CN115333624B - Visible light indoor positioning method, system and computer readable medium based on spectrum estimation detection - Google Patents
Visible light indoor positioning method, system and computer readable medium based on spectrum estimation detection Download PDFInfo
- Publication number
- CN115333624B CN115333624B CN202210965366.7A CN202210965366A CN115333624B CN 115333624 B CN115333624 B CN 115333624B CN 202210965366 A CN202210965366 A CN 202210965366A CN 115333624 B CN115333624 B CN 115333624B
- Authority
- CN
- China
- Prior art keywords
- light source
- positioning
- visible light
- indoor positioning
- signal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 238000001228 spectrum Methods 0.000 title claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 238000004891 communication Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000003062 neural network model Methods 0.000 claims abstract description 13
- 238000009434 installation Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 19
- 210000002569 neuron Anatomy 0.000 claims description 13
- 230000003595 spectral effect Effects 0.000 claims description 12
- 230000003287 optical effect Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 238000000926 separation method Methods 0.000 claims description 8
- 238000005286 illumination Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 230000001934 delay Effects 0.000 claims description 4
- 230000003111 delayed effect Effects 0.000 claims description 4
- 230000001678 irradiating effect Effects 0.000 claims description 4
- 230000005284 excitation Effects 0.000 claims description 2
- 230000005404 monopole Effects 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 4
- 238000005311 autocorrelation function Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/11—Arrangements specific to free-space transmission, i.e. transmission through air or vacuum
- H04B10/114—Indoor or close-range type systems
- H04B10/116—Visible light communication
-
- 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
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/079—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
- H04B10/0795—Performance monitoring; Measurement of transmission parameters
- H04B10/07955—Monitoring or measuring power
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Optical Communication System (AREA)
Abstract
The invention discloses a visible light indoor positioning method, a visible light indoor positioning system and a visible light indoor communication link system model based on spectrum estimation detection; establishing an LED channel diffuse reflection model comprising a direct line-of-sight link LOS and a first-order reflection link NLOS; setting the installation interval of LEDs and dividing a positioning area on the basis of the LED channel diffuse reflection model, and constructing an indoor VLC positioning system channel model; selecting a plurality of positioning points in a positioning area, separating multiple light source signals based on a spectrum estimation detection method, obtaining power values of different light source signals, and storing the obtained power values of different light source signals of each positioning point and calibration coordinates thereof into a database; and constructing and training a visible light indoor positioning neural network model by taking the data stored in the database as a neural network training data set, and performing visible light indoor positioning by using the trained visible light indoor positioning neural network model to realize accurate positioning of a complex indoor environment.
Description
Technical Field
The invention belongs to the technical field of visible light indoor positioning, and relates to a visible light indoor positioning method, a system and a computer readable medium based on spectrum estimation detection.
Background
With the gradual maturity of the visible light communication technology and the deep research of the related application of indoor positioning, the indoor positioning technology is more and more widely focused by researchers at home and abroad, and statistics shows that more than half of human activities are performed indoors, and the positioning navigation service demands of large indoor places such as libraries, hospitals, supermarkets and underground parking lots are increased. Although many indoor positioning technologies based on wireless communication exist commonly nowadays, such as WIFI positioning, infrared positioning, ultrasonic positioning, bluetooth positioning, ultra wideband positioning, etc., most of wireless signals are affected by electromagnetic interference and multipath fading in the positioning process, so that the positioning accuracy of the system is not guaranteed, and meanwhile, the energy consumption of equipment is high, and certain limitations are provided. The indoor positioning technology is a novel indoor positioning technology by utilizing visible light, combines illumination and communication, has rich spectrum resources and no electromagnetic interference, has incomparable advantages of the traditional wireless radio frequency communication, has become a new research hot spot in the wireless communication field in recent years, has rapid development along with the development of the visible light communication technology in the current stage, is discussed as one of the indoor access modes of a fifth generation mobile communication system, and has very wide application prospect.
Visible Light Communication (VLC) indoor positioning techniques can be divided into two main categories, image Sensor (IS) based indoor positioning techniques and high-precision Photo Detector (PD) based indoor positioning techniques, respectively, according to the type of receiver. The accuracy of the indoor positioning method based on the Image Sensor (IS) IS related to the measurement accuracy of an actual device, the device cost IS high, and the method IS only suitable for indoor stationary or slowly moving object positioning. When positioning with a Photodetector (PD), algorithms based on Angle of arrival (AOA), time of arrival (TimeofArrival, TOA) and received signal strength (ReceivedSignalStrength, RSS) belong to conventional positioning algorithms. The positioning algorithm based on the RSS is widely used with the advantages of simple theoretical implementation, strong portability and the like, but on the premise of ensuring illumination, the accurate light source information separation cannot be performed by overlapping the light source signals, and the accurate positioning of the complex indoor environment is difficult to realize.
Disclosure of Invention
The embodiment of the invention aims to provide a visible light indoor positioning method, a visible light indoor positioning system and a computer readable medium based on spectrum estimation detection, which are used for solving the problems that the accurate light source information separation cannot be carried out by overlapping light source signals on the premise of ensuring illumination and the accurate positioning of a complex indoor environment is difficult to realize in the existing positioning algorithm based on RSS.
The first technical scheme adopted by the embodiment of the invention is as follows: the visible light indoor positioning method based on spectrum estimation detection is carried out according to the following steps:
step 1, building a visible light indoor communication link system model;
step 2, establishing an LED channel diffuse reflection model comprising a direct line-of-sight link LOS and a first-order reflection link NLOS;
step 3, setting the installation interval of LEDs and dividing a positioning area on the basis of the LED channel diffuse reflection model, and constructing an indoor VLC positioning system channel model;
step 4, selecting a plurality of positioning points in the positioning area, separating the multiple light source signals based on a spectrum estimation detection method, obtaining power values of different light source signals, and storing the obtained power values of the different light source signals of each positioning point and calibration coordinates thereof into a database;
and 5, constructing and training a visible light indoor positioning neural network model by taking the data stored in the database as a training data set of the neural network, and performing visible light indoor positioning by using the trained visible light indoor positioning neural network model.
The second technical scheme adopted by the embodiment of the invention is as follows: visible light indoor positioning system based on spectral estimation detects, including a plurality of LED lamps and photoelectric detector, still includes:
a memory for storing instructions executable by the processor;
and a processor for executing the instructions to implement the visible light indoor positioning method based on spectrum estimation detection as described above.
The third technical scheme adopted by the embodiment of the invention is as follows: a computer readable medium storing computer program code which, when executed by a processor, implements a visible light indoor positioning method based on spectral estimation detection as described above.
The embodiment of the invention has the beneficial effects that: aiming at the problem that the attenuation factor of each LED lamp in the space transmission process can not be accurately obtained in the traditional RSS-based visible light indoor positioning method, on the basis of signal intensity, a Pisarenko harmonic decomposition algorithm is combined with a neural network, and a visible light indoor positioning model based on combination of PSD detection and the neural network is provided, the method has good effects on multi-LED light source frequency estimation and power extraction of loading sinusoidal signals with different frequencies under the background of colored noise and low signal to noise ratio, and the separated LED light source power values are trained and tested in the neural network, so that the indoor positioning precision of a visible light system can be remarkably improved, and the accurate positioning is realized. The problem that accurate light source information separation cannot be carried out on the superposition of light source signals on the premise of ensuring illumination in the existing positioning algorithm based on RSS and accurate positioning of a complex indoor environment is difficult to realize is solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a visible light communication link system model.
Fig. 2 is a schematic diagram of a diffuse reflection model of an LED channel.
FIG. 3 is a schematic diagram of an indoor VLC positioning system channel model.
Fig. 4 is a block diagram of a spectral estimation detection method.
Fig. 5 is a block diagram of an indoor positioning method based on spectral estimation detection and neural network.
Fig. 6 is a plot of frequency-power distribution of each light source measured at coordinates (4, 1, 0) by an indoor positioning method based on spectral estimation detection and neural network with a signal-to-noise ratio of 10 dB.
Fig. 7 is a plot of frequency versus power for each light source measured at coordinates (2,3,0) by an indoor positioning method based on spectral estimation detection and neural network with a signal-to-noise ratio of 10 dB.
Fig. 8 is a three-dimensional distribution diagram of positioning errors at h=0 based on a spectral estimation detection and an indoor positioning method of a neural network.
Fig. 9 is a graph of measured positioning error for an indoor positioning method based on spectral estimation detection and neural network.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described in the following in conjunction with the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The embodiment provides a visible light indoor positioning method based on spectrum estimation detection, which comprises the following steps:
step 1, as shown in figure 1, building a visible light indoor communication link system model by taking a 4m multiplied by 3m indoor room as an experimental simulation model;
step 2, an LED channel diffuse reflection model including a direct line-of-sight link LOS and a first order reflection link NLOS is established, as shown in fig. 2, wherein the light intensity from a single light source to any point is defined as:
I(φ i )＝I 0 cos m φ i (1)
wherein I is 0 Represents the central luminous intensity of the LED, phi i Representing the emission angle of the ith LED, m representing the lambertian reflection order corresponding to the visible light source reduced to lambertian source, the direct horizontal illuminance E of the jth Photodetector (PD) under a multiple LED light source j The method comprises the following steps:
wherein E is ij Indicating that the jth PD receives the illuminance of the ith LED,representing the incident angle of the direct light source received by the jth PD, the jth PD has coordinates (x) j ,y j ,0)，(X i ,Y i ,Z i ) For the coordinates of the ith LED, M is the total number of LEDs.
Assuming that the secondary light source generated by any LED light source is P point, the coordinate of P point can be expressed as P (X 1 ,Y 1 ,Z 1 ) Similarly, the reflected light intensity I of the secondary light source generated by the ith LED light source and directly irradiating the P point i ' is defined as:
I' i ＝kI i cos m-1 β (3)
wherein I is i The illumination intensity of the secondary light source generated by the ith LED light source and directly irradiating the P point is represented, k is the reflection coefficient of the wall surface, beta represents the emission angle of the secondary light source, m-1 represents secondary reflection, and the reflected illumination E 'of the jth PD under the multi-level light source' j The method comprises the following steps:
wherein E is ij Representing the illuminance of the secondary light source of the ith LED received by the jth PD.
The illuminance E of any M LED light sources received by the jth PD is:
step 3, setting the installation interval of LEDs and dividing a positioning area on the basis of the LED channel diffuse reflection model in step 2, specifically determining the installation interval of the LEDs through two conditions of the standard deviation of illuminance of a receiving plane and the minimum value of RSS of the receiving plane, so that the illuminance of indoor light reaches the illuminance standard, constructing an indoor VLC positioning system channel model shown in fig. 3, wherein the positioning area is an indoor space with length L, width W and height H, M LED light sources at a transmitting end are uniformly distributed on a ceiling, and a photoelectric detector PD is positioned on the indoor ground; the LED installation space and the positioning area division of the embodiment are unified in the simulation stage, the length and width are 4m, 4m and 5m, and the LED installation space and the positioning area can be enlarged and reduced according to the proportion in the actual positioning stage;
step 4, selecting a plurality of positioning points in the positioning area, and separating multiple light source signals based on a spectrum estimation detection method shown in fig. 4 to obtain power values of different light source signals:
firstly, modulating LED light sources to enable each matrix light source combined by a plurality of lamp beads to load different carrier signals, and assuming that the ith LED light source at a transmitting end is frequency f i The modulating signal generated by the ith LED light source at the transmitting end is:
x i (n)＝A i sin(2πf i n)(1≤i≤M) (6)
wherein A is i For modulating the amplitude of the signal, i.e. the optical power signal generated by the ith LED light source, f i The optical power signal generated for the ith LED light source is at a time domain frequency, n is an argument of the signal in the time domain, typically n=1, 2,3 ….
Based on the linear nature of the sinusoidal signal, there are:
sin(2πf i n+θ)+sin[2πf i (n-2)+θ)]＝2cos(2πf i )sin[2πf i (n-1)+θ] (7)
where θ is the phase shift of the sinusoidal signal;
substituting the formula (6) into the formula (7) to obtain a differential equation:
x i (n)-2cos(2πf i )x i (n-1)+x i (n-2)＝0 (8)
wherein x is i (n-1) is X i The argument n of (n) delays the 1 unit of delay signal x i (n-2) is X i The argument n of (n) delays the delayed signal by 2 units.
The Z-transform is performed simultaneously on both the left and right sides of the formula (8), and there are:
[1-2cos(2πf i )z -1 +z -2 ]X i (z)＝0 (9)
wherein X is i (z) is x i The z transform of (n), z is complex, so:
1-2cos(2πf i )z -1 +z -2 ＝0 (10)
two radicals in the formula (10) areThe sine wave frequency is:
wherein Re (z) i ) Representing z i Of (2), im (z) i ) Representing z i Imaginary part, z i Is the modulation signal x generated by the ith LED light source i Root of Z-transformation of (n).
Therefore, according to the above process, M LED lamps are derived, when M LED lamps are driven by signals with different frequencies at the same time, the modulation signal x generated by the ith LED light source i The root of the Z-transformation of (n) can be determined by equation (12):
wherein,is z i Complex conjugate of (2); a, a 0 =1, there is symmetry in the coefficients, i.e. a i ＝a 2M-i (i＝0,1,...，M)。
The differential equation corresponding to equation (12) is:
wherein x is i (n-i) is X i The argument n of (n) delays the delayed signal by i units, n-i representing that the argument n is delayed by i units.
Then, a plurality of positioning points are selected in the positioning area, and the signals received by the receiving end are as follows:
where y (n) is the observed signal received by the PD and containing white noise e (n), H (0) is the optical channel DC gain,is the total noise variance.
Will beSubstituting into formula (13), obtain:
wherein y (n-i) is a delay signal for delaying an argument n of y (n) by i units, and e (n-i) is a delay signal for delaying an argument n of e (n) by i units;
writing formula (15) into matrix form to obtain
Y T A＝E T A (16)
Wherein:
taking the mathematical expectation from both sides of the left multiplication vector Y of the formula (16) to obtain E { YY ] T The } is:
wherein R is Y Is the matrix formed by the autocorrelation function of the received observation signal, namely the autocorrelation matrix, R y (0) Representing the signal x emitted by the 0 th light source 0 The result of the autocorrelation operation of (n);
wherein,is the autocorrelation matrix R of the observed signal set { y (n) } Y Eigenvalue lambda of i And coefficient vector A of the characteristic polynomial is corresponding to the characteristic value lambda i The dimension of the noise subspace is 1, which is defined by the minimum eigenvalue +.>The corresponding feature vector is formed, and thus a coefficient vector a can be calculated.
In the operation of the Pisarenko harmonic decomposition method, the autocorrelation matrix R is generally obtained from a p×p (p > 2M) dimension Y To avoid multiple solutions of coefficient vector A caused by multiple eigenvalues, R is required to be calculated Y Performing dimension reduction treatment, namely:
the PD receiving end obtains the characteristic polynomial in the formula (20), and then obtains the coefficient vector A through the formula (19), namely a is obtained i Autocorrelation matrix R Y Is the result of autocorrelation operation of each subharmonic component of the observed signal received by the receiving terminal PD, and then Z-transform is performed on the formula (13) to obtain Z i That is, f can be obtained from the formula (11) i 。
According to signal x i (n) statistically independent of white noise e (n), the autocorrelation matrix of the received signal y (n) in equation (14) is:
wherein R is x Is the signal x i (n) autocorrelation function, R e Is the autocorrelation function of white noise e (n), σ ω White noise variance, I is noise figure; e, e i Is a number M of linearly independent vectors,using the obtained f i Calculating to obtain a vector e i Then to vector e i Performing DTFT to obtain->P i Is the power of the light signal emitted by the ith LED lamp detected by the receiving end, P i ＝|A i | 2 。
Let it be assumed that the eigenvector a of the signal subspace 1 ,a 2 ,...,a M Has been normalized, i.eAs a result of:
R Y a i ＝λ i a i ,i＝1,2,...,M (22)
taking the two sides of the upper part to the leftThen get
R of formula (21) Y Substituted into the above, there are
Simplified to obtain
Wherein,is the frequency f i Processing signal subspace feature vector a i Square amplitude of DTFT of (1), namely:
after finding a i Andthen, calculate according to equation (26) to get +.> Is to x i (n) representation after DTFT, < + >>a i Is the signal intensity of the ith LED light source, w i Is x i (n) frequency coefficients in the complex frequency domain,is x i (n) frequencies in the complex frequency domain, so equation (26) can be written as:
the above equation represents M linear equations with M unknowns P written in matrix form:
solving the equation set to obtain a power matrix P= [ P ] 1 P 2 … P i … P M ]Complete the separation of multiple light source signals, wherein P i Corresponding to the power emitted by the ith LED light source received by the PD.
And finally, storing the obtained power values of the different light source signals of each positioning point and the calibration coordinates thereof into a database to finish the establishment of the database.
And 5, fig. 5 is a visible light indoor positioning frame based on spectrum estimation detection and a neural network, wherein the database data established in the step 4 is used as a training data set of the neural network, and the functional relation between the optical power and the calibration coordinates is fitted through the neural network. The neural network is a three-layer BP neural network and comprises an input layer, an implicit layer and an output layer, wherein the input layer consists of M neurons, the output layer consists of three neurons, the input of the input layer is a power matrix P which is obtained based on Pisarenko data separation, and the output layer outputs the relative coordinates of an optimized unknown positioning point.
Randomly selecting Q points as reference points of a fingerprint data set in a positioning area H=0M plane, namely an xy plane, and separating each reference point by a Pisarenko harmonic decomposition method to obtain the power of M LED light sources as the fingerprint data set, wherein the recording information corresponding to the n (1 n is less than or equal to Q) fingerprint points is as follows:
F n ＝(n,x n ,y n ,z n ,P n1 ,P n2 ,...,P nM )(1≤n≤Q) (29)
wherein, (x) n ,y n ,z n ) Representing the true coordinate position of the nth fingerprint point, P nM Indicating that the nth fingerprint point is at (x n ,y n ,z n ) The received light power value of the Mth LED light source.
Wherein the number of training dataset samples is K and the number of test dataset samples is L (l+k=q). The matrix constructed by the light power values of the M LED light sources received by each fingerprint point is an input training set. In the training process, the output layer continuously advances the positioning error intoAnd (3) carrying out back propagation, and continuously approaching to the actual positioning coordinates by continuously correcting the weight and the threshold value of each layer, so that the positioning accuracy is improved, and a neural network training model is obtained. Modeling input training set matrix X T Can be expressed as:
wherein X is d ＝(P d1 ,P d2 ,....,P dM ) And (d is more than or equal to 1 and less than or equal to K) representing Pisarenko power estimated values of M LED light sources received by the d-th position reference point in the training set. For each training sample, the output of each neuron is calculated from front to back.
The excitation function is a monopole S-shaped function expression:
wherein,coefficients that are unipolar sigmoid functions.
The output layer weight coefficient is:
Δθ k ＝-ηβ′O k (1-O k )(d k -O k ) (32)
wherein, beta' is the input vector of the output layer, namely the output of the hidden layer, d k Representing the expected value of the kth neuron of the output layer, eta being the learning rate, the input of the kth neuron of the output layer beingOutput is O k ＝f(I k )，O j The output of the jth neuron of the upper layer neural network is Q is the total number of neurons of the upper layer neural network, w jk To weight between I/O layer and hidden layer, O k For the output of the kth neuron of the current layer neural network, f () is a unipolar S-type functionWill I k Sending the obtained gradient data into an activation function for calculation, and preventing the neural network gradient from disappearing.
The hidden layer weight coefficient is:
wherein O is i Output of the ith neuron as hidden layer, O j The output of the j-th neuron of the hidden layer is represented, i and j are the number of rows and columns of the connection weight matrix respectively, and L is the number of input data; delta k For the partial derivative of the error transfer function of the kth hidden layer with respect to each neuron of the output, β "is the input vector of the current hidden layer, i.e. the output of the previous hidden layer, w jk Weights for the previous hidden layer and the current hidden layer.
And testing the trained neural network model by adopting test set data, if the performance reaches the standard, ending the whole training process, otherwise, continuing to adjust the super parameters to train the neural network model until the test performance reaches the standard. The reference point in each test set and the matrix P of the light power values of M LEDs correspondingly received are brought into a BP neural network model after training, and a neural network model test data set is input into the matrixCan be expressed as:
wherein,the light power values of the M LED light sources received by the q-th reference fingerprint point in the test set are represented, and the corresponding output matrix is as follows:
wherein,the predicted coordinates of the q-th reference fingerprint point in the test set.
And 6, performing visible light indoor positioning by using the neural network model trained and tested in the step 5.
Compared with other traditional visible light indoor positioning methods, the performance of the visible light indoor positioning method based on spectrum estimation detection is improved: as shown in fig. 6 to 7, under the condition that the signal-to-noise ratio is 10dB, the predicted frequency and the power value have no larger deviation, the maximum frequency error is 1.253HZ, the power is sensitive to change along with the positioning point distance, the maximum power estimation error is 0.125W, the extracted power values of the LEDs are used as training input data, the stability is good, the identification degree is high, and the Pisarenko harmonic decomposition method can be well applied to the extraction/separation of multi-LED mixed light signals positioned in a visible light room.
As shown in fig. 8, the overall result of three-dimensional positioning at h=0 meters is shown, the open circles represent real position coordinates, the stars represent position coordinates tested by the BP neural network, and the predicted position and the actual position coordinates have no large deviation from the results in the graph, the average error is 2.12 cm, and the overall three-dimensional average positioning error is 3.81 cm.
And verifying the positioning accuracy and stability of the positioning system through an actual measurement positioning experiment. Setting up a three-dimensional test space with the side length of 0.8m, uniformly arranging 4 LED light sources with the power of 5W on the top of the space, setting up a two-dimensional coordinate system with a plane angle as an original point and 5cm as an interval on the plane at the bottom of the space, drawing interval grid points on the plane at the bottom of the space, selecting 289 equidistant measurement positions at each interval point, and loading sinusoidal signals with different frequencies on the corresponding LED light sources through optical driving by a signal generator to enable the LEDs to periodically transmit the optical signals; at the receiving end, the PD is used as a signal receiver, horizontally placed at 289 equidistant measuring positions in a positioning area, responsible for converting received optical signals into electric signals, collected by an oscilloscope after passing through an amplifier, separated by a Pisarenko harmonic decomposition algorithm to obtain optical power vectors of 4 LED light sources corresponding to the positions, collected 40 times of power values for each light source, sequenced and removed to remove extremum and average, used as each group of light source power value data of the point, and finally selected 289 groups of training data and 20 groups of test position data according to a neural network positioning algorithm, and tested for multiple times to obtain the position coordinates of the PD. The 289 sets of data are then imported into the neural network for processing and training according to the neural network localization algorithm set forth in this embodiment. The result shows that the probability of being less than 5cm is 60%, the probability of being less than 2 cm is 10%, and the average positioning error is 4.28 cm, so that the actual measurement positioning accuracy is high and the positioning effect is stable.
Example 2
The embodiment provides a visible light indoor positioning system based on spectrum estimation detection, which comprises a plurality of LED lamps and a photoelectric detector, and further comprises: a memory for storing instructions executable by the processor; and a processor for executing the instructions to implement the visible light indoor positioning method based on spectrum estimation detection as described in embodiment 1 above.
A visible light indoor positioning system based on spectral estimation detection may include an internal communication bus, a Processor (Processor), a Read Only Memory (ROM), a Random Access Memory (RAM), a communication port, and a hard disk. The internal communication bus can realize data communication among components of the visible light indoor positioning system based on spectrum estimation detection. The processor may make the determination and issue the prompt. In some embodiments, a processor may be comprised of one or more processors. The communication port can realize data communication outside the visible light indoor positioning system based on spectrum estimation detection. In some embodiments, the visible light indoor positioning system based on spectral estimation detection may also send and receive information and data from the network through the communication port. The visible light indoor positioning system based on spectrum estimation detection may also comprise program storage units of different forms as well as data storage units, such as hard disk, read Only Memory (ROM) and Random Access Memory (RAM), capable of storing various data files for computer processing and/or communication, and possible program instructions for execution by the processor. The processor executes these instructions to implement the main part of the method. The result processed by the processor is transmitted to the tested device through the communication port and is displayed on the tested device interface.
The method for positioning the visible light indoor based on spectrum estimation detection can be implemented as a computer program, stored in a hard disk and recorded in a processor for execution. Accordingly, embodiments of the present invention also provide a computer readable medium storing computer program code which, when executed by a processor, implements a visible light indoor positioning method based on spectral estimation detection as described above.
When the visible light indoor positioning method based on spectrum estimation detection is implemented as a computer program, the method can also be stored in a computer readable storage medium as an article. For example, computer-readable storage media may include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips), optical disks (e.g., compact Disk (CD), digital Versatile Disk (DVD)), smart cards, and flash memory devices (e.g., electrically erasable programmable read-only memory (EPROM), cards, sticks, key drives). Furthermore, various storage media described by embodiments of the invention can represent one or more devices and/or other machine-readable media for storing information. The term "machine-readable medium" can include, without being limited to, wireless channels and various other media (and/or storage media) capable of storing, containing, and/or carrying code and/or instructions and/or data.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (9)
1. The visible light indoor positioning method based on spectrum estimation detection is characterized by comprising the following steps of:
step 1, building a visible light indoor communication link system model;
step 2, establishing an LED channel diffuse reflection model comprising a direct line-of-sight link LOS and a first-order reflection link NLOS;
step 3, setting the installation interval of LEDs and dividing a positioning area on the basis of the LED channel diffuse reflection model, and constructing an indoor VLC positioning system channel model;
step 4, selecting a plurality of positioning points in the positioning area, separating the multiple light source signals based on a spectrum estimation detection method, obtaining power values of different light source signals, and storing the obtained power values of the different light source signals of each positioning point and calibration coordinates thereof into a database;
step 5, using the data stored in the database as a training data set of the neural network, constructing and training a visible light indoor positioning neural network model, and carrying out visible light indoor positioning by using the trained visible light indoor positioning neural network model;
step 4, performing multi-light source signal separation based on a spectrum estimation detection method to obtain power values of different light source signals, and solving a formula (28) to obtain a power matrix P= [ P ] 1 P 2 … P i … P M ]，P i And (3) for the power transmitted by the ith LED lamp received by the PD, finishing multi-light source signal separation:
wherein,is obtained by performing DTFT on the received modulation signal generated by the ith LED light source,A i amplitude, a, of a modulated signal generated for the ith LED light source received by PD i Is the intensity, w, of the modulated signal generated by the ith LED light source received by the PD i Is the frequency coefficient of the modulation signal generated by the ith LED light source received by PD in the complex frequency domain,/>Is the frequency of the modulation signal generated by the ith LED light source received by the PD in the complex frequency domain, lambda i Is the autocorrelation matrix R of the set of observed signals received by PD Y Is the observed signal containing white noise e (n), sigma ω Is the variance of the white noise e (n).
2. The indoor positioning method of visible light based on spectrum estimation detection according to claim 1, wherein the LED channel diffuse reflection model including the direct line of sight link LOS and the first order reflection link NLOS established in step 2 is:
I(φ i )＝I 0 cos m φ i (1)
I′ i ＝kI i cos m-1 β (2)
wherein I is 0 Represents the central luminous intensity of the LED, phi i Represents the emission angle of the ith LED, m represents the Langerhans reflection order, I' i Representing the reflected light intensity of the secondary light source generated by the ith LED light source and directly irradiating the P point of the wall surface, I i Representing the illumination intensity of the secondary light source generated by the ith LED light source and directly irradiating the P point of the wall surface, wherein the coordinate of the P point is P (X 1 ,Y 1 ,Z 1 ) K is the reflection coefficient of the wall surface, and beta represents the emission angle of the secondary light source; e is the illuminance of any M LED light sources received by the jth Photoelectric Detector (PD), E j E 'is the direct horizontal illuminance of the jth PD under the multi-LED light source' j The reflected illuminance of the jth PD under the multi-level light source;representing the incident angle of the direct light source received by the jth PD, the jth PD has coordinates (x) j ,y j 0), the coordinates of the ith LED are (X i ,Y i ,Z i )，M is the total number of LEDs.
3. The method for indoor positioning of visible light based on spectrum estimation detection according to claim 1, wherein in step 4, a Pisarenko harmonic decomposition method is adopted to separate multiple light source signals, so as to obtain power values of different light source signals.
4. The indoor positioning method based on spectrum estimation detection according to claim 1, wherein at the PD receiving end, the method is first according toCalculating vector e i ，f i The time domain frequency of the modulated signal generated for the ith LED light source is then determined for vector e i Performing DTFT to obtain->Then calculate +.>
Wherein, at the PD receiving end, the time domain frequency f of the emission signal loaded by the ith LED light source i The method is calculated by the following steps:
when M LED lamps are driven by signals with different frequencies at the same time, the modulation signal x generated by the ith LED light source i The root of the Z-transformation of (n) is determined by equation (12):
wherein,is z i Complex conjugate of (2); a, a 0 ＝1，a i ＝a 2M-i ,i＝0,1,...,M；
The differential equation corresponding to equation (12) is:
wherein x is i (n-i) is X i The independent variable n of (n) delays the delay signal by i units, and n-i represents that the independent variable n is delayed by i units;
z-transforming the left and right sides of the formula (13) simultaneously to obtain a modulation signal x generated by the ith LED light source i Root Z of Z transform of (n) i ；
Finally, the time domain frequency f of the emission signal loaded by the ith LED light source is obtained through the following formula i ：
Wherein Re (z) i ) Representing z i Of (2), im (z) i ) Representing z i Is a virtual part of (c).
5. The method for indoor positioning in visible light based on spectrum estimation detection as claimed in claim 4, wherein x is i Signal intensity a of (n) i Is determined by the following process:
selecting a plurality of positioning points in the positioning area, and receiving signals received by a receiving end under the interference of a visible light channel, wherein the signals are as follows:
where y (n) is the observed signal received by the PD and containing white noise e (n), H (0) is the optical channel DC gain,is the total noise variance;
will beSubstituting into formula (13), obtain:
wherein y (n-i) is a delay signal for delaying an argument n of y (n) by i units, and e (n-i) is a delay signal for delaying an argument n of e (n) by i units;
writing formula (15) into matrix form to obtain
Y T A＝E T A (16)
Wherein:
taking the mathematical expectation from both sides of the left multiplication vector Y of the formula (16) to obtain E { YY ] T The } is:
wherein R is Y Is the autocorrelation matrix of the received observed signal, R y (i) Representing signal x i The result of the autocorrelation operation of (n);
wherein,is the autocorrelation matrix R of the observed signal set { y (n) } Y Eigenvalue lambda of i And coefficient vector A of the characteristic polynomial is corresponding to the characteristic value lambda i Is a feature vector of (1);
for R Y Performing dimension reduction treatment, namely:
solving the characteristic polynomial in the formula (20), and then obtaining the coefficient vector A by the formula (19), namely obtaining x i Signal intensity a of (n) i 。
6. The method for indoor positioning of visible light based on spectrum estimation detection according to any one of claims 1 to 5, wherein in step 5, the constructed indoor positioning neural network model of visible light is a BP neural network, the input of the BP neural network is a power matrix P of a multi-light source signal obtained based on spectrum estimation detection, and the output is the relative coordinates of an unknown positioning point;
the BP neural network comprises an input layer, an output layer and at least one hidden layer, wherein the input layer is composed of M neurons, and the output layer is composed of three neurons.
7. The method for indoor positioning of visible light based on spectrum estimation detection according to any one of claims 1 to 5, wherein when the indoor positioning neural network model of visible light is constructed and trained in step 5, the excitation function is a monopole S-type function, and the expression is:
wherein,coefficients that are unipolar sigmoid functions.
8. Visible light indoor positioning system based on spectral estimation detects, including a plurality of LED lamps and photoelectric detector, its characterized in that still includes:
a memory for storing instructions executable by the processor;
a processor for executing the instructions to implement the method of any one of claims 1 to 7.
9. A computer readable medium, characterized in that a computer program code is stored, which, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210965366.7A CN115333624B (en) | 2022-08-12 | 2022-08-12 | Visible light indoor positioning method, system and computer readable medium based on spectrum estimation detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210965366.7A CN115333624B (en) | 2022-08-12 | 2022-08-12 | Visible light indoor positioning method, system and computer readable medium based on spectrum estimation detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115333624A CN115333624A (en) | 2022-11-11 |
| CN115333624B true CN115333624B (en) | 2024-04-12 |
Family
ID=83924593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210965366.7A Active CN115333624B (en) | 2022-08-12 | 2022-08-12 | Visible light indoor positioning method, system and computer readable medium based on spectrum estimation detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115333624B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732537A (en) * | 2018-05-08 | 2018-11-02 | 北京理工大学 | A kind of indoor visible light localization method based on neural network and received signal strength |
| CN111090074A (en) * | 2019-12-23 | 2020-05-01 | 武汉邮电科学研究院有限公司 | Indoor visible light positioning method and equipment based on machine learning |
| CN111664853A (en) * | 2020-06-22 | 2020-09-15 | 北京大学 | Linear regression model-based NLOS interference-resistant visible light positioning method and system |
| CN112468954A (en) * | 2020-11-03 | 2021-03-09 | 西安工业大学 | Visible light indoor stereo positioning method based on neural network |
| CN113709661A (en) * | 2021-07-30 | 2021-11-26 | 西安交通大学 | Single-site indoor hybrid positioning method and system based on LOS (line of Signaling) identification |
-
2022
- 2022-08-12 CN CN202210965366.7A patent/CN115333624B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732537A (en) * | 2018-05-08 | 2018-11-02 | 北京理工大学 | A kind of indoor visible light localization method based on neural network and received signal strength |
| CN111090074A (en) * | 2019-12-23 | 2020-05-01 | 武汉邮电科学研究院有限公司 | Indoor visible light positioning method and equipment based on machine learning |
| CN111664853A (en) * | 2020-06-22 | 2020-09-15 | 北京大学 | Linear regression model-based NLOS interference-resistant visible light positioning method and system |
| CN112468954A (en) * | 2020-11-03 | 2021-03-09 | 西安工业大学 | Visible light indoor stereo positioning method based on neural network |
| CN113709661A (en) * | 2021-07-30 | 2021-11-26 | 西安交通大学 | Single-site indoor hybrid positioning method and system based on LOS (line of Signaling) identification |
Non-Patent Citations (4)
| Title |
|---|
| 基于WiFi信道状态信息的室内定位跟踪技术研究;张凌雁;中国博士学位论文全文数据库信息科技辑;全文 * |
| 基于神经网络的可见光室内立体定位研究;赵黎等;中国激光;全文 * |
| 基于采用天牛须搜索算法优化神经网络的可见光室内定位方法;赵黎等;光通信技术;全文 * |
| 多照明区域协作的室内可见光定位;王旭东等;光电子・激光;20170415;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115333624A (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107181543B (en) | Three-dimensional indoor passive positioning method based on propagation model and position fingerprint | |
| CN106093852A (en) | A kind of method improving WiFi fingerprint location precision and efficiency | |
| CN105430740B (en) | Indoor wireless positioning method based on WiFi signal Strength Simulation Yu location fingerprint algorithm | |
| CN108924756A (en) | Indoor orientation method based on WiFi double frequency-band | |
| Aranda et al. | Performance analysis of fingerprinting indoor positioning methods with BLE | |
| Finstad et al. | Fast parameter estimation of binary mergers for multimessenger follow-up | |
| CN104540221A (en) | WLAN indoor positioning method based on semi-supervised SDE algorithm | |
| CN106970379A (en) | Based on distance-measuring and positioning method of the Taylor series expansion to indoor objects | |
| CN111624551A (en) | Positioning method, device and system based on visible light communication | |
| Luo et al. | A space-frequency joint detection and tracking method for line-spectrum components of underwater acoustic signals | |
| Jacobson et al. | Using the world wide lightning location network (WWLLN) to study very low frequency transmission in the earth-ionosphere waveguide: 1. Comparison with a full-wave model | |
| Zhou et al. | Decomposition of LF resultant waves with multipropagation modes in the Earth-ionosphere waveguide | |
| CN115333624B (en) | Visible light indoor positioning method, system and computer readable medium based on spectrum estimation detection | |
| CN113591760A (en) | Far-field multi-human-body gait monitoring method based on millimeter waves | |
| CN113219408A (en) | Improved RBF neural network indoor visible light positioning method and system | |
| Ehrman et al. | Automated target recognition using passive radar and coordinated flight models | |
| CN116930963A (en) | Through-wall imaging method based on wireless communication system | |
| CN116466335A (en) | Indoor visible light positioning method and system based on clustering and deep neural network | |
| Arsan | Accurate indoor positioning with ultra-wide band sensors | |
| Chakraborty et al. | On estimating the location and the 3-d shape of an object in an indoor environment using visible light | |
| CN113271542B (en) | Indoor mobile terminal positioning method based on Bluetooth and visible light | |
| Farid et al. | A WLAN fingerprinting based indoor localization technique via artificial neural network | |
| CN108646212A (en) | Relative fingerprint positioning method based on data purification under condition of unknown transmitting power | |
| Heidari | A testbed for real-time performance evaluation of RSS-based indoor geolocation systems in laboratory environment | |
| CN111239682B (en) | Electromagnetic emission source positioning system and method |
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 |