CN106323330A - Non-contact-type step count method based on WiFi motion recognition system - Google Patents
Non-contact-type step count method based on WiFi motion recognition system Download PDFInfo
- Publication number
- CN106323330A CN106323330A CN201610668171.0A CN201610668171A CN106323330A CN 106323330 A CN106323330 A CN 106323330A CN 201610668171 A CN201610668171 A CN 201610668171A CN 106323330 A CN106323330 A CN 106323330A
- Authority
- CN
- China
- Prior art keywords
- wifi
- recognition system
- motion recognition
- subcarrier
- motion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a non-contact type step count method based on a WiFi motion recognition system. The method comprises the steps of obtaining timing sequence CSI amplitude fragment of walking action through the WiFi motion recognition system to obtain Nv subcarriers by processing; conducting wavelet decomposition for action fragments of the Nv subcarriers obtained to obtain detail coefficients of different frequency ranges; screening out the detail coefficients in the frequency ranges which represent CSI amplitude variations caused by foot movement, reconstituting detail signal corresponding to each subcarrier, and calculating short-time energy for reconstituting the signal; screening and calculating effective identify number of crest to obtain stable step number value by calculating with a combination of the statistical results of the Nv subcarriers. The non-contact type step count method based on the WIFI motion recognition system doesn't need to carry any step count device, sensors the influence of foot movement on WiFi signal CSI amplitude when human body walks according to a multipath propagation model of WiFi signal to further calculate the step number of human body walking with a non-contact type and has more stable step calculation results compared with traditional methods.
Description
Technical field
The invention belongs to WiFi perception and indoor positioning technologies field, more particularly to one based on WiFi action recognition skill
Art, the frequency domain character in conjunction with channel condition information (CSI) realizes the method that contactless meter walks.
Background technology
The step-recording method of main flow is mostly based on sensor and vision at present.The most sensor-based step-recording method leads to
Cross acceleration information and the angle change information of gyroscope reading accelerometer in smart machine entrained by human body in real time, identify
People's rhythm characteristic when walking, and realize step function according to threshold value set in advance.Due to people in the process of walking, different
The movement velocity of body part (e.g., waist and leg) and motion amplitude often difference are relatively big, and meter step equipment is placed on body
Body different parts can produce different acceleration and angle change information.Especially, do not stop when meter step equipment is placed in hands
When rocking, rocking action can be identified as action on foot by this kind equipment, will rock number of times and be calculated as step number, in turn results in and " crosses meter
Number ".Therefore, the accuracy of meter step is placed on human body particular location by equipment is affected bigger.It addition, when the speed of travel is the most slow
Slowly, when body kinematics amplitude is less, this type of meter step equipment is difficult to accurately count step.
The method of another kind of view-based access control model is mainly by identifying that people's its foot in walking occurs in photographic head coverage
Step number is recorded with the process disappeared.Although such method overcomes accuracy based on sensor meter step by human body different parts
The shortcoming of motion amplitude impact, but it is affected relatively big by illumination condition, is difficult under dark surrounds running.Photographic head simultaneously
Use the risk that there is individual privacy leakage.Additionally, step-recording method based on sensor and vision is required to during meter step
People carries corresponding hardware device at any time, thus limits the range of application of these step-recording methods to a certain extent.
Along with the development of WiFi cognition technology, utilize WiFi signal carry out passive type personnel's detection, contactless humanbody move
Identify, the application system such as respiration detection and voice eavesdropping emerges in an endless stream.Doppler effect according to wireless signal and multipath effect
Should, in wireless network environment, the people of motion knows from experience the propagation path changing wireless signal so that receive amplitude and the phase of signal
Position changes.Identification and the detection of type games each to human body can be realized by this change of perception.It addition, utilize WiFi to believe
Number channel condition information to carry out indoor positioning be also the focus studied in recent years, step number in indoor positioning be one important
Parameter, research is the most easily and accurately measured step number and is had the highest practical value.
Summary of the invention
For technical problem present in main flow step-recording method, the present invention seeks to: provide a kind of based on WiFi action
The contactless step-recording method of identification system, it is not necessary to user carries any hardware device, the channel condition information to walking motion
CSI amplitude fragment carries out wavelet decomposition, it is thus achieved that the reconstruction signal of the detail coefficients corresponding to foot motion, calculates its short-time energy
And combine the step Numerical that the acquisition of multicarrier result of calculation is stable.
The technical scheme is that
A kind of contactless step-recording method based on WiFi motion recognition system, it is characterised in that comprise the following steps:
S01: obtained the sequential CSI amplitude fragment of walking motion by WiFi motion recognition system, is processed and obtains NvHeight
Carrier wave；
S02: to the N obtainedvThe action fragment of individual subcarrier carries out wavelet decomposition, obtains the details system of different frequency scope
Number；
S03: filter out the detail coefficients representing the CSI amplitude variations place frequency range that foot motion causes, reconstruct is every
The detail signal that individual subcarrier is corresponding, and calculate the short-time energy of reconstruction signal；
S04: screen and add up significant wave peak number, and merge NvThe statistical result of individual subcarrier is calculated stable step number
Value.
Preferably, the sequential CSI amplitude fragment of the walking motion in described step S01 is NsThe matrix of × T dimension, wherein Ns
For subcarrier number, its numerical value is relevant with communication bandwidth and selected sampling instrument, and T is sample points.
Preferably, the process in described step S01 obtains NvIndividual subcarrier includes that the direct current removing this CSI amplitude fragment becomes
Point, filter high-frequency noise, select the N that the variance of each subcarrier is biggervIndividual subcarrier.
Preferably, described step S04 includes that peak height is not less than 2dB by peak width between 500～1000 sampled points,
The interval between adjacent two crests crest not less than 0.5 second is as Valid peak, using Valid peak as step number, by NvIndividual
The meansigma methods of subcarrier gained step number is as step Numerical.
The present invention discloses again a kind of contactless step counting system based on WiFi motion recognition system, it is characterised in that
Including:
Data processing module, at the sequential CSI amplitude fragment of the walking motion that WiFi motion recognition system obtains
Reason, obtains NvIndividual subcarrier；
Wavelet decomposition module, to the N obtainedvThe action fragment of individual subcarrier carries out wavelet decomposition, obtains different frequency model
The detail coefficients enclosed；
Short-time energy computing module, filters out and represents the thin of CSI amplitude variations place frequency range that foot motion causes
Joint coefficient, reconstructs the detail signal that each subcarrier is corresponding, and calculates the short-time energy of reconstruction signal；
Step number statistical module, screens and adds up significant wave peak number, and merge NvThe statistical result of individual subcarrier is calculated
Stable step Numerical.
Preferably, the sequential CSI amplitude fragment of described walking motion is NsThe matrix of × T dimension, wherein NsFor subcarrier
Number, its numerical value is relevant with communication bandwidth and selected sampling instrument, and T is sample points.
Preferably, described data processing module removes the flip-flop of this CSI amplitude fragment, filters the height included in it
Frequently noise, selects the N that the variance of each subcarrier is biggervIndividual subcarrier.
Preferably, described short-time energy computing module carries out windowing process framing to the detail signal of reconstruct, calculates every
The short-time energy of one frame.
Preferably, described step number statistical module is by peak width between 500～1000 sampled points, and peak height is not less than 2dB,
The interval between adjacent two crests crest not less than 0.5 second is as Valid peak, using Valid peak as step number, by NvIndividual
The meansigma methods of subcarrier gained step number is as step Numerical.
Compared with prior art, the invention have the advantage that
(1) need not user and carry any meter step equipment, according to the multipath transmisstion model of WiFi signal, perception human body walking
Time foot motion impact that WiFi signal CSI amplitude is caused, and then calculate human body walking step number in a non-contact manner.
(2) meter step result mainly reflects the motion conditions of foot, is not easily susceptible to the impact at other positions of health, meter step knot
Fruit is more stable than tradition step-recording method, is not likely to produce " crossing counting " phenomenon.
Accompanying drawing explanation
Below in conjunction with the accompanying drawings and embodiment the invention will be further described:
Fig. 1 is the flow chart of the present invention contactless step-recording method based on WiFi motion recognition system；
Fig. 2 is the algorithm flow chart adding up significant wave peak number in the present invention；
Fig. 3 is the walking motion original waveform obtained from WiFi motion recognition system in the embodiment of the present invention；
Fig. 4 is to utilize low pass filter filtered walking motion waveform in the embodiment of the present invention；
Fig. 5 be in the embodiment of the present invention after wavelet decomposition each layer wavelet coefficient；
Fig. 6 is the signal after utilizing the 4th layer of detail coefficients reconstruct in the embodiment of the present invention；
Fig. 7 is the short-time energy result of calculation of reconstruction signal in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with specific embodiment, such scheme is described further.Should be understood that these embodiments are for illustrating
The present invention and be not limited to limit the scope of the present invention.The implementation condition used in embodiment can be done according to the condition of concrete producer
Adjusting further, not marked implementation condition is usually the condition in normal experiment.
Embodiment:
The present invention contactless step counting system based on WiFi motion recognition system mainly includes data processing module, small echo
Decomposing module, short-time energy computing module and step number statistical module, each resume module flow process is as it is shown in figure 1, comprise the following steps:
S01: data processing module obtains the sequential CSI amplitude fragment of walking motion by WiFi motion recognition system, place
Reason, removes the flip-flop of this fragment, filters the high-frequency noise included in it, and select NvThe data of individual subcarrier are used for school
Positive final result；The sequential CSI amplitude fragment of walking motion is a NsThe matrix of × T dimension, wherein NsFor subcarrier number, its
Numerical value is relevant with communication bandwidth and selected sampling instrument；T is sample points.Walking motion fragment is from existing WiFi action
Obtaining in identification system, the sample rate of application claims motion recognition system is not less than 500Hz.
Wave filter selected in data processing module is Butterworth low pass filter, and it can retain by high degree
Detailed information in primary signal, is mainly used in filtering appts or environment the high-frequency noise produced, retains because of human body walking institute
The frequency content caused.It addition, using variance as the selection standard of subcarrier in the present invention, select the N that variance is biggerv(1≤Nv
≤Ns) individual subcarrier carries out subsequent treatment.
S02: the wavelet decomposition module N to obtainingvThe action fragment of individual subcarrier carries out wavelet decomposition, obtains different frequency
The detail coefficients of scope；
Use Daubechies db4 wavelet basis each selected subcarrier is carried out wavelet decomposition, concrete Decomposition order according to
Sample rate determines.Wavelet decomposition purpose is the frequency range isolating the CSI amplitude change caused because of foot motion, thus
Perception foot motion conditions when walking.
S03: short-time energy computing module filters out and represents CSI amplitude variations place frequency range that foot motion causes
Detail coefficients, reconstructs the detail signal that each subcarrier is corresponding, and calculates the short-time energy of reconstruction signal；
Short-time energy computing module has mainly used for reference short-time energy effect in speech analysis, at reconstruction signal in short-term
In energy, each crest can be considered foot for the time being when a course of a step medium velocity is the fastest.
S04: step number statistical module screens and add up significant wave peak number, and merges NvThe statistical result of individual subcarrier calculates
To stable step Numerical.
In view of the existence of external interference, the most all of crest is caused by foot motion, it is therefore desirable to statistics is effectively
Crest.The statistics of Valid peak depends on the screening criterias such as the interval between peak height, peak width and adjacent two peaks.When effectively
After crest is selected, corresponding crest number is step number.N the most at lastvThe meansigma methods of individual subcarrier gained step number is as pin of the present invention
The step Numerical that a certain walking fragment computations is gone out.
The flow chart of the Valid peak filtering algorithm that wherein step number statistical module relates to is as shown in Figure 2.
In data processing module, it is desirable to the sample rate of WiFi motion recognition system is set to 1000Hz, is known by action
The walking motion original waveform that other system obtains is as it is shown on figure 3, can be seen that from original waveform wherein containing a lot of high frequency makes an uproar
Sound.The frequency range that when walking in view of people, foot motion causes typically, between 50～70Hz, is arranged here
Butterworth low pass filter is 80Hz by frequency, thus remains the frequency content that foot motion causes.Filter it
After waveform as shown in Figure 4, wherein majority of high frequency noise is filtered out.It is difficult to find out and foot from filtered waveform
Move relevant cadence information, therefore cannot directly utilize the CSI amplitude waveshape step number of time domain, it is necessary to combine frequency domain character
Analyse in depth.Gained action fragment comprises 30 subcarriers, selects front 10 subcarriers of variance maximum in the present invention
Data are for correcting final result of calculation.
It is 1000Hz in view of the sample rate in the present embodiment, so to each selected son in small echo processing module
Carrier wave performs the wavelet decomposition operation of 4 layers, and wherein the 4th layer of frequency range that detail coefficients is corresponding is caused by foot motion
Frequency range.The wavelet decomposition result of one of them subcarrier is as shown in Figure 5.
In short-time energy computing module, first with the details letter that the 4th layer of detail coefficients structure of wavelet decomposition is corresponding
Number, the detail signal of reconstruct is as shown in Figure 6.The detail signal of reconstruct is carried out windowing process framing, calculates the short of each frame
Shi Nengliang.Window function used in the present embodiment is Hamming window, window a length of 500.Calculated short-time energy such as Fig. 7 institute
Show.
In step number statistical module, using the result of calculation of short-time energy as input, use algorithm flow screening shown in Fig. 2
Go out to meet pre-conditioned Valid peak.Wherein requiring peak width between 500～1000 sampled points, peak height is not less than 2dB,
Interval between adjacent two crests is not less than 0.5 second, is 500 sampled points.The significant wave peak number that screening obtains is root
According to the calculated step number of current sub-carrier, finally take the meansigma methods of 10 subcarrier result of calculations as embodiment of the present invention meter
Calculate gained step Numerical.
Examples detailed above, only for technology design and the feature of the explanation present invention, its object is to allow the person skilled in the art be
Will appreciate that present disclosure and implement according to this, can not limit the scope of the invention with this.All according to present invention essence
God's equivalent transformation of being done of essence or modification, all should contain within protection scope of the present invention.
Claims (9)
1. a contactless step-recording method based on WiFi motion recognition system, it is characterised in that comprise the following steps:
S01: obtained the sequential CSI amplitude fragment of walking motion by WiFi motion recognition system, is processed and obtains NvIndividual subcarrier；
S02: to the N obtainedvThe action fragment of individual subcarrier carries out wavelet decomposition, obtains the detail coefficients of different frequency scope；
S03: filter out the detail coefficients representing the CSI amplitude variations place frequency range that foot motion causes, reconstruct every height
The detail signal that carrier wave is corresponding, and calculate the short-time energy of reconstruction signal；
S04: screen and add up significant wave peak number, and merge NvThe statistical result of individual subcarrier is calculated stable step Numerical.
Contactless step-recording method based on WiFi motion recognition system the most according to claim 1, it is characterised in that institute
The sequential CSI amplitude fragment stating the walking motion in step S01 is NsThe matrix of × T dimension, wherein NsFor subcarrier number, its number
Being worth relevant with communication bandwidth and selected sampling instrument, T is sample points.
Contactless step-recording method based on WiFi motion recognition system the most according to claim 1, it is characterised in that institute
The process stated in step S01 obtains NvIndividual subcarrier includes the flip-flop removing this CSI amplitude fragment, filters high-frequency noise,
Select the N that the variance of each subcarrier is biggervIndividual subcarrier.
Contactless step-recording method based on WiFi motion recognition system the most according to claim 1, it is characterised in that institute
Stating step S04 and include by peak width between 500～1000 sampled points, peak height is not less than 2dB, between adjacent two crests
The interval crest not less than 0.5 second is as Valid peak, using Valid peak as step number, by NvPutting down of individual subcarrier gained step number
Average is as step Numerical.
5. a contactless step counting system based on WiFi motion recognition system, it is characterised in that including:
Data processing module, processes the sequential CSI amplitude fragment of the walking motion that WiFi motion recognition system obtains,
To NvIndividual subcarrier；
Wavelet decomposition module, to the N obtainedvThe action fragment of individual subcarrier carries out wavelet decomposition, obtains the thin of different frequency scope
Joint coefficient；
Short-time energy computing module, filters out the details system representing the CSI amplitude variations place frequency range that foot motion causes
Number, reconstructs the detail signal that each subcarrier is corresponding, and calculates the short-time energy of reconstruction signal；
Step number statistical module, screens and adds up significant wave peak number, and merge NvThe statistical result of individual subcarrier is calculated stable
Step Numerical.
Contactless step counting system based on WiFi motion recognition system the most according to claim 5, it is characterised in that institute
The sequential CSI amplitude fragment stating walking motion is NsThe matrix of × T dimension, wherein NsFor subcarrier number, its numerical value and communication bandwidth
Relevant with selected sampling instrument, T is sample points.
Contactless step counting system based on WiFi motion recognition system the most according to claim 5, it is characterised in that institute
State data processing module and remove the flip-flop of this CSI amplitude fragment, filter the high-frequency noise included in it, select each sub-load
The N that the variance of ripple is biggervIndividual subcarrier.
Contactless step counting system based on WiFi motion recognition system the most according to claim 5, it is characterised in that institute
State short-time energy computing module and the detail signal of reconstruct is carried out windowing process framing, calculate the short-time energy of each frame.
Contactless step counting system based on WiFi motion recognition system the most according to claim 5, it is characterised in that institute
Stating step number statistical module by peak width between 500～1000 sampled points, peak height is not less than 2dB, between adjacent two crests
Interval not less than the crest of 0.5 second as Valid peak, using Valid peak as step number, by NvIndividual subcarrier gained step number
Meansigma methods is as step Numerical.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610668171.0A CN106323330B (en) | 2016-08-15 | 2016-08-15 | Contactless step-recording method based on WiFi motion recognition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610668171.0A CN106323330B (en) | 2016-08-15 | 2016-08-15 | Contactless step-recording method based on WiFi motion recognition system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106323330A true CN106323330A (en) | 2017-01-11 |
| CN106323330B CN106323330B (en) | 2019-01-11 |
Family
ID=57739456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610668171.0A Active CN106323330B (en) | 2016-08-15 | 2016-08-15 | Contactless step-recording method based on WiFi motion recognition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106323330B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108489509A (en) * | 2018-06-06 | 2018-09-04 | 天津大学 | A kind of non-contact single step-recording method and system based on commercial Wi-Fi |
| CN108548545A (en) * | 2018-06-06 | 2018-09-18 | 天津大学 | A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi |
| CN110013252A (en) * | 2019-04-18 | 2019-07-16 | 北京邮电大学 | Obtain method, apparatus, electronic equipment and the readable storage medium storing program for executing of respiratory state |
| CN110069134A (en) * | 2019-03-29 | 2019-07-30 | 北京大学 | A method of hand aerial mobile track is restored using radio-frequency signal |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015054419A1 (en) * | 2013-10-08 | 2015-04-16 | University Of Washington Through Its Center For Commercialization | Devices, systems, and methods for controlling devices using gestures |
| CN104766427A (en) * | 2015-04-27 | 2015-07-08 | 太原理工大学 | Detection method for illegal invasion of house based on Wi-Fi |
| CN104951757A (en) * | 2015-06-10 | 2015-09-30 | 南京大学 | Action detecting and identifying method based on radio signals |
| CN105807935A (en) * | 2016-04-01 | 2016-07-27 | 中国科学技术大学苏州研究院 | Gesture control man-machine interactive system based on WiFi |
| CN105810222A (en) * | 2014-12-30 | 2016-07-27 | 研祥智能科技股份有限公司 | Defect detection method, device and system for audio equipment |
-
2016
- 2016-08-15 CN CN201610668171.0A patent/CN106323330B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015054419A1 (en) * | 2013-10-08 | 2015-04-16 | University Of Washington Through Its Center For Commercialization | Devices, systems, and methods for controlling devices using gestures |
| CN105810222A (en) * | 2014-12-30 | 2016-07-27 | 研祥智能科技股份有限公司 | Defect detection method, device and system for audio equipment |
| CN104766427A (en) * | 2015-04-27 | 2015-07-08 | 太原理工大学 | Detection method for illegal invasion of house based on Wi-Fi |
| CN104951757A (en) * | 2015-06-10 | 2015-09-30 | 南京大学 | Action detecting and identifying method based on radio signals |
| CN105807935A (en) * | 2016-04-01 | 2016-07-27 | 中国科学技术大学苏州研究院 | Gesture control man-machine interactive system based on WiFi |
Non-Patent Citations (2)
| Title |
|---|
| SHENG TAN 等: "WiFinger: Leveraging Commodity WiFi for Fine-grained Finger Gesture Recognition", 《MOBIHOC"16 PROCEEDINGS OF THE 17TH ACM INTERNATIONAL SYMPOSIUM ON MOBILE AD HOC NETWORKING AND COMPUTING》 * |
| 朱海 等: "基于信道状态信息的WiFi环境感知技术", 《南京邮电大学学报（自然科学版）》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108489509A (en) * | 2018-06-06 | 2018-09-04 | 天津大学 | A kind of non-contact single step-recording method and system based on commercial Wi-Fi |
| CN108548545A (en) * | 2018-06-06 | 2018-09-18 | 天津大学 | A kind of non-contact more people's step-recording methods and system based on commercial Wi-Fi |
| CN110069134A (en) * | 2019-03-29 | 2019-07-30 | 北京大学 | A method of hand aerial mobile track is restored using radio-frequency signal |
| CN110069134B (en) * | 2019-03-29 | 2020-11-27 | 北京大学 | Method for restoring aerial moving track of hand by using radio frequency signal |
| CN110013252A (en) * | 2019-04-18 | 2019-07-16 | 北京邮电大学 | Obtain method, apparatus, electronic equipment and the readable storage medium storing program for executing of respiratory state |
| CN110013252B (en) * | 2019-04-18 | 2021-03-23 | 北京邮电大学 | Method and device for acquiring respiratory state, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106323330B (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108388912B (en) | Sleep staging method based on multi-sensor feature optimization algorithm | |
| CN105105737B (en) | Motion state rhythm of the heart method based on photoplethaysmography and spectrum analysis | |
| CN101599127B (en) | Method for extracting and identifying characteristics of electro-ocular signal | |
| Khan et al. | A robust heart rate monitoring scheme using photoplethysmographic signals corrupted by intense motion artifacts | |
| Zhang et al. | Sample entropy analysis of surface EMG for improved muscle activity onset detection against spurious background spikes | |
| CN106323330A (en) | Non-contact-type step count method based on WiFi motion recognition system | |
| CN102499694B (en) | Method for eliminating interference to blood oxygen saturation monitoring | |
| CN104161505A (en) | Motion noise interference eliminating method suitable for wearable heart rate monitoring device | |
| CN109508728B (en) | Novel identity authentication method for wearable equipment | |
| CN105997043B (en) | A kind of pulse frequency extracting method based on wrist wearable device | |
| US20170143226A1 (en) | Action Recognition Method and Device Based on Surface Electromyography Signal | |
| CN103610461B (en) | Based on the EEG Signal Denoising method of dual density small echo neighborhood dependent thresholds process | |
| CN106691425A (en) | Wrist heart rate monitoring method of sports bracelet | |
| CN106066995A (en) | A kind of wireless unbundling human body behavioral value algorithm | |
| CN110069199A (en) | A kind of skin-type finger gesture recognition methods based on smartwatch | |
| CN105426814A (en) | Old people stumbling detection method based on handset | |
| CN106308801B (en) | A method of human body respiration frequency is detected using smart phone | |
| Zou et al. | An ultra-low power QRS complex detection algorithm based on down-sampling wavelet transform | |
| CN103932693A (en) | Method for measuring human body heart rate on basis of mobile phone image | |
| Zhu et al. | MICROST: A mixed approach for heart rate monitoring during intensive physical exercise using wrist-type PPG signals | |
| CN109009125A (en) | Driver's fine granularity monitoring of respiration method and system based on audio frequency of mobile terminal | |
| CN103230267A (en) | Anti-movement-interference extraction method for pulse rates | |
| CN113848544A (en) | Human body existence induction detection method and device based on Doppler radar and storage medium | |
| KR102221839B1 (en) | Real-time cardiac rate detection apparatus in noisy environment and method thereof | |
| CN110852200B (en) | Non-contact human body action detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |