CN106289309A - Step-recording method based on 3-axis acceleration sensor and device - Google Patents
Step-recording method based on 3-axis acceleration sensor and device Download PDFInfo
- Publication number
- CN106289309A CN106289309A CN201610950804.7A CN201610950804A CN106289309A CN 106289309 A CN106289309 A CN 106289309A CN 201610950804 A CN201610950804 A CN 201610950804A CN 106289309 A CN106289309 A CN 106289309A
- Authority
- CN
- China
- Prior art keywords
- point
- valley
- personage
- peak
- target
- 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)
Abstract
nullThe invention discloses a kind of step-recording method based on 3-axis acceleration sensor and device，The method includes: detect peak point and valley point in the waveform of this aimed acceleration signal，And the number of peak point and valley point and this peak point and the number of this valley point is determined according to testing result，Using the number of this peak point or this valley point as this cadence feature，The type of sports of this personage is determined according to this cadence feature，And utilize the preset time window and preset peak-to-valley value window that this type of sports is corresponding，Target peak point and target valley point is determined in the waveform of this aimed acceleration signal，The step number that the number of this target peak point or the number of this target valley point are moved as this personage，So cadence feature by extracting personage may determine that the different motion state of personage，Utilize each kinestate to having different time windows and peak-to-valley value window，Can effectively eliminate interference，So that the step number calculated is more accurate.
Description
Technical field
The invention belongs to electronic technology field, particularly relate to a kind of step-recording method based on 3-axis acceleration sensor and dress
Put.
Background technology
Current people to jogging, the motion such as walking and stroll increasingly makes earnest efforts.Not only can be prevented by the motion of science
Disease, state of making the life better, it is also possible to prevent athletic injury.In order to meet public demand, it is proposed much intelligence on the market and sets
Standby, such as equipment such as motion bracelet, motion foot rings, the most basic function of the most such equipment is to calculate step number.Good calculating step
The step number that calculates of method of number could more closing to reality step number, the method therefore calculating step number is particularly important.
In prior art, the mode calculating step number is divided into two categories below: a class is peak detection methods, and the method is from sensing
The sinusoidal wave form flex point that device obtains judges paces；Another kind of is dynamic threshold judgment mode, and the method is just obtaining from sensor
String waveform declines district and judges paces.First kind meter step mode is easily subject to the interference of external factor and causes meter step inaccurate, example
As, smart motion bracelet, it is inaccurate that the action of wrist is easily caused meter step.Equations of The Second Kind meter step mode converts at kinestate
Time, calculate paces also according to previous kinestate, cause meter step inaccurate, and then have impact on meter step accuracy.
Summary of the invention
The present invention provides a kind of step-recording method based on 3-axis acceleration sensor and device, it is intended to solve because of prior art
In step-recording method be easily subject to the interference of external factor or cannot calculate, according to kinestate, the meter step that paces are caused
Inaccurate problem.
A kind of based on 3-axis acceleration sensor the step-recording method that the present invention provides, including: passed by 3-axis acceleration
Sensor obtains acceleration information when personage moves, and by pretreatment, described acceleration information is obtained aimed acceleration signal
Waveform；Detect peak point and valley point in the waveform of described aimed acceleration signal, and according to testing result determine peak point and
Valley point and the number of described peak point and the number of described valley point；The number of described peak point or described valley point is made
For the cadence feature of described personage, determine the type of sports of described personage according to the cadence feature of described personage, and utilize described
Preset time window that type of sports is corresponding and preset peak-to-valley value window, in the waveform of described aimed acceleration signal
Determine target peak point and target valley point；Using the number of described target peak point or the number of described target valley point as institute
State the step number of personage's motion.
A kind of based on 3-axis acceleration sensor the step count set that the present invention provides, including: passed by 3-axis acceleration
Sensor obtains acceleration information when personage moves, and by described acceleration information by pretreatment, obtains aimed acceleration signal
Waveform；Detect peak point and valley point in the waveform of described aimed acceleration signal, and determine peak point according to testing result
With valley point and the number of described peak point and the number of described valley point；By described peak point or the number of described valley point
As the cadence feature of described personage, determine the type of sports of described personage according to the cadence feature of described personage, and utilize institute
State preset time window corresponding to type of sports and preset peak-to-valley value window, at the waveform of described aimed acceleration signal
In determine target peak point and target valley point；Using the number of described target peak point or the number of described target valley point as
The step number of described personage motion.
The step-recording method based on 3-axis acceleration sensor of present invention offer and device, pass through 3-axis acceleration sensor
Obtain acceleration information when personage moves, by described acceleration information by pretreatment, obtain the ripple of aimed acceleration signal
Shape；Detect peak point and valley point in the waveform of described aimed acceleration signal, and determine peak point and paddy according to testing result
It is worth point and the number of described peak point and the number of described valley point；Using the number of described peak point or described valley point as
The cadence feature of described personage, determines the type of sports of described personage, and utilizes described fortune according to the cadence feature of described personage
Move preset time window corresponding to type and preset peak-to-valley value window, in the waveform of described aimed acceleration signal really
Set the goal peak point and target valley point；Using the number of described target peak point or the number of described target valley point as described
The step number of personage's motion, so the cadence feature by extracting personage may determine that the different motion state of personage, utilize each
Kinestate, to having different time windows and peak-to-valley value window, can effectively eliminate interference, so that the step number calculated
More accurate.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some embodiments of invention.
Fig. 1 is that the flow process that realizes of the step-recording method based on 3-axis acceleration sensor that first embodiment of the invention provides is shown
It is intended to；
Fig. 2 is that the flow process that realizes of the step-recording method based on 3-axis acceleration sensor that second embodiment of the invention provides is shown
It is intended to；
Fig. 3 is the structural representation of the step count set based on 3-axis acceleration sensor that third embodiment of the invention provides
Figure；
Fig. 4 is the structural representation of the step count set based on 3-axis acceleration sensor that fourth embodiment of the invention provides
Figure.
Detailed description of the invention
For making the goal of the invention of the present invention, feature, the advantage can be the most obvious and understandable, below in conjunction with the present invention
Accompanying drawing in embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that described reality
Executing example is only a part of embodiment of the present invention, and not all embodiments.Based on the embodiment in the present invention, people in the art
The every other embodiment that member is obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
Refer to Fig. 1, Fig. 1 and the reality of step-recording method based on 3-axis acceleration sensor is provided for first embodiment of the invention
Existing schematic flow sheet, can be applicable to mobile phone, intelligent watch, Intelligent bracelet, Intelligent insole, intelligence running shoes etc. and has step function
In mobile terminal, the step-recording method based on 3-axis acceleration sensor shown in Fig. 1, mainly comprise the steps that
S101, obtained acceleration information when personage moves by 3-axis acceleration sensor, and by this acceleration information
By pretreatment, obtain the waveform of aimed acceleration signal.
3-axis acceleration sensor can detect the acceleration signal of moving object.In embodiments of the present invention, by three
Axle acceleration sensor can measure three-dimensional acceleration data when people moves, and this acceleration information is carried out pretreatment, with
Waveform to aimed acceleration signal.This pretreatment is used for eliminating DC level and noise.
S102, detect peak point and valley point in the waveform of this aimed acceleration signal, and determine peak according to testing result
The number of value point and valley point and this peak point and the number of this valley point.
The waveform of this aimed acceleration signal includes crest and trough.
S103, using the number of this peak point or this valley point as the cadence feature of this personage, according to the cadence of this personage
Feature determines the type of sports of this personage, and utilizes the preset time window and preset peak-to-valley value that this type of sports is corresponding
Window, determines target peak point and target valley point in the waveform of this aimed acceleration signal.
Time window and peak-to-valley value window are all the parameters pre-set.The number of peak point is equal to the number of valley point.
Alternatively, using the meansigma methods of this peak point and the summation of this valley point number as the cadence feature of this personage.This type of sports
For the type divided according to personage's cadence feature.
S104, the step number that the number of this target peak point or the number of this target valley point are moved as this personage.
Here identical with the number of target valley point due to the number of target peak point, so determining the motion step of this personage
Number can also be: using the meansigma methods of target peak point and the summation of target valley point number as the motion step number of this personage.
It should be noted that a target peak point in waveform and target valley point represent a step of personage, also
That is, the first aim peak point being arranged in waveform and first object valley point represent a step of personage, are arranged in ripple
Second target peak point in shape and second target valley point represent more one step of this personage, the like, due to so
Principle and for the ease of calculate, so the number of this target peak point or the number of this target valley point are transported as this personage
Dynamic step number.
In the embodiment of the present invention, obtain acceleration information when personage moves by 3-axis acceleration sensor, this is added
Speed data obtains the waveform of aimed acceleration signal by pretreatment, detects peak point in the waveform of this aimed acceleration signal
And valley point, and the number of peak point and valley point and this peak point and the number of this valley point is determined according to testing result,
Using the number of described peak point or described valley point as the cadence feature of described personage, the cadence feature according to described personage is true
The type of sports of fixed described personage, and utilize the preset time window and preset peak-to-valley value window that this type of sports is corresponding
Mouthful, the waveform of this aimed acceleration signal determines target peak point and target valley point, by the number of this target peak point
Or the step number that the number of this target valley point is moved as this personage, so the cadence feature by extracting personage may determine that people
The different motion state of thing, utilizes each kinestate to having different time windows and peak-to-valley value window, can effectively disappear
Except interference, so that the step number calculated is more accurate.
Refer to the step-recording method based on 3-axis acceleration sensor that Fig. 2, Fig. 2 provide for second embodiment of the invention
Realize schematic flow sheet, can be applicable to mobile phone, intelligent watch, Intelligent bracelet, Intelligent insole, intelligence running shoes etc. and there is step function
Mobile terminal in, the step-recording method based on 3-axis acceleration sensor shown in Fig. 2, mainly comprise the steps that
S201, by 3-axis acceleration sensor obtain personage move time acceleration information, this acceleration information is led to
Cross pretreatment, obtain the waveform of aimed acceleration signal.
3-axis acceleration sensor can detect the acceleration signal of moving object.In embodiments of the present invention, by three
Axle acceleration sensor can measure three-dimensional acceleration data when people moves, and this acceleration information is carried out pretreatment, with
Waveform to aimed acceleration signal.This pretreatment is used for eliminating DC level and noise.The process of pretreatment includes: data are closed
One-tenth process, bandpass filtering process and smoothing process.
Alternatively, acceleration information when personage moves is obtained by 3-axis acceleration sensor, by this acceleration information
Obtain target data by pretreatment, and formed the waveform of aimed acceleration signal by this target data and include:
The time series data of acceleration signal when being moved by 3-axis acceleration sensor acquisition personage, and during by this
Between sequence data carry out delivery summation operation or the Data Synthesis computing of quadratic sum rooting computing, with obtain synthesis data；
The data of this synthesis are carried out bandpass filtering, to obtain filtered acceleration signal；
This filtered acceleration signal is smoothed, obtains the waveform of this aimed acceleration signal.
Wherein the cut-off frequency scope of this bandpass filtering is [0.5,5] Hz.Data Synthesis computing includes two kinds of computing modes
One is delivery summation operation, and another kind is quadratic sum rooting computing.If obtaining personage by 3-axis acceleration sensor and moving
Time the time series data of acceleration signal can be expressed as (ax(t), ay(t), az(t)), then Data Synthesis can be by following two
The mode of kind, one is that the formula that delivery is sued for peace is expressed as:
A (t)=| ax(t)|+|ay(y)|+|az(t)|
Two is that the formula of quadratic sum rooting is expressed as:
It should be noted that seasonal effect in time series data are for the acceleration information gathered under different time.T is sampling
Moment.
The wave filter that this bandpass filtering uses is for there being limit for length's unit impulse response (FIR, Finite Impulse
Response) wave filter and infinite impulse response (IIR, Infinite Impulse Response) digital filter.The logical filter of band
The cut-off frequency scope of ripple is the frequency according to personage's walking and the frequency configuration of running.
This filtered acceleration signal is smoothed, obtains the waveform of this aimed acceleration signal.
Acceleration information in this filtered acceleration signal can be counted by smoothing processing in many ways
Meansigma methods computing, it is also possible to the acceleration information in this filtered acceleration signal is weighted smoothing operation.
S202, detect peak point and valley point in the waveform of this aimed acceleration signal, and determine peak according to testing result
The number of value point and valley point and this peak point and the number of this valley point.
The waveform of this aimed acceleration signal includes crest and trough.
Alternatively, detect peak point and valley point in the waveform of this aimed acceleration signal, and determine according to testing result
The number of peak point and valley point and this peak point and the number of this valley point particularly as follows:
By preset sliding window, it is judged that the waveform of this aimed acceleration signal sampled point in this sliding window is
No for peak point to be confirmed or valley point to be confirmed；
The most then judge whether the sampling number between adjacent two peak points to be confirmed belongs to presetting range, and judge
Whether the sampling number between adjacent two valley points to be confirmed belongs to this presetting range, and wherein said presetting range is 0.2*fs
To 5*fs, fsIntrinsic sample frequency for described 3-axis acceleration sensor；
If, it is determined that this peak point to be confirmed is peak point, and determines that this valley point to be confirmed is valley point；
Determine the number of this peak point and the number of this valley point.
Preset sliding window is 2N+1, represents and during t, respectively chooses N number of point about t in waveform, and N is at ripple
Shape gathers and counts.Whether having peak point in the point gathered when then judging t by following formula 1, this formula 1 is:
A (t-N+1)-a (t-N) ＞ 0&a (t-N+2)-a (t-N+1) ＞ 0& ... &a (t+N-1)-a (t+N) ＞ 0
If this formula 1 is true, it is determined that this collection point N is peak point to be confirmed；If this formula 1 is false, it is determined that this is adopted
Collection point N is not peak point.
Whether having valley point in the point gathered when judging t by formula 2, this formula 2 is:
A (t-N+1)-a (t-N) ＜ 0&a (t-N+2)-a (t-N+1) ＜ 0& ... &a (t+N-1)-a (t+N) ＜ 0
If this formula 2 is true, it is determined that this collection point N is valley point to be confirmed, if this formula 2 is false, it is determined that this is adopted
Collection point N is not valley point.
The value of N can affect the accuracy of judgement, if N value is too big, then causes Partial peaks point or the valley point cannot be by
Find；If N value is too small, then judge that the accuracy rate of peak point or valley point declines, therefore the preferred value of N in the embodiment of the present invention
It is 3 or 4.
This presetting range is the intrinsic sample frequency (f of 0.2 times to 5 timess), i.e. 0.2*fsTo 5*fs。fsParameter is that three axles add
The intrinsic sample frequency of velocity sensor.General fsMore than or equal to 50HZ.
S203, using the number of described peak point or described valley point as the cadence feature of described personage, according to described people
The cadence feature of thing determines the type of sports of described personage, and utilizes preset time window that this type of sports is corresponding and pre-
The peak-to-valley value window put, determines target peak point and target valley point in the waveform of this aimed acceleration signal.
Time window and peak-to-valley value window are all the parameters pre-set.The number of peak point is equal to the number of valley point.
Alternatively, using the meansigma methods of this peak point and the summation of this valley point number as the cadence feature of this personage.This type of sports
For the type divided according to personage's cadence feature.
Using the number of described peak point or described valley point as the cadence feature of described personage, according to the step of described personage
Frequently feature determine described personage type of sports particularly as follows:
The baseline locomotor type of preset target quantity, and arrange pre-for the baseline locomotor state outside static or interference type
Put cadence scope；
Using the number of this peak point or the number of this valley point as the cadence feature of this personage；
Judge whether the cadence feature of this personage belongs to this preset cadence scope；
If so, the type of sports determining this personage is this baseline locomotor type corresponding to preset cadence scope.
Wherein this baseline locomotor type includes: type of being careful, type of hurrying up, running type and static or interference type.
Type, type of hurrying up, the preset cadence scope of running type of being wherein careful is respectively as follows:
Wherein, k1, min=1, k1, max=1.5；k2, min=1.5,
k2, max=2.3；k3, min=2.3, k3, max=5.
Using the number of this peak point or the number of this valley point as the cadence feature of this personage, then judge this personage's
Cadence feature belongs to the preset cadence scope of above-mentioned any type of sports, if being not to belong to this predetermined frequency scope, the most really
The type of sports of this personage fixed is static or interference type.
Alternatively, preset time window and preset peak-to-valley value window that this type of sports is corresponding are utilized, at this mesh
Mark acceleration signal waveform in determine target peak point and target valley point particularly as follows:
Judge whether the time interval between adjacent peak point and valley point is positioned at corresponding preset of this type of sports
In time window, and judge whether the difference of the numerical value of adjacent peak point and valley point is more than preset threshold；
If judged result is it is, it is determined that this peak point is target peak point and this valley point is target valley point.
For different baseline locomotor types, it is prefixed multiple time window: baseline locomotor type is corresponding for type of being careful
Preset time window beBaseline locomotor type is that preset time window corresponding to type of hurrying up isBaseline locomotor type is that preset time window corresponding to running type is
When which baseline locomotor type the type of sports of this personage is it is necessary to choose the time window of correspondence, such as, the motion of this personage
Type is running type, then choose preset time window and beThe most static or interference type does not has
Corresponding time window, because static or interference type does not has step number, need not carry out utilizing corresponding preset of this type of sports
Time window and preset peak-to-valley value window, determine target peak point and target paddy in the waveform of this aimed acceleration signal
The calculating process of value point.
Whether the difference of the preset numerical value that peak-to-valley value window is adjacent peak point and valley point is more than preset threshold, its
In this preset threshold be that the median of difference of the target peak point in preset time period and target valley point is multiplied by proportionality coefficient,
This preset time period is 2 seconds.The span of this proportionality coefficient is [0.5,0.9], if wherein this personage hand when motion
Shake is very violent, then the value of this proportionality coefficient is 0.5, if this personage shakes without hand when motion, then and this proportionality coefficient
Value is 0.9.In actual applications, in the span of this proportionality coefficient, hand shake is the most violent, taking of this proportionality coefficient
It is worth the least, otherwise then the value of this proportionality coefficient is the biggest.
It should be noted that in an initial condition, do not perform to judge that the difference of the numerical value of adjacent peak point and valley point is
The no process more than preset threshold；If including target peak point in the preset time period before the moment of current peak-to-valley value window
With target valley point, then the target peak point in this preset threshold is preset time period and the median of the difference of target valley point
It is multiplied by proportionality coefficient.
S204, the step number that the number of this target peak point or the number of this target valley point are moved as this personage.
Here identical with the number of target valley point due to the number of target peak point, so determining the motion step of this personage
Number can also be: using the meansigma methods of target peak point and the summation of target valley point number as the motion step number of this personage.
It should be noted that a target peak point in waveform and target valley point represent a step of personage, also
That is, the first aim peak point being arranged in waveform and first object valley point represent a step of personage, are arranged in ripple
Second target peak point in shape and second target valley point represent more one step of this personage, the like, due to so
Principle and for the ease of calculate, so the number of this target peak point or the number of this target valley point are transported as this personage
Dynamic step number.
It should be noted that f in above-mentioned formulasParameter is the intrinsic sample frequency of 3-axis acceleration sensor.General fsGreatly
In or equal to 50HZ.
In the embodiment of the present invention, obtain acceleration information when personage moves by 3-axis acceleration sensor, this is added
Speed data obtains the waveform of aimed acceleration signal by pretreatment, detects peak point in the waveform of this aimed acceleration signal
And valley point, and the number of peak point and valley point and this peak point and the number of this valley point is determined according to testing result,
Using the number of described peak point or described valley point as the cadence feature of described personage, the cadence feature according to described personage is true
The type of sports of fixed described personage, and utilize the preset time window and preset peak-to-valley value window that this type of sports is corresponding
Mouthful, the waveform of this aimed acceleration signal determines target peak point and target valley point, by the number of this target peak point
Or the step number that the number of this target valley point is moved as this personage, so the cadence feature by extracting personage may determine that people
The different motion state of thing, utilizes each kinestate to having different time windows and peak-to-valley value window, can effectively disappear
Except interference, so that the step number calculated is more accurate.
Experimental data that the method by the embodiment of the present invention be somebody's turn to do obtained is presented herein below, referring specifically to as follows:
For 4 different testers, the meter step statistical result of different motion (running, stair activity, usually walk).Experiment
In test, the sample frequency of 3-axis acceleration sensor is 100Hz, and theoretical step number is 100 steps.From table, result can
Go out: for different sexes, different motion, use the step-recording method in above-described embodiment, meter step accuracy rate to be up to 100%,
Minimum 90%, Average Accuracy reaches 95.9%, as shown in table 1 below.It can thus be seen that this step-recording method in above-described embodiment
For different sexes, different motion type has sane meter step accuracy rate output, and has reliability.It is simultaneous for dissimilarity
Other and different motion type meter step accuracy rate is an advantage over step-recording method of the prior art.
Table 1
| Tester | Sex | Test mode | Actual step number | Test step number | Accuracy rate |
| Tester 1 | Female | Run | 100 | 93 | 93% |
| Tester 1 | Female | Go upstairs | 100 | 98 | 98% |
| Tester 1 | Female | Go downstairs | 100 | 98 | 98% |
| Tester 1 | Female | Usually walk | 100 | 90 | 90% |
| Tester 2 | Female | Run | 100 | 94 | 94% |
| Tester 2 | Female | Go upstairs | 100 | 94 | 94% |
| Tester 2 | Female | Go downstairs | 100 | 93 | 93% |
| Tester 2 | Female | Usually walk | 100 | 98 | 98% |
| Tester 3 | Man | Run | 100 | 99 | 99% |
| Tester 3 | Man | Go upstairs | 100 | 94 | 94% |
| Tester 3 | Man | Go downstairs | 100 | 98 | 98% |
| Tester 3 | Man | Usually walk | 100 | 90 | 90% |
| Tester 4 | Man | Run | 100 | 99 | 99% |
| Tester 4 | Man | Go upstairs | 100 | 100 | 100% |
| Tester 4 | Man | Go downstairs | 100 | 97 | 97% |
| Tester 4 | Man | Usually walk | 100 | 100 | 100% |
Referring to Fig. 3, Fig. 3 is the step count set based on 3-axis acceleration sensor that third embodiment of the invention provides
Structural representation, for convenience of description, illustrate only the part relevant to the embodiment of the present invention.Adding based on three axles of Fig. 3 example
The step count set of velocity sensor can be earlier figures 1 and embodiment illustrated in fig. 2 provide based on 3-axis acceleration sensor
The executive agent of step-recording method.The step count set based on 3-axis acceleration sensor of Fig. 3 example, specifically includes that pretreatment mould
Block 301, detection processing module 302 and determine module 303.The most each functional module describes in detail as follows:
Pretreatment module 301, for being obtained acceleration information when personage moves by 3-axis acceleration sensor, should
Acceleration information passes through pretreatment, obtains the waveform of aimed acceleration signal；
Detection processing module 302, peak point and valley point in the waveform detecting this aimed acceleration signal, and according to
Testing result determines the number of peak point and valley point and this peak point and the number of this valley point；
Determine module 303, for using the number of described peak point or described valley point as the cadence feature of described personage,
Cadence feature according to described personage determines the type of sports of described personage, and utilizes the preset time that this type of sports is corresponding
Window and preset peak-to-valley value window, determine target peak point and target valley in the waveform of this aimed acceleration signal
Point；
Determine module 303, be additionally operable to the number of this target peak point or the number of this target valley point as this personage
The step number of motion.
The details that the present embodiment is not most, refers to the description of aforementioned embodiment illustrated in fig. 1, and here is omitted.
It should be noted that in the embodiment of the step count set based on 3-axis acceleration sensor of figure 3 above example,
The division of each functional module is merely illustrative of, in actual application can as required, the configuration requirement of such as corresponding hardware or
The convenient consideration of the realization of person's software, and above-mentioned functions distribution is completed by different functional modules, will image processing apparatus
Internal structure be divided into different functional modules, to complete all or part of function described above.And, actual application
In, the corresponding functional module in the present embodiment can be to be realized by corresponding hardware, it is also possible to is performed phase by corresponding hardware
The software answered completes.Each embodiment that this specification provides all can apply foregoing description principle, below repeats no more.
In the embodiment of the present invention, pretreatment module 301 obtains acceleration when personage moves by 3-axis acceleration sensor
Degrees of data, by this acceleration information by pretreatment, obtains the waveform of aimed acceleration signal, and detection processing module 302 detects
Peak point and valley point in the waveform of this aimed acceleration signal, and determine peak point and valley point according to testing result and be somebody's turn to do
The number of peak point and the number of this valley point, determine module 303 using the number of described peak point or described valley point as institute
State the cadence feature of personage, determine the type of sports of described personage according to the cadence feature of described personage, and utilize this motion class
Preset time window that type is corresponding and preset peak-to-valley value window, determine target in the waveform of this aimed acceleration signal
Peak point and target valley point, determine module 303 using the number of this target peak point or the number of this target valley point as this
The step number of personage's motion, so the cadence feature by extracting personage may determine that the different motion state of personage, utilize each
Kinestate, to having different time windows and peak-to-valley value window, can effectively eliminate interference, so that the step number calculated
More accurate.
Refer to the step count set based on 3-axis acceleration sensor that Fig. 4, Fig. 4 provide for fourth embodiment of the invention
Structural representation, for convenience of description, illustrate only the part relevant to the embodiment of the present invention.Adding based on three axles of Fig. 4 example
The step count set of velocity sensor can be earlier figures 1 and embodiment illustrated in fig. 2 provide based on 3-axis acceleration sensor
The executive agent of step-recording method.The step count set based on 3-axis acceleration sensor of Fig. 4 example, specifically includes that pretreatment mould
Block 401, detection processing module 402 and determine module 403, wherein, pretreatment module 401 includes: calculating sub module 4011 and filter
Marble module 4012；Detection processing module 402 includes: first judges that submodule 4021 and first determines submodule 4022；Determine
Module 403 includes: arranges submodule 4031, second judge that submodule 4032 and second determines submodule 4033.The most each function
Module describes in detail as follows:
Pretreatment module 401, for being obtained acceleration information when personage moves by 3-axis acceleration sensor, should
Acceleration information passes through pretreatment, obtains the waveform of aimed acceleration signal.
3-axis acceleration sensor can detect the acceleration signal of moving object.In embodiments of the present invention, pretreatment
Module 401 can measure three-dimensional acceleration data when people moves by 3-axis acceleration sensor, enters this acceleration information
Row pretreatment, to obtain the waveform of aimed acceleration signal.This pretreatment is used for eliminating DC level and noise.The mistake of pretreatment
Journey includes: Data Synthesis process, bandpass filtering process and smoothing process.
Alternatively, pretreatment module 401 includes: calculating sub module 4011 and filtering submodule 4012.
Calculating sub module 4011, for by 3-axis acceleration sensor obtain personage move time acceleration signal time
Between sequence data, and this time series data is carried out delivery summation operation or quadratic sum rooting computing Data Synthesis fortune
Calculate, to obtain the data of synthesis；
Filtering submodule 4012, for carrying out bandpass filtering by the data of this synthesis, to obtain filtered acceleration letter
Number；
Calculating sub module 4011, is additionally operable to be smoothed this filtered acceleration signal, obtains this target and add
The waveform of rate signal.
Wherein the cut-off frequency scope of this bandpass filtering is [0.5,5] Hz.Data Synthesis computing includes two kinds of computing modes
One is delivery summation operation, and another kind is quadratic sum rooting computing.If calculating sub module 4011 is sensed by 3-axis acceleration
Device obtains the time series data of acceleration signal when personage moves can be expressed as (ax(t), ay(t), az(t)), then data
Synthesis can be by following two mode, and one is that the formula that delivery is sued for peace is expressed as:
A (t)=| ax(t)|+|ay(t)|+|az(t)|
Two is that the formula of quadratic sum rooting is expressed as:
It should be noted that seasonal effect in time series data are for the acceleration information gathered under different time.T takes
Value.
The wave filter that this bandpass filtering uses is FIR filter or iir digital filter.The cut-off frequency model of bandpass filtering
Enclose is the frequency according to personage's walking and the frequency configuration of running.
This filtered acceleration signal is smoothed by calculating sub module 4011, obtains this aimed acceleration signal
Waveform.Acceleration information in this filtered acceleration signal can be counted by smoothing processing in many ways
Meansigma methods computing, it is also possible to the acceleration information in this filtered acceleration signal is weighted smoothing operation.
Detection processing module 402 detects peak point and valley point in the waveform of this aimed acceleration signal, and according to detection
Result determines the number of peak point and valley point and this peak point and the number of this valley point.
The waveform of this aimed acceleration signal includes crest and trough.
Alternatively, detection processing module 402 includes: first judges that submodule 4021 and first determines submodule 4022.
First judges submodule 4021, for by preset sliding window, it is judged that the waveform of this aimed acceleration signal
Whether the sampled point in this sliding window is peak point to be confirmed or valley point to be confirmed；
First judges submodule 4021, is additionally operable to the most then to judge between the numerical value of adjacent two peak points to be confirmed
Whether sampling number belongs to presetting range, and judges whether the sampling number between the numerical value of adjacent two valley points to be confirmed belongs to
In this presetting range, wherein this presetting range is 0.2*fsTo 5*fs, fsIntrinsic sampling frequency for described 3-axis acceleration sensor
Rate；
First determines submodule 4022, if for, it is determined that this peak point to be confirmed is peak point, and determines that this is treated
Confirmation valley point is valley point, and determines the number of this peak point and the number of this valley point.
Preset sliding window is 2N+1, represents and during t, respectively chooses N number of point about t in waveform, and N is at ripple
Shape gathers and counts.Then first judges whether have peak in the point gathered when submodule 4021 judges t by following formula 1
Value point, this formula 1 is:
A (t-N+1)-a (t-N) ＞ 0&a (t-N+2)-a (t-N+1) 0& ... &a (t+N-1-at+N > 0
If this formula 1 is true, then first determines that submodule 4022 determines that this collection point N is peak point to be confirmed；If these public affairs
Formula 1 is false, then first determines that submodule 4022 determines that this collection point N is not peak point.
First judges whether have valley point in the point gathered when submodule 4021 judges t by formula 2, this formula 2
For:
A (t-N+1)-a (t-N) ＜ 0&a (t-N+2)-a (t-N+1 ＜ 0& ... &a (t+N-1)-a (t+N) ＜ 0
If this formula 2 is true, then first determines that submodule 4022 determines that this collection point N is valley point to be confirmed, if these public affairs
Formula 2 is false, then first determines that submodule 4022 determines that this collection point N is not valley point.
The value of N can affect the accuracy of judgement, if N value is too big, then causes Partial peaks point or the valley point cannot be by
Find；If N value is too small, then judges that the accuracy rate of peak point or valley point can decline, therefore in the embodiment of the present invention, N preferably takes
Value is 3 or 4.
This presetting range is the intrinsic sample frequency (f of 0.2 times to 5 timess), i.e. 0.2*fsTo 5*fs。fsParameter is that three axles add
The intrinsic sample frequency of velocity sensor.General fsMore than or equal to 50HZ.
Determine module 403, for using the number of described peak point or described valley point as the cadence feature of described personage,
Cadence feature according to described personage determines the type of sports of described personage, and utilizes the preset time that this type of sports is corresponding
Window and preset peak-to-valley value window, determine target peak point and target valley in the waveform of this aimed acceleration signal
Point.
Time window and peak-to-valley value window are all the parameters pre-set.The number of peak point is equal to the number of valley point.
Optionally it is determined that module 403 is additionally operable to the meansigma methods of this peak point and the summation of this valley point number as the step of this personage
Frequently feature.This type of sports is the type divided according to personage's cadence feature.
Determine that module 403 includes: submodule 4031 is set, second judges that submodule 4032 and second determines submodule
4033。
Submodule 4031 is set, for the baseline locomotor type of preset target quantity, and is static or outside interference type
Baseline locomotor state preset cadence scope is set；
Submodule 4031 is set, is additionally operable to the number of this peak point or the number of this valley point as the cadence of this personage
Feature；
Second judges submodule 4032, for judging whether the cadence feature of this personage belongs to this preset cadence scope；
Second determines submodule 4033, for if so, determining that the type of sports of this personage is right by this preset cadence scope
The baseline locomotor type answered.
Wherein this baseline locomotor type includes: type of being careful, type of hurrying up, running type and static or interference type.Wherein it is careful
Type, type of hurrying up, the preset cadence scope of running type are respectively as follows: Wherein, k1, min=1, k1, max=1.5；k2, min=1.5, k2, max=2.3；k3, min
=2.3, k3, max=5.
Submodule 4031 is set using the number of this peak point or the number of this valley point as the cadence feature of this personage, so
Rear second judges that submodule 4032 judges that the cadence feature of this personage belongs to the preset cadence scope of above-mentioned any type of sports,
If second to determine that submodule 4033 is additionally operable to not be to belong to this predetermined frequency scope, it is determined that the type of sports of this personage is quiet
Stop or interference type.
Second judges submodule 4032, the time interval being additionally operable to judge between adjacent peak point and valley point whether position
In the preset time window that this type of sports is corresponding, and judge adjacent peak point and valley point numerical value difference whether
More than preset threshold；
Second determines submodule, if being additionally operable to 4033 judged results and being is, it is determined that this peak point is target peak point
It is target valley point with this valley point.
For different baseline locomotor types, it is prefixed multiple time window: baseline locomotor type is corresponding for type of being careful
Preset time window beBaseline locomotor type is that preset time window corresponding to type of hurrying up isBaseline locomotor type is that preset time window corresponding to running type is
When which baseline locomotor type the type of sports of this personage is it is necessary to choose the time window of correspondence, such as, the motion of this personage
Type is running type, then choose preset time window and beThe most static or interference type does not has
Corresponding time window, because static or interference type does not has step number, need not carry out utilizing corresponding preset of this type of sports
Time window and preset peak-to-valley value window, determine target peak point and target paddy in the waveform of this aimed acceleration signal
The calculating process of value point.
Whether the difference of the preset numerical value that peak-to-valley value window is adjacent peak point and valley point is more than preset threshold, its
In this preset threshold be that the median of difference of the target peak point in preset time period and target valley point is multiplied by proportionality coefficient,
This preset time period is 2 seconds.The span of this proportionality coefficient is [0.5,0.9], if wherein this personage hand when motion
Shake is very violent, then the value of this proportionality coefficient is 0.5, if this personage shakes without hand when motion, then and this proportionality coefficient
Value is 0.9.In actual applications, in the span of this proportionality coefficient, hand shake is the most violent, taking of this proportionality coefficient
It is worth the least, otherwise then the value of this proportionality coefficient is the biggest.
It should be noted that in an initial condition, do not perform to judge that the difference of the numerical value of adjacent peak point and valley point is
The no process more than preset threshold；If including target peak point in the preset time period before the moment of current peak-to-valley value window
With target valley point, then the target peak point in this preset threshold is preset time period and the median of the difference of target valley point
It is multiplied by proportionality coefficient.
Determine module 403, be additionally operable to the number of this target peak point or the number of this target valley point as this personage
The step number of motion.
Here identical with the number of target valley point due to the number of target peak point, so determining the motion step of this personage
Number can also be: using the meansigma methods of target peak point and the summation of target valley point number as the motion step number of this personage.
It should be noted that a target peak point in waveform and target valley point represent a step of personage, also
That is, the first aim peak point being arranged in waveform and first object valley point represent a step of personage, are arranged in ripple
Second target peak point in shape and second target valley point represent more one step of this personage, the like, due to so
Principle and for the ease of calculate, so the number of this target peak point or the number of this target valley point are transported as this personage
Dynamic step number.
It should be noted that f in above-mentioned formulasParameter is the intrinsic sample frequency of 3-axis acceleration sensor.General fsGreatly
In or equal to 50HZ.
The details that the present embodiment is not most, refers to the description of earlier figures 1 and embodiment illustrated in fig. 2, and here is omitted.
In the embodiment of the present invention, pretreatment module 401 obtains acceleration when personage moves by 3-axis acceleration sensor
Degrees of data, by this acceleration information by pretreatment, obtains the waveform of aimed acceleration signal, and detection processing module 402 detects
Peak point and valley point in the waveform of this aimed acceleration signal, and determine peak point and valley point according to testing result and be somebody's turn to do
The number of peak point and the number of this valley point, determine module 403 using the number of described peak point or described valley point as institute
State the cadence feature of personage, determine the type of sports of described personage according to the cadence feature of described personage, and utilize this motion class
Preset time window that type is corresponding and preset peak-to-valley value window, determine target in the waveform of this aimed acceleration signal
Peak point and target valley point, determine module 403 using the number of this target peak point or the number of this target valley point as this
The step number of personage's motion, so the cadence feature by extracting personage may determine that the different motion state of personage, utilize each
Kinestate, to having different time windows and peak-to-valley value window, can effectively eliminate interference, so that the step number calculated
More accurate.
In multiple embodiments provided herein, it should be understood that disclosed system, apparatus and method, permissible
Realize by another way.Such as, device embodiment described above is only schematically, such as, and described module
Dividing, be only a kind of logic function and divide, actual can have other dividing mode, the most multiple modules or assembly when realizing
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not performs.Another point, shown or
The coupling each other discussed or direct-coupling or communication linkage can be the indirect couplings by some interfaces, device or module
Close or communication linkage, can be electrical, machinery or other form.
The described module illustrated as separating component can be or may not be physically separate, shows as module
The parts shown can be or may not be physical module, i.e. may be located at a place, or can also be distributed to multiple
On mixed-media network modules mixed-media.Some or all of module therein can be selected according to the actual needs to realize the mesh of the present embodiment scheme
's.
It addition, each functional module in each embodiment of the present invention can be integrated in a processing module, it is also possible to
It is that modules is individually physically present, it is also possible to two or more modules are integrated in a module.Above-mentioned integrated mould
Block both can realize to use the form of hardware, it would however also be possible to employ the form of software function module realizes.
If described integrated module realizes and as independent production marketing or use using the form of software function module
Time, can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part that in other words prior art contributed or this technical scheme completely or partially can be with the form of software product
Embodying, this computer software product is stored in a storage medium, including some instructions with so that a computer
Equipment (can be personal computer, server, or the network equipment etc.) performs the complete of method described in each embodiment of the present invention
Portion or part steps.And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
It should be noted that for aforesaid each method embodiment, in order to simplicity describes, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, some step can use other order or carry out simultaneously.Secondly, those skilled in the art also should know
Knowing, it might not be all this that embodiment described in this description belongs to preferred embodiment, involved action and module
Bright necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not has the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiments.
It is more than to step-recording method based on 3-axis acceleration sensor provided by the present invention and the description of device, for
Those skilled in the art, according to the thought of the embodiment of the present invention, the most all can change
Part, to sum up, this specification content should not be construed as limitation of the present invention.
Claims (10)
1. a step-recording method based on 3-axis acceleration sensor, it is characterised in that including:
Acceleration information when personage moves is obtained, by described acceleration information by pre-place by 3-axis acceleration sensor
Reason, obtains the waveform of aimed acceleration signal；
Detect peak point and valley point in the waveform of described aimed acceleration signal, and determine peak point and paddy according to testing result
It is worth point and the number of described peak point and the number of described valley point；
Using the number of described peak point or described valley point as the cadence feature of described personage, the cadence according to described personage is special
Levy the type of sports determining described personage, and utilize the preset time window and preset peak valley that described type of sports is corresponding
Value window, determines target peak point and target valley point in the waveform of described aimed acceleration signal；
The step number that the number of described target peak point or the number of described target valley point are moved as described personage.
Method the most according to claim 1, it is characterised in that described by 3-axis acceleration sensor acquisition personage's motion
Time acceleration information, described acceleration information is obtained target data by pretreatment, and is formed mesh by described target data
The waveform of mark acceleration signal includes:
The time series data of acceleration signal when being moved by 3-axis acceleration sensor acquisition personage, and by the described time
Sequence data carries out delivery summation operation or the Data Synthesis computing of quadratic sum rooting computing, to obtain the data of synthesis；
The data of described synthesis are carried out bandpass filtering, to obtain filtered acceleration signal, wherein said bandpass filtering
Cut-off frequency scope is [0.5,5] Hz；
Described filtered acceleration signal is smoothed, obtains the waveform of described aimed acceleration signal.
Method the most according to claim 2, it is characterised in that peak in the waveform of described detection described aimed acceleration signal
Value point and valley point, and determine peak point and valley point and the number of described peak point and described valley point according to testing result
Number include:
By preset sliding window, it is judged that the waveform of described aimed acceleration signal sampled point in described sliding window is
No for peak point to be confirmed or valley point to be confirmed；
The most then judge whether the sampling number between the numerical value of adjacent two peak points to be confirmed belongs to presetting range, and sentence
Whether the sampling number between the numerical value of disconnected adjacent two valley points to be confirmed belongs to described presetting range, wherein said preset model
Enclose for 0.2*fsTo 5*fs, fsIntrinsic sample frequency for described 3-axis acceleration sensor；
If, it is determined that described peak point to be confirmed is peak point, and determines that described valley point to be confirmed is valley point；
Determine number and the number of described valley point of described peak point.
Method the most according to claim 3, it is characterised in that described by the number work of described peak point or described valley point
For the cadence feature of described personage, determine that the type of sports of described personage includes according to the cadence feature of described personage:
The baseline locomotor type of preset target quantity, and preset step is set for the baseline locomotor state outside static or interference type
Frequently scope, wherein said baseline locomotor type includes: type of being careful, type of hurrying up, running type and described static or interference
Type；
Using the number of described peak point or the number of described valley point as the cadence feature of described personage；
Judge whether the cadence feature of described personage belongs to described preset cadence scope；
If so, the type of sports determining described personage is the baseline locomotor type corresponding to described preset cadence scope.
Method the most according to claim 4, it is characterised in that the described preset time utilizing described type of sports corresponding
Window and preset peak-to-valley value window, determine target peak point and target valley in the waveform of described aimed acceleration signal
Point includes:
Judge when whether the time interval between adjacent peak point and valley point is positioned at described type of sports corresponding preset
Between in window, and judge that whether the difference of numerical value of adjacent peak point and valley point is more than preset threshold, described preset gate
Limit value is that the median of the difference of the target peak point in preset time period and target valley point is multiplied by proportionality coefficient, wherein said ratio
Example coefficient is [0.5,0.9]；
If judged result is it is, it is determined that described peak point is target peak point and described valley point is target valley point.
6. a step count set based on 3-axis acceleration sensor, it is characterised in that described device includes:
Pretreatment module, for obtaining acceleration information when personage moves, by described acceleration by 3-axis acceleration sensor
Degrees of data passes through pretreatment, obtains the waveform of aimed acceleration signal；
Detection processing module, peak point and valley point in the waveform detecting described aimed acceleration signal, and according to detection
Result determines peak point and valley point and the number of described peak point and the number of described valley point；
Determine module, for using the number of described peak point or described valley point as the cadence feature of described personage, according to institute
The cadence feature stating personage determines the type of sports of described personage, and utilizes the preset time window that described type of sports is corresponding
And preset peak-to-valley value window, the waveform of described aimed acceleration signal determines target peak point and target valley point；
Described determine module, be additionally operable to the number of described target peak point or the number of described target valley point as described people
The step number of thing motion.
Device the most according to claim 6, it is characterised in that described pretreatment module includes:
Calculating sub module, for obtaining the time series number of acceleration signal when personage moves by 3-axis acceleration sensor
According to, and described time series data is carried out delivery summation operation or the Data Synthesis computing of quadratic sum rooting computing, with
Data to synthesis；
Filtering submodule, carries out bandpass filtering, to be filtered for the acceleration signal data of described synthesis formed
After acceleration signal, the cut-off frequency scope of wherein said bandpass filtering is [0.5,5] Hz；
Described calculating sub module, is additionally operable to be smoothed described filtered acceleration signal, obtains described target and add
The waveform of rate signal.
Device the most according to claim 7, it is characterised in that described detection processing module includes:
First judges submodule, for by preset sliding window, it is judged that the waveform of described aimed acceleration signal is described
Whether the numerical value of the sampled point in sliding window is peak point to be confirmed or valley point to be confirmed；
Described first judges submodule, is additionally operable to the sampling the most then judging between the numerical value of adjacent two peak points to be confirmed
Count and whether belong to presetting range, and judge whether the sampling number between the numerical value of adjacent two valley points to be confirmed belongs to institute
Stating presetting range, wherein said presetting range is 0.2*fsTo 5*fs, fsIntrinsic sampling frequency for described 3-axis acceleration sensor
Rate；
First determines submodule, if for, it is determined that described peak point to be confirmed is peak point, and determines described to be confirmed
Valley point is valley point, and determines number and the number of described valley point of described peak point.
Device the most according to claim 8, it is characterised in that described determine that module includes:
Submodule is set, for the baseline locomotor type of preset target quantity, and is static or benchmark fortune outside interference type
Dynamic state arranges preset cadence scope, and wherein said baseline locomotor type includes: type of being careful, type of hurrying up, running type with
And described static or interference type；
Described submodule is set, is additionally operable to the number of described peak point or the number of described valley point as the step of described personage
Frequently feature；
Second judges submodule, for judging whether the cadence feature of described personage belongs to described preset cadence scope；
Second determines submodule, is corresponding to described preset cadence scope for if so, determining the type of sports of described personage
Baseline locomotor type.
Device the most according to claim 9, it is characterised in that
Described second judges submodule, and whether the time interval being additionally operable to judge between adjacent peak point and valley point is positioned at institute
State in the preset time window that type of sports is corresponding, and judge that the difference of the numerical value of adjacent peak point and valley point is the biggest
In preset threshold, described preset threshold is the median of the difference of the target peak point in preset time period and target valley point
Being multiplied by proportionality coefficient, wherein said proportionality coefficient is [0.5,0.9]；
Described second determines submodule, if being additionally operable to judged result and being is, it is determined that described peak point be target peak point and
Described valley point is target valley point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610950804.7A CN106289309B (en) | 2016-10-26 | 2016-10-26 | Step-recording method and device based on 3-axis acceleration sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610950804.7A CN106289309B (en) | 2016-10-26 | 2016-10-26 | Step-recording method and device based on 3-axis acceleration sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106289309A true CN106289309A (en) | 2017-01-04 |
| CN106289309B CN106289309B (en) | 2019-08-16 |
Family
ID=57720216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610950804.7A Active CN106289309B (en) | 2016-10-26 | 2016-10-26 | Step-recording method and device based on 3-axis acceleration sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106289309B (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107091650A (en) * | 2017-04-27 | 2017-08-25 | 重庆邮电大学 | A kind of software step-recording method based on mobile phone acceleration and range sensor |
| CN107273857A (en) * | 2017-06-19 | 2017-10-20 | 深圳市酷浪云计算有限公司 | The recognition methods of athletic performance and device, electronic equipment |
| CN107314775A (en) * | 2017-05-17 | 2017-11-03 | 浙江利尔达物联网技术有限公司 | A kind of switching at runtime based on 3-axis acceleration sensor calculates the step-recording method of axle |
| CN107421560A (en) * | 2017-07-31 | 2017-12-01 | 青岛真时科技有限公司 | A kind of step-recording method, device and wrist type pedometer |
| CN107727110A (en) * | 2017-09-11 | 2018-02-23 | 上海斐讯数据通信技术有限公司 | The statistical method and device of a kind of step number |
| CN107747950A (en) * | 2017-09-28 | 2018-03-02 | 上海惠芽信息技术有限公司 | Step recording method and device |
| CN108195395A (en) * | 2017-11-17 | 2018-06-22 | 捷开通讯(深圳)有限公司 | Mobile terminal and its step-recording method, storage device |
| CN108279021A (en) * | 2018-01-26 | 2018-07-13 | 广东欧珀移动通信有限公司 | Step-recording method, electronic device and computer readable storage medium |
| CN108680181A (en) * | 2018-04-23 | 2018-10-19 | Oppo广东移动通信有限公司 | Wireless headset, step-recording method and Related product based on headset detection |
| CN108827293A (en) * | 2018-06-28 | 2018-11-16 | 河北工业大学 | A kind of 3 D positioning system based on inertial measurement component |
| CN108960016A (en) * | 2017-05-25 | 2018-12-07 | 富士通株式会社 | The method and apparatus for detecting specific action |
| CN109222329A (en) * | 2017-04-12 | 2019-01-18 | 佛山市丈量科技有限公司 | A kind of step length calculation method and the Intelligent insole for configuring this method |
| CN110617743A (en) * | 2019-09-02 | 2019-12-27 | 中国人民解放军总参谋部第六十研究所 | Hot start method for target drone aircraft avionics equipment |
| CN110721456A (en) * | 2019-10-09 | 2020-01-24 | 成都乐动信息技术有限公司 | Pedal frequency detection method based on three-axis sensor |
| CN110811578A (en) * | 2019-11-27 | 2020-02-21 | 青岛歌尔智能传感器有限公司 | Step counting device and step counting method thereof, controller and readable storage medium |
| CN111238527A (en) * | 2020-01-15 | 2020-06-05 | 桂林市优创电子科技有限公司 | Step counting method based on three-axis acceleration sensor |
| CN111536989A (en) * | 2020-05-26 | 2020-08-14 | 江南大学 | Adaptive time window step counting method based on peak detection |
| CN111780780A (en) * | 2020-06-16 | 2020-10-16 | 贵州省人民医院 | Step counting method and device based on filter bank |
| CN112113581A (en) * | 2020-10-26 | 2020-12-22 | 平安科技（深圳）有限公司 | Abnormal step counting identification method, step counting method, device, equipment and medium |
| CN112244820A (en) * | 2020-11-13 | 2021-01-22 | 青岛迈金智能科技有限公司 | Method for measuring running gait by using three-axis accelerometer |
| CN113030502A (en) * | 2021-03-05 | 2021-06-25 | 东莞市猎声电子科技有限公司 | Method for processing irregular acceleration sensor signals in walking process |
| CN113159838A (en) * | 2021-04-09 | 2021-07-23 | 上海掌门科技有限公司 | Method, apparatus, medium, and program product for pushing target presentation information |
| US11426627B2 (en) | 2017-08-23 | 2022-08-30 | Huawei Technologies Co., Ltd. | Method and apparatus for counting foot step based on acceleration information, and device |
| US11487965B2 (en) | 2017-08-23 | 2022-11-01 | Huawei Technologies Co., Ltd. | Method and apparatus for counting foot step based on stride frequency, and device |
| CN115828070A (en) * | 2023-02-14 | 2023-03-21 | 成都体育学院 | Motion data processing method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102297701A (en) * | 2010-06-22 | 2011-12-28 | 雅马哈株式会社 | Pedometer |
| CN105496416A (en) * | 2015-12-28 | 2016-04-20 | 歌尔声学股份有限公司 | Human motion state recognition method and device |
-
2016
- 2016-10-26 CN CN201610950804.7A patent/CN106289309B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102297701A (en) * | 2010-06-22 | 2011-12-28 | 雅马哈株式会社 | Pedometer |
| CN105496416A (en) * | 2015-12-28 | 2016-04-20 | 歌尔声学股份有限公司 | Human motion state recognition method and device |
Non-Patent Citations (3)
| Title |
|---|
| 刘程: ""自适应计步检测算法研究"", 《压电与声光》 * |
| 卢文: ""基于STM32和LIS3DSH的高精度计步器设计"", 《应用天地》 * |
| 陈国良: ""一种基于自适应波峰检测的MEMS计步算法"", 《中国惯性技术学报》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109222329B (en) * | 2017-04-12 | 2021-08-03 | 纵联汽车工业工程研究(天津)有限公司 | Walking length calculating method and intelligent insole configured with same |
| CN109222329A (en) * | 2017-04-12 | 2019-01-18 | 佛山市丈量科技有限公司 | A kind of step length calculation method and the Intelligent insole for configuring this method |
| CN107091650A (en) * | 2017-04-27 | 2017-08-25 | 重庆邮电大学 | A kind of software step-recording method based on mobile phone acceleration and range sensor |
| CN107314775A (en) * | 2017-05-17 | 2017-11-03 | 浙江利尔达物联网技术有限公司 | A kind of switching at runtime based on 3-axis acceleration sensor calculates the step-recording method of axle |
| CN107314775B (en) * | 2017-05-17 | 2019-09-10 | 浙江利尔达物联网技术有限公司 | A kind of switching at runtime based on 3-axis acceleration sensor calculates the step-recording method of axis |
| CN108960016A (en) * | 2017-05-25 | 2018-12-07 | 富士通株式会社 | The method and apparatus for detecting specific action |
| CN107273857A (en) * | 2017-06-19 | 2017-10-20 | 深圳市酷浪云计算有限公司 | The recognition methods of athletic performance and device, electronic equipment |
| CN107421560A (en) * | 2017-07-31 | 2017-12-01 | 青岛真时科技有限公司 | A kind of step-recording method, device and wrist type pedometer |
| US11426627B2 (en) | 2017-08-23 | 2022-08-30 | Huawei Technologies Co., Ltd. | Method and apparatus for counting foot step based on acceleration information, and device |
| US11487965B2 (en) | 2017-08-23 | 2022-11-01 | Huawei Technologies Co., Ltd. | Method and apparatus for counting foot step based on stride frequency, and device |
| WO2019047410A1 (en) * | 2017-09-11 | 2019-03-14 | 上海斐讯数据通信技术有限公司 | Method and apparatus for counting the number of steps |
| CN107727110A (en) * | 2017-09-11 | 2018-02-23 | 上海斐讯数据通信技术有限公司 | The statistical method and device of a kind of step number |
| CN107747950A (en) * | 2017-09-28 | 2018-03-02 | 上海惠芽信息技术有限公司 | Step recording method and device |
| CN108195395A (en) * | 2017-11-17 | 2018-06-22 | 捷开通讯(深圳)有限公司 | Mobile terminal and its step-recording method, storage device |
| CN108279021A (en) * | 2018-01-26 | 2018-07-13 | 广东欧珀移动通信有限公司 | Step-recording method, electronic device and computer readable storage medium |
| CN108680181A (en) * | 2018-04-23 | 2018-10-19 | Oppo广东移动通信有限公司 | Wireless headset, step-recording method and Related product based on headset detection |
| CN108827293A (en) * | 2018-06-28 | 2018-11-16 | 河北工业大学 | A kind of 3 D positioning system based on inertial measurement component |
| CN108827293B (en) * | 2018-06-28 | 2020-06-09 | 河北工业大学 | Three-dimensional positioning system based on inertia measurement element |
| CN110617743A (en) * | 2019-09-02 | 2019-12-27 | 中国人民解放军总参谋部第六十研究所 | Hot start method for target drone aircraft avionics equipment |
| CN110721456A (en) * | 2019-10-09 | 2020-01-24 | 成都乐动信息技术有限公司 | Pedal frequency detection method based on three-axis sensor |
| CN110721456B (en) * | 2019-10-09 | 2020-12-25 | 成都乐动信息技术有限公司 | Pedal frequency detection method based on three-axis sensor |
| CN110811578A (en) * | 2019-11-27 | 2020-02-21 | 青岛歌尔智能传感器有限公司 | Step counting device and step counting method thereof, controller and readable storage medium |
| CN111238527A (en) * | 2020-01-15 | 2020-06-05 | 桂林市优创电子科技有限公司 | Step counting method based on three-axis acceleration sensor |
| CN111238527B (en) * | 2020-01-15 | 2023-09-29 | 桂林市优创电子科技有限公司 | Step counting method based on triaxial acceleration sensor |
| CN111536989B (en) * | 2020-05-26 | 2021-08-24 | 江南大学 | Adaptive time window step counting method based on peak detection |
| CN111536989A (en) * | 2020-05-26 | 2020-08-14 | 江南大学 | Adaptive time window step counting method based on peak detection |
| CN111780780A (en) * | 2020-06-16 | 2020-10-16 | 贵州省人民医院 | Step counting method and device based on filter bank |
| CN111780780B (en) * | 2020-06-16 | 2022-06-03 | 贵州省人民医院 | Step counting method and device based on filter bank |
| CN112113581A (en) * | 2020-10-26 | 2020-12-22 | 平安科技（深圳）有限公司 | Abnormal step counting identification method, step counting method, device, equipment and medium |
| CN112113581B (en) * | 2020-10-26 | 2024-03-08 | 平安科技（深圳）有限公司 | Abnormal step counting identification method, step counting method, device, equipment and medium |
| CN112244820A (en) * | 2020-11-13 | 2021-01-22 | 青岛迈金智能科技有限公司 | Method for measuring running gait by using three-axis accelerometer |
| CN113030502B (en) * | 2021-03-05 | 2023-10-31 | 东莞市猎声电子科技有限公司 | Method for processing irregular acceleration sensor signals in walking process |
| CN113030502A (en) * | 2021-03-05 | 2021-06-25 | 东莞市猎声电子科技有限公司 | Method for processing irregular acceleration sensor signals in walking process |
| CN113159838A (en) * | 2021-04-09 | 2021-07-23 | 上海掌门科技有限公司 | Method, apparatus, medium, and program product for pushing target presentation information |
| CN115828070A (en) * | 2023-02-14 | 2023-03-21 | 成都体育学院 | Motion data processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106289309B (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106289309A (en) | Step-recording method based on 3-axis acceleration sensor and device | |
| CN103712632B (en) | A kind of step-recording method based on 3 axle accelerometers and pedometer | |
| CN103767710B (en) | Human motion state monitors method and apparatus | |
| CN105496416A (en) | Human motion state recognition method and device | |
| CN103954295B (en) | A kind of step-recording method based on acceleration transducer | |
| CN104990562B (en) | Step-recording method based on auto-correlation computation | |
| CN101354265B (en) | Method and device for counting steps | |
| CN106030246B (en) | The equipment that is counted for the number of cycles of the cycle movement to object, method and system | |
| CN102445214B (en) | Step counting method based on 3D (three-dimensional) gravity sensor of intelligent mobile phone | |
| CN104567912B (en) | Method for realizing pedometer on Android mobile phone | |
| CN105806359A (en) | Step counting method and pedometer | |
| CN103997572A (en) | Step counting method and device based on data of acceleration sensor of mobile phone | |
| WO2018048561A1 (en) | Devices and methods for fall detection based on phase segmentation | |
| CN106767888A (en) | A kind of meter based on Wave crest and wave trough detection walks algorithm | |
| CN104406604A (en) | Step counting method | |
| CN101394781A (en) | Body parameter sensing | |
| CN106108913B (en) | Error count walks removing method, device and wearable device | |
| CN104580660B (en) | A kind of mobile intelligent terminal and its step-recording method, system | |
| CN102954803A (en) | Adaptive step-counting processing system and method | |
| Tran et al. | A high-accuracy step counting algorithm for iPhones using accelerometer | |
| CN112067015A (en) | Step counting method and device based on convolutional neural network and readable storage medium | |
| CN107091650A (en) | A kind of software step-recording method based on mobile phone acceleration and range sensor | |
| CN108814618A (en) | A kind of recognition methods of motion state, device and terminal device | |
| Seo et al. | Step counting on smartphones using advanced zero-crossing and linear regression | |
| Tomlein et al. | Advanced Pedometer for Smartphone-based Activity Tracking. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |