CN109696175A - A kind of step counting detection method and system based on wrist type device - Google Patents
A kind of step counting detection method and system based on wrist type device Download PDFInfo
- Publication number
- CN109696175A CN109696175A CN201910017225.0A CN201910017225A CN109696175A CN 109696175 A CN109696175 A CN 109696175A CN 201910017225 A CN201910017225 A CN 201910017225A CN 109696175 A CN109696175 A CN 109696175A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- judgement
- wrist type
- type device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 210000000707 wrist Anatomy 0.000 title claims abstract description 35
- 230000001133 acceleration Effects 0.000 claims abstract description 23
- 238000009825 accumulation Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000001276 controlling effect Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 6
- 238000005259 measurement Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 12
- 230000009184 walking Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000004927 fusion Effects 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
The invention discloses a kind of step counting detection methods based on wrist type device, comprising steps of S1, collector acquisition accelerometer data, gyro data and magnetometer data；S2, processor merge the data acquired in step S1, obtain posture information；S3, processor carry out wrist type step counting feature according to gyro data and determine, carry out next step if meeting judgement, otherwise return step S1；S4, processor carry out posture feature judgement according to the posture information in step S2, carry out next step if meeting judgement, otherwise return step S1；S5, processor carry out acceleration signature judgement according to accelerometer data, if meeting judgement, repeat step S1 to S5 after adding up step number, otherwise return step S1.The posture information of present invention combination detection device itself can prevent the situation of erroneous detection or missing inspection occur during step counting, improve the accuracy of step counting measurement.
Description
Technical field
The present invention relates to step counting algorithmic technique field, specially a kind of step counting detection method based on wrist type device and it is
System.
Background technique
Gradually attention with people to own health provides motion detection and following function and starts to write to have obtained quickly
Development.As forms of motion most common in people's daily life, carrying out statistics to the step number of walking is to walking movement for walking
The best standard of quantization.Currently, step-recording method is calculated mainly by means of acceleration signature.But common step-recording method tool
There is limitation could accurate measurement during only human body carries out on foot according to standard Zou rule posture.When people carries out compared to just
It often walks faster or slower or arm irregular fluctuation or user's own bodies situation and the age leads to different walkings
When posture, the wave character of acceleration can be made complex, traditional judgment method or peak detection based on dynamic threshold
Method is detected, and can have the situation of missing inspection or erroneous detection.
Summary of the invention
The purpose of the invention is to provide a kind of step counting detection method and system based on wrist type device, in conjunction with detection
The posture information of device itself can prevent the situation of erroneous detection or missing inspection occur during step counting, improve the standard of step counting measurement
True property.
In order to achieve the above-mentioned object of the invention, the invention adopts the following technical scheme: a kind of based on wrist type device
Detection method is walked, comprising steps of
S1, collector acquisition accelerometer data, gyro data and magnetometer data；
S2, processor merge the data acquired in step S1, obtain posture information；
S3, processor carry out wrist type step counting feature according to gyro data and determine, carry out if meeting judgement in next step
Suddenly, otherwise return step S1；
S4, processor carry out posture feature judgement according to the posture information in step S2, carry out if meeting judgement next
Step, otherwise return step S1；
S5, processor carry out acceleration signature judgement according to accelerometer data, if meeting judgement, add up weight after step number
Step S1 to S5 is answered, otherwise return step S1.
Preferably, step S3 includes:
S301, processor extract the axis value of each axis in gyro data；
S302, judge that each axis value whether in corresponding axis value threshold range, if then carrying out next step, is otherwise returned
Return step 1.
Preferably, step S4 includes:
S401, processor extract the judgement waveform in posture information, determine gap periods according to Wave crest and wave trough；
S402, gap periods are judged whether within the scope of Ct value, if then carrying out next step, otherwise return step
1。
Preferably, the Ct value range is 0.6 second to 3 seconds.
Preferably, step S5 includes:
S501, processor extract the acceleration value of each axis in accelerometer data,
S502, the acceleration value of each axis is judged whether within the scope of corresponding acceleration rate threshold, if then carrying out next
Step, otherwise return step 1；
S504, accumulative step number and return step 1 resurvey data.
Preferably, the posture information includes pitch angle and roll angle.
Preferably, in step sl, collector carries out data acquisition by the frequency of 50Hz.
In order to achieve the above-mentioned object of the invention, the invention adopts the following technical scheme: a kind of based on wrist type device
Detection system is walked, including
Central control module, for regulating and controlling the operation of modules in detection system；
Data acquisition module for acquiring accelerometer data, gyro data and magnetometer data, and will collect
Data be sent to central control module；
Step number determines mould group, connects central control module, the data that central control module arrives data collecting module collected
Be sent to step number determination module, the step number determination module according to collected data judging whether be really be step number, and will sentence
Determine result and returns central control module；
Step number accumulation module, connects central control module, central control module to the judgement result of step number determination module into
Row determines, when determining result is true step number, step number accumulation module adds up step number on the basis of original step number.
Preferably, the step number determines that mould group includes the first determination module, the second determination module and third module,
- the first determination module determines for wrist type step counting feature, when the judgement of the first determination module passes through, operation the
Two determination modules are determined, are otherwise interrupted and are determined, central control module control data acquisition module resurveys data；
- the second determination module determines for posture feature；When the judgement of the second determination module passes through, operation third determines
Module is determined, is otherwise interrupted and is determined, central control module control data acquisition module resurveys data；
Third determination module determines for acceleration signature, when the judgement of third determination module passes through, step number
Mould group is determined to determine to pass through.
It preferably, further include data processing module, data processing module connects central control module, by data acquisition module
Collected accelerometer data, gyro data and magnetometer data are merged, and posture information is obtained, and the step number determines
Module carries out step number judgement by accelerometer data, gyro data, magnetometer data and posture information.
Preferably, the data acquisition module carries out data acquisition by the frequency of 50Hz.
Compared with prior art, the step counting detection method using above-mentioned technical proposal based on wrist type device and it is
System, has the following beneficial effects:
One, using the step counting detection method and system of the invention based on wrist type device, gyro data is added to people
The swing state of body arm is judged, using the swing state of arm as the first judgement of wrist type step counting feature, Neng Gouti
The accuracy of high step counting detection.
Two, gyro data, accelerator data and magnetometer data are subjected to fusion clearing at posture information, from many aspects
To less judging for people, the accuracy of step counting equipment step counting can be improved, reduce erroneous detection and missing inspection.
Detailed description of the invention
Fig. 1 is that the present invention is based on the general steps flow charts of the step counting detection method embodiment of wrist type device；
Fig. 2 is that the present invention is based on the flow charts of the step counting detection method embodiment of wrist type device；
Fig. 3 is the acceleration information waveform diagram normally waved；
Fig. 4 is the ACC data analysis chart in the present embodiment；
Fig. 5 is the attitude angle waveform diagram during swing arm；
Fig. 6 is that the present invention is based on the module connection diagrams of the step counting detection system of wrist type device.
Specific embodiment
Below with reference to the accompanying drawings embodiments of the present invention are described more fully.
Fig. 3 is the acceleration information comparison diagram normally waved, due to passing through research wrist device during people walks,
The wave character of acceleration is complex be not placed on the fixed position of people acceleration signature it is obvious, so traditional threshold value and
Peak-value detection method is readily formed erroneous judgement or missing inspection.
The position drawn a circle in Fig. 3 is to be easy misjudged peak value, is readily formed using the method for traditional lookup peak value
Erroneous judgement.If general dynamic threshold method is added, i.e., calculating threshold value is added using the extreme value in signal period and is judged, counted
It is as follows to calculate formula:
ρ=[max { Acc (τ k) }+min { Acc (τ k) }]/2
After calculating analysis by above-mentioned formula, Fig. 4 is obtained after handling data, Fig. 4 is ACC data analysis chart, but is used
This method equally fails to obtain preferable effect, and the P4 point in Fig. 4 fails to be detected.
But when observing attitude angle data, people has found that feature is more significant in swing arm, and the data waveform can utilize inspection
It surveys peak-to-valley value and accurately determines the step number that people walks during swing arm, and a cycle representative of swing arm has walked two steps.
Corresponding posture information as shown in figure 5, each period in Fig. 5 can accurately be measured by finding peak value.
Therefore as shown in Figure 1 for the present invention is based on the step flow chart of the step counting detection method of wrist type device, one kind is based on
The step counting detection method of wrist type device, comprising steps of
S1, collector acquisition accelerometer data, gyro data and magnetometer data；
The data acquired in step S1 are carried out fusion resolving by S2, processor, obtain posture information；
S301, processor extract the axis value of each axis in gyro data；
S302, judge that each axis value whether in corresponding axis value threshold range, if then carrying out next step, is otherwise returned
Return step 1.
S401, processor extract the judgement waveform in posture information, determine gap periods according to Wave crest and wave trough；
S402, gap periods are judged whether within the scope of Ct value, if then carrying out next step, otherwise return step
S1。
S501, processor extract the acceleration value of each axis in accelerometer data,
S502, the acceleration value of each axis is judged whether within the scope of corresponding acceleration rate threshold, if then carrying out next
Step, otherwise return step 1；
S504, accumulative step number and return step 1 resurvey data.
Below with reference to the flow chart of Fig. 2, detection method of the invention is further described:
It combines accelerometer data, gyro data and magnetometer data fusion to carry out attitude algorithm first, obtains people and exist
The wrist device real-time attitude information during swing arm, posture information include pitch angle and roll angle etc. on foot.The process is benefit
Secondary treatment is carried out with all the sensors data, with the extraction of characteristic information later.During realization, the acquisition of use
Frequency is that 50HZ carries out fusion resolving attitude angle, then sets a 2s caching array as the period is determined, constantly caches magnetic
The value of power meter, three axis accelerometer and gyroscope.
Then gyro data is judged again, in the process of walking, arm is around using shoulder as axis rotation to people
, therefore, only need to judge whether the axis value of each axis of three-axis gyroscope reaches threshold value at this time.Three axis are used in the present embodiment
Gyroscope, the Z axis value in three-axis gyroscope reach threshold value Gzmin, and other two axis grox, groy should be respectively smaller than Gxmax,
Gymax, so that it may determine that the arm of people is in the process of a normal swing arm, that is, completes the judgement of wrist type step counting feature.
Enter in next step after meeting condition, otherwise waits for new sample data.
At this point, coming data at some cycles interval by continuous buffer update in the posture information obtained using fusion
Interior lookup Wave crest and wave trough value, one group of Wave crest and wave trough are a possible effective step, enter back into next step.It should be noted here that
It is after having searched a step, gap periods should be 0.6S-3s, which behaves twice of period of walking, i.e. arms swing
In a cycle, people has walked two steps.If being less than the peak value occurred in gap periods, do not adopt, until gap periods are in
When in threshold range, search again.
After above-mentioned lookup confirmation, while value ACCx, ACCy, the ACCz etc. for judging three axis accelerometer, it is desirable that at this time
The value of acceleration meets ACCxmin < ACCx < ACCxmax, ACCymin < ACCy < ACCymax, ACCzmin < ACCz < ACCzmax,
Step number confirmation can be completed, it is cumulative numerically to carry out step number in current step counting.
It is illustrated in figure 6 the module connection diagram of the step counting detection system the present invention is based on wrist type device, including in
Control module is entreated, for regulating and controlling the operation of modules in detection system；Data acquisition module is counted for acquiring acceleration
According to, gyro data and magnetometer data, and collected data are sent to central control module；Step number determines mould group, even
Connect central control module, central control module by data collecting module collected to data be sent to step number determination module, it is described
Step number determination module according to collected data judging whether be really be step number, and will determine result return central control module；
Step number accumulation module connects central control module, and central control module determines the judgement result of step number determination module, when
When determining that result is true step number, step number accumulation module adds up step number on the basis of original step number.
Wherein, the step number determines that mould group includes the first determination module, the second determination module and third module, and first determines
Module determines that, when the judgement of the first determination module passes through, the second determination module of operation is sentenced for wrist type step counting feature
It is fixed, it otherwise interrupts and determines, central control module control data acquisition module resurveys data；Second determination module is used for appearance
State feature determines；When the judgement of the second determination module passes through, operation third determination module is determined, is otherwise interrupted and is determined, in
Centre control module control data acquisition module resurveys data；Third determination module, for acceleration signature determine, when and only
When the judgement of third determination module passes through, step number determines mould group to determine to pass through.
It wherein, further include data processing module, data processing module connects central control module, data acquisition module is adopted
Accelerometer data, gyro data and the magnetometer data collected is merged, and posture information is obtained, and the step number determines mould
Block carries out step number judgement by accelerometer data, gyro data, magnetometer data and posture information.
It is the preferred embodiment of the present invention above, does not depart from original of the invention for those of ordinary skill in the art
Under the premise of reason, several variations and modifications can also be made, these also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of step counting detection method based on wrist type device, it is characterised in that: comprising steps of
S1, collector acquisition accelerometer data, gyro data and magnetometer data；
S2, processor merge the data acquired in step S1, obtain posture information；
S3, processor carry out wrist type step counting feature according to gyro data and determine, carry out next step if meeting judgement, no
Then return step S1；
S4, processor carry out posture feature judgement according to the posture information in step S2, carry out next step if meeting judgement,
Otherwise return step S1；
S5, processor carry out acceleration signature judgement according to accelerometer data, if meeting judgement, repeat to walk after adding up step number
Rapid S1 to S5, otherwise return step S1.
2. the step counting detection method according to claim 1 based on wrist type device, it is characterised in that: step S3 includes:
S301, processor extract the axis value of each axis in gyro data；
S302, each axis value is judged whether in corresponding axis value threshold range, if then carrying out next step, otherwise return to step
Rapid 1.
3. the step counting detection method according to claim 1 based on wrist type device, it is characterised in that: step S4 includes:
S401, processor extract the judgement waveform in posture information, determine gap periods according to Wave crest and wave trough；
S402, gap periods are judged whether within the scope of Ct value, if then carrying out next step, otherwise return step S1.
4. the step counting detection method according to claim 3 based on wrist type device, it is characterised in that: the Ct value
Range is 0.6 second to 3 seconds.
5. the step counting detection method according to claim 1 based on wrist type device, it is characterised in that: step S5 includes:
S501, processor extract the acceleration value of each axis in accelerometer data,
S502, the acceleration value of each axis is judged whether within the scope of corresponding acceleration rate threshold, if then carrying out next step,
Otherwise return step 1；
S504, accumulative step number and return step 1 resurvey data.
6. the step counting detection method according to claim 1 or 3 based on wrist type device, it is characterised in that: the posture
Information includes pitch angle and roll angle.
7. a kind of step counting detection system based on wrist type device, it is characterised in that: including
Central control module, for regulating and controlling the operation of modules in detection system；
Data acquisition module, for acquiring accelerometer data, gyro data and magnetometer data, and by collected number
According to being sent to central control module；
Step number determines mould group, connects central control module, and the data that central control module arrives data collecting module collected are sent
Give step number determination module, the step number determination module according to collected data judging whether be really be step number, and will determine to tie
Fruit returns central control module；
Step number accumulation module, connects central control module, and central control module sentences the judgement result of step number determination module
Fixed, when determining result is true step number, step number accumulation module adds up step number on the basis of original step number.
8. the step counting detection method according to claim 7 based on wrist type device, it is characterised in that: the step number determines
Mould group includes the first determination module, the second determination module and third module,
- the first determination module determines that, when the judgement of the first determination module passes through, operation second is sentenced for wrist type step counting feature
Cover half block is determined, is otherwise interrupted and is determined, central control module control data acquisition module resurveys data；
- the second determination module determines for posture feature；When the judgement of the second determination module passes through, third determination module is run
Determined, otherwise interrupt and determine, central control module control data acquisition module resurveys data；
Third determination module determines that when the judgement of third determination module passes through, step number determines for acceleration signature
Mould group is to determine to pass through.
9. the step counting detection method according to claim 7 based on wrist type device, it is characterised in that: further include at data
Module is managed, data processing module connects central control module, the accelerometer data that data collecting module collected is arrived, gyroscope
Data and magnetometer data are merged, and posture information is obtained, and the step number determination module passes through accelerometer data, gyroscope
Data, magnetometer data and posture information carry out step number judgement.
10. the step counting detection method according to claim 7 based on wrist type device, it is characterised in that: the data are adopted
Collect module and data acquisition is carried out by the frequency of 50Hz.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910017225.0A CN109696175A (en) | 2019-01-08 | 2019-01-08 | A kind of step counting detection method and system based on wrist type device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910017225.0A CN109696175A (en) | 2019-01-08 | 2019-01-08 | A kind of step counting detection method and system based on wrist type device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109696175A true CN109696175A (en) | 2019-04-30 |
Family
ID=66232612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910017225.0A Pending CN109696175A (en) | 2019-01-08 | 2019-01-08 | A kind of step counting detection method and system based on wrist type device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109696175A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104075730A (en) * | 2014-07-02 | 2014-10-01 | 电子科技大学 | Gait counting method and gait counter |
| CN107917707A (en) * | 2017-11-20 | 2018-04-17 | 北京邮电大学 | The definite method, apparatus and electronic equipment in pedestrian direction under a kind of any attitude |
| CN108955719A (en) * | 2018-06-21 | 2018-12-07 | 四川斐讯信息技术有限公司 | A kind of step counting detection method and system based on wrist type device |
-
2019
- 2019-01-08 CN CN201910017225.0A patent/CN109696175A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104075730A (en) * | 2014-07-02 | 2014-10-01 | 电子科技大学 | Gait counting method and gait counter |
| CN107917707A (en) * | 2017-11-20 | 2018-04-17 | 北京邮电大学 | The definite method, apparatus and electronic equipment in pedestrian direction under a kind of any attitude |
| CN108955719A (en) * | 2018-06-21 | 2018-12-07 | 四川斐讯信息技术有限公司 | A kind of step counting detection method and system based on wrist type device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109579853B (en) | Inertial navigation indoor positioning method based on BP neural network | |
| CN104596537B (en) | A kind of step-recording method | |
| CN108634960B (en) | A kind of gait online test method for ectoskeleton wearer | |
| CN103027687A (en) | Old people fall detection and alarm system based on 3D (3-dimensional) accelerometer and gyroscope | |
| CN106256396B (en) | Sports support device, sports support method, exercise assistance system and storage medium | |
| CN108844533A (en) | A kind of free posture PDR localization method based on Multi-sensor Fusion and attitude algorithm | |
| CN106923839A (en) | Exercise assist device, exercising support method and recording medium | |
| US20200179753A1 (en) | Real time golf swing training aid | |
| US11580878B2 (en) | Real time sports motion training aid | |
| CN106067001A (en) | A kind of action identification method and system | |
| CN113450539B (en) | Fall detection method | |
| WO2019047410A1 (en) | Method and apparatus for counting the number of steps | |
| CN107019501B (en) | Remote tumble detection method and system based on genetic algorithm and probabilistic neural network | |
| CN113128379A (en) | Human body falling detection method, computer readable storage medium and electronic device | |
| CN206470693U (en) | A kind of Emotion identification system based on wearable device | |
| CN206121113U (en) | Yoga evaluation system based on multisensor | |
| CN109512435B (en) | Walking posture correction instrument capable of detecting in real time | |
| US20210158029A1 (en) | Action-estimating device | |
| CN105448039A (en) | Tumble-detecting method decreasing false alarm rate | |
| CN109991896A (en) | Robot falling prediction method and device and storage device | |
| CN109696175A (en) | A kind of step counting detection method and system based on wrist type device | |
| Chunsheng et al. | Human gait feature data analysis and person identification based on IMU | |
| CN103826202B (en) | Based on the method that mobile phone sensor information improves the bounce of WiFi positioning results | |
| Uddin et al. | SmartSpaghetti: Accurate and robust tracking of Human's location | |
| CN107510335B (en) | A kind of cup amount of drinking water statistical method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190430 |