CN108548545A - A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi - Google Patents
A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi Download PDFInfo
- Publication number
- CN108548545A CN108548545A CN201810574110.7A CN201810574110A CN108548545A CN 108548545 A CN108548545 A CN 108548545A CN 201810574110 A CN201810574110 A CN 201810574110A CN 108548545 A CN108548545 A CN 108548545A
- Authority
- CN
- China
- Prior art keywords
- signal
- csi
- people
- commercial
- contact
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C22/00—Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
- G01C22/006—Pedometers
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The non-contact more people's step-recording methods and system, method that the invention discloses a kind of based on commercial Wi Fi include the following steps：The CSI signals of participant are acquired by commercial Wi Fi；The sum of the mean absolute deviation that d (t) is all amplitude datas in a time slide window is defined, the noise level N (t) in the t periods is sought according to d (t), noise signal is screened out from CSI signals；The static component that each subcarrier in CSI signals is rejected by your filter of Han Consulting, other noises are further removed using Sa Weiciji Grays filter；Tensor resolution is introduced, by signal decomposition and signal fused, the running signal that single people generates is obtained, everyone step number is estimated by wave crest monitoring again later.System includes：The receiving terminal of microprocessor, the transmitting terminal of Wi Fi and Wi Fi.
Description
Technical field
The present invention relates to computer networks, are related specifically to feature extraction, and Data Mining more particularly to one kind are based on
The non-contact more people's step-recording methods and system of commercial Wi-Fi.
Background technology
With the development of wireless technology, wireless signal can be not only used for transmission data, can also be used to perceive environment,
Direct projection, reflection and scattering occurs on the wireless signal of WiFi equipment generation object different around under indoor environment, finally arrives
Up to receiving device, therefore wireless signal carries the information of ambient enviroment.
By establishing the relationship of the wave character of channel state information and goal task in receiving device physical layer, Ke Yijin
Row indoor positioning, Activity recognition, security monitoring and medical monitoring etc..Previous Activity recognition system, they are generally using photograph
Camera, wearable sensor and software radio carry out pursuit movement information, although these equipment captures action is accurate
Degree is high, but expensive, and universality is low.
Other systems then utilize the method for machine learning to CSI (the Channel State in commercial WiFi equipment
Information radio channel status informations) signal is trained, finally corelation behaviour is identified using model, but model
Not only time consumption for training, and it is larger to the dependence of feature, so the use of trained method being difficult to develop lightweight, and be good for
Strong user interface.
The present invention will use conventional commercial Wi-Fi equipment to carry out step number estimation, it is cheap, and universality is high；In skill
Unsupervised method will be used to estimate the step number of more people's movements in art, it efficiently, and is not necessarily to training.
Invention content
The present invention provides a kind of non-contact more people's step-recording methods based on commercial Wi-Fi, the present invention use a series of letters
Number processing handles Wi-Fi signal with data mining technology, and multiple people can be carried out using conventional Wi-Fi equipment by realizing
Meter step, it is described below：1, a kind of non-contact more people's step-recording methods based on commercial Wi-Fi, the method includes following steps
Suddenly：
The CSI signals of participant are acquired by commercial Wi-Fi；
The sum of the mean absolute deviation that d (t) is all amplitude datas in a time slide window is defined, is asked according to d (t)
The noise level N (t) in the t periods is taken, noise signal is screened out from CSI signals；
The static component that each subcarrier in CSI signals is rejected by your filter of Han Consulting, is filtered using Sa Weiciji-Gray
Wave device further removes other noises；
Tensor resolution is introduced, by signal decomposition and signal fused, the running signal that single people generates is obtained, leads to again later
Wave crest monitoring is crossed to estimate everyone step number.
It is described
Wherein, ap(n) indicate that the data packet index corresponding to subcarrier p is the amplitude at n, P is sub-carrier indices
Maximum value (being herein 90), N are the set of all data packet indexes in sliding window, and L is the length of sliding window, and E is sliding
The mean value of all data packet amplitudes in window.
The method is extended to CSI using the method for Hunk thatization by the CSI amplitude matrixs obtained after other noises are removed
Tensor.
The signal fused is specially：
Reinforce decompositing the periodicity of the signal come using auto-correlation；
Carry out the similitude of metric signal between any two using average Fu Leixie distances, average Fu Leixie distances consider simultaneously
Position along the point of curve and sequence, it can identify the offset in autocorrelation signal, be very suitable between measurement curve
Similarity；
It is module come to each using the friendly matching algorithm of stable house using the Fu Leixie distances between autocorrelation signal
The decomposed signal that people generates is matched two-by-two；
Finally, two similar signals are permeated signal in a manner of being averaged, takes average one side that can drop
On the other hand the deviation of low decomposed signal can ensure that the fusion of signal carries out under the same time.
A kind of non-contact more people's step counting systems based on commercial Wi-Fi, the system comprises：The hair of microprocessor, WiFi
End and the receiving terminal of WiFi are penetrated,
The transmitting terminal and receiving terminal of the WiFi is put on the ground, and transmitting terminal and receiving terminal are point-blank；
It collects on the receive side after completing CSI data, CSI data are sent to microprocessor by receiving terminal by ICP/IP protocol
On device, microprocessor handles CSI data by MATLAB；
That is, rejecting the static component of each subcarrier in CSI signals by your filter of Han Consulting, Sa Weiciji-lattice are used
Thunder filter further removes other noises；
Tensor resolution is introduced, by signal decomposition and signal fused, the running signal that single people generates is obtained, leads to again later
Wave crest monitoring is crossed to estimate everyone step number.
The advantageous effect of technical solution provided by the invention is：
1, the present invention can be realized indoor more people using conventional Wi-Fi equipment and count step, and cheap and universality is high.
2, data processing method proposed by the present invention, can be used for other field, have good versatility；The present invention
New approaches, new concept are provided for the exploitation of immersion game station.
3, on the one hand the meaning of meter step is the action of specification running in place, on the other hand can increase running in place itself
Interest, body-building is become into a kind of amusement game, for example, can in advance to use the system that the present invention designs carry out the time and
Step number is set, and then completes scheduled step number at the appointed time, white-collar job person can be played in office game in 3 minutes with
It releives pressure, kinsfolk can usually carry out the match of jog in place step number to promote emotion using the scrappy time.
4, it is contemplated that the present invention may be use with medical rehabilitation, such as：Patient does quantitative movement daily, to reach the mesh of rehabilitation
's.
Description of the drawings
Fig. 1 is a kind of flow chart of non-contact more people's step-recording methods based on commercial Wi-Fi；
Fig. 2 is the front and back schematic diagram compared of CSI amplitudes noise reduction；
Wherein, (a) is CSI original signals；(b) it is the signal after CSI noise reductions.
Fig. 3 is the result schematic diagram that CP is decomposed；
Fig. 4 is the result schematic diagram of signal fused；
Fig. 5 is system construction drawing.
Specific implementation mode
To make the object, technical solutions and advantages of the present invention clearer, embodiment of the present invention is made below further
It is described in detail on ground.
Embodiment 1
A kind of non-contact more people's step-recording methods based on commercial Wi-Fi, referring to Fig. 1, this approach includes the following steps：
101：The CSI signals of participant are acquired by commercial Wi-Fi；
102：The sum of the mean absolute deviation that d (t) is all amplitude datas in a time slide window is defined, according to d
(t) the noise level N (t) in the t periods is sought, noise signal is screened out from CSI signals；
103：The static component that each subcarrier in CSI signals is rejected by your filter of Han Consulting, uses Sa Weiciji-lattice
Thunder filter further removes other noises；
104：Tensor resolution is introduced, by signal decomposition and signal fused, obtains the running signal that single people generates, later
Everyone step number is estimated by wave crest monitoring again.
Wherein, described in step 102：
Wherein, ap(n) indicate that the data packet index corresponding to subcarrier p is the amplitude at n, P is sub-carrier indices
Maximum value (being herein 90), N are the set of all data packet indexes in sliding window, and L is the length of sliding window, and E is sliding
The mean value of all data packet amplitudes in window.
Further, this method is expanded using the method for Hunk thatization by the CSI amplitude matrixs obtained after other noises are removed
Exhibition is CSI tensors.
Wherein, the signal fused is specially：
Reinforce decompositing the periodicity of the signal come using auto-correlation；
Carry out the similitude of metric signal between any two using average Fu Leixie distances, average Fu Leixie distances consider simultaneously
Position along the point of curve and sequence, it can identify the offset in autocorrelation signal, be very suitable between measurement curve
Similarity；
It is module come to each using the friendly matching algorithm of stable house using the Fu Leixie distances between autocorrelation signal
The decomposed signal that people generates is matched two-by-two；
Finally, two similar signals are permeated signal in a manner of being averaged, takes average one side that can drop
On the other hand the deviation of low decomposed signal can ensure that the fusion of signal carries out under the same time.
In conclusion the embodiment of the present invention is handled using a series of signal handles Wi-Fi signal with data mining technology,
Meter step can be carried out using conventional Wi-Fi equipment to multiple people by realizing.
Embodiment 2
The embodiment of the present invention proposes a kind of non-contact more people's step-recording methods based on commercial Wi-Fi, referring to Fig. 1, the party
Method includes the following steps：
One, motion detection
Amplitude information is extracted from the WiFi signal collected first, then needs monitoring to jog and whether starts.In reality
It is observed that the fluctuation of the time series of CSI signals caused by people's movement is bigger than background noise, in order to measure during testing
Change this fluctuation, defines the sum of the mean absolute deviation that d (t) is all amplitude datas in a time slide window：
Wherein, ap(n) indicate that the data packet index corresponding to subcarrier p is the amplitude at n, P is sub-carrier indices
Maximum value (being herein 90), N are the set of all data packet indexes in sliding window, and L is the length of sliding window, and E is sliding
The mean value of all data packet amplitudes in window.
Due to when indoor nobody moves, the fluctuation of CSI signals is mainly caused by noise, and noise level with
Time is slowly varying, so tracking the variation of noise level using the algorithm of dynamic threshold.
First, the mean absolute deviation d (t) in a time slide window, the embodiment of the present invention are calculated according to formula (1)
The time slide window used is 200 sampled points, and about 0.2s uses index sliding average in this time slide window
To update the noise level N (t) in the t periods：
N (t)=(1- αn)N(t-1)+αn×d(t) (2)
Wherein, αnFor constant coefficient.
Herein, factor alpha is arranged in the embodiment of the present inventionnIt is 0.15.Once or terminate movement when, the time of CSI signals
Violent fluctuation can occur at this moment for sequence, and in addition combined with experimental data, it is noise that monitor value, which is arranged, in the embodiment of the present invention
At 3 times of horizontal updated value N ' (t), it is believed that jogging starts, and and then the embodiment of the present invention can carry out at noise reduction data
Reason.
Two, Noise reducing of data
The CSI data packets obtained from commercial WiFi equipment contain static component, low-frequency disturbance and pulse noise, a side
Face is asynchronous by clock, caused by the interference of radio wave and the variation of transmitting terminal transmission power, on the other hand, in actual rings
In border, people, due to the shake of parts of body, can also make to be mixed into different degrees of low frequency in CSI data and make an uproar during jogging
The extraction for existing for motion feature of sound and high frequency noise, these noises increases difficulty, in addition, being needed to more in subsequent step
People's signal matches, and the process is very sensitive for noise, this requirement will not only be effectively removed noise, but also be wanted after denoising
Waveform is maintained not to be changed as far as possible, traditional IIR (infinite impulse response) low-pass filtering can not after the filtering very well
Maintenance waveform it is constant, herein and be not suitable for, since pulse noise band is roomy in CSI data, energy is high, so bandpass filtering
Noise can not be effectively removed.
In order to solve these problems, the embodiment of the present invention is picked using Hampel Filter (Han Consulting's that filter) first
Except the static component of each subcarrier in CSI data specifically can be divided into following two step：
1) big window is set, and the Hampel Filter of small threshold value obtain the static component of each subcarrier；
Wherein, big window is set, and the concrete operation step of the Hampel Filter of small threshold value is those skilled in the art institute
Known, the embodiment of the present invention does not repeat this.
2) above-mentioned static component is subtracted in original CSI data；Then, using Savizky-Golay filter (Sas
Wei Ciji-Gray's filter) further remove other noises；
Wherein, Savizky-Golay filter be it is a kind of in time domain based on Local Polynomial least square fitting
The step of filtering method can keep CSI amplitude signal waveforms not to be changed while removing noise, specific filtering is this
Well known to field technology personnel, the embodiment of the present invention does not repeat this.
When specific implementation, it can also realize that above-mentioned step, the present invention are real using other filters or filtering method
It is without limitation to apply example.
Three, more people's signal extractions
And the extraction for signal of running for more people, since CSI signals are influenced by multiple people's self-movements simultaneously, first because
Son analysis obviously can not isolate the running signal of each individual, secondly multiple people's running on spot from the mixed signal that more people run
When step, the frequency of leg comes from multiple people, and time-frequency conversion can not also detach the motion frequency of multiple people's legs under same time point,
In order to which the running signal and further fine granularity of isolating each individual from the CSI amplitude informations that multiple people's running in place generate are carved
The movement details of leg during picture running in place, the method that the embodiment of the present invention introduces tensor resolution, part processing are main
It is divided into two parts：Signal decomposition and signal fused, after tensor resolution, the embodiment of the present invention can obtain single people's generation
Running signal carries out everyone step number estimation later.
1, signal decomposition
A, tensor constructs
After Noise reducing of data, the embodiment of the present invention obtains CSI amplitude matrixs, its dimension is the number of data packet
CSI amplitude matrixs are extended to CSI by × subcarrier number, the method that then embodiment of the present invention utilizes Hankel (Hunk that) to change
The signal of each row subcarrier in CSI amplitude matrixs is tieed up Hankel matrixes by tensor, specifically, the embodiment of the present invention with 2
Storage, such 60 row sub-carrier signal can be formed by the tensor of one 3 dimension, define HrThe subcarrier r structures for being N for signal length
The size made is the Hankel matrixes of I × J, and I, J and N meet condition：I+J-1=N, the I=J=of setting of the embodiment of the present invention here
(N+1)/2, so for subcarrier r, by the way that Hankel matrix Hs as follows after Hankelization, can be constructedr：
Herein, hr(i) it indicates the amplitude that data packet index is i under r-th of subcarrier in Hr matrixes, sets in an experiment
Set N=5000, and I=J=2500.
If theoretical 1, detecting indoors under environment has R running in place signal, ignore in other interference
Under the conditions of, Hankel matrix Hs that subcarrier r is constructedrCorresponding order is 2R.
It proves：When analyzing the data structure of jog in place leg signal, it is assumed that noise is ignored, i-th people's
Leg signal can be expressed as：The signal observed from each subcarrier can be expressed as：
Here KiThe coefficient of leg signal when being i-th of people's jog in place, whereinI-th of people's in Y (t)
Leg walks signalIt can further be decomposed, then had using Euler's formula：
Each leg signal can be independently split as two exponential signals with different parameters.For R leg
Signal has：
Herein, new signalIts coefficientFor being received in discrete time
The data packet arrived can be used and receive signalTo indicate.Notice that Y (n) is considered by 2R difference
The exponential polynomials of exponential term composition, n=1,2,3 ..., N here, Y (n), which is mapped as size, isHankel squares
Battle array, therefore have：
Know that Hankel matrixes can carry out Vandermode (vandermonde is special) and decompose, i.e.,：
Vandermode matrixes hereinAnd
Since Vandermonde (vandermonde is special) matrix is made of different series, it is full rank, so
Hankel ranks of matrix are 2R.
Need to isolate the leg signal of R running in place according to 1,2R signal component of theory.Next, considering noise
For Hankel matrix HsrInfluence, due to the influence of noise, Hankel matrix HsrIt is full rank in fact, but theory 1 shows Hr
Order be 2R, it means that as long as the signal-to-noise ratio of signal is not too low, the decomposition ingredient of first 2R weight is than remaining ingredient
It is more healthy and stronger.This also indicates that the structure of Hankel matrixes can effectively detach running in place signal from white noise, true
Upper to pass through tensor resolution, different signals can be by good noise reduction and separation.The follow-up present invention can carry out CP decomposition to tensor
To extract the jogging signal of multiple people.
2, CP is decomposed
After CSI tensor construction completes, the running signal of multiple people is estimated using CP decomposition, according to theory 1, really
The number for determining CSI tensor resolution ingredients is 2R, carries out CP decomposition to tensor using alternating least-squares, CP can after the completion of decomposing
To obtain 2R 1 tensor of order, 1 tensor of each order is made of 3 vectorial appositions, and 3 × 2R vector is formed 3 matrix difference
It is represented with A, B, C, in order to ensure to decompose the validity of ingredient, next can prove the uniqueness that CP is decomposed, be decomposed about CP
Uniqueness, its basic theories are as follows：
The fact 1：For the tensor χ that order is L, if kA+kB+kC>=2L+2, then the CP decomposition of tensor χ is unique.Herein
kA、kBAnd kCMatrix A, B and the C that order is k are respectively represented, order is the very big of the file for the Line independent that k indicates a matrix here
Number is k.
There is following theory for the CSI tensors of establishment based on the above fact：
Theory 2：The CP decomposition for CSI the tensor χ, tensor χ that order for establishment is 2R is unique.
It proves：CSI tensor χ are created using K Hankel matrix, according to theory 1, r-th of Hankel matrix HrOrder
It is 2R, for A matrixes and B ranks of matrix kA=2R, kB=2R, on the other hand, since the amplitude data of 60 subcarriers comes from
Two antennas, this two antennas are mutual indepedent, so the order k of Matrix Cc≥2.Therefore expression formula kA+kB+kC>=2R+2R+2=2
(2R)+2 meets the fact 1, it was demonstrated that finish.
Theorem 2 show to the CSI tensors of establishment carry out CP decompose its decomposition the result is that unique, it can be effective
The leg signal of more people's runnings is extracted, system uses matrix A as decomposed signal a1,a2,a3,…,a2R。
3, signal fused
After the CSI tensor data of construction are decomposed by CP, 2R signal, i.e. S can be obtained from A matrixes1,S2,
S3,…,S2R, but their index is random alignment, decomposites the signal come and does not ensure that similar signal is located at phase
Adjacent position devises a kind of Signal Matching algorithm therefore, it is necessary to be matched the signal come is decomposited two-by-two so that belongs to
In same person two similar Signal Matchings in a pair.
First, reinforce decompositing the periodicity of the signal come using auto-correlation, using auto-correlation function it is main there are two
Reason, decomposed signal, which is on the one hand done auto-correlation, can increase data length, promote the accuracy of wave crest detection, on the other hand by
The amplitude signal obtained after being decomposed by CP is offset, and can be reduced this offset by auto-correlation, be increased the week of signal
Phase property.
Second, carry out the similitude of metric signal between any two using average Fr é chet (Fu Leixie) distance, average Fr é
Chet distances consider position and the sequence of the point along curve simultaneously, it can identify the offset in autocorrelation signal, very
The similarity being suitble between measurement curve, it is usually more preferable than famous Hausdorff (this bold and unconstrained Dorr) distance.
Third, using Stable Roommate Matching (stable house friend matching algorithm) between autocorrelation signal
Fr é chet distances matched two-by-two come the decomposed signal generated to everyone for module.Finally, similar by two
Signal is permeated signal in a manner of being averaged, and takes average one side that can reduce the deviation of decomposed signal, on the other hand
It can ensure that the fusion of signal carries out under the same time.
4, wave crest monitors
List leg is raised to fall and be passed through when interval time jogs with normal person between step when only needing to jog based on normal person
The time gone through constrains wave crest (trough) spacing and wave crest (trough) width, and in fact due to the use of Hankel
Matrix and CP, which are decomposed, carrys out smooth motion curve, so seldom including spurious peaks, of last legal wave crest and trough in curve
Number is the estimated value of everyone step number.
Embodiment 3
Below in conjunction with the accompanying drawings in the embodiment of the present invention 1 and 2 effect and effect be shown.
This example provides the embodiment of invention for based on CSI data processings, is as follows：
Using a laptop as WiFi access points, i.e. transmitting terminal, another laptop as receiving terminal,
Two notebooks have been respectively mounted Intel 5300NIC and Ubuntu 14.04LTS desktop edition systems, and receiving terminal has 3 antennas, hair
Penetrating end has 3 antennas, and it is a wavelength (5.2cm) often to hold the distance between 3 antennas, and on straight line, WiFi
Transmitting terminal and receiving terminal put on the ground, for the two at a distance of 3m, the transmission rate of data packet is 1024HZ, transmitting terminal and receiving terminal
Point-blank, the link of transmission is operated on 165 channels that frequency range is 5.825GHz, and the embodiment of the present invention selects 5GHz's
Frequency range without select 2.4GHz frequency range the reason of be 5GHz frequency ranges wavelength it is shorter, short wavelength has higher point to movement velocity
Resolution.After using Linux CSI tool to collect and complete CSI data on the receive side, receiving terminal is by ICP/IP protocol by CSI
Data, which are sent to, to be configured on Intel i7-5600U 2.6GHz computers, and CSI data are handled finally by MATLAB.
When the present invention proceeds by monitoring to activity first, according to formula (2), once monitor that activity starts, it will be right
Data carry out noise reduction process.
Fig. 2 presents an example of Noise reducing of data, before and after 30 sub-carrier amplitude Noise reducing of data of CSI
Waveform can be seen that original CSI amplitude datas and contain there are many high frequency noise and static component, use it is proposed that noise reduction
After method, static component is removed efficiently with most of noise, in addition from the whole shape of signal, width and flat
In terms of slippage degree, illustrates our noise-reduction method, not only effectively remove the noise in CSI amplitude datas, while can also
Preferably maintain the waveform of original CSI amplitude datas.In next processing, which will be used in carrying for single signal
It takes.
After the completion of noise reduction, to the data configuration tensor after noise reduction, the technical detail of tensor construction refers to technical solution A tensors
Construct part.Then CSI tensors are decomposed using CP decomposition.The component number of decomposition is the number for people.
Fig. 3 shows that the CSI tensors comprising 3 people (R=3) are after CP is decomposed as a result, of the invention real in order to embody
The accuracy of the method for example design is applied, during the experiment, 3 experimenters of purposive arrangement, the first original place is slowly stepped on
It walks, second normal jog in place of people, third individual's fast speed running in place, as can see from Figure 46 signals, Ke Yifen
It it is 3 groups, first group is signal 1 and signal 3, and second group is signal 2 and signal 6, and third group is signal 4 and signal 5.
First it is observed that first group of signal wave crest is the most sparse, second group of signal is more compared with first group of signal wave crest
Intensive, third group signal wave crest is the most intensive, this is because the cadence difference of 3 experimenters causes.Secondly, it can also be observed that
Similar signal is not on adjacent position, this is because the signal index that CP decomposes output is random, therefore subsequently needs
Identify similar signal, and the signal of permeating indicates the running in place signal of a people.
Signal fused is carried out later.Fig. 4 shows the fusion results of the signal after the above processing step, it can be seen that obtains
The motion feature that 3 signals indicate leg when the running in place of 3 people was obtained, by taking the 3rd experimenter as an example, system is starting to estimate
When counting step number, tester's one leg first leaves ground, and peak is reached in 0.12s, then starts to fall, in 0.31s
When, ground is fallen back to, then another leg lifts, and reaches peak when 0.40s, and when 0.62s falls back to ground, thus complete
At 2 steps, it can be seen that the method for design of the embodiment of the present invention, the not only careful variation of leg signal when featuring running in place
Feature, and achieved the purpose that estimate step number.
Wave crest after fusion is counted, as everyone step number.
Embodiment 4
A kind of non-contact more people's step counting systems based on commercial Wi-Fi, referring to Fig. 5, which includes：Microprocessor, hair
Penetrate end and receiving terminal.
Herein a kind of immersing for similar cool run has been designed and Implemented using not modified business WiFi equipment for the first time
Formula games system, it can carry out more people and count step, and system includes two WiFi equipments, and an equipment (such as router) persistently emits
Wireless signal, another equipment (such as laptop) constantly receive wireless signal, and when game starts, participant is firstly the need of body
Body is upright, and both feet are opened with shoulder with width, and both arms are naturally drooped in body both sides.Then one leg is bent, and foot is raised up to knee
Highly.Homonymy arm swing backward, offside arm are swung forward.Another one leg is slight curving, and foot stays on the ground, and weight concentrates on
Toe.Then the leg lifted is put back into initial position, then lifts another one leg, repeat the above action, both sides are alternately repeated action
To recommendation step number.During participant plays, WiFi signal is reflected by participant generates unique, fluctuation change
The CSI signals of change, in receiving terminal since WiFi signal is influenced by multipath effect, so system can utilize signal processing technology
To obtain the step number for estimating multiple participant's jog in place.
To the model of each device in addition to doing specified otherwise, the model of other devices is not limited the embodiment of the present invention,
As long as the device of above-mentioned function can be completed.
It will be appreciated by those skilled in the art that attached drawing is the schematic diagram of a preferred embodiment, the embodiments of the present invention
Serial number is for illustration only, can not represent the quality of embodiment.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Claims (5)
1. a kind of non-contact more people's step-recording methods based on commercial Wi-Fi, which is characterized in that the described method comprises the following steps：
The CSI signals of participant are acquired by commercial Wi-Fi；
The sum of the mean absolute deviation that d (t) is all amplitude datas in a time slide window is defined, t is sought according to d (t)
Noise level N (t) in period screens out noise signal from CSI signals；
The static component that each subcarrier in CSI signals is rejected by your filter of Han Consulting, uses Sa Weiciji-Gray's filter
Further remove other noises；
Tensor resolution is introduced, by signal decomposition and signal fused, the running signal that single people generates is obtained, passes through wave again later
Everyone step number is estimated in peak monitoring.
2. a kind of non-contact more people's step-recording methods based on commercial Wi-Fi according to claim 1, which is characterized in that institute
It states
Wherein, ap(n) indicate that the data packet index corresponding to subcarrier p is the amplitude at n, P is the maximum value of sub-carrier indices
(being herein 90), N are the set of all data packet indexes in sliding window, and L is the length of sliding window, and E is in sliding window
All data packet amplitudes mean value.
3. a kind of non-contact more people's step-recording methods based on commercial Wi-Fi according to claim 1, which is characterized in that institute
It states method and is extended to CSI tensors by the CSI amplitude matrixs obtained after other noises are removed using the method for Hunk thatization.
4. a kind of non-contact more people's step-recording methods based on commercial Wi-Fi according to claim 1, which is characterized in that institute
Stating signal fused is specially：
Reinforce decompositing the periodicity of the signal come using auto-correlation；
Carry out the similitude of metric signal between any two using average Fu Leixie distances, average Fu Leixie distances consider simultaneously along
The position of the point of curve and sequence, it can identify the offset in autocorrelation signal, be very suitable for measurement curve between it is similar
Degree；
Everyone is produced as module using the friendly matching algorithm of stable house using the Fu Leixie distances between autocorrelation signal
Raw decomposed signal is matched two-by-two；
Finally, two similar signals are permeated signal in a manner of being averaged, takes average one side that can reduce point
The deviation for solving signal, on the other hand can ensure that the fusion of signal carries out under the same time.
5. a kind of non-contact more people's step counting systems based on commercial Wi-Fi, which is characterized in that the system comprises：Microprocessor,
The transmitting terminal of WiFi and the receiving terminal of WiFi,
The transmitting terminal and receiving terminal of the WiFi is put on the ground, and transmitting terminal and receiving terminal are point-blank；
It collects on the receive side after completing CSI data, CSI data are sent to microprocessor by receiving terminal by ICP/IP protocol
On, microprocessor handles CSI data by MATLAB；
That is, rejecting the static component of each subcarrier in CSI signals by your filter of Han Consulting, filtered using Sa Weiciji-Gray
Wave device further removes other noises；
Tensor resolution is introduced, by signal decomposition and signal fused, the running signal that single people generates is obtained, passes through wave again later
Everyone step number is estimated in peak monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574110.7A CN108548545A (en) | 2018-06-06 | 2018-06-06 | A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574110.7A CN108548545A (en) | 2018-06-06 | 2018-06-06 | A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108548545A true CN108548545A (en) | 2018-09-18 |
Family
ID=63492518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810574110.7A Pending CN108548545A (en) | 2018-06-06 | 2018-06-06 | A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108548545A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105844216A (en) * | 2016-03-11 | 2016-08-10 | 南京航空航天大学 | Detection and matching mechanism for recognition of handwritten letters using WiFi signals |
| CN105873212A (en) * | 2016-05-16 | 2016-08-17 | 南京邮电大学 | Indoor-environment-person detection method based on channel state information |
| CN106323330A (en) * | 2016-08-15 | 2017-01-11 | 中国科学技术大学苏州研究院 | Non-contact-type step count method based on WiFi motion recognition system |
-
2018
- 2018-06-06 CN CN201810574110.7A patent/CN108548545A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105844216A (en) * | 2016-03-11 | 2016-08-10 | 南京航空航天大学 | Detection and matching mechanism for recognition of handwritten letters using WiFi signals |
| CN105873212A (en) * | 2016-05-16 | 2016-08-17 | 南京邮电大学 | Indoor-environment-person detection method based on channel state information |
| CN106323330A (en) * | 2016-08-15 | 2017-01-11 | 中国科学技术大学苏州研究院 | Non-contact-type step count method based on WiFi motion recognition system |
Non-Patent Citations (1)
| Title |
|---|
| XUYU WANG: ""TensorBeat: Tensor Decomposition for Monitoring Multiperson Breathing Beats with Commodity WiFi"", 《ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mortazavi et al. | Determining the single best axis for exercise repetition recognition and counting on smartwatches | |
| CN106066995B (en) | A kind of wireless unbundling human body behavioral value algorithm | |
| Shoaib et al. | A hierarchical lazy smoking detection algorithm using smartwatch sensors | |
| Muehlbauer et al. | What can an arm holster worn smart phone do for activity recognition? | |
| CN107506684A (en) | Gait recognition method and device | |
| CN110168316B (en) | Foot step counting method, device and equipment based on step frequency | |
| CN106170746A (en) | By the mobile property calculation paces of motion and energy expenditure | |
| KR102089002B1 (en) | Method and wearable device for providing feedback on action | |
| JP2016513999A5 (en) | ||
| CN110730473B (en) | WiFi activity recognition-oriented signal feature extraction method | |
| Das et al. | Strength training: A fitness application for indoor based exercise recognition and comfort analysis | |
| CN108489509A (en) | A kind of non-contact single step-recording method and system based on commercial Wi-Fi | |
| CN109740418B (en) | Yoga action identification method based on multiple acceleration sensors | |
| Sen et al. | Did you take a break today? detecting playing foosball using your smartwatch | |
| Bastwesy et al. | Wi-nod: Head nodding recognition by wi-fi csi toward communicative support for quadriplegics | |
| Jakkala et al. | Deep CSI learning for gait biometric sensing and recognition | |
| CN108548545A (en) | A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi | |
| Lisowska et al. | Cross-cohort Evaluation of Machine Learning Approaches to Fall Detection from Accelerometer Data. | |
| CN117179751A (en) | Signal processing method, device, electronic equipment and storage medium | |
| Nguyen-Huu et al. | Smartwatch/Smartphone Cooperative Indoor Lifelogging System. | |
| CN112364770A (en) | Commercial Wi-Fi-based human activity recognition and action quality evaluation method | |
| CN105147249B (en) | The wearable or implantable devices evaluation system of one kind and method | |
| US11426627B2 (en) | Method and apparatus for counting foot step based on acceleration information, and device | |
| CN109497984A (en) | A kind of processing method and relevant device of heart rate signal | |
| Maheedhar et al. | StayFit: A wearable application for Gym based power training |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180918 |
|
| RJ01 | Rejection of invention patent application after publication |