[go: up one dir, main page]

CN107303181A - A kind of step motion recognition method based on six axle sensors - Google Patents

A kind of step motion recognition method based on six axle sensors Download PDF

Info

Publication number
CN107303181A
CN107303181A CN201710349657.2A CN201710349657A CN107303181A CN 107303181 A CN107303181 A CN 107303181A CN 201710349657 A CN201710349657 A CN 201710349657A CN 107303181 A CN107303181 A CN 107303181A
Authority
CN
China
Prior art keywords
crest
axle
pin
method based
recognition method
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
Application number
CN201710349657.2A
Other languages
Chinese (zh)
Other versions
CN107303181B (en
Inventor
李磊磊
蔡盛贵
华高坚
陈顺平
何佳
徐毅
沈帅帅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang lierda core technology Co., Ltd
Original Assignee
ZHEJIANG LIERDA INTERNET OF THINGS TECHNOLOGY Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ZHEJIANG LIERDA INTERNET OF THINGS TECHNOLOGY Co Ltd filed Critical ZHEJIANG LIERDA INTERNET OF THINGS TECHNOLOGY Co Ltd
Priority to CN201710349657.2A priority Critical patent/CN107303181B/en
Publication of CN107303181A publication Critical patent/CN107303181A/en
Application granted granted Critical
Publication of CN107303181B publication Critical patent/CN107303181B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/103Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A61B5/112Gait analysis

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Dentistry (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Physiology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention discloses a kind of step motion recognition method based on six axle sensors.It comprises the following steps:The detection data of the axle sensor of microcomputer reads six output, draw the resultant acceleration change curve of the axle resultant accelerations of XYZ tri-, detect the crest in resultant acceleration change curve, when the corresponding axle resultant accelerations of XYZ tri- of some crest are less than or equal to 1.5g, the crest is removed, when the sampled point between two neighboring crest is less than setting value K, the minimum crest of the axle resultant accelerations of XYZ in the two crests tri- is removed, at the time of crest corresponding time point is that pin lands;The pin landing posture that the continuous N number of sampling time point corresponding Y-axis magnitude of angular velocity after the moment judges each pin landing moment is landed according to each pin.The landing posture of pin when the present invention can recognize people's motion, is easy to what user understood oneself to walk appearance or running style.

Description

A kind of step motion recognition method based on six axle sensors
Technical field
Know the present invention relates to step motion identification technology field, more particularly to a kind of step motion based on six axle sensors Other method.
Background technology
Modern much focuses on the daily exercise of oneself, the monitoring that meter step is taken exercise as a kind of effective record, monitoring very much Means, are widely used in intelligent running shoes.Existing intelligent running shoes are being mounted therein with 3-axis acceleration sensor, but it Step can only simply be counted, it is impossible to the landing posture of pin when recognizing people's motion, be unfavorable for that user understands oneself walks appearance or running style.
The content of the invention
The purpose of the present invention is to overcome in intelligent running shoes at present to install 3-axis acceleration sensor, can only simply count step, no The technical problem of the landing posture of pin moves identification side there is provided a kind of step based on six axle sensors when can recognize people's motion Method, the landing posture of pin when it can recognize people's motion is easy to what user understood oneself to walk appearance or running style.
A kind of step motion recognition method based on six axle sensors of the present invention, comprises the following steps:
The detection data of the axle sensor of microcomputer reads six output, the resultant acceleration change for drawing the axle resultant accelerations of XYZ tri- is bent Crest in line chart, detection resultant acceleration change curve, when the corresponding axle resultant accelerations of XYZ tri- of some crest are less than or equal to During setting value F, the crest is removed, when the sampled point between two neighboring crest is less than setting value K, by the two crests The minimum crest of the axle resultant accelerations of XYZ tri- is removed, at the time of crest corresponding time point is that pin lands;
Microprocessor judges the pin landing posture at each pin landing moment, judges that the pin at some pin landing moment lands the side of posture Method comprises the following steps:The corresponding Y-axis magnitude of angular velocity of continuous N number of sampling time point after the pin landing moment is found out, is looked for The minimum value MIN gone out in this N number of Y-axis magnitude of angular velocity(Gy), selected from this N number of Y-axis magnitude of angular velocity positioned at minimum value MIN(Gy) The corresponding Y-axis magnitude of angular velocity of sampling time point after the sampling time point at place, is looked for from these Y-axis magnitude of angular velocities selected Go out maximum MAX(Gy), calculated minimum MIN(Gy)With maximum MAX(Gy)Average value AVG(Gy)If, AVG(Gy)Greatly In M1 or MAX(Gy)More than M2, then judge that the pin landing posture at pin landing moment lands posture for front foot, otherwise judge the pin The pin landing posture for landing the moment is that the rear foot lands posture.
In the technical program, six axle sensors of this method are arranged in shoe body, the X-axis positive direction court of six axle sensors To in front of shoe body, Y-axis positive direction towards on the left of shoe body, Z axis positive direction straight up, by the motion conditions for detecting human body list pin Calculate pin landing posture.
This method judges crest according to the maximum of change curve in resultant acceleration change curve, when the axles of XYZ tri- are closed When acceleration exceedes setting value F, you can inside the Rule of judgment for entering crest, while spurious peaks can be also introduced, because people walks Or the limiting frequency run can be evaluated whether out, the spacing between crest will not be less than K sampled point, so when two crests Between when being smaller than K, you can according to crest value size, choose larger value as the crest of a meter step, i.e. numerical value compared with Big crest is true crest, and the less crest of numerical value is spurious peaks.
At the time of crest corresponding time point is that pin lands, by the crest above calculated, can obtain pin landing when Carve, theoretically analyze, the process of front and rear pin landing is substantially in the process rotated around Y-axis, is counterclockwise revolved around Y-axis Turn, be worth just, to be rotated clockwise around Y-axis, it is negative to be worth.When this method extracts continuous N number of sampling after pin lands the moment Between put corresponding Y-axis magnitude of angular velocity, first find out the minimum value MIN in this N number of Y-axis magnitude of angular velocity(Gy), then find out minimum value MIN (Gy)The maximum MAX in the corresponding Y-axis magnitude of angular velocity of remaining sampling time point after place sampling time point(Gy), calculate Minimum value MIN(Gy)With maximum MAX(Gy)Average value AVG(Gy)If, AVG(Gy)More than M1 or MAX(Gy)More than M2, Then judge that the pin landing posture at pin landing moment lands posture for front foot, otherwise judge the pin landing posture at pin landing moment Posture is landed for the rear foot.
Preferably, a kind of step motion recognition method based on six axle sensors is further comprising the steps of:Micro- place Manage crest number A of the device in resultant acceleration change curve and calculate current pedometer B, B=(A-1)× 2, as step number B During less than c, caching step number B numerical value, microprocessor does not export step number B numerical value, when step number B is more than or equal to c, microprocessor Device output step number B numerical value.
, there is primary wave due to only being set on a shoes on six axle sensors, resultant acceleration change curve in c >=6 Peak, people or so pin has respectively walked a step, so, crest and the relation that step number is 1 to 2, i.e., one crest correspondence are walked 2 steps.Due to There are spurious peaks, so last crest is it cannot be determined whether be true crest, this method is in one crest of newest appearance, Whether be true crest, so this method meter step has the delayed of crest if calculating previous crest.Caching step number, which is used primarily in, to be sentenced Disconnected when to initially enter meter step state, in order to avoid some are disturbed, such as any of pin is rocked, and caching step number is devised here Exactly meter step mode is initially entered when step number is more than or equal to when c is walked, microprocessor output step number B numerical value to display screen etc. Module, the step number produced below will be added up, then first these step numbers of temporary cache when c steps are not reaching to.
Preferably, a kind of step motion recognition method based on six axle sensors is further comprising the steps of:Work as conjunction When all there is not new crest in continuous d sampled point after last crest in acceleration change curve map, microprocessor Device terminates this meter step, and resultant acceleration change curve is reset, if now step number B is more than or equal to c, calculates this meter Total step number C=B+2 of step.
C >=6, continuous d after last crest(Such as 80)When individual sampled point all new crest does not occur, people is judged Body stop motion, terminates meter step, and total step number adds 2, i.e., last delayed crest is converted into step number adds total step number.
Preferably, the detection frequency of six axle sensor is 25HZ, K is 8-15.
Preferably, the N is 8-12.
Preferably, the M1 is 80-120 degrees seconds, the M2 is 30-50 degrees seconds.
Preferably, during the detection data of the axle sensor of microcomputer reads six output, using kalman filter method pair The data of six axle sensors output are filtered.Kalman filter method makes obtained data more smooth, and computation complexity is more Low, efficiency is faster.
Preferably, the data of six axle sensors report pattern to use fifo mode.
The beneficial effects of the invention are as follows:The landing posture of pin, is easy to user to understand walking for oneself when can recognize people's motion Appearance or running style, and then correct appearance or running style, it is to avoid sprain for exercise.
Brief description of the drawings
Fig. 1 is a kind of workflow diagram of the present invention.
Embodiment
Below by embodiment, and with reference to accompanying drawing, technical scheme is described in further detail.
Embodiment:A kind of step motion recognition method based on six axle sensors of the present embodiment, as shown in figure 1, including Following steps:
Six axle sensors are exported by the detection data of the axle sensor of microcomputer reads six output using kalman filter method Data are filtered, and are drawn in the resultant acceleration change curve of the axle resultant accelerations of XYZ tri-, detection resultant acceleration change curve Crest, when the corresponding axle resultant accelerations of XYZ tri- of some crest be less than or equal to 1.5g when, the crest is removed, when adjacent two When sampled point between individual crest is less than setting value 10, the minimum crest of the axle resultant accelerations of XYZ in the two crests tri- is removed, Retain the maximum crest of the axle resultant accelerations of XYZ tri-, at the time of crest corresponding time point is that pin lands;
Microprocessor judges the pin landing posture at each pin landing moment, judges that the pin at some pin landing moment lands the side of posture Method comprises the following steps:The corresponding Y-axis magnitude of angular velocity of continuous 10 sampling times point after the pin landing moment is found out, is looked for The minimum value MIN gone out in this 10 Y-axis magnitude of angular velocities(Gy), selected from this 10 Y-axis magnitude of angular velocities positioned at minimum value MIN (Gy)The corresponding Y-axis magnitude of angular velocity of sampling time point after the sampling time point at place, from these Y-axis magnitude of angular velocities selected In find out maximum MAX(Gy), calculated minimum MIN(Gy)With maximum MAX(Gy)Average value AVG(Gy)If, AVG (Gy)More than 100 degrees seconds or MAX(Gy)More than 40 degrees seconds, then judge that the pin landing posture at pin landing moment is landed for front foot Posture, otherwise judges that the pin landing posture at pin landing moment lands posture for the rear foot.
Crest number A of the microprocessor in resultant acceleration change curve calculates current pedometer B, and B=(A- 1)× 2, when step number B is less than 6, caching step number B numerical value, microprocessor does not export step number B numerical value, be more than as step number B or During equal to 6, microprocessor output step number B numerical value and preservation.
Continuous 80 sampled points all do not occur new after last crest in resultant acceleration change curve During crest, microprocessor terminates this meter step, resultant acceleration change curve is reset, if now step number B is more than or equal to 6, calculate total step number C=B+2 of this meter step.
Six axle sensors use this sensor of MPU6500 come for example, MPU6500 sensors set sample rate for 25Hz, the calculatings axle of collection are the angular speed range that AxAyAz and GxGyGz, the range of acceleration are set to positive and negative 8g, gyroscope Pattern is reported using fifo mode etc. for positive and negative 500 degree/s and data.Consider for power saving, sensor will under not working condition Into low-power consumption mode.It can also be waken up under this low-power consumption mode scene, it is main here to use what interrupting movement woke up Method, is exactly when the axle resultant accelerations of XYZ tri- exceed certain threshold value(Such as 250mg)When, sensor reenters mode of operation.
Six axle sensors of this method are arranged in shoe body, and the X-axis positive directions of six axle sensors is towards in front of shoe body, Y-axis Positive direction is towards shoe body left side, and Z axis positive direction straight up, appearance is landed by detecting that the motion conditions of human body list pin calculate pin State and the step number of motion.The detection data of six axle sensors output are after kalman filter method is filtered, then by microprocessor Device processing identification.Kalman filter method makes that obtained data are more smooth, and computation complexity is lower, and efficiency is faster.
This method judges crest according to the maximum of change curve in resultant acceleration change curve after filtering, works as XYZ When three axle resultant accelerations are more than 1.5g, you can inside the Rule of judgment for entering crest, while spurious peaks can be also introduced, because people walks The limiting frequency of road or running can be evaluated whether out, and the spacing between crest will not be less than 10 sampled points, so when two Between crest when being smaller than 10, you can according to crest value size, choose larger value as the crest of a meter step, that is, count The larger crest of value is true crest, and the less crest of numerical value is spurious peaks.
At the time of crest corresponding time point is that pin lands, by the crest above calculated, can obtain pin landing when Carve, theoretically analyze, the process of front and rear pin landing is substantially in the process rotated around Y-axis, is counterclockwise revolved around Y-axis Turn, be worth just, to be rotated clockwise around Y-axis, it is negative to be worth.When this method extracts continuous 10 samplings after pin lands the moment Between put corresponding Y-axis magnitude of angular velocity, first find out the minimum value MIN in this 10 Y-axis magnitude of angular velocities(Gy), then find out minimum value MIN(Gy)The maximum MAX in the corresponding Y-axis magnitude of angular velocity of remaining sampling time point after place sampling time point(Gy), Calculated minimum MIN(Gy)With maximum MAX(Gy)Average value AVG(Gy)If, AVG(Gy)More than M1 or MAX(Gy)Greatly In M2, then judge that the pin landing posture at pin landing moment lands posture for front foot, otherwise judge that the pin at pin landing moment falls Ground posture is that the rear foot lands posture.
Due to only setting crest of appearance, people on six axle sensors, resultant acceleration change curve on a shoes Left and right pin has respectively walked a step, so, crest and the relation that step number is 1 to 2, i.e., corresponding 2 steps of walking of one crest.It is pseudo- due to existing Crest, so last crest is it cannot be determined whether be true crest, this method is in one crest of newest appearance, before just calculating Whether one crest is true crest, so this method meter step has the delayed of crest.Caching step number, which is used primarily in, to be determined when Initially enter meter step state, in order to avoid some are disturbed, such as any of pin rocks, devise here caching step number be exactly when Initially enter meter step mode when step number is more than 5 step, microprocessor output step number B numerical value to the modules such as display screen, display screen Step number is shown, the step number produced below will be added up, then these step numbers of elder generation's temporary cache when 5 step is not reaching to are micro- Processor does not export step number B numerical value to modules such as display screens, and display screen does not show step number.
When continuous 80 sampled points all new crest do not occur after last crest, judge that human body stops fortune It is dynamic, terminate meter step, total step number adds 2, i.e., last delayed crest is converted into step number adds total step number.

Claims (8)

1. a kind of step motion recognition method based on six axle sensors, it is characterised in that comprise the following steps:
The detection data of the axle sensor of microcomputer reads six output, the resultant acceleration change for drawing the axle resultant accelerations of XYZ tri- is bent Crest in line chart, detection resultant acceleration change curve, when the corresponding axle resultant accelerations of XYZ tri- of some crest are less than or equal to During setting value F, the crest is removed, when the sampled point between two neighboring crest is less than setting value K, by the two crests The minimum crest of the axle resultant accelerations of XYZ tri- is removed, at the time of crest corresponding time point is that pin lands;
Microprocessor judges the pin landing posture at each pin landing moment, judges that the pin at some pin landing moment lands the side of posture Method comprises the following steps:The corresponding Y-axis magnitude of angular velocity of continuous N number of sampling time point after the pin landing moment is found out, is looked for The minimum value MIN gone out in this N number of Y-axis magnitude of angular velocity(Gy), selected from this N number of Y-axis magnitude of angular velocity positioned at minimum value MIN(Gy) The corresponding Y-axis magnitude of angular velocity of sampling time point after the sampling time point at place, is looked for from these Y-axis magnitude of angular velocities selected Go out maximum MAX(Gy), calculated minimum MIN(Gy)With maximum MAX(Gy)Average value AVG(Gy)If, AVG(Gy)Greatly In M1 or MAX(Gy)More than M2, then judge that the pin landing posture at pin landing moment lands posture for front foot, otherwise judge the pin The pin landing posture for landing the moment is that the rear foot lands posture.
2. a kind of step motion recognition method based on six axle sensors according to claim 1, it is characterised in that also wrap Include following steps:Crest number A of the microprocessor in resultant acceleration change curve calculates current pedometer B, and B= (A-1)× 2, when step number B is less than c, caching step number B numerical value, microprocessor does not export step number B numerical value, when step number B is more than Or during equal to c, microprocessor output step number B numerical value.
3. a kind of step motion recognition method based on six axle sensors according to claim 2, it is characterised in that also wrap Include following steps:Continuous d sampled point does not all occur newly after last crest in resultant acceleration change curve Crest when, microprocessor terminate this meter step, resultant acceleration change curve is reset, if now step number B is more than or waited In c, total step number C=B+2 of this meter step is calculated.
4. a kind of step motion recognition method based on six axle sensors according to claim 1 or 2 or 3, its feature exists In:The detection frequency of six axle sensor is 25HZ, and K is 8-15.
5. a kind of step motion recognition method based on six axle sensors according to claim 4, it is characterised in that:It is described N is 8-12.
6. a kind of step motion recognition method based on six axle sensors according to claim 4, it is characterised in that:It is described M1 is 80-120 degrees seconds, and the M2 is 30-50 degrees seconds.
7. a kind of step motion recognition method based on six axle sensors according to claim 1 or 2 or 3, its feature exists In:During the detection data of the axle sensor of microcomputer reads six output, six axle sensors are exported using kalman filter method Data be filtered.
8. a kind of step motion recognition method based on six axle sensors according to claim 1 or 2 or 3, its feature exists In:The data of six axle sensors report pattern to use fifo mode.
CN201710349657.2A 2017-05-17 2017-05-17 Step motion identification method based on six-axis sensor Active CN107303181B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710349657.2A CN107303181B (en) 2017-05-17 2017-05-17 Step motion identification method based on six-axis sensor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710349657.2A CN107303181B (en) 2017-05-17 2017-05-17 Step motion identification method based on six-axis sensor

Publications (2)

Publication Number Publication Date
CN107303181A true CN107303181A (en) 2017-10-31
CN107303181B CN107303181B (en) 2019-12-24

Family

ID=60151126

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710349657.2A Active CN107303181B (en) 2017-05-17 2017-05-17 Step motion identification method based on six-axis sensor

Country Status (1)

Country Link
CN (1) CN107303181B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110108278A (en) * 2019-05-22 2019-08-09 北京卡路里信息技术有限公司 It is landed determining method and device based on the foot of six axle sensors
CN110595500A (en) * 2019-07-30 2019-12-20 福建省万物智联科技有限公司 Method for accurately counting steps and intelligent shoes
CN110694252A (en) * 2019-10-09 2020-01-17 成都乐动信息技术有限公司 Running posture detection method based on six-axis sensor
CN110876613A (en) * 2019-09-27 2020-03-13 深圳先进技术研究院 Human motion state identification method and system and electronic equipment

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1272926A (en) * 1997-10-02 2000-11-08 个人电子设备有限公司 Measuring foot contact time and foot loft time of person in locomotion
WO2008035827A1 (en) * 2006-09-21 2008-03-27 Jongchul Kim Pedestrian navigation method and apparatus for using geographic information system
US20080229614A1 (en) * 2002-09-23 2008-09-25 Santa Ana Roland C Interchangeable footwear comprising multiple shoe inserts
CN101750096A (en) * 2008-11-28 2010-06-23 佛山市顺德区顺达电脑厂有限公司 Step-counting processing system and method
CN102670217A (en) * 2012-05-04 2012-09-19 嘉兴市制衡精仪有限公司 Wearable sensor measuring device and method for lower limb joint acting force and moment
CN103983273A (en) * 2014-04-29 2014-08-13 华南理工大学 Real-time step length estimation method based on acceleration sensor
CN104567912A (en) * 2015-02-02 2015-04-29 河海大学 Method for realizing pedometer on Android mobile phone
CN105188530A (en) * 2013-05-10 2015-12-23 欧姆龙健康医疗事业株式会社 Walking posture meter and program
CN106123911A (en) * 2016-08-06 2016-11-16 深圳市爱康伟达智能医疗科技有限公司 A kind of based on acceleration sensor with the step recording method of angular-rate sensor
CN106225804A (en) * 2016-08-01 2016-12-14 珠海安润普科技有限公司 A kind of pedometer shoes cushion device and step-recording method
CN106225803A (en) * 2016-07-20 2016-12-14 浪潮软件集团有限公司 A Step Counting Method Based on Triaxial Accelerator
CN106482733A (en) * 2016-09-23 2017-03-08 南昌大学 Zero velocity update method based on plantar pressure detection in pedestrian navigation

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1272926A (en) * 1997-10-02 2000-11-08 个人电子设备有限公司 Measuring foot contact time and foot loft time of person in locomotion
US20080229614A1 (en) * 2002-09-23 2008-09-25 Santa Ana Roland C Interchangeable footwear comprising multiple shoe inserts
WO2008035827A1 (en) * 2006-09-21 2008-03-27 Jongchul Kim Pedestrian navigation method and apparatus for using geographic information system
CN101750096A (en) * 2008-11-28 2010-06-23 佛山市顺德区顺达电脑厂有限公司 Step-counting processing system and method
CN102670217A (en) * 2012-05-04 2012-09-19 嘉兴市制衡精仪有限公司 Wearable sensor measuring device and method for lower limb joint acting force and moment
CN105188530A (en) * 2013-05-10 2015-12-23 欧姆龙健康医疗事业株式会社 Walking posture meter and program
CN103983273A (en) * 2014-04-29 2014-08-13 华南理工大学 Real-time step length estimation method based on acceleration sensor
CN104567912A (en) * 2015-02-02 2015-04-29 河海大学 Method for realizing pedometer on Android mobile phone
CN106225803A (en) * 2016-07-20 2016-12-14 浪潮软件集团有限公司 A Step Counting Method Based on Triaxial Accelerator
CN106225804A (en) * 2016-08-01 2016-12-14 珠海安润普科技有限公司 A kind of pedometer shoes cushion device and step-recording method
CN106123911A (en) * 2016-08-06 2016-11-16 深圳市爱康伟达智能医疗科技有限公司 A kind of based on acceleration sensor with the step recording method of angular-rate sensor
CN106482733A (en) * 2016-09-23 2017-03-08 南昌大学 Zero velocity update method based on plantar pressure detection in pedestrian navigation

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110108278A (en) * 2019-05-22 2019-08-09 北京卡路里信息技术有限公司 It is landed determining method and device based on the foot of six axle sensors
CN110108278B (en) * 2019-05-22 2021-07-09 北京卡路里信息技术有限公司 Foot landing determination method and device based on six-axis sensor
CN110595500A (en) * 2019-07-30 2019-12-20 福建省万物智联科技有限公司 Method for accurately counting steps and intelligent shoes
CN110595500B (en) * 2019-07-30 2021-08-10 福建省万物智联科技有限公司 Method for accurately counting steps and intelligent shoes
CN110876613A (en) * 2019-09-27 2020-03-13 深圳先进技术研究院 Human motion state identification method and system and electronic equipment
CN110876613B (en) * 2019-09-27 2022-07-22 深圳先进技术研究院 A kind of human body motion state recognition method, system and electronic device
CN110694252A (en) * 2019-10-09 2020-01-17 成都乐动信息技术有限公司 Running posture detection method based on six-axis sensor

Also Published As

Publication number Publication date
CN107303181B (en) 2019-12-24

Similar Documents

Publication Publication Date Title
CN107343789B (en) Step motion identification method based on three-axis acceleration sensor
CN107303181A (en) A kind of step motion recognition method based on six axle sensors
CN103616034B (en) A kind of network pedometer based on bluetooth and step-recording method
CN107314775A (en) A kind of switching at runtime based on 3-axis acceleration sensor calculates the step-recording method of axle
CN110876613B (en) A kind of human body motion state recognition method, system and electronic device
US10653339B2 (en) Time and frequency domain based activity tracking system
CN103712632B (en) A kind of step-recording method based on 3 axle accelerometers and pedometer
CN102302370B (en) A fall detection method and device
JP6567658B2 (en) Device and method for classifying user activity and / or counting user steps
CN104007822A (en) Large database based motion recognition method and device
CN105771187A (en) Motion state detecting method and intelligent shoe based on method
CN105877757A (en) Multi-sensor integrated human motion posture capturing and recognizing device
CN109528212A (en) Abnormal gait recognition device and method
CN104269025B (en) Wearable single node feature and the position choosing method of monitoring is fallen down towards open air
CN105030260A (en) Judgment method for motion state and footwear
CN106681478A (en) Simple scheme for distinguishing state of portable wearable device
CN108008151A (en) A kind of moving state identification method and system based on 3-axis acceleration sensor
CN106644208A (en) Riding capability analyzing system and riding capability analyzing method
CN107024976A (en) Human body attitude detecting system and its detection method based on MEMS inertial sensor
CN108958482A (en) A kind of similitude action recognition device and method based on convolutional neural networks
CN104586402A (en) Feature extracting method for body activities
CN107393260A (en) A kind of sitting based reminding method, device and wrist type sitting reminiscences
CN110648478B (en) Drowning detection system and method based on wireless communication
CN106643785B (en) A kind of adaptive step number detection method of multi-source information based on MEMS Inertial Measurement Units
CN106960542A (en) A kind of low-power consumption falling detection device based on interruption driving

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20191202

Address after: Room 1302, building 1, no.1326, Wenyi West Road, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province

Applicant after: Zhejiang lierda core technology Co., Ltd

Address before: Yuhang District, Hangzhou City, Zhejiang Province, 311121 West No. 1500 Building No. 1 room 105

Applicant before: ZHEJIANG LIERDA INTERNET OF THINGS TECHNOLOGY CO., LTD.

GR01 Patent grant
GR01 Patent grant