AP measured at a certain reference point, a euclidean distance of the corresponding AP weighted by a dispersion coefficient; the distance weight factor calculation submodule 34 is used for calculating distance weight factors of corresponding reference points according to the Euclidean distances between the reference points with the preset number from small to large and the object to be positioned; the physical coordinate calculation submodule 35 is configured to calculate a physical position coordinate of the object to be positioned according to distance weight factors between the reference points in the preset number and the object to be positioned.
According to the object position positioning system provided by the above embodiment, the modules of the object position positioning system act together to realize the steps of the object position positioning method in the above embodiment, so as to realize the indoor object position positioning function. Specifically, the position matching in the online stage is carried out by applying a weighted K nearest neighbor algorithm improved based on discrete coefficients, the weight of each AP signal intensity is calculated by using the discrete coefficients, and the weight of the AP signal is added into the position fingerprint matching algorithm, so that the error of the final positioning result caused by the instability of the AP signal is effectively reduced, and the positioning precision of the indoor object position is improved.
Firstly, acquiring a signal intensity value for each AP signal source m times at a point to be positioned, calculating a weighted Euclidean distance between the point to be positioned and each reference point through a discrete coefficient weighted Euclidean distance formula, sequencing the calculated weighted Euclidean distances from small to large, selecting k reference points with the minimum weighted Euclidean distance, respectively calculating a distance weight factor of each reference point in the k reference points, and finally calculating a physical position coordinate of the point to be positioned.
The mean value of the signal strength measured m times by each AP is different, so that the dispersion degree of the sample data of each AP can be better reflected by using the dispersion coefficient of each AP. The AP with large dispersion coefficient has large signal intensity value fluctuation and weaker stability; and the AP with small dispersion coefficient has small signal intensity value fluctuation and strong stability. When the similarity between the to-be-positioned point and the reference point is represented by using the weighted Euclidean distance improved based on the discrete coefficient, in the calculation process of the weight, the reciprocal of the discrete coefficient is used for calculation, so that the weight factor of the AP with a large discrete coefficient can be smaller, and the error caused by the instability of the AP signal to the final positioning result can be effectively reduced.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An object position locating method comprising an off-line phase and an on-line phase, the off-line phase comprising:
deploying reference points, and collecting signal strength values of all APs at each reference point;
establishing a position fingerprint database according to the signal strength values of all APs acquired at all the reference points and the physical position coordinates of the corresponding reference points;
characterized in that said online phase comprises:
measuring a signal strength value of each AP at an object to be located;
matching the measured signal intensity value of the object to be positioned with the position fingerprint database;
and obtaining the physical position coordinates of the object to be positioned according to the matching result.
2. The method according to claim 1, wherein the step of measuring the signal strength value of each AP at the object to be located comprises:
and measuring the signal strength value of each AP for preset times at the position of the object to be positioned, and constructing a matrix according to the measurement results of the predicted times for all the APs.
3. The object position locating method according to claim 2, wherein the process of matching the measured signal strength value of the object to be located with the position fingerprint database specifically comprises:
calculating a discrete coefficient of an AP according to a standard deviation and an average value of signal strength value measurement results for a certain AP preset times;
calculating the weight of the corresponding AP signal strength value according to the discrete coefficient of each AP;
calculating to obtain Euclidean distance of a corresponding AP after weighting by a discrete coefficient according to the weight of a certain AP signal intensity value, the average value of signal intensity value measurement results of preset times of the current AP and the signal intensity value of the corresponding AP measured by a certain reference point;
calculating distance weight factors of corresponding reference points according to the Euclidean distances from a preset number of reference points with the Euclidean distances from small to large to the Euclidean distances of the object to be positioned;
and calculating the physical position coordinates of the object to be positioned according to the distance weight factors of the reference points with the preset number and the object to be positioned.
4. The method according to claim 3, wherein the specific process of calculating the weight of the AP signal strength value according to the discrete coefficient of each AP comprises:
according to the discrete coefficient V of ith AP in n APsiCalculating the reciprocal of the discrete coefficient by the discrete coefficient V according to equation (1)iCalculating to obtain the weight W of the ith AP signal intensity valuei：
Figure FDA0002869290690000021
5. The method according to claim 4, wherein the weight of the AP signal strength value, the average of the signal strength value measurements of the current AP for a predetermined number of times, and a referenceThe signal intensity value of the corresponding AP measured by the point is calculated to obtain the Euclidean distance D of the corresponding AP weighted by the discrete coefficientjThe concrete formula of (1) is as follows:
Figure FDA0002869290690000022
wherein, WiIs the weight, avr, of the ith AP signal strength valueiIs the average of the m signal strength values, rssi, of the ith AP acquired at the object to be locatedjiFor the signal strength value of the ith AP measured at the jth reference point in the location fingerprint database, DjAnd the weighted Euclidean distance between the object to be positioned and the jth reference point.
6. The object position locating method according to claim 5, wherein the specific process of calculating the distance weight factor of the corresponding reference point according to the Euclidean distance from a preset number of reference points with the Euclidean distance from small to large and the Euclidean distance of the object to be located comprises:
sorting the weighted Euclidean distances between the object to be positioned and each reference point from small to large;
selecting the first k reference points with the weighted Euclidean distance from small to large, and calculating the distance weight factor of each reference point in the k reference points according to the formula (2):
Figure FDA0002869290690000023
wherein, ω isiDistance weighting factor for the ith reference point, DiAnd the Euclidean distance between the ith reference point in the k nearest neighbor reference points and the object to be positioned is weighted based on the discrete coefficient.
7. The object position locating method according to claim 6, wherein the specific formula for obtaining the physical position coordinates of the object to be located by calculating the distance weight factor between the reference points of the preset number and the object to be located is as follows:
Figure FDA0002869290690000024
wherein (x)i，yi) The physical position coordinates of the ith reference point in the k nearest neighbor reference points in the position fingerprint database.
8. The object location positioning method according to any one of claims 1 to 7, wherein the signal strength values of the respective APs measured at the reference points are input into the location fingerprint database after data preprocessing, and the signal strength values of each AP measured at the object to be positioned are matched with the location fingerprint database after data preprocessing.
9. An object position locating system to which the object position locating method according to any one of claims 1 to 8 is applied, comprising: an offline system and an online system;
the off-line system comprises an off-line signal measurement module and a database construction module, wherein the off-line signal measurement module is used for collecting signal intensity values of all APs at deployed reference points, and the database construction module is used for establishing a position fingerprint database according to the collected signal intensity values and physical position coordinates of the reference points;
the online system comprises an online signal measuring module, a data matching module and a coordinate determining module;
the online signal measurement module is used for measuring the signal strength value of each AP at an object to be positioned;
the data matching module is used for matching the measured signal intensity value of the object to be positioned with the position fingerprint database;
and the coordinate determination module determines the physical position coordinate of the object to be positioned according to the matching result of the data matching module.
10. The object position locating system according to claim 9, wherein the data matching module includes a discrete coefficient calculation sub-module, a weight calculation sub-module, a weighted euclidean distance calculation sub-module, a distance weight factor calculation sub-module, and a physical coordinate calculation sub-module;
the discrete coefficient calculation submodule is used for calculating the discrete coefficient of the AP according to the standard deviation and the average value of the signal intensity value measurement results for a certain AP preset times;
the weight calculation submodule is used for calculating the weight of the corresponding AP signal strength value according to the discrete coefficient of each AP;
the weighted Euclidean distance calculation submodule is used for calculating to obtain the Euclidean distance of the corresponding AP after the corresponding AP is weighted by the discrete coefficient according to the weight of a certain AP signal intensity value, the average value of the signal intensity value measurement results of the preset times of the current AP and the signal intensity value of the corresponding AP measured by a certain reference point;
the distance weight factor calculation submodule is used for calculating distance weight factors of corresponding reference points according to the Euclidean distances between a preset number of reference points with the Euclidean distances from small to large and the object to be positioned;
and the physical coordinate calculation submodule is used for calculating the physical position coordinate of the object to be positioned according to the distance weight factors of the reference points with the preset number and the object to be positioned.
CN202011593423.0A 2020-12-29 2020-12-29 Object position positioning method and positioning system Active CN112714493B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011593423.0A CN112714493B (en) 2020-12-29 2020-12-29 Object position positioning method and positioning system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011593423.0A CN112714493B (en) 2020-12-29 2020-12-29 Object position positioning method and positioning system

Publications (2)

Publication Number Publication Date
CN112714493A true CN112714493A (en) 2021-04-27
CN112714493B CN112714493B (en) 2023-03-24

Family

ID=75546233

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011593423.0A Active CN112714493B (en) 2020-12-29 2020-12-29 Object position positioning method and positioning system

Country Status (1)

Country Link
CN (1) CN112714493B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113645691A (en) * 2021-09-16 2021-11-12 中国联合网络通信集团有限公司 Indoor positioning method, server and terminal
CN114449652A (en) * 2022-01-28 2022-05-06 湖南大学 WIFI indoor positioning method based on reliable AP selection
CN117237594A (en) * 2023-11-13 2023-12-15 深圳市物新智能科技有限公司 Precise positioning method and system for manipulator based on visual positioning

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106851573A (en) * 2017-01-22 2017-06-13 西安交通大学 Joint weighting k nearest neighbor indoor orientation method based on log path loss model
WO2017185828A1 (en) * 2016-04-26 2017-11-02 中兴通讯股份有限公司 Fingerprint positioning method and apparatus
CN107333276A (en) * 2017-05-27 2017-11-07 南京邮电大学 WiFi location fingerprint localization methods based on weighted chi-square distance
CN110300372A (en) * 2019-07-11 2019-10-01 桂林电子科技大学 A kind of WIFI indoor orientation method based on location fingerprint

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017185828A1 (en) * 2016-04-26 2017-11-02 中兴通讯股份有限公司 Fingerprint positioning method and apparatus
CN106851573A (en) * 2017-01-22 2017-06-13 西安交通大学 Joint weighting k nearest neighbor indoor orientation method based on log path loss model
CN107333276A (en) * 2017-05-27 2017-11-07 南京邮电大学 WiFi location fingerprint localization methods based on weighted chi-square distance
CN110300372A (en) * 2019-07-11 2019-10-01 桂林电子科技大学 A kind of WIFI indoor orientation method based on location fingerprint

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张力仁，沈建京: "基于方差滤波的动态自适应室内指纹定位算法", 《计算机应用研究》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113645691A (en) * 2021-09-16 2021-11-12 中国联合网络通信集团有限公司 Indoor positioning method, server and terminal
CN114449652A (en) * 2022-01-28 2022-05-06 湖南大学 WIFI indoor positioning method based on reliable AP selection
CN117237594A (en) * 2023-11-13 2023-12-15 深圳市物新智能科技有限公司 Precise positioning method and system for manipulator based on visual positioning
CN117237594B (en) * 2023-11-13 2024-03-22 深圳市物新智能科技有限公司 Precise positioning method and system for manipulator based on visual positioning

Also Published As

Publication number Publication date
CN112714493B (en) 2023-03-24

Similar Documents

Publication Publication Date Title
CN112714493B (en) Object position positioning method and positioning system
CN107318084B (en) Fingerprint positioning method and device based on optimal similarity
CN104703143B (en) A kind of indoor orientation method based on WIFI signal intensity
CN106646338B (en) A kind of quickly accurate indoor orientation method
CN110557716B (en) Indoor positioning method based on lognormal model
CN106793082B (en) Mobile equipment positioning method in WLAN/Bluetooth heterogeneous network environment
CN104883734B (en) A kind of indoor Passive Location based on geographical fingerprint
CN109413578B (en) Indoor positioning method based on fusion of WIFI and PDR
CN109951798A (en) Merge the enhancing location fingerprint indoor orientation method of Wi-Fi and bluetooth
KR101901039B1 (en) Method and apparatus for cross device automatic calibration
CN106454747B (en) Wireless positioning method of mobile phone terminal
Zou et al. A mutual information based online access point selection strategy for WiFi indoor localization
CN109348416B (en) Fingerprint indoor positioning method based on binary k-means
CN105898692A (en) Indoor positioning method and apparatus
CN113115224B (en) Indoor positioning method and indoor positioning device
CN110611952B (en) Fingerprint matching and positioning method
CN114578283A (en) NLOS transmission base station identification and positioning method based on angle residual error
CN109302674B (en) WiFi indoor positioning method based on multiple filtering
Anuwatkun et al. A diff-based indoor positioning system using fingerprinting technique and k-means clustering algorithm
CN111465093A (en) Fingerprint positioning method and device, electronic equipment and computer storage medium
CN109041208B (en) Positioning method and positioning server based on Wi-Fi fingerprint database
Li et al. NQRELoc: AP selection via nonuniform quantization RSSI entropy for indoor localization
Subakti et al. Indoor Localization with Fingerprint Feature Extraction
CN108574927B (en) Mobile terminal positioning method and device
CN112083375A (en) Cooperative positioning algorithm based on position fingerprints and Taylor

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