CN113038596B - Indoor positioning method, device, equipment and computer readable storage medium - Google Patents
Indoor positioning method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN113038596B CN113038596B CN202110196626.4A CN202110196626A CN113038596B CN 113038596 B CN113038596 B CN 113038596B CN 202110196626 A CN202110196626 A CN 202110196626A CN 113038596 B CN113038596 B CN 113038596B
- Authority
- CN
- China
- Prior art keywords
- positioning
- reference points
- candidate reference
- reference point
- terminal
- 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.)
- Active
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses an indoor positioning method, an indoor positioning device, indoor positioning equipment and a computer readable storage medium, wherein the method comprises the following steps: collecting a first RSS vector measured at a plurality of reference points of known locations in an indoor environment; acquiring a second RSS vector measured by the terminal to be positioned; according to the second RSS vector and the first RSS vector, a preset neural network is adopted to obtain the equivalent distance between the terminal to be positioned and each reference point; selecting a plurality of positioning anchor points from a plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point; positioning a terminal to be positioned by adopting a plurality of positioning anchor points to obtain the position of the terminal to be positioned; the preset neural network is adopted to fit the equivalent distance between two points in the indoor environment, so that the positioning anchor point is selected to position the terminal to be positioned, and the indoor positioning precision can be effectively improved.
Description
Technical Field
The present invention relates to the field of wireless network positioning technologies, and in particular, to an indoor positioning method, apparatus, device, and computer-readable storage medium.
Background
In recent years, with the increase of the popularity of intelligent terminals, various mobile terminal applications are also coming to the development of the underground injection type. Among them, Location Based Services (LBS) are an important class, and the application range covers medical care, logistics management, security, navigation, location-based information delivery, location-based network security, location-based user participation in games, and the like, and there is a great development space. Traditional wireless terminal location relies primarily on GPS and wireless base stations for location, both of which are geometry-based location methods that determine the location of a terminal by measuring the distance from an anchor node to the terminal. In the outdoor environment, the distance measurement precision is high, so that the traditional wireless terminal positioning method can obtain high positioning precision. In an indoor environment, on one hand, accurate distance measurement is difficult due to the fact that a large number of non-line-of-sight propagation paths exist; on the other hand, in the traditional RF fingerprint positioning, the vector distance of the RF signal characteristic vector is simply taken as the physical distance measurement, and errors are introduced, so that the indoor positioning errors are large, and the indoor positioning accuracy is influenced.
Disclosure of Invention
In view of the foregoing problems, an object of the present invention is to provide an indoor positioning method, apparatus, device and computer readable storage medium, which can effectively improve indoor positioning accuracy.
In a first aspect, an embodiment of the present invention provides an indoor positioning method, including:
collecting a first RSS vector measured at a plurality of reference points of known locations in an indoor environment;
acquiring a second RSS vector measured by the terminal to be positioned;
obtaining the equivalent distance between the terminal to be positioned and each reference point by adopting a preset neural network according to the second RSS vector and the first RSS vector;
selecting a plurality of positioning anchor points from a plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point;
and positioning the terminal to be positioned by adopting a plurality of positioning anchor points to obtain the position of the terminal to be positioned.
As an improvement of the above solution, said acquiring a first RSS vector measured at a plurality of reference points with known locations in an indoor environment comprises:
in an off-line stage, dividing the indoor environment into a plurality of grids; wherein each grid is provided with at least one reference point with a known position; the indoor environment is provided with N access points;
and acquiring the signal intensity from the N access points at each reference point to obtain the N-dimensional signal characteristics of the corresponding reference point as a first RSS vector of the corresponding reference point.
As an improvement of the above solution, the selecting a plurality of positioning anchor points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each of the reference points includes:
selecting K candidate reference points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point; the maximum equivalent distance corresponding to the selected candidate reference point is smaller than the minimum equivalent distance corresponding to the unselected reference point;
calculating the average coordinate and the standard deviation of the candidate reference points according to the positions of the K candidate reference points;
and selecting a plurality of positioning anchor points from the K candidate reference points according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates and a preset deviation threshold value.
As an improvement of the above solution, selecting a plurality of positioning anchor points from the K candidate reference points according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates, and a preset deviation threshold includes:
calculating a deviation value of any one candidate reference point according to the position of any one candidate reference point, the average coordinate and the standard deviation of the coordinate;
comparing the deviation value of any one of the candidate reference points with the deviation threshold value;
when the deviation value of any one candidate reference point is larger than the deviation threshold value, determining any one candidate reference point as an abnormal point, and rejecting any one candidate reference point;
and when the deviation value of any one candidate reference point is less than or equal to the deviation threshold value, taking any one candidate reference point as a positioning anchor point.
As an improvement of the above solution, the calculating a deviation value of any one of the candidate reference points according to the position of any one of the candidate reference points, the average coordinate and the standard deviation of the coordinate includes
Calculating a deviation value of the ith candidate reference point according to formula (1) or (2);
wherein (x)i，yi) Representing the position of the ith candidate reference point, wherein i belongs to K, and K is the number of the candidate reference points;
mean coordinates representing K candidate reference points, (std)x，stdy) The standard deviation of the mean coordinates is indicated.
As an improvement of the above scheme, the positioning the terminal to be positioned by using the plurality of positioning anchor points to obtain the position of the terminal to be positioned includes:
calculating the weight of each positioning anchor point according to the equivalent distance corresponding to each positioning anchor point;
acquiring a positioning position obtained by positioning the terminal to be positioned by each positioning anchor point;
and according to the weight of each positioning anchor point, carrying out weighted summation on the positioning position corresponding to each positioning anchor point to obtain the final position of the terminal to be positioned.
As an improvement of the above scheme, the method further comprises a training step of the neural network:
constructing a fingerprint database according to the position of the reference point and the first RSS vector;
grouping the fingerprints in the fingerprint database pairwise; wherein a fingerprint comprises the location of one of said reference points and its first RSS vector;
calculating the physical distance between the reference points corresponding to the two fingerprints in each group according to the positions of the reference points corresponding to the two fingerprints in each group;
obtaining a training data set by the physical distance and second RSS vectors of two corresponding reference points;
training a neural network by adopting the training data set to obtain the preset neural network; and taking the physical distance in the training data set as the output of the neural network, and taking the first RSS vectors of the two reference points corresponding to the physical distance as the input of the neural network.
In a second aspect, an embodiment of the present invention provides an indoor positioning apparatus, including:
the system comprises a first RSS vector acquisition module, a second RSS vector acquisition module and a first RSS vector acquisition module, wherein the first RSS vector acquisition module is used for acquiring first RSS vectors measured at a plurality of reference points with known positions in an indoor environment;
the second RSS vector acquisition module is used for acquiring a second RSS vector measured by the terminal to be positioned;
the equivalent distance calculation module is used for obtaining the equivalent distance between the terminal to be positioned and each reference point by adopting a preset neural network according to the second RSS vector and the first RSS vector;
the positioning anchor point selecting module is used for selecting a plurality of positioning anchor points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point;
and the positioning module is used for positioning the terminal to be positioned by adopting a plurality of positioning anchor points to obtain the position of the terminal to be positioned.
In a third aspect, an embodiment of the present invention provides an indoor positioning device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor, when executing the computer program, implements the indoor positioning method according to any one of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, an apparatus in which the computer-readable storage medium is located is controlled to perform the indoor positioning method according to any one of the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that: collecting a first RSS vector measured at a plurality of reference points at known locations in an indoor environment; acquiring a second RSS vector measured by the terminal to be positioned; obtaining the equivalent distance between the terminal to be positioned and each reference point by adopting a preset neural network according to the second RSS vector and the first RSS vector; selecting a plurality of positioning anchor points from a plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point; and positioning the terminal to be positioned by adopting a plurality of positioning anchor points to obtain the position of the terminal to be positioned. The preset neural network is adopted to fit the equivalent distance between two points in the indoor environment, so that the positioning anchor point is selected to position the terminal to be positioned, and the indoor positioning precision can be effectively improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an indoor positioning method according to a first embodiment of the present invention;
FIG. 2 is a schematic view of an indoor environment provided by an embodiment of the present invention;
FIG. 3 is a cumulative probability distribution curve of positioning errors according to an embodiment of the present invention;
FIG. 4 is a schematic view of an indoor positioning apparatus according to a second embodiment of the present invention;
fig. 5 is a schematic diagram of an indoor positioning apparatus according to a third embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Please refer to fig. 1, which is a flowchart illustrating an indoor positioning method according to a first embodiment of the present invention, the indoor positioning method includes:
s1: collecting a first RSS vector measured at a plurality of reference points of known locations in an indoor environment;
s2: acquiring a second RSS vector measured by the terminal to be positioned;
s3: obtaining the equivalent distance between the terminal to be positioned and each reference point by adopting a preset neural network according to the second RSS vector and the first RSS vector;
s4: selecting a plurality of positioning anchor points from a plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point;
s5: and positioning the terminal to be positioned by adopting a plurality of positioning anchor points to obtain the position of the terminal to be positioned.
In the embodiment of the invention, the second RSS vector measured by the terminal to be positioned and the first RSS vector of the reference point corresponding to each fingerprint of the data fingerprint database are input into a preset neural network to obtain the equivalent distance between the terminal to be positioned and each reference point, and a plurality of positioning anchor points are screened out from the reference points according to the equivalent distance by fitting the equivalent distance between the terminal to be positioned and the reference points in an indoor environment for positioning the terminal to be positioned, so that the indoor positioning precision can be effectively improved.
In an alternative embodiment, S1: before collecting a first RSS vector measured at a number of reference points at known locations in an indoor environment, comprising:
in an off-line stage, dividing the indoor environment into a plurality of grids; wherein each grid is provided with at least one reference point with a known position; the indoor environment is provided with N access points;
and acquiring the signal intensity from the N access points at each reference point to obtain the N-dimensional signal characteristics of the corresponding reference point as a first RSS vector of the corresponding reference point.
Constructing a fingerprint database in an off-line stage: dividing an indoor environment into a plurality of grids, wherein Reference points (RP, Reference points) with known positions are taken in each grid, assuming that the total number of the Reference points is M, and N Access Points (AP) are arranged in the indoor environment; then, RF signal characteristics from N access points are measured at each reference point, in the present example RSS is taken as the signal characteristic, and then the signal characteristic received at the s-th reference point can be denoted as N-dimensional signal characteristic, i.e. the first RSS vector. The first RSS vector and the location of the corresponding reference point are then stored as a fingerprint in a fingerprint database.
In an alternative embodiment, the method further comprises the step of training the neural network:
constructing a fingerprint database according to the position of the reference point and the first RSS vector;
grouping the fingerprints in the fingerprint database pairwise; wherein a fingerprint comprises a position of the reference point and a first RSS vector;
calculating the physical distance between the reference points corresponding to the two fingerprints in each group according to the positions of the reference points corresponding to the two fingerprints in each group;
obtaining a training data set by the physical distance and second RSS vectors of two corresponding reference points;
training a neural network by adopting the training data set to obtain the preset neural network; and taking the physical distance in the training data set as the output of the neural network, and taking the first RSS vectors of the two reference points corresponding to the physical distance as the input of the neural network.
In the embodiment of the invention, as shown in fig. 2, fingerprint collection is performed in an office area of about 30 meters × 20 meters, 6 access points AP are distributed in the environment, 180 reference points RP are taken in the office area, and the reference points are respectively marked as RP1,RP2,…,RP180. The wireless signal strength RSS is used as the signal feature, so the first RSS vector of the s-th reference point can be recorded as RSSs＝{RSSs1,RSSs2,…,RSSs6}, one fingerprint may be denoted FPs＝{(xs,ys),(RSSs1,RSSs2,…,RSSs6) }; where, s is 1, 2, …, 180, the fingerprint set is denoted as FP { FP ═ FP1,FP2,…,FP180}。
In the off-line stage, the fingerprints in the fingerprint database are combined pairwise according to a formula
Calculating the physical distance between the corresponding reference points to obtain
And combining the numbers, and storing the physical distance obtained by calculation and the corresponding fingerprint pair together to form a training data set. Wherein (x)a，ya)，(xb，yb) Indicating the reference point RPaAnd a reference point RPbOf the position of (a).
And constructing a neural network which comprises an input layer, a hidden layer and an output layer. According to a pre-established neural network, an input layer of the neural network comprises 12 nodes, and a hidden layer comprises 24 nodes; inputting an RSS vector pair, namely RSS vectors of two reference points corresponding to a physical distance, and outputting a sequence of a neural network for the corresponding physical distance; wherein, the weight v of the connection line from the input layer node to the hidden layer nodeijIs set to all 1, and the connection weight u from the hidden layer to the output layerjAre set to all 1 s, which will be adaptively updated according to the training algorithm during the training process, and the training stop condition is set to the distance fromThe distance error (the difference between the equivalent distance and the physical distance between the reference points of the input training) is smaller than a first set value (for example, 0.5m), or the training is stopped when the number of times of training reaches a second set value. The training algorithm of the neural network is trained by using an algorithm such as a newton method, a steepest descent method, and an LM algorithm (Levenberg-Marquardt, Levenberg-Marquardt algorithm), and preferably, the LM algorithm is used in the embodiment of the present invention. It should be noted that newton method, steepest descent method, and LM algorithm belong to the prior art in the field, and are not described herein again.
Training a neural network by adopting data in a training data set, wherein the output of the jth hidden layer node is as follows:
the output of the whole neural network is:
where M denotes the number of reference points, where vlijIndicating that the jth hidden layer is connected with the RSSliWeight of the corresponding input layer node, ujIs the weight connecting the jth hidden layer and output layer nodes. And thetajRepresenting the threshold of the jth hidden layer node, and δ is the threshold of the output layer. The initial value of the weight can be set according to experience, and self-adaptive adjustment is carried out in the training process. The threshold may also be set empirically. And the trained neural network inputs the second RSS vector measured by the terminal to be positioned and the first RSS vector of the reference point corresponding to each fingerprint of the data fingerprint database, and outputs the equivalent distance between the terminal to be positioned and each reference point.
In the embodiment of the invention, the relation between the RF signal characteristic vector distance between two positions in the space and the physical distance between the two positions is fitted by utilizing the neural network, the method is suitable for fitting the nonlinear function relation which is difficult to express by using a conventional function form, and compared with the traditional method for positioning the RF fingerprint, the method only simply takes the vector distance of the RF signal characteristic vector as the physical distance measurement or uses some specific functions to fit the relation between the RF signal characteristic vector distance and the physical distance, the method can reduce errors and effectively improve the indoor positioning precision. Meanwhile, the data of the training neural network is the combination of every two fingerprints in the fingerprint database, the number of the data is far larger than the number of the fingerprint entries, and compared with the RF fingerprint positioning scheme which adopts the artificial neural network and deep learning in the prior art, the method can greatly improve the number of training samples and improve the accuracy of predicting the equivalent distance between two points, thereby further improving the indoor positioning accuracy.
In an optional embodiment, the selecting, according to the equivalent distance between the terminal to be positioned and each of the reference points, a plurality of positioning anchor points from the plurality of reference points includes:
selecting K candidate reference points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point; the maximum equivalent distance corresponding to the selected candidate reference point is smaller than the minimum equivalent distance corresponding to the unselected reference point;
calculating the average coordinate and the standard deviation of the candidate reference points according to the positions of the K candidate reference points;
and selecting a plurality of positioning anchor points from the K candidate reference points according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates and a preset deviation threshold value.
In the embodiment of the present invention, in the online phase, the second RSS vector measured by the terminal to be positioned is RSSolSending the second RSS vector to a background positioning engine, and enabling the background positioning engine to send the second RSS vector to the background positioning engineolRespectively pairing with the first RSS vectors of the reference points in the fingerprint database, and inputting the paired first RSS vectors and second RSS vectorsolInputting the equivalent distance d between the terminal to be positioned and each reference point into a neural network, and outputting the equivalent distance d between the terminal to be positioned and each reference point by the neural network#。
Then, selecting K reference points with smaller equivalent distances from the equivalent distances output by the neural network as candidate reference points, specifically, selecting K reference points with smaller distances by sorting the output equivalent distances from small to large, then selecting the reference points corresponding to the K equivalent distances in the front row, or comparing the output equivalent distances, and selecting the K reference points with smaller distances, or selecting the K reference points with smaller equivalent distances by the following formula:
Ωt+1＝Ωt/{ridx(t)},Ω1＝Ω
wherein Ω ═ { r ═ r1,r2,…,rM}, symbol Ωt/{ridx(t)Denotes the set left after the element idx (t) is removed from the set. The set of candidate reference points extracted in this step is denoted as C ═ RPl1,RPl2,…,RPlK}。
In an optional embodiment, the selecting, according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates, and a preset deviation threshold, a plurality of positioning anchor points from the K candidate reference points includes:
calculating a deviation value of any one candidate reference point according to the position of any one candidate reference point, the average coordinate and the standard deviation of the coordinate;
comparing the deviation value of any one of the candidate reference points with the deviation threshold value;
when the deviation value of any one of the candidate reference points is larger than the deviation threshold value, determining any one of the candidate reference points as an abnormal point, and rejecting any one of the candidate reference points;
and when the deviation value of any one candidate reference point is less than or equal to the deviation threshold value, taking any one candidate reference point as a positioning anchor point.
In an alternative embodiment, the calculating the deviation value of any one of the candidate reference points according to the position of any one of the candidate reference points, the average coordinate and the standard deviation of the coordinate includes
Calculating a deviation value of the ith candidate reference point according to formula (1) or (2);
wherein (x)i，yi) Representing the position of the ith candidate reference point, wherein i belongs to K, and K is the number of the candidate reference points;
mean coordinates representing K candidate reference points, (std)x，stdy) The standard deviation of the mean coordinates is indicated.
In the embodiment of the invention, when the requirements are met
Or
When the candidate reference points are abnormal points, the corresponding candidate reference points are removed from the set C, and the rest candidate reference points are used as positioning anchor points; where τ represents a preset deviation threshold, which may be set empirically. Preferably, τ -5 and K-5.
In an optional embodiment, the positioning the terminal to be positioned by using the plurality of positioning anchor points to obtain the position of the terminal to be positioned includes:
calculating the weight of each positioning anchor point according to the equivalent distance corresponding to each positioning anchor point;
acquiring a positioning position obtained by positioning the terminal to be positioned by each positioning anchor point;
and according to the weight of each positioning anchor point, carrying out weighted summation on the positioning position corresponding to each positioning anchor point to obtain the final position of the terminal to be positioned.
In the embodiment of the invention, according to the formula (3), calculating the weight of the jth positioning anchor point;
wherein the content of the first and second substances,
and representing the equivalent distance corresponding to the jth positioning anchor point, wherein j belongs to m, and m is the number of the positioning anchor points.
The position estimation of the terminal to be positioned is as follows:
in the embodiment of the invention, after the abnormal reference points are removed in the steps, the position of the terminal to be positioned is estimated by adopting a weighted average mode for the positioning anchor points. As shown in fig. 3, a positioning error cumulative probability distribution curve of the indoor positioning method according to the embodiment of the present invention and other positioning methods is shown, and it can be seen that the indoor positioning method according to the embodiment of the present invention can significantly improve the indoor positioning accuracy.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
in an off-line stage, training a neural network through the RSS and the position of the collected reference point, and fitting the relation between the RSS vector distance between the two positions and the physical distance of the two positions; then in the online positioning stage, inputting an RSS vector at a reference point of a terminal to be positioned and a known position, and outputting an equivalent distance between the terminal to be positioned and the reference point; and finally, estimating the position of the target to be positioned by using the output equivalent distance in combination with a classical KNN algorithm and abnormal point elimination and finally adopting the positioning anchor point after the abnormal point elimination. The embodiment of the invention fully considers the distortion problem between the RSS vector distance and the physical distance between the two positions, and can effectively improve the positioning precision. Meanwhile, compared with the traditional scheme, the method and the device utilize the conventional RSS fingerprints, pairwise matching of the fingerprints is performed, more data can be acquired for training compared with the existing scheme, and the difficulty that the workload of data acquisition in the early stage of the existing scheme is huge is overcome.
Referring to fig. 4, a second embodiment of the present invention provides an indoor positioning device, including:
the system comprises a first RSS vector acquisition module 1, a first RSS vector acquisition module and a second RSS vector acquisition module, wherein the first RSS vector acquisition module is used for acquiring first RSS vectors measured at reference points with known positions in an indoor environment;
the second RSS vector acquisition module 2 is used for acquiring a second RSS vector measured by the terminal to be positioned;
the equivalent distance calculation module 3 is configured to obtain an equivalent distance between the terminal to be positioned and each reference point by using a preset neural network according to the second RSS vector and the first RSS vector;
the positioning anchor point selecting module 4 is used for selecting a plurality of positioning anchor points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point;
and the positioning module 5 is configured to position the terminal to be positioned by using a plurality of positioning anchor points to obtain the position of the terminal to be positioned.
In an alternative embodiment, the first RSS vector acquiring module 1 comprises:
the grid dividing unit is used for dividing the indoor environment into a plurality of grids in an off-line stage; wherein each grid is provided with at least one reference point with a known position; the indoor environment is provided with N access points;
and the signal acquisition unit is used for acquiring the signal intensity from the N access points at each reference point to obtain the N-dimensional signal characteristics of the corresponding reference point as a first RSS vector of the corresponding reference point.
In an alternative embodiment, the positioning anchor selection module 5 includes:
the first selection unit is used for selecting K candidate reference points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point; the maximum equivalent distance corresponding to the selected candidate reference point is smaller than the minimum equivalent distance corresponding to the unselected reference point;
the average coordinate calculation unit is used for calculating the average coordinate of the candidate reference points and the standard deviation thereof according to the positions of the K candidate reference points;
and the second selection unit is used for selecting a plurality of positioning anchor points from the K candidate reference points according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates and a preset deviation threshold value.
In an alternative embodiment, the second selecting unit includes:
a positioning deviation calculation unit, configured to calculate a deviation value of any one of the candidate reference points according to the position of any one of the candidate reference points, the average coordinate, and a standard deviation of the coordinates;
a comparing unit, configured to compare a deviation value of any one of the candidate reference points with the deviation threshold;
the removing unit is used for confirming that any one candidate reference point is an abnormal point and removing any one candidate reference point when the deviation value of any one candidate reference point is larger than the deviation threshold value;
and the selecting unit is used for taking any one candidate reference point as a positioning anchor point when the deviation value of any one candidate reference point is less than or equal to the deviation threshold value.
In an alternative embodiment, the positioning deviation calculating unit is configured to calculate a deviation value of the ith candidate reference point according to formula (1) or (2);
wherein (x)i，yi) Expressing the position of the ith candidate reference point, wherein i belongs to K, and K is the number of the candidate reference points;
mean coordinates representing K candidate reference points, (std)x，stdy) The standard deviation of the mean coordinates is indicated.
In an alternative embodiment, the positioning module 6 comprises:
the weight calculation unit is used for calculating the weight of each positioning anchor point according to the equivalent distance corresponding to each positioning anchor point;
the position calculation unit is used for acquiring a positioning position obtained by positioning the terminal to be positioned by each positioning anchor point;
and the weighted summation unit is used for carrying out weighted summation on the positioning position corresponding to each positioning anchor point according to the weight of each positioning anchor point to obtain the final position of the terminal to be positioned.
In an alternative embodiment, the apparatus further comprises:
the fingerprint database construction module is used for constructing a fingerprint database according to the position of the reference point and the first RSS vector;
the fingerprint grouping module is used for grouping the fingerprints in the fingerprint database in pairs; wherein a fingerprint comprises a location of said reference point and a first RSS vector;
the distance calculation module is used for calculating the physical distance between the reference points corresponding to the two fingerprints in each group according to the positions of the reference points corresponding to the two fingerprints in each group;
the training set building module is used for obtaining a training data set by the physical distance and second RSS vectors of two corresponding reference points;
the network training module is used for training a neural network by adopting the training data set to obtain the preset neural network; and taking the physical distance in the training data set as the output of the neural network, and taking the first RSS vectors of the two reference points corresponding to the physical distance as the input of the neural network.
It should be noted that the principle and technical effect of the indoor positioning device according to the embodiment of the present invention are the same as those of the indoor positioning method according to the first embodiment, and are not described herein again.
Referring to fig. 5, a schematic diagram of an indoor positioning apparatus according to a fifth embodiment of the present invention is shown. As shown in fig. 5, the indoor positioning apparatus includes: at least one processor 11, such as a CPU, at least one network interface 14 or other user interface 13, a memory 15, at least one communication bus 12, the communication bus 12 for enabling connectivity communication between these components. The user interface 13 may optionally include a USB interface, and other standard interfaces, wired interfaces. The network interface 14 may optionally include a Wi-Fi interface as well as other wireless interfaces. The memory 15 may comprise a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 15 may optionally comprise at least one memory device located remotely from the aforementioned processor 11.
In some embodiments, memory 15 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof:
an operating system 151, which contains various system programs for implementing various basic services and for processing hardware-based tasks;
and (5) a procedure 152.
Specifically, the processor 11 is configured to call the program 152 stored in the memory 15 to execute the indoor positioning method according to the foregoing embodiment, for example, step S1 shown in fig. 1. Alternatively, the processor implements the functions of the modules/units in the above embodiments of the apparatus when executing the computer program, for example, the first RSS vector collecting module.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the indoor positioning device.
The indoor positioning device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The indoor positioning equipment may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic illustrations are merely examples of an indoor positioning apparatus and do not constitute a limitation of an indoor positioning apparatus, and may include more or fewer components than those illustrated, or some components in combination, or different components.
The Processor 11 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 11 is the control center of the indoor positioning apparatus, and various interfaces and lines are used to connect the various parts of the entire indoor positioning apparatus.
The memory 15 may be used to store the computer programs and/or modules, and the processor 11 implements various functions of the indoor positioning apparatus by running or executing the computer programs and/or modules stored in the memory and calling up data stored in the memory. The memory 15 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 15 may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein the module/unit integrated with the indoor positioning device, if implemented in the form of a software functional unit and sold or used as a stand-alone product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
A sixth embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the indoor positioning method according to any one of the first embodiments.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. An indoor positioning method, comprising:
collecting a first RSS vector measured at a plurality of reference points of known locations in an indoor environment;
acquiring a second RSS vector measured by the terminal to be positioned;
obtaining the equivalent distance between the terminal to be positioned and each reference point by adopting a preset neural network according to the second RSS vector and the first RSS vector;
selecting a plurality of positioning anchor points from a plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point;
positioning the terminal to be positioned by adopting a plurality of positioning anchor points to obtain the position of the terminal to be positioned;
selecting a plurality of positioning anchor points from a plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point, wherein the selecting comprises the following steps:
selecting K candidate reference points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point; the maximum equivalent distance corresponding to the selected candidate reference point is smaller than the minimum equivalent distance corresponding to the unselected reference point;
calculating the average coordinate and the standard deviation of the candidate reference points according to the positions of the K candidate reference points;
selecting a plurality of positioning anchor points from the K candidate reference points according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates and a preset deviation threshold;
selecting a plurality of positioning anchor points from the K candidate reference points according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates and a preset deviation threshold, wherein the method comprises the following steps:
calculating the deviation value of any one candidate reference point according to the position of any one candidate reference point, the average coordinate and the standard deviation of the coordinate;
comparing the deviation value of any one of the candidate reference points with the deviation threshold value;
when the positioning deviation value of any one candidate reference point is larger than the deviation threshold value, determining any one candidate reference point as an abnormal point, and rejecting any one candidate reference point;
and when the deviation value of any one candidate reference point is less than or equal to the deviation threshold value, taking any one candidate reference point as a positioning anchor point.
2. The indoor positioning method of claim 1, wherein said acquiring a first RSS vector measured at a number of reference points of known location in an indoor environment comprises:
in an off-line stage, dividing the indoor environment into a plurality of grids; wherein each grid is provided with at least one reference point with a known position; the indoor environment is provided with N access points;
and acquiring the signal intensity from the N access points at each reference point to obtain the N-dimensional signal characteristics of the corresponding reference point as a first RSS vector of the corresponding reference point.
3. The indoor positioning method of claim 1, wherein the calculating of the deviation value of any one of the candidate reference points according to the position of any one of the candidate reference points, the average coordinate, and the standard deviation of the coordinates comprises
Calculating a deviation value of the ith candidate reference point according to formula (1) or (2);
wherein (x)i，yi) Expressing the position of the ith candidate reference point, wherein i belongs to K, and K is the number of the candidate reference points;
mean coordinates representing K candidate reference points, (std)x，stdy) The standard deviation of the mean coordinates is indicated.
4. The indoor positioning method of claim 1, wherein the positioning the terminal to be positioned by using the plurality of positioning anchors to obtain the position of the terminal to be positioned, comprises:
calculating the weight of each positioning anchor point according to the equivalent distance corresponding to each positioning anchor point;
acquiring a positioning position obtained by positioning each positioning anchor point on the terminal to be positioned;
and according to the weight of each positioning anchor point, carrying out weighted summation on the positioning position corresponding to each positioning anchor point to obtain the final position of the terminal to be positioned.
5. The indoor positioning method of claim 1, further comprising a training step of a neural network:
constructing a fingerprint database according to the position of the reference point and the first RSS vector;
grouping the fingerprints in the fingerprint database pairwise; wherein a fingerprint comprises the location of one of said reference points and its first RSS vector;
calculating the physical distance between the reference points corresponding to the two fingerprints in each group according to the positions of the reference points corresponding to the two fingerprints in each group;
obtaining a training data set by the physical distance and the first RSS vectors of the two corresponding reference points;
training a neural network by adopting the training data set to obtain the preset neural network; and taking the physical distance in the training data set as the output of the neural network, and taking the first RSS vectors of the two reference points corresponding to the physical distance as the input of the neural network.
6. An indoor positioning device, comprising:
the system comprises a first RSS vector acquisition module, a second RSS vector acquisition module and a first RSS vector acquisition module, wherein the first RSS vector acquisition module is used for acquiring first RSS vectors measured at a plurality of reference points with known positions in an indoor environment;
the second RSS vector acquisition module is used for acquiring a second RSS vector measured by the terminal to be positioned;
the equivalent distance calculation module is used for obtaining the equivalent distance between the terminal to be positioned and each reference point by adopting a preset neural network according to the second RSS vector and the first RSS vector;
the positioning anchor point selecting module is used for selecting a plurality of positioning anchor points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point;
the positioning module is used for positioning the terminal to be positioned by adopting the plurality of positioning anchor points to obtain the position of the terminal to be positioned;
the positioning anchor point selecting module comprises:
the first selection unit is used for selecting K candidate reference points from the plurality of reference points according to the equivalent distance between the terminal to be positioned and each reference point; the maximum equivalent distance corresponding to the selected candidate reference point is smaller than the minimum equivalent distance corresponding to the unselected reference point;
the average coordinate calculation unit is used for calculating the average coordinate of the candidate reference points and the standard deviation thereof according to the positions of the K candidate reference points;
the second selection unit is used for selecting a plurality of positioning anchor points from the K candidate reference points according to the positions of the K candidate reference points, the average coordinate, the standard deviation of the coordinates and a preset deviation threshold;
the second selecting unit comprises:
a positioning deviation calculation unit, configured to calculate a deviation value of any one of the candidate reference points according to the position of any one of the candidate reference points, the average coordinate, and a standard deviation of the coordinates;
a comparing unit, configured to compare a deviation value of any one of the candidate reference points with the deviation threshold;
the removing unit is used for confirming that any one candidate reference point is an abnormal point and removing any one candidate reference point when the deviation value of any one candidate reference point is larger than the deviation threshold value;
and the selecting unit is used for taking any one candidate reference point as a positioning anchor point when the deviation value of any one candidate reference point is less than or equal to the deviation threshold value.
7. An indoor positioning device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the indoor positioning method of any one of claims 1-5 when executing the computer program.
8. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the indoor positioning method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110196626.4A CN113038596B (en) | 2021-02-22 | 2021-02-22 | Indoor positioning method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110196626.4A CN113038596B (en) | 2021-02-22 | 2021-02-22 | Indoor positioning method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113038596A CN113038596A (en) | 2021-06-25 |
| CN113038596B true CN113038596B (en) | 2022-06-17 |
Family
ID=76461487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110196626.4A Active CN113038596B (en) | 2021-02-22 | 2021-02-22 | Indoor positioning method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113038596B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105872981A (en) * | 2016-03-30 | 2016-08-17 | 河海大学常州校区 | Indoor positioning method based on signal synthesis and artificial neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102413564B (en) * | 2011-11-25 | 2014-07-23 | 北京工业大学 | Indoor positioning method based on BP neural network and improved centroid algorithm |
| US9237418B2 (en) * | 2013-07-26 | 2016-01-12 | Marvell World Trade Ltd. | Positioning database management applied to server-based positioning system |
| CN107509171A (en) * | 2017-09-01 | 2017-12-22 | 广州杰赛科技股份有限公司 | Indoor orientation method and device |
| CN109618280A (en) * | 2019-01-03 | 2019-04-12 | 广州杰赛科技股份有限公司 | Localization method, device, equipment and storage medium based on dynamic reference node |
-
2021
- 2021-02-22 CN CN202110196626.4A patent/CN113038596B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105872981A (en) * | 2016-03-30 | 2016-08-17 | 河海大学常州校区 | Indoor positioning method based on signal synthesis and artificial neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113038596A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110766080B (en) | Method, device and equipment for determining labeled sample and storage medium | |
| CN112218330B (en) | Positioning method and communication device | |
| CN112132277A (en) | Federal learning model training method and device, terminal equipment and storage medium | |
| CN110933632B (en) | Terminal indoor positioning method and system | |
| CN105512627A (en) | Key point positioning method and terminal | |
| WO2020119372A1 (en) | Field intensity prediction method and apparatus, and device and storage medium | |
| CN112364439A (en) | Simulation test method and device for automatic driving system and storage medium | |
| CN109657539B (en) | Face value evaluation method and device, readable storage medium and electronic equipment | |
| CN108770057B (en) | Method for determining predetermined fingerprint database, method and device for positioning fingerprint, and storage medium | |
| CN109788432B (en) | Indoor positioning method, device, equipment and storage medium | |
| CN107526058A (en) | Indoor orientation method, apparatus and system | |
| CN111182460A (en) | Hybrid indoor positioning method and device, computer equipment and storage medium | |
| CN105682039B (en) | A kind of RF fingerprint positioning method and system | |
| CN113038596B (en) | Indoor positioning method, device, equipment and computer readable storage medium | |
| CN109889977B (en) | Bluetooth positioning method, device, equipment and system based on Gaussian regression | |
| CN111563134B (en) | Fingerprint database clustering method, system, equipment and storage medium of positioning system | |
| CN111654808A (en) | Method and system for updating fingerprint database and wifi positioning method and system | |
| CN110958565B (en) | Method and device for calculating signal distance, computer equipment and storage medium | |
| CN112822626B (en) | Terminal positioning method and device, storage medium and electronic equipment | |
| CN112241767A (en) | Pipe network water pressure monitoring node arrangement method, device, equipment and storage medium | |
| CN109581288B (en) | Indoor positioning method, equipment and storage medium | |
| CN111194000B (en) | Distance measurement method and system based on Bluetooth fusion hybrid filtering and neural network | |
| CN113868939A (en) | Wind power probability density evaluation method, device, equipment and medium | |
| CN111008324A (en) | Travel service pushing method, system and device under big data and readable storage medium | |
| CN110636525A (en) | Credibility perception-based data transmission control method suitable for 5G network |
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 |