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
- motion
- acceleration data
- axis
- state
- data
- 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
- 230000033001 locomotion Effects 0.000 title claims abstract description 124
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 230000001133 acceleration Effects 0.000 claims abstract description 96
- 230000005484 gravity Effects 0.000 claims abstract description 67
- 238000001914 filtration Methods 0.000 claims abstract description 22
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 7
- 238000009825 accumulation Methods 0.000 claims description 12
- 206010062519 Poor quality sleep Diseases 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 238000013501 data transformation Methods 0.000 claims description 4
- 230000000284 resting effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 7
- 230000009471 action Effects 0.000 description 5
- 230000036541 health Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 230000004622 sleep time Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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 the technical field of motion state detection, and particularly relates to a motion state detection method and device.
Background
In consumer electronics, the development of wearable products is changing day by day and becomes an important growth point for pulling the consumer electronics to grow; the intelligent bracelet/watch is an important component of wearable electronic products, and the development is particularly rapid.
The intelligent bracelet/watch identifies the motion state of the wearer through a built-in acceleration sensor, analyzes the health condition of the wearer and the like. However, the accuracy of the current identification method for the motion state is low, and the use experience of a user is seriously influenced.
Disclosure of Invention
The invention provides a motion state detection method, which improves the motion state identification accuracy.
In order to solve the technical problems, the invention adopts the following technical scheme:
a motion state detection method, the method comprising:
acquiring acceleration data through a three-axis acceleration sensor;
carrying out low-pass filtering on the collected acceleration data to obtain gravity acceleration data;
carrying out high-pass filtering on the acquired acceleration data to obtain motion acceleration data;
acquiring a gravity sensitive shaft;
selecting motion acceleration data on the gravity sensitive axis, and performing Fourier transform;
and identifying the motion state according to the frequency and the amplitude of the Fourier transform result.
Further, the acquiring the gravity sensitive axis specifically includes:
acquiring three-axis data of x, y and z of the gravity acceleration data;
respectively calculating the data accumulation sum of the x axis, the y axis and the z axis;
and selecting an axis corresponding to the accumulation sum maximum value as a gravity sensitive axis.
Still further, the motion acceleration data on the gravity sensing axis is subjected to 64-point Fourier transform.
Further, the identifying the motion state according to the frequency and the amplitude of the fourier transform result specifically includes:
(1) when F is less than 0.5Hz, if A is less than or equal to 360 degrees, the movement state is static/sleeping;
(2) when F is more than 0.5Hz and more than 2Hz, if A is more than or equal to 360 Hz, the movement state is walking;
(3) when the frequency is more than or equal to 4Hz and more than 2Hz,
if A is not less than 3400, the exercise state is running;
if 3400 is more than A and is more than or equal to 360, the motion state is walking;
(4) when F is more than 4Hz and more than 5.5Hz, if A is more than 3400, the exercise state is running;
where F is the frequency and A is the maximum amplitude.
Further, (1) when 2Hz is more than or equal to F and more than 0.5Hz,
if A is larger than or equal to 1800, the motion state is fast walking;
if 1800 & gtA is more than or equal to 360, the motion state is slow walking;
(2) when the frequency is more than or equal to 4Hz and more than 2Hz,
if 3400 is more than A and is more than or equal to 1800, the motion state is walking;
if 1800 & gtA is larger than or equal to 360, the movement state is slow walking.
Preferably, if the exercise state is walking or running, the number of steps of walking or running is determined from the peak-to-peak or valley-to-valley values of the exercise acceleration data.
Further, if the motion state is still/sleep, the still/sleep state is judged according to the motion intensity: quiescent state, attempted sleep state, light sleep state, deep sleep state.
Still further, the determining the still/sleep state according to the exercise intensity specifically includes:
(1) judging the motion intensity according to the maximum amplitude A:
if A is less than the first set value, the exercise intensity is low;
if the first set value is less than or equal to A and less than the second set value, the exercise intensity is the middle exercise intensity;
if A is larger than or equal to a second set value, the exercise intensity is high;
wherein the first set value and the second set value represent a judgment threshold value of the exercise intensity, and the first set value is smaller than the second set value;
(2) judging the resting/sleeping state according to the ratio of the low exercise intensity to the medium exercise intensity:
within a set time period:
if the ratio of the exercise intensity is more than 15%, the state is static;
if the low exercise intensity ratio is less than 85%, the sleep state is tried;
if the low exercise intensity accounts for 85% -90%, the sleep state is a light sleep state;
if the ratio of the low exercise intensity is more than 90%, the sleep state is a deep sleep state.
A motion state detection apparatus, the apparatus comprising: the three-axis acceleration sensor is used for acquiring acceleration data; the low-pass filter is used for carrying out low-pass filtering on the acquired acceleration data to obtain gravity acceleration data; the high-pass filter is used for carrying out high-pass filtering on the acquired acceleration data to obtain motion acceleration data; the gravity sensitive shaft acquisition module is used for acquiring a gravity sensitive shaft; the data transformation module is used for carrying out Fourier transformation on the motion acceleration data on the gravity sensitive axis; and the identification module is used for identifying the motion state according to the frequency and the amplitude of the Fourier transform result.
Further, the gravity sensitive axis acquisition module includes: the data selection unit is used for acquiring the data of the x, y and z axes of the gravity acceleration data; the calculating unit is used for calculating the data accumulation sum of the x axis, the y axis and the z axis; and the judging unit is used for selecting the axis corresponding to the accumulation sum maximum value as the gravity sensitive axis.
Compared with the prior art, the invention has the advantages and positive effects that: according to the motion state detection method and device, the acceleration data are subjected to low-pass filtering to obtain the gravity acceleration data, the acceleration data are subjected to high-pass filtering to obtain the motion acceleration data, the motion acceleration data on the gravity sensitive axis are selected to be subjected to Fourier transform, and the motion state is identified according to the frequency and the amplitude of the Fourier transform result, so that the identification accuracy is high; in addition, because only the motion acceleration data on the gravity sensitive axis is selected for Fourier transform, the data processing speed is improved, the detection efficiency of the whole motion detection method is further improved, a wearer can accurately and quickly know the motion state conveniently, and the use experience of the user is improved.
Other features and advantages of the present invention will become more apparent from the following detailed description of the invention when taken in conjunction with the accompanying drawings.
Drawings
FIG. 1 is a flow chart of one embodiment of a motion state detection method proposed by the present invention;
FIG. 2 is a flow chart of the acquisition of the gravity sensitive axis of FIG. 1;
FIG. 3 is a flow chart of the determination of the still/sleep state based on exercise intensity of FIG. 1;
fig. 4 is a schematic structural diagram of an embodiment of the motion state detection device according to the present invention;
fig. 5 is a schematic structural diagram of the gravity-sensitive axis acquisition module in fig. 4.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and examples.
The motion state detection method of the present embodiment mainly includes the following steps, as shown in fig. 1.
Step S1: and acquiring acceleration data through a three-axis acceleration sensor.
In the embodiment, the acquisition frequency of the triaxial acceleration sensor is 25Hz, the sampling digit number is 12 digits, and the measuring range is ± 8G.
Step S2: carrying out low-pass filtering on the collected acceleration data to obtain gravity acceleration data; and carrying out high-pass filtering on the acquired acceleration data to obtain the motion acceleration data.
The frequency of the gravity acceleration is concentrated on 0-0.5 Hz, and the frequency of the motion acceleration is concentrated on more than 1 Hz. The digital filter is implemented using a difference equation. And respectively designing a low-pass filter parameter and a high-pass filter parameter according to the frequency characteristics of the gravity acceleration and the motion acceleration. In this embodiment, the low pass filter has an order of 5 and the high pass filter has an order of 5.
The fifth order difference equation is:
wherein,
x (n), x (n-1), x (n-2), x (n-3), x (n-4) and x (n-5) are used as input;
y (n), y (n-1), y (n-2), y (n-3), y (n-4) and y (n-5) are output;
x (n), y (n) are input and output at the current time, respectively;
x (n-1) and y (n-1) are input and output at the moment of n-1 respectively;
x (n-2) and y (n-2) are input and output at the moment of n-2 respectively;
x (n-3) and y (n-3) are input and output at the moment of n-3 respectively;
x (n-4) and y (n-4) are input and output at the moment of n-4 respectively;
x (n-5) and y (n-5) are input and output at the time of n-5 respectively;
b0、b1、b2、b3、b4、b5coefficients x (n), x (n-1), x (n-2), x (n-3), x (n-4), x (n-5), respectively; a is0、a1、a2、a3、a4、a5Coefficients for y (n), y (n-1), y (n-2), y (n-3), y (n-4), y (n-5), respectively; according to the characteristics of the filter, the filter can be solved through matlab.
For example, according to the characteristics of the low-pass filter, the coefficients are solved by matlab: b0、b1、b2、b3、b4、b50.005697260391747, -0.015373021668546, 0.009787689699089, 0.009787689699089, -0.015373021668546, 0.005697260391747; a is0、a1、a2、a3、a4、a51.000000000000000, -4.555306658232217, 8 respectively.364724372384901、-7.735045790224121、3.600565371916987、-0.674713439000970。
For example, according to the characteristics of the high-pass filter, the coefficients are solved by matlab: b0、b1、b2、b3、b4、b50.748492395854167, -3.720442166646449, 7.419000766140107, -7.419000766140107, 3.720442166646450, -0.748492395854167; a is0、a1、a2、a3、a4、a51.000000000000000, -4.394515159443736, 7.781237674485100, -6.933413385072246, 3.106924323424174 and-0.559780114856186 respectively.
Step S3: and acquiring a gravity sensitive axis, selecting motion acceleration data on the gravity sensitive axis, and performing Fourier transform.
The acquisition of the gravity sensitive axis specifically comprises the following steps, which are shown in fig. 2.
S31: and acquiring the data of the x, y and z axes of the gravity acceleration data.
S32: and respectively calculating the data accumulation sum of the x axis, the y axis and the z axis.
S33: and selecting an axis corresponding to the data accumulation sum maximum value as a gravity sensitive axis.
For example, the x-axis data of the gravity acceleration data is x1、x2、x3、......、xmAnd y-axis data is y1、y2、y3、......、ymZ-axis data being z1、z2、z3、......、zm. The sum of the x-axis data is x1+x2+x3+......+xmThe sum of the data on the y-axis is y1+y2+y3+......+ymThe sum of the data in the z-axis is z1+z2+z3+......+zm. Assuming that the sum of data for the z-axis is maximum, the z-axis is the gravity sensitive axis.
And after the gravity sensitive axis is determined, selecting the motion acceleration data on the gravity sensitive axis, and performing Fourier transform. In the present embodiment, 64-point FFT transformation is performed on the selected motion acceleration data to improve the data processing accuracy. Because the acquisition frequency of the acceleration sensor is 25HZ, zero padding is performed on 25 data to 64 data, 64-point FFT conversion is performed, and the resolution is as follows: 25/64-0.39 Hz.
In the embodiment, only the motion acceleration data on the gravity sensitive axis is selected to perform fourier transform, instead of the motion acceleration data on all axes, so that the data processing speed is high, and the detection efficiency of the whole motion detection method is improved.
Step S4: and identifying the motion state according to the frequency and the amplitude of the Fourier transform result.
Fourier transform, the analysis of the signal can be transformed from the time domain to the frequency domain. Some signals are difficult to grasp from time domain analysis, but if transformed to frequency domain for analysis, the features, i.e., the amplitude/frequency characteristics of the signal, are easily seen.
The amplitude/frequency characteristic of the signal on the frequency domain can be obtained through Fourier transform, and then the difference characteristics of the frequency and the amplitude of walking/running/still (sleeping) actions of a person are combined, so that action classification can be well carried out according to the result of the Fourier transform, namely walking, running and still (sleeping) actions are identified according to the maximum amplitude and the frequency of the maximum amplitude, and the identification accuracy of the motion state is improved.
In this embodiment, the specific identification process is as follows:
(1) when F is less than 0.5Hz, if A is less than or equal to 360 degrees, the movement state is still/sleep.
(2) When F is more than 0.5Hz and more than 2Hz, if A is more than 360 Hz, the movement state is walking.
When the motion state is walking, the motion state of walking can be further divided. If A is larger than or equal to 1800, the motion state is fast walking; if 1800 & gtA is larger than or equal to 360, the movement state is slow walking.
(3) When F is more than 2Hz and more than or equal to 4 Hz:
if A is not less than 3400, the exercise state is running.
If 3400 > A is more than or equal to 360, the motion state is walking.
When the motion state is walking, the motion state of walking can be further divided. If 3400 is more than A and is more than or equal to 1800, the motion state is walking; if 1800 & gtA is larger than or equal to 360, the movement state is slow walking.
(4) When F is more than 4Hz and more than 5.5Hz, if A is more than 3400, the exercise state is running.
Where F is the frequency and A is the maximum amplitude.
(5) When F is more than or equal to 5.5Hz, the interference is caused, and the identification is not carried out.
Therefore, the motion state can be quickly and accurately identified through the frequency and the amplitude.
Step S5: and if the motion state is walking or running, determining the walking or running steps according to the peak-peak value or the valley-valley value of the motion acceleration data on the gravity sensitive axis.
Peak-peak (or trough-trough) represents one step, and the number of steps to walk or run is confirmed from the peak-peak or trough-trough value.
When counting the step number, eliminating the interference action by windowing to improve the accuracy of the step number counting. The windowing processing principle is as follows: the "time window" is defined according to the frequency characteristics of the walking and running actions (fastest movement as 1s movement 5 steps; slowest movement as 2s movement 1 steps) for excluding ineffective vibrations. Suppose that the fastest running speed of people is 5 steps per second, and the slowest walking speed is 1 step per 2 seconds, so that the time interval of two effective steps is within a time window of [0.2, 2.0] s, and all steps of which the time interval exceeds the time window are excluded, thereby improving the accuracy of step counting.
Step S6: if the motion state is still/sleep, judging the still/sleep state according to the motion intensity: quiescent state, attempted sleep state, light sleep state, deep sleep state.
The determination of the still/sleep state is performed by counting the exercise intensity, which specifically includes the following steps, as shown in fig. 3.
Step S61: and judging the motion intensity according to the maximum amplitude A.
If A is less than the first set value, the exercise intensity is low;
if the first set value is less than or equal to A and less than the second set value, the exercise intensity is the middle exercise intensity;
if A is larger than or equal to the second set value, the exercise intensity is high.
Wherein the first set value and the second set value represent a judgment threshold value of the exercise intensity. The first set value is less than the second set value. In the present embodiment, the first set value is 45, and the second set value is 75.
Step S62: and judging the resting/sleeping state according to the ratio of the low exercise intensity to the medium exercise intensity.
Within a set period of time, such as 2 minutes:
if the ratio of the exercise intensity is more than 15%, the state is static;
if the low exercise intensity ratio is less than 85%, the sleep state is tried;
if the low exercise intensity accounts for 85% -90%, the sleep state is a light sleep state;
if the ratio of the low exercise intensity is more than 90%, the sleep state is a deep sleep state.
The four states of the static/sleep state are judged according to the exercise intensity, the judgment is accurate, and a user can accurately know the sleep quality of the user, so that the exercise amount, the sleep time and the like of the user are adjusted, and the aim of healthy life is fulfilled.
Step S7: and (5) storing.
The exercise state, the step number, the time stamp and other information are stored, so that the exercise and sleep conditions in different time periods in one day can be analyzed conveniently, the exercise condition bar chart and the sleep condition bar chart in different time periods can be drawn, and the health condition of a wearer can be monitored conveniently.
According to the motion state detection method, the acceleration data are subjected to low-pass filtering to obtain the gravity acceleration data, the acceleration data are subjected to high-pass filtering to obtain the motion acceleration data, the motion acceleration data on the gravity sensitive shaft are selected to be subjected to Fourier transform, and the motion state is identified according to the frequency and the amplitude of the Fourier transform result, so that the accuracy rate of motion state identification is improved, and the identification accuracy rate is high; in addition, because only the motion acceleration data on the gravity sensitive axis is selected for Fourier transform, the data processing speed is improved, the detection efficiency of the whole motion detection method is further improved, a wearer can accurately and quickly know the motion state conveniently, and the use experience of the user is improved.
The embodiment also provides a motion state detection device, which mainly comprises a three-axis acceleration sensor, a low-pass filter, a high-pass filter, a gravity sensitive axis acquisition module, a data transformation module, an identification module and the like, and is shown in fig. 4.
And the three-axis acceleration sensor is used for acquiring acceleration data.
And the low-pass filter is used for carrying out low-pass filtering on the acquired acceleration data to obtain the gravity acceleration data.
And the high-pass filter is used for carrying out high-pass filtering on the acquired acceleration data to obtain the motion acceleration data.
And the gravity sensitive shaft acquisition module is used for acquiring a gravity sensitive shaft. The gravity sensitive axis acquisition module mainly comprises a data selection unit, a calculation unit and a judgment unit, and is shown in fig. 5. Specifically, the data selection unit is used for acquiring the data of the x, y and z axes of the gravity acceleration data; the calculating unit is used for calculating the data accumulation sum of the x axis, the y axis and the z axis; and the judging unit is used for selecting the axis corresponding to the accumulation sum maximum value as the gravity sensitive axis.
And the data transformation module is used for carrying out Fourier transformation on the motion acceleration data on the gravity sensitive axis.
And the identification module is used for identifying the motion state according to the frequency and the amplitude of the Fourier transform result.
The operation process of the motion state detection device has been described in detail in the motion state detection method, and is not described herein again.
The motion state detection device of the embodiment performs low-pass filtering on acceleration data to obtain gravity acceleration data, performs high-pass filtering on the acceleration data to obtain motion acceleration data, selects the motion acceleration data on a gravity sensitive shaft to perform Fourier transform, and performs motion state identification according to the frequency and amplitude of the Fourier transform result, so that the identification accuracy is high; in addition, because only the motion acceleration data on the gravity sensitive axis is selected for Fourier transform, the data processing speed is improved, the detection efficiency of the whole motion detection method is further improved, a wearer can accurately and quickly know the motion state conveniently, and the use experience of the user is improved.
The motion state detection device of this embodiment can be applied to wearing class products such as intelligent bracelet/wrist-watch to the health condition of monitoring person of wearing is strengthened the function of intelligent bracelet/wrist-watch.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A motion state detection method is characterized in that: the method comprises the following steps:
acquiring acceleration data through a three-axis acceleration sensor;
carrying out low-pass filtering on the collected acceleration data to obtain gravity acceleration data;
carrying out high-pass filtering on the acquired acceleration data to obtain motion acceleration data;
acquiring a gravity sensitive shaft;
selecting motion acceleration data on the gravity sensitive axis, and performing Fourier transform;
and identifying the motion state according to the frequency and the amplitude of the Fourier transform result.
2. The motion state detection method according to claim 1, characterized in that: the acquiring of the gravity sensitive shaft specifically comprises:
acquiring three-axis data of x, y and z of the gravity acceleration data;
respectively calculating the data accumulation sum of the x axis, the y axis and the z axis;
and selecting an axis corresponding to the accumulation sum maximum value as a gravity sensitive axis.
3. The motion state detection method according to claim 1, characterized in that: and carrying out 64-point Fourier transform on the motion acceleration data on the gravity sensitive axis.
4. The motion state detection method according to claim 1, characterized in that: the identifying of the motion state according to the frequency and the amplitude of the fourier transform result specifically includes:
(1) when F is less than 0.5Hz, if A is less than or equal to 360 degrees, the movement state is static/sleeping;
(2) when F is more than 0.5Hz and more than 2Hz, if A is more than or equal to 360 Hz, the movement state is walking;
(3) when the F is more than 2HZ at the temperature of 4HZ and more than or equal to F,
if A is not less than 3400, the exercise state is running;
if 3400 is more than A and is more than or equal to 360, the motion state is walking;
(4) when F is more than 4Hz and more than 5.5Hz, if A is more than 3400, the exercise state is running;
where F is the frequency and A is the maximum amplitude.
5. The motion state detection method according to claim 4, characterized in that:
(1) when the frequency is more than or equal to 2Hz and more than 0.5Hz,
if A is larger than or equal to 1800, the motion state is fast walking;
if 1800 & gtA is more than or equal to 360, the motion state is slow walking;
(2) when the frequency is more than or equal to 4Hz and more than 2Hz,
if 3400 is more than A and is more than or equal to 1800, the motion state is walking;
if 1800 & gtA is larger than or equal to 360, the movement state is slow walking.
6. The motion state detection method according to claim 4, characterized in that: and if the motion state is walking or running, determining the walking or running steps according to the peak-peak value or the valley-valley value of the motion acceleration data.
7. The motion state detection method according to claim 4, characterized in that: if the motion state is still/sleep, judging the still/sleep state according to the motion intensity: quiescent state, attempted sleep state, light sleep state, deep sleep state.
8. The motion state detection method according to claim 7, characterized in that: the judging the still/sleep state according to the exercise intensity specifically comprises:
(1) judging the motion intensity according to the maximum amplitude A:
if A is less than the first set value, the exercise intensity is low;
if the first set value is less than or equal to A and less than the second set value, the exercise intensity is the middle exercise intensity;
if A is larger than or equal to a second set value, the exercise intensity is high;
wherein the first set value and the second set value represent a judgment threshold value of the exercise intensity, and the first set value is smaller than the second set value;
(2) judging the resting/sleeping state according to the ratio of the low exercise intensity to the medium exercise intensity:
within a set time period:
if the ratio of the exercise intensity is more than 15%, the state is static;
if the low exercise intensity ratio is less than 85%, the sleep state is tried;
if the low exercise intensity accounts for 85% -90%, the sleep state is a light sleep state;
if the ratio of the low exercise intensity is more than 90%, the sleep state is a deep sleep state.
9. A motion state detection device characterized by: the device comprises:
the three-axis acceleration sensor is used for acquiring acceleration data;
the low-pass filter is used for carrying out low-pass filtering on the acquired acceleration data to obtain gravity acceleration data;
the high-pass filter is used for carrying out high-pass filtering on the acquired acceleration data to obtain motion acceleration data;
the gravity sensitive shaft acquisition module is used for acquiring a gravity sensitive shaft;
the data transformation module is used for carrying out Fourier transformation on the motion acceleration data on the gravity sensitive axis;
and the identification module is used for identifying the motion state according to the frequency and the amplitude of the Fourier transform result.
10. The motion state detection device according to claim 9, wherein: the gravity sensitive axis acquisition module includes:
the data selection unit is used for acquiring the data of the x, y and z axes of the gravity acceleration data;
the calculating unit is used for calculating the data accumulation sum of the x axis, the y axis and the z axis;
and the judging unit is used for selecting the axis corresponding to the accumulation sum maximum value as the gravity sensitive axis.
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 | 美新微纳传感系统有限公司 | 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 | 美新微纳传感系统有限公司 | 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 |
|---|---|---|
| CN106491138B (en) | A kind of motion state detection method and device | |
| CN103997572B (en) | A kind of step-recording method based on mobile phone acceleration sensor data and device | |
| CN105496416B (en) | A kind of recognition methods of human motion state and device | |
| CN104990562B (en) | Step-recording method based on auto-correlation computation | |
| EP2962637B1 (en) | Human motion status monitoring method and device | |
| CN103727959B (en) | Step-recording method and device | |
| CN110664390B (en) | Heart rate monitoring system and method based on wrist strap type PPG and deep learning | |
| KR101690649B1 (en) | Activity classification in a multi-axis activity monitor device | |
| CN104215257B (en) | High-precision and high pseudo-step removing human step-counting method integrating power consumption management | |
| CN104095615A (en) | Human sleep monitoring method and system | |
| JP6134872B1 (en) | Device, method and system for counting the number of cycles of periodic motion of a subject | |
| CN103954295A (en) | Step-counting method based on acceleration sensor | |
| JP2004089267A (en) | Sleeping depth estimation device and bedding equipped with the same | |
| CN111772639B (en) | Motion pattern recognition method and device for wearable equipment | |
| JP6300026B2 (en) | Measuring device and measuring method | |
| CN113017559A (en) | Vital sign extraction algorithm and system based on piezoelectric film sensor | |
| CN108072386B (en) | Step counting method and device | |
| CN108592941A (en) | A kind of step-recording method based on 3-axis acceleration | |
| US20150032033A1 (en) | Apparatus and method for identifying movement in a patient | |
| WO2014191803A1 (en) | Acceleration-based step activity detection and classification on mobile devices | |
| Singh et al. | Internet of things–triggered and power-efficient smart pedometer algorithm for intelligent wearable devices | |
| CN106562771A (en) | Embedded platform-oriented pet sleep identification method | |
| CN104305958B (en) | The photoelectricity volume ripple Multivariate analysis method of a kind of pole autonomic nerve state in short-term | |
| CN109061215A (en) | A kind of speed detection method and wearable device based on wearable device | |
| CN108981744B (en) | Step frequency real-time calculation method based on machine learning and low-pass filtering |
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 |