CN106491138A - A kind of motion state detection method and device - Google Patents
A kind of motion state detection method and device Download PDFInfo
- Publication number
- CN106491138A CN106491138A CN201610946341.7A CN201610946341A CN106491138A CN 106491138 A CN106491138 A CN 106491138A CN 201610946341 A CN201610946341 A CN 201610946341A CN 106491138 A CN106491138 A CN 106491138A
- Authority
- CN
- China
- Prior art keywords
- kinestate
- data
- acceleration
- gravity
- axle
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1123—Discriminating type of movement, e.g. walking or running
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Anesthesiology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of motion state detection method and device, method includes:Collection acceleration information；Low-pass filtering is carried out to acceleration information, obtains acceleration of gravity data；High-pass filtering is carried out to acceleration information, obtains moving acceleration data；Gravity sensitive axle is obtained, the moving acceleration data on the gravity sensitive axle is chosen, is carried out Fourier transformation；Frequency and amplitude according to Fourier transformation result carries out the identification of kinestate.The present invention carries out low-pass filtering and obtains acceleration of gravity data to acceleration information, high-pass filtering is carried out to acceleration information obtains moving acceleration data, the moving acceleration data that chooses on gravity sensitive axle carries out Fourier transformation, frequency and amplitude according to Fourier transformation result carries out the identification of kinestate, and recognition accuracy is high；Fourier transformation is carried out due to only choosing the moving acceleration data on gravity sensitive axle, data processing speed is improve, is improve the detection efficiency of whole method for testing motion.
Description
Technical field
The invention belongs to motion state detection technical field, specifically, be related to a kind of motion state detection method and
Device.
Background technology
In consumer electronics product, the development for dressing class product is maked rapid progress, and becomes electronic product growth of stimulating consumption
An important growth point；Intelligent bracelet/wrist-watch is an important component part for dressing electronic product, and development is also especially
Rapidly.
Intelligent bracelet/wrist-watch recognizes the kinestate of wearer by built-in acceleration sensor, analyzes wearer's
Health status etc..But the recognition methodss accuracy rate to kinestate has a strong impact on the experience of user than relatively low at present.
Content of the invention
The invention provides a kind of motion state detection method, improves moving state identification accuracy rate.
For solving above-mentioned technical problem, the present invention is achieved using following technical proposals：
A kind of motion state detection method, methods described include:
Acceleration information is gathered by 3-axis acceleration sensor；
Low-pass filtering is carried out to the acceleration information for collecting, and obtains acceleration of gravity data；
High-pass filtering is carried out to the acceleration information for collecting, and obtains moving acceleration data；
Obtain gravity sensitive axle；
The moving acceleration data on the gravity sensitive axle is chosen, Fourier transformation is carried out；
Frequency and amplitude according to Fourier transformation result carries out the identification of kinestate.
Further, the acquisition gravity sensitive axle, specifically includes：
Obtain three number of axle evidence of x, y, z of acceleration of gravity data；
Respectively calculate x-axis, y-axis, the data accumulation of z-axis and；
It is gravity sensitive axes to select the cumulative and corresponding axle of maximum.
Further, 64 points of Fourier transformations are carried out to the moving acceleration data in gravity sensitive axes.
Further, the frequency and amplitude according to Fourier transformation result carries out the identification of kinestate, concrete bag
Include：
(1) in F ＜ 0.5Hz, if A≤360, kinestate is static/sleep；
(2) in 2Hz >=F ＞ 0.5Hz, if A >=360, kinestate is on foot；
(3) in 4Hz >=F ＞ 2Hz,
If A >=3400, kinestate is running；
If 3400 ＞ A >=360, kinestate is on foot；
(4) in 5.5Hz >=F ＞ 4Hz, if A >=3400, kinestate is running；
Wherein, F is frequency, and A is maximum amplitude.
Further, (1) in 2Hz >=F ＞ 0.5Hz,
If A >=1800, kinestate is to hurry up；
If 1800 ＞ A >=360, kinestate is to be careful；
(2) in 4Hz >=F ＞ 2Hz,
If 3400 ＞ A >=1800, kinestate is on foot；
If 1800 ＞ A >=360, kinestate is to be careful.
Preferably, if kinestate is for walking or running, according to peak-to-peak value or the valley-valley of moving acceleration data
Value determines the step number that walks or run.
Further, if kinestate is static/sleep, static/sleep state is judged according to exercise intensity：Static
State, trial sleep state, either shallow sleep state, deep sleep.
Further, described static/sleep state is judged according to exercise intensity, specifically include：
(1) exercise intensity is judged according to maximum amplitude A：
If the first setting values of A ＜, exercise intensity is harmonic motion intensity；
If the first setting value≤the second setting values of A ＜, exercise intensity is middle exercise intensity；
If A >=the second setting value, exercise intensity is high exercise intensity；
Wherein, the first setting value and the second setting value represent the judgment threshold of exercise intensity, and the first setting value is less than
Second setting value；
(2) static/sleep state is judged according to the accounting of harmonic motion intensity and middle exercise intensity：
In setting time section：
If middle exercise intensity accounting is more than 15%, for resting state；
If harmonic motion intensity accounting is less than 85%, for attempting sleep state；
If harmonic motion intensity accounting is 85%～90%, for either shallow sleep state；
If harmonic motion intensity accounting is more than 90%, for deep sleep.
A kind of motion state detection device, described device include：3-axis acceleration sensor, accelerates the number of degrees for gathering
According to；Low pass filter, carries out low-pass filtering for the acceleration information to collecting, and obtains acceleration of gravity data；High pass is filtered
Ripple device, carries out high-pass filtering for the acceleration information to collecting, and obtains moving acceleration data；Gravity sensitive axle obtains mould
Block, for obtaining gravity sensitive axle；Data transformation module, for carrying out in Fu to the moving acceleration data in gravity sensitive axes
Leaf transformation；Identification module, for carrying out the identification of kinestate according to the frequency and amplitude of Fourier transformation result.
Further, the gravity sensitive axle acquisition module includes：Data selecting unit, for obtaining acceleration of gravity number
According to three number of axle evidence of x, y, z；Computing unit, for calculate x-axis, y-axis, the data accumulation of z-axis and；Judging unit, for selecting
The cumulative and corresponding axle of maximum is gravity sensitive axes.
Compared with prior art, advantages of the present invention and good effect are：The motion state detection method of the present invention and dress
Put, low-pass filtering is carried out to acceleration information and obtains acceleration of gravity data, high-pass filtering is carried out to acceleration information and is transported
Dynamic acceleration information, the moving acceleration data that chooses on gravity sensitive axle carry out Fourier transformation, are tied according to Fourier transformation
The frequency and amplitude of fruit carry out the identification of kinestate, and recognition accuracy is high；It is additionally, since the fortune that only chooses on gravity sensitive axle
Dynamic acceleration information carries out Fourier transformation, improves data processing speed, and then improves the inspection of whole method for testing motion
Efficiency is surveyed, is easy to wearer accurately and rapidly to know kinestate, is improve the experience of user.
After the specific embodiment of the present invention is read in conjunction with the accompanying, the other features and advantages of the invention will become more clear
Chu.
Description of the drawings
Fig. 1 is the flow chart of one embodiment of motion state detection method proposed by the present invention；
Fig. 2 is the flow chart for obtaining gravity sensitive axle in Fig. 1；
Fig. 3 is to judge static/dormant flow chart according to exercise intensity in Fig. 1；
Fig. 4 is the structural representation of one embodiment of motion state detection device proposed by the present invention；
Fig. 5 is the structural representation of gravity sensitive axle acquisition module in Fig. 4.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, below with reference to drawings and Examples,
The present invention is described in further detail.
The motion state detection method of the present embodiment mainly comprises the steps, shown in Figure 1.
Step S1：Acceleration information is gathered by 3-axis acceleration sensor.
In the present embodiment, the frequency acquisition of 3-axis acceleration sensor be 25Hz, sampling resolution be 12, range for ±
8G.
Step S2：Low-pass filtering is carried out to the acceleration information for collecting, and obtains acceleration of gravity data；To collected
Acceleration information carries out high-pass filtering, obtains moving acceleration data.
The frequency of acceleration of gravity concentrates on 0～0.5Hz, and the frequency of acceleration of motion concentrates on more than 1Hz.Using difference
Equation is realizing digital filter.Frequency characteristic according to acceleration of gravity and acceleration of motion separately designs low pass filter ginseng
Number and high pass filter parameter.In the present embodiment, the exponent number of low pass filter is 5, and the exponent number of high pass filter is 5.
Five order difference equations are：
Wherein,
X (n), x (n-1), x (n-2), x (n-3), x (n-4), x (n-5) are input；
Y (n), y (n-1), y (n-2), y (n-3), y (n-4), y (n-5) are output；
X (n), y (n) are respectively the input and output at current time；
X (n-1), y (n-1) are respectively the input and output at n-1 moment；
X (n-2), y (n-2) are respectively the input and output at n-2 moment；
X (n-3), y (n-3) are respectively the input and output at n-3 moment；
X (n-4), y (n-4) are respectively the input and output at n-4 moment；
X (n-5), y (n-5) are respectively the input and output at n-5 moment；
b0、b1、b2、b3、b4、b5Respectively x (n), x (n-1), x (n-2), x (n-3), x (n-4), the coefficient of x (n-5)；
a0、a1、a2、a3、a4、a5Respectively y (n), y (n-1), y (n-2), y (n-3), y (n-4), the coefficient of y (n-5)；According to wave filter
Characteristic, can be solved by matlab.
For example, according to the characteristic of low pass filter, each coefficient is solved by matlab：b0、b1、b2、b3、b4、b5Respectively
For 0.005697260391747, -0.015373021668546,0.009787689699089,0.009787689699089, -
0.015373021668546、0.005697260391747；a0、a1、a2、a3、a4、a5Respectively 1.000000000000000 ,-
4.555306658232217、8.364724372384901、-7.735045790224121、3.600565371916987、-
0.674713439000970.
For example, according to the characteristic of high pass filter, each coefficient is solved by matlab：b0、b1、b2、b3、b4、b5Respectively
For 0.748492395854167, -3.720442166646449,7.419000766140107, -7.419000766140107,
3.720442166646450、-0.748492395854167；a0、a1、a2、a3、a4、a5Respectively 1.000000000000000 ,-
4.394515159443736、7.781237674485100、-6.933413385072246、3.106924323424174、-
0.559780114856186.
Step S3：Gravity sensitive axle is obtained, the moving acceleration data on the gravity sensitive axle is chosen, is carried out Fourier's change
Change.
Obtain gravity sensitive axle and specifically include following step, shown in Figure 2.
S31：Obtain three number of axle evidence of x, y, z of acceleration of gravity data.
S32：Respectively calculate x-axis, y-axis, the data accumulation of z-axis and.
S33：It is gravity sensitive axes to select data accumulation and the corresponding axle of maximum.
For example, the x-axis data of acceleration of gravity data are x1、x2、x3、......、xm, y-axis data are y1、y2、
y3、......、ym, z-axis data are z1、z2、z3、......、zm.The data accumulation of x-axis and be x1+x2+x3+......+xm, y-axis
Data accumulation and be y1+y2+y3+......+ym, the data accumulation of z-axis and be z1+z2+z3+......+zm.Assume the number of z-axis
According to cumulative and maximum, then z-axis is gravity sensitive axes.
After gravity sensitive axle determines, the moving acceleration data on the gravity sensitive axle is chosen, Fourier transformation is carried out.?
In the present embodiment, the moving acceleration data of selection is carried out 64 points of FFTs, to improve data processing precision.Due to accelerating
The frequency acquisition of degree sensor is 25HZ, and 25 data paddings are carried out 64 points of FFTs, resolution to 64 data therefore
For：25/64=0.39Hz.
In the present embodiment, Fourier transformation is carried out due to only choosing the moving acceleration data on gravity sensitive axle, and
Moving acceleration data on not all axle, therefore data processing speed is very fast, improves the inspection of whole method for testing motion
Survey efficiency.
Step S4：Frequency and amplitude according to Fourier transformation result carries out the identification of kinestate.
Fourier transformation, can will transform from the time domain to frequency domain to the analysis of signal.Some signals are difficult from time-domain analyses
Signal characteristic is held, but is gone to analyze if transforming to frequency domain, be just readily seen feature, namely be readily seen the signal
Amplitude/frequency characteristic.
As Fourier transformation can obtain amplitude/frequency characteristic of the signal on frequency domain, walking/running in conjunction with people
The frequency of step/static (sleep) action and the difference characteristic of amplitude, can be very good to enter action according to the result of Fourier transformation
Work is classified, namely the frequency being located according to maximum amplitude and maximum amplitude carry out on foot, run, static (sleep) action is known
Not, the recognition accuracy of kinestate is improve.
In the present embodiment, specific identification process is：
(1) in F ＜ 0.5Hz, if A≤360, kinestate is static/sleep.
(2) in 2Hz >=F ＞ 0.5Hz, if A >=360, kinestate is on foot.
When kinestate is on foot, this kinestate of walking can further be divided.If A >=1800,
Then kinestate is to hurry up；If 1800 ＞ A >=360, kinestate is to be careful.
(3) in 4Hz >=F ＞ 2Hz：
If A >=3400, kinestate is running.
If 3400 ＞ A >=360, kinestate is on foot.
When kinestate is on foot, this kinestate of walking can further be divided.If 3400 ＞ A >=
1800, then kinestate is on foot；If 1800 ＞ A >=360, kinestate is to be careful.
(4) in 5.5Hz >=F ＞ 4Hz, if A >=3400, kinestate is running.
Wherein, F is frequency, and A is maximum amplitude.
(5) in F >=5.5Hz, it is interference, is not identified.
Therefore, kinestate can quickly and accurately be recognized by frequency and amplitude.
Step S5：If kinestate is for walking or running, according to the moving acceleration data on gravity sensitive axle
Peak-to-peak value or valley-valley value determine the step number that walks or run.
Peak-peak (or valley-valley) represents a step, is confirmed according to peak-to-peak value or valley-valley value on foot or running step number.
When step number is counted, violate-action is removed by windowing process, to improve step number statistical accuracy.At adding window
Managing principle is：According to walk and running action frequency characteristic (most fast action be 1s move 5 steps；Most slow action is transported for 2s
Dynamic 1 step) defining " time window ", for excluding invalid vibration.Assume that the most fast velocity of people is 5 step per second, most slowly
Walking speed be per 2 seconds 1 steps, so, the time interval of two effective paces within time window [0.2,2.0] s, the time
Interval should be all excluded beyond all paces of the time window, so as to improve step number statistical accuracy.
Step S6：If kinestate is static/sleep, static/sleep state is judged according to exercise intensity：Static shape
State, trial sleep state, either shallow sleep state, deep sleep.
Static/dormant judgement is carried out by the statistics to exercise intensity, specifically includes following step, referring to figure
Shown in 3.
Step S61：Exercise intensity is judged according to maximum amplitude A.
If the first setting values of A ＜, exercise intensity is harmonic motion intensity；
If the first setting value≤the second setting values of A ＜, exercise intensity is middle exercise intensity；
If A >=the second setting value, exercise intensity is high exercise intensity.
Wherein, the first setting value and the second setting value represent the judgment threshold of exercise intensity.First setting value is less than second
Setting value.In the present embodiment, the first setting value is 45, and the second setting value is 75.
Step S62：Accounting according to harmonic motion intensity and middle exercise intensity judges static/sleep state.
In setting time section, in such as 2 minutes：
If middle exercise intensity accounting is more than 15%, for resting state；
If harmonic motion intensity accounting is less than 85%, for attempting sleep state；
If harmonic motion intensity accounting is 85%～90%, for either shallow sleep state；
If harmonic motion intensity accounting is more than 90%, for deep sleep.
Judge that static/dormant four states, accuracy of judgement are easy to user accurately to know oneself according to exercise intensity
Sleep quality, so as to adjust oneself quantity of motion, length of one's sleep etc., reach the purpose of healthy living.
Step S7：Preserve.
The information such as kinestate, step number, timestamp are preserved, is easy to analyze the motion of different time sections, sleep in one day
Situation, and the motion conditions block diagram and sleep quality block diagram of different time sections is drawn out, it is easy to the health for monitoring wearer
Situation.
The motion state detection method of the present embodiment, carries out low-pass filtering and obtains acceleration of gravity number to acceleration information
According to, acceleration information is carried out high-pass filtering obtain moving acceleration data, choose gravity sensitive axle on acceleration of motion number
According to Fourier transformation is carried out, the frequency and amplitude according to Fourier transformation result carries out the identification of kinestate, improves motion
The accuracy rate of state recognition, recognition accuracy are high；Being additionally, since the moving acceleration data that only chooses on gravity sensitive axle is carried out
Fourier transformation, improves data processing speed, and then improves the detection efficiency of whole method for testing motion, is easy to wearer
Accurately and rapidly know kinestate, improve the experience of user.
The present embodiment also proposed a kind of motion state detection device, the device mainly include 3-axis acceleration sensor,
Low pass filter, high pass filter, gravity sensitive axle acquisition module, data transformation module, identification module etc., shown in Figure 4.
3-axis acceleration sensor, for gathering acceleration information.
Low pass filter, carries out low-pass filtering for the acceleration information to collecting, and obtains acceleration of gravity data.
High pass filter, carries out high-pass filtering for the acceleration information to collecting, and obtains moving acceleration data.
Gravity sensitive axle acquisition module, for obtaining gravity sensitive axle.Gravity sensitive axle acquisition module mainly includes data
Unit, computing unit, judging unit is chosen, shown in Figure 5.Specifically, data selecting unit, for obtaining gravity acceleration
Three number of axle evidence of x, y, z of degrees of data；Computing unit, for calculate x-axis, y-axis, the data accumulation of z-axis and；Judging unit, is used for
It is gravity sensitive axes to select the cumulative and corresponding axle of maximum.
Data transformation module, for carrying out Fourier transformation to the moving acceleration data in gravity sensitive axes.
Identification module, for carrying out the identification of kinestate according to the frequency and amplitude of Fourier transformation result.
The course of work of specific motion state detection device, describes in detail in above-mentioned motion state detection method, this
It will not go into details at place.
The motion state detection device of the present embodiment, carries out low-pass filtering and obtains acceleration of gravity number to acceleration information
According to, acceleration information is carried out high-pass filtering obtain moving acceleration data, choose gravity sensitive axle on acceleration of motion number
According to Fourier transformation is carried out, the frequency and amplitude according to Fourier transformation result carries out the identification of kinestate, recognition accuracy
High；Being additionally, since the moving acceleration data that only chooses on gravity sensitive axle carries out Fourier transformation, improves data processing speed
Degree, and then the detection efficiency of whole method for testing motion is improve, it is easy to wearer accurately and rapidly to know kinestate, carries
The high experience of user.
The motion state detection device of the present embodiment can be applicable to the wearing class product such as Intelligent bracelet/wrist-watch, to strengthen intelligence
The function of energy bracelet/wrist-watch, monitors the health condition of wearer.
Above example is only in order to illustrating technical scheme, rather than is limited；Although with reference to aforementioned reality
Apply example to be described in detail the present invention, for the person of ordinary skill of the art, still can be to aforementioned enforcement
Technical scheme described in example is modified, or carries out equivalent to which part technical characteristic；And these are changed or replace
Change, do not make the essence of appropriate technical solution depart from the spirit and scope of claimed technical solution of the invention.
Claims (10)
1. a kind of motion state detection method, it is characterised in that：Methods described includes:
Acceleration information is gathered by 3-axis acceleration sensor；
Low-pass filtering is carried out to the acceleration information for collecting, and obtains acceleration of gravity data；
High-pass filtering is carried out to the acceleration information for collecting, and obtains moving acceleration data；
Obtain gravity sensitive axle；
The moving acceleration data on the gravity sensitive axle is chosen, Fourier transformation is carried out；
Frequency and amplitude according to Fourier transformation result carries out the identification of kinestate.
2. motion state detection method according to claim 1, it is characterised in that：The acquisition gravity sensitive axle, specifically
Including：
Obtain three number of axle evidence of x, y, z of acceleration of gravity data；
Respectively calculate x-axis, y-axis, the data accumulation of z-axis and；
It is gravity sensitive axes to select the cumulative and corresponding axle of maximum.
3. motion state detection method according to claim 1, it is characterised in that：Motion in gravity sensitive axes is accelerated
Degrees of data carries out 64 points of Fourier transformations.
4. motion state detection method according to claim 1, it is characterised in that：Described according to Fourier transformation result
Frequency and amplitude carry out the identification of kinestate, specifically include：
（1）In F ＜ 0.5Hz, if A≤360, kinestate is static/sleep；
（2）In 2Hz >=F ＞ 0.5Hz, if A >=360, kinestate is on foot；
（3）In 4HZ >=F ＞ 2HZ,
If A >=3400, kinestate is running；
If 3400 ＞ A >=360, kinestate is on foot；
（4）In 5.5Hz >=F ＞ 4Hz, if A >=3400, kinestate is running；
Wherein, F is frequency, and A is maximum amplitude.
5. motion state detection method according to claim 4, it is characterised in that：
（1）In 2Hz >=F ＞ 0.5Hz,
If A >=1800, kinestate is to hurry up；
If 1800 ＞ A >=360, kinestate is to be careful；
（2）In 4Hz >=F ＞ 2Hz,
If 3400 ＞ A >=1800, kinestate is on foot；
If 1800 ＞ A >=360, kinestate is to be careful.
6. motion state detection method according to claim 4, it is characterised in that：If kinestate is to walk or run
Step, then determine the step number that walks or run according to the peak-to-peak value of moving acceleration data or valley-valley value.
7. motion state detection method according to claim 4, it is characterised in that：If kinestate is static/sleep,
Static/sleep state is judged according to exercise intensity then：Resting state, trial sleep state, either shallow sleep state, deep sleep's shape
State.
8. motion state detection method according to claim 7, it is characterised in that：Described judged according to exercise intensity quiet
Only/sleep state, specifically includes：
（1）Exercise intensity is judged according to maximum amplitude A：
If the first setting values of A ＜, exercise intensity is harmonic motion intensity；
If the first setting value≤the second setting values of A ＜, exercise intensity is middle exercise intensity；
If A >=the second setting value, exercise intensity is high exercise intensity；
Wherein, the first setting value and the second setting value represent the judgment threshold of exercise intensity, and the first setting value is less than second
Setting value；
（2）Accounting according to harmonic motion intensity and middle exercise intensity judges static/sleep state：
In setting time section：
If middle exercise intensity accounting is more than 15%, for resting state；
If harmonic motion intensity accounting is less than 85%, for attempting sleep state；
If harmonic motion intensity accounting is 85%～90%, for either shallow sleep state；
If harmonic motion intensity accounting is more than 90%, for deep sleep.
9. a kind of motion state detection device, it is characterised in that：Described device includes：
3-axis acceleration sensor, for gathering acceleration information；
Low pass filter, carries out low-pass filtering for the acceleration information to collecting, and obtains acceleration of gravity data；
High pass filter, carries out high-pass filtering for the acceleration information to collecting, and obtains moving acceleration data；
Gravity sensitive axle acquisition module, for obtaining gravity sensitive axle；
Data transformation module, for carrying out Fourier transformation to the moving acceleration data in gravity sensitive axes；
Identification module, for carrying out the identification of kinestate according to the frequency and amplitude of Fourier transformation result.
10. motion state detection device according to claim 9, it is characterised in that：The gravity sensitive axle acquisition module
Including：
Data selecting unit, for obtaining three number of axle evidence of x, y, z of acceleration of gravity data；
Computing unit, for calculate x-axis, y-axis, the data accumulation of z-axis and；
Judging unit, is gravity sensitive axes for selecting the cumulative and corresponding axle of maximum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610946341.7A CN106491138B (en) | 2016-10-26 | 2016-10-26 | A kind of motion state detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610946341.7A CN106491138B (en) | 2016-10-26 | 2016-10-26 | A kind of motion state detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106491138A true CN106491138A (en) | 2017-03-15 |
| CN106491138B CN106491138B (en) | 2019-04-09 |
Family
ID=58322986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610946341.7A Active CN106491138B (en) | 2016-10-26 | 2016-10-26 | A kind of motion state detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106491138B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107167159A (en) * | 2017-04-26 | 2017-09-15 | 青岛海信移动通信技术股份有限公司 | The method and mobile terminal of a kind of mobile terminal step |
| CN108332745A (en) * | 2018-05-03 | 2018-07-27 | 深圳瑞德感知科技有限公司 | Small distance movement track tracing device, system and method |
| CN108814618A (en) * | 2018-04-27 | 2018-11-16 | 歌尔科技有限公司 | A kind of recognition methods of motion state, device and terminal device |
| CN108937860A (en) * | 2018-06-06 | 2018-12-07 | 歌尔科技有限公司 | A kind of motion state monitoring method, system and equipment and storage medium |
| CN108986883A (en) * | 2017-06-02 | 2018-12-11 | 四川理工学院 | A kind of moving state identification system and method based on Android platform |
| CN109387203A (en) * | 2017-08-03 | 2019-02-26 | 卡西欧计算机株式会社 | Activity situation analytical equipment, movable state analyzing method and recording medium |
| CN110180158A (en) * | 2019-07-02 | 2019-08-30 | 乐跑体育互联网（武汉）有限公司 | A kind of running state identification method, system and terminal device |
| CN110680337A (en) * | 2019-10-23 | 2020-01-14 | 无锡慧眼人工智能科技有限公司 | Method for identifying action types |
| CN111643091A (en) * | 2020-05-18 | 2020-09-11 | 歌尔科技有限公司 | Motion state detection method and device |
| CN112042554A (en) * | 2020-08-15 | 2020-12-08 | 天津市可利农物联科技产业发展有限公司 | Pig exercise amount monitoring device and exercise amount detection scoring method thereof |
| CN112716637A (en) * | 2020-12-25 | 2021-04-30 | 深圳市力博得科技有限公司 | Tooth surface abnormal state detection method and intelligent toothbrush |
| CN113340322A (en) * | 2021-06-25 | 2021-09-03 | 歌尔科技有限公司 | Step counting method and device, electronic equipment and readable storage medium |
| CN114440884A (en) * | 2022-04-11 | 2022-05-06 | 天津果实科技有限公司 | Intelligent analysis method for human body posture for intelligent posture correction equipment |
| WO2022111203A1 (en) * | 2020-11-25 | 2022-06-02 | 安徽华米健康科技有限公司 | Heart rate detection method and device |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101394787A (en) * | 2006-03-14 | 2009-03-25 | 索尼株式会社 | Body movement detector, body movement detection method and body movement detection program |
| CN101526352A (en) * | 2009-04-01 | 2009-09-09 | 西北工业大学 | Orienting method of gravity direction on moving platform |
| CN101685026A (en) * | 2008-09-24 | 2010-03-31 | 三一重工股份有限公司 | Method and device for calibrating zero position output value of sensitive shaft of tilt angle sensor |
| WO2011003218A1 (en) * | 2009-07-07 | 2011-01-13 | Han Zheng | Acceleration motion identify method and system thereof |
| CN102003961A (en) * | 2008-08-29 | 2011-04-06 | 索尼公司 | Velocity calculation device,velocity calculation method, and navigation device |
| CN102289306A (en) * | 2011-08-30 | 2011-12-21 | 江苏惠通集团有限责任公司 | Attitude sensing equipment and positioning method thereof as well as method and device for controlling mouse pointer |
| CN102654515A (en) * | 2011-03-04 | 2012-09-05 | 美新微纳传感***有限公司 | Calibration algorithm for z sensitive shaft of three-shaft acceleration transducer |
| US20140019080A1 (en) * | 2012-07-12 | 2014-01-16 | Vital Connect, Inc. | Calibration of a chest-mounted wireless sensor device for posture and activity detection |
| CN103733078A (en) * | 2011-08-18 | 2014-04-16 | 皇家飞利浦有限公司 | Estimating velocity in a horizontal or vertical direction from acceleration measurements |
| US20140243682A1 (en) * | 2011-10-20 | 2014-08-28 | Koninklijke Philips N.V. | Device and method for monitoring movement and orientation of the device |
| US8876738B1 (en) * | 2007-04-04 | 2014-11-04 | Dp Technologies, Inc. | Human activity monitoring device |
| CN104132662A (en) * | 2014-07-25 | 2014-11-05 | 辽宁工程技术大学 | Closed-loop Kalman filter inertial positioning method based on zero velocity update |
-
2016
- 2016-10-26 CN CN201610946341.7A patent/CN106491138B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101394787A (en) * | 2006-03-14 | 2009-03-25 | 索尼株式会社 | Body movement detector, body movement detection method and body movement detection program |
| US8876738B1 (en) * | 2007-04-04 | 2014-11-04 | Dp Technologies, Inc. | Human activity monitoring device |
| CN102003961A (en) * | 2008-08-29 | 2011-04-06 | 索尼公司 | Velocity calculation device,velocity calculation method, and navigation device |
| CN101685026A (en) * | 2008-09-24 | 2010-03-31 | 三一重工股份有限公司 | Method and device for calibrating zero position output value of sensitive shaft of tilt angle sensor |
| CN101526352A (en) * | 2009-04-01 | 2009-09-09 | 西北工业大学 | Orienting method of gravity direction on moving platform |
| WO2011003218A1 (en) * | 2009-07-07 | 2011-01-13 | Han Zheng | Acceleration motion identify method and system thereof |
| CN102654515A (en) * | 2011-03-04 | 2012-09-05 | 美新微纳传感***有限公司 | Calibration algorithm for z sensitive shaft of three-shaft acceleration transducer |
| CN103733078A (en) * | 2011-08-18 | 2014-04-16 | 皇家飞利浦有限公司 | Estimating velocity in a horizontal or vertical direction from acceleration measurements |
| CN102289306A (en) * | 2011-08-30 | 2011-12-21 | 江苏惠通集团有限责任公司 | Attitude sensing equipment and positioning method thereof as well as method and device for controlling mouse pointer |
| US20140243682A1 (en) * | 2011-10-20 | 2014-08-28 | Koninklijke Philips N.V. | Device and method for monitoring movement and orientation of the device |
| US20140019080A1 (en) * | 2012-07-12 | 2014-01-16 | Vital Connect, Inc. | Calibration of a chest-mounted wireless sensor device for posture and activity detection |
| CN104132662A (en) * | 2014-07-25 | 2014-11-05 | 辽宁工程技术大学 | Closed-loop Kalman filter inertial positioning method based on zero velocity update |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107167159A (en) * | 2017-04-26 | 2017-09-15 | 青岛海信移动通信技术股份有限公司 | The method and mobile terminal of a kind of mobile terminal step |
| CN107167159B (en) * | 2017-04-26 | 2020-06-23 | 青岛海信移动通信技术股份有限公司 | Mobile terminal step counting method and mobile terminal |
| CN108986883A (en) * | 2017-06-02 | 2018-12-11 | 四川理工学院 | A kind of moving state identification system and method based on Android platform |
| CN108986883B (en) * | 2017-06-02 | 2021-08-10 | 四川理工学院 | Motion state identification system and method based on Android platform |
| CN109387203A (en) * | 2017-08-03 | 2019-02-26 | 卡西欧计算机株式会社 | Activity situation analytical equipment, movable state analyzing method and recording medium |
| CN108814618A (en) * | 2018-04-27 | 2018-11-16 | 歌尔科技有限公司 | A kind of recognition methods of motion state, device and terminal device |
| CN108332745A (en) * | 2018-05-03 | 2018-07-27 | 深圳瑞德感知科技有限公司 | Small distance movement track tracing device, system and method |
| CN108937860B (en) * | 2018-06-06 | 2021-02-02 | 歌尔科技有限公司 | Motion state monitoring method, system and equipment and storage medium |
| CN108937860A (en) * | 2018-06-06 | 2018-12-07 | 歌尔科技有限公司 | A kind of motion state monitoring method, system and equipment and storage medium |
| CN110180158A (en) * | 2019-07-02 | 2019-08-30 | 乐跑体育互联网（武汉）有限公司 | A kind of running state identification method, system and terminal device |
| CN110680337A (en) * | 2019-10-23 | 2020-01-14 | 无锡慧眼人工智能科技有限公司 | Method for identifying action types |
| CN111643091A (en) * | 2020-05-18 | 2020-09-11 | 歌尔科技有限公司 | Motion state detection method and device |
| CN112042554A (en) * | 2020-08-15 | 2020-12-08 | 天津市可利农物联科技产业发展有限公司 | Pig exercise amount monitoring device and exercise amount detection scoring method thereof |
| WO2022111203A1 (en) * | 2020-11-25 | 2022-06-02 | 安徽华米健康科技有限公司 | Heart rate detection method and device |
| CN112716637A (en) * | 2020-12-25 | 2021-04-30 | 深圳市力博得科技有限公司 | Tooth surface abnormal state detection method and intelligent toothbrush |
| CN112716637B (en) * | 2020-12-25 | 2022-10-25 | 东莞市力博得电子科技有限公司 | Tooth surface abnormal state detection method and intelligent toothbrush |
| CN113340322A (en) * | 2021-06-25 | 2021-09-03 | 歌尔科技有限公司 | Step counting method and device, electronic equipment and readable storage medium |
| CN114440884A (en) * | 2022-04-11 | 2022-05-06 | 天津果实科技有限公司 | Intelligent analysis method for human body posture for intelligent posture correction equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106491138B (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106491138A (en) | A kind of motion state detection method and device | |
| CN104990562B (en) | Step-recording method based on auto-correlation computation | |
| CN104200234B (en) | Human action models and recognition methods | |
| CN103954295B (en) | A kind of step-recording method based on acceleration transducer | |
| CN103997572B (en) | A kind of step-recording method based on mobile phone acceleration sensor data and device | |
| JP6567658B2 (en) | Device and method for classifying user activity and / or counting user steps | |
| WO2015100707A1 (en) | Step counting method and apparatus | |
| CN106767888A (en) | A kind of meter based on Wave crest and wave trough detection walks algorithm | |
| CN105877757A (en) | Multi-sensor integrated human motion posture capturing and recognizing device | |
| CN105030260A (en) | Judgment method for motion state and footwear | |
| CN112464738B (en) | Improved naive Bayes algorithm user behavior identification method based on mobile phone sensor | |
| CN107588784A (en) | A kind of state recognition and the method, apparatus and terminal distinguished | |
| CN107091650A (en) | A kind of software step-recording method based on mobile phone acceleration and range sensor | |
| CN108008151A (en) | A kind of moving state identification method and system based on 3-axis acceleration sensor | |
| CN108836337A (en) | A method of personalized sufficient type health detection is carried out by foot movement state | |
| CN105180959A (en) | Anti-interference step counting method for wrist type step counting devices | |
| CN110169774A (en) | A kind of moving state identification system and method based on block chain | |
| CN107270931A (en) | A kind of IOS and the general gait auto-correlation pedometer of Android platform | |
| CN104586402A (en) | Feature extracting method for body activities | |
| CN108827290A (en) | A kind of human motion state inverting device and method | |
| CN103417216B (en) | Pressure center nonlinear feature extraction method based on complexity | |
| CN111772639B (en) | Motion pattern recognition method and device for wearable equipment | |
| JP5699717B2 (en) | Step detection device, electronic device and program | |
| CN105760819A (en) | Daily activity recognition method based on acceleration signal | |
| US20150032033A1 (en) | Apparatus and method for identifying movement in a patient |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |