CN110595501A - Running distance correction method based on three-axis sensor - Google Patents
Running distance correction method based on three-axis sensor Download PDFInfo
- Publication number
- CN110595501A CN110595501A CN201910952486.1A CN201910952486A CN110595501A CN 110595501 A CN110595501 A CN 110595501A CN 201910952486 A CN201910952486 A CN 201910952486A CN 110595501 A CN110595501 A CN 110595501A
- Authority
- CN
- China
- Prior art keywords
- axis
- data
- acceleration data
- value
- characteristic value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/14—Receivers specially adapted for specific applications
- G01S19/19—Sporting applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/20—Distances or displacements
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/40—Acceleration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a running distance correction method based on a three-axis sensor, which comprises the following steps: s1: acquiring x-axis acceleration data and z-axis acceleration data, which are acquired by a three-axis sensor and are in the running direction of a user, during the abnormal GPS positioning; s2: fusing the acceleration data of the two axes to obtain synthetic axis data; s3: detecting wave crests and wave troughs of the synthetic axis data to obtain a gait cycle; s4: calculating to obtain a first characteristic value, a second characteristic value, a third characteristic value, a fourth characteristic value, a fifth characteristic value and a sixth characteristic value according to the synthetic axis data in each gait cycle to form a characteristic vector; s5: inputting the characteristic vector into a pre-trained linear regression model to obtain a step length predicted value; s6: and calculating the product of the step length predicted value and the gait cycle number during the abnormal GPS positioning period to obtain the running distance during the abnormal GPS positioning period. The method and the device can improve the accuracy and stability of running distance calculation.
Description
Technical Field
The invention relates to the technical field of motion detection, in particular to a running distance correction method based on a three-axis sensor.
Background
With the pursuit of people to scientific sports becoming higher and higher, the sports wearing equipment becomes the indispensable equipment of vast running enthusiasts, for example sports watch, the check out test set of wearing on the foot etc.. The sports wearing equipment can detect running data, wherein the running distance is very basic and very important data, and therefore the accuracy of guaranteeing the running distance is an important index of the sports wearing equipment.
At present, the sports wearing equipment mainly relies on the GPS to calculate the distance of running, and the GPS can realize all-weather, continuous, real-time three-dimensional navigation location and speed measurement in the global scope, and after the sports wearing equipment received real-time GPS locating point data, can calculate the distance between two adjacent GPS locating points according to corresponding algorithm, finally adds up all distances and obtains the distance of running.
Calculating the running distance by GPS is relatively accurate in the case of a relatively good GPS signal. However, the accuracy of the running distance is affected by the disadvantage that GPS positioning is greatly affected by the environment, and when the GPS positioning is abnormal, such as loss, interruption or drift of GPS signals, a large error is caused to the calculation of the running distance.
Disclosure of Invention
The invention mainly solves the technical problem of providing a running distance correction method based on a three-axis sensor, which can improve the accuracy and stability of running distance calculation.
In order to solve the technical problems, the invention adopts a technical scheme that: provided is a running distance correction method based on a three-axis sensor, the running distance correction method comprising: s1: acquiring x-axis acceleration data and z-axis acceleration data, which are acquired by the three-axis sensor and are in the running direction of the user, during the abnormal GPS positioning; s2: fusing the x-axis acceleration data and the z-axis acceleration data to obtain synthetic axis data; s3: detecting wave crests and wave troughs of the synthetic axis data to obtain a gait cycle; s4: calculating a first characteristic value, a second characteristic value, a third characteristic value, a fourth characteristic value, a fifth characteristic value and a sixth characteristic value according to the synthetic axis data in each gait cycle to form a characteristic vector, wherein the first characteristic value is represented asThe second characteristic value is represented asThe third feature value is represented asThe fourth feature value is represented by f4 ═ p2-p1)/J, the fifth feature value is represented by f5 ═ p3-p1)/J, and the sixth feature value is represented byWherein the content of the first and second substances,representing the difference between the maximum value of the z-axis acceleration data and the acceleration data at the z-axis p2,represents the minimum of the x-axis acceleration data,represents the minimum value of z-axis acceleration data, M, K, J represents a constant, p1 and p3 represent the valleys of the synthetic axis data in one gait cycle, and p2 represents the peaks of the synthetic axis data in one gait cycle; s5: inputting the characteristic vector into a pre-trained linear regression model to obtain a step length prediction value, wherein the linear regression model is obtained by training historical running posture data of a plurality of runners; s6: and calculating the product of the step length predicted value and the gait cycle number in the abnormal GPS positioning period to obtain the running distance in the abnormal GPS positioning period.
As a preferred embodiment of the present invention, the step S1 further includes: and carrying out smooth filtering on the x-axis acceleration data, the z-axis acceleration data and the y-axis gyroscope data.
As a preferred embodiment of the present invention, when smoothing filtering the x-axis acceleration data, the filtering formula adopted is:
wherein N is a constant, xiThe ith acceleration data is represented.
As a preferred embodiment of the present invention, the expression of the linear regression model is:
Dist=f*w+b
where w and b both represent parameters of the linear regression model.
Different from the prior art, the invention has the beneficial effects that: according to the invention, during the abnormal GPS positioning period, the running distance is calculated through the data of the three-axis sensor and the linear regression model with smaller calculation amount, and the running distance during the abnormal GPS positioning period is used for correction, so that the accuracy and stability of the running distance calculation can be improved.
Drawings
Fig. 1 is a schematic flow chart of a running distance correction method based on a three-axis sensor according to an embodiment of the present invention.
FIG. 2 is a waveform diagram of composite axis data in an example application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the running distance calibration method based on a three-axis sensor according to the embodiment of the present invention includes the following steps:
s1: during GPS positioning abnormity, x-axis acceleration data and z-axis acceleration data in the running direction of the user, which are acquired by a three-axis sensor, are acquired.
In order to facilitate data acquisition and extraction, a proper installation position and direction need to be selected for the three-axis sensor, and in a specific example, the three-axis sensor is worn on the vamp of a user. It should be noted that the three-axis sensor in this embodiment may be integrated into an electronic product, and then the electronic product should be worn on the upper of the user.
Whether the GPS positioning is abnormal or not can be judged according to a specific zone bit in the GPS positioning data, if the zone bit is A, the GPS positioning is normal, and if the zone bit is V, the GPS positioning is abnormal.
S2: and fusing the acceleration data of the x axis and the acceleration data of the z axis to obtain the synthetic axis data.
S3: and detecting wave crests and wave troughs of the synthetic axis data to obtain a gait cycle.
Since the leg-stepping motion is a repeated process during running, the x-axis acceleration data and the z-axis acceleration data are regular periodic data, and correspondingly, the synthesized axis data is also regular periodic data, as shown in fig. 2, which is a waveform diagram of the synthesized axis data in an application example, in the diagram, P1 and P3 represent wave troughs, and P2 represents wave crests. Therefore, a peak and a trough exist in each cycle, and the gait cycle can be obtained by detecting the polarity of the peak and the trough.
S4: calculating to obtain a first characteristic value, a second characteristic value, a third characteristic value, a fourth characteristic value, a fifth characteristic value and a sixth characteristic value according to the synthetic axis data in each gait cycle to form a characteristic vector, wherein the first characteristic value is represented asThe second characteristic value is represented asThe third feature value is represented asThe fourth feature value is represented by f4 ═ p2-p1)/J, the fifth feature value is represented by f5 ═ p3-p1)/J, and the sixth feature value is represented byWherein the content of the first and second substances,representing the difference between the maximum value of the z-axis acceleration data and the acceleration data at the z-axis p2,represents the minimum of the x-axis acceleration data,represents the minimum value of z-axis acceleration data, M, K, J represents a constant, p1 and p3 represent the valleys of the synthesized axis data in one gait cycle, and p2 represents the peaks of the synthesized axis data in one gait cycle.
M, K, J are determined by the span of the three-axis sensor, and in one specific application, M is 7000, K is 1000, and J is 55.
The feature vector includes a first feature value, a second feature value, a third feature value, a fourth feature value, a fifth feature value, and a sixth feature value, and is expressed as f ═ f1, f2, f3, f4, f5, and f 6.
S5: and inputting the characteristic vector into a pre-trained linear regression model to obtain a step length predicted value, wherein the linear regression model is obtained by training historical running posture data of a plurality of runners.
In this embodiment, the expression of the linear regression model is:
Dist=f*w+b
where w and b both represent parameters of the linear regression model.
S6: and calculating the product of the step length predicted value and the gait cycle number during the abnormal GPS positioning period to obtain the running distance during the abnormal GPS positioning period.
The running distance is obtained by adopting the method of the embodiment of the invention only during the abnormal GPS positioning, and the distance between adjacent GPS positioning points is continuously calculated to be used as the running distance after the GPS positioning is normal.
In this embodiment, step S1 further includes: and carrying out smooth filtering on the x-axis acceleration data, the z-axis acceleration data and the y-axis gyroscope data. For example, when smoothing the x-axis acceleration data, the filter formula used is:
where N is a constant, e.g. N-6, xiThe ith acceleration data is represented.
For z-axis acceleration data and y-axis gyroscope data, the same filtering formula can be used for smoothing filtering.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (4)
1. A running distance correction method based on a three-axis sensor is characterized by comprising the following steps:
s1: acquiring x-axis acceleration data and z-axis acceleration data, which are acquired by the three-axis sensor and are in the running direction of the user, during the abnormal GPS positioning;
s2: fusing the x-axis acceleration data and the z-axis acceleration data to obtain synthetic axis data;
s3: detecting wave crests and wave troughs of the synthetic axis data to obtain a gait cycle;
s4: calculating a first characteristic value, a second characteristic value, a third characteristic value, a fourth characteristic value, a fifth characteristic value and a sixth characteristic value according to the synthetic axis data in each gait cycle to form a characteristic vector, wherein the first characteristic value represents a characteristic vectorIs composed ofThe second characteristic value is represented asThe third feature value is represented asThe fourth feature value is represented by f4 ═ p2-p1)/J, the fifth feature value is represented by f5 ═ p3-p1)/J, and the sixth feature value is represented byWherein the content of the first and second substances,representing the difference between the maximum value of the z-axis acceleration data and the acceleration data at the z-axis p2,represents the minimum of the x-axis acceleration data,represents the minimum value of z-axis acceleration data, M, K, J represents a constant, p1 and p3 represent the valleys of the synthetic axis data in one gait cycle, and p2 represents the peaks of the synthetic axis data in one gait cycle;
s5: inputting the characteristic vector into a pre-trained linear regression model to obtain a step length prediction value, wherein the linear regression model is obtained by training historical running posture data of a plurality of runners;
s6: and calculating the product of the step length predicted value and the gait cycle number in the abnormal GPS positioning period to obtain the running distance in the abnormal GPS positioning period.
2. The method for correcting running distance based on three-axis sensors as claimed in claim 1, wherein the step S1 further comprises:
and carrying out smooth filtering on the x-axis acceleration data, the z-axis acceleration data and the y-axis gyroscope data.
3. The method of claim 2, wherein the smoothing filter is applied to the x-axis acceleration data according to the following formula:
wherein N is a constant, xiThe ith acceleration data is represented.
4. The method of claim 1, wherein the linear regression model is expressed as:
Dist=f*w+b
where w and b both represent parameters of the linear regression model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910952486.1A CN110595501B (en) | 2019-10-09 | 2019-10-09 | Running distance correction method based on three-axis sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910952486.1A CN110595501B (en) | 2019-10-09 | 2019-10-09 | Running distance correction method based on three-axis sensor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110595501A true CN110595501A (en) | 2019-12-20 |
CN110595501B CN110595501B (en) | 2022-10-04 |
Family
ID=68865916
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910952486.1A Active CN110595501B (en) | 2019-10-09 | 2019-10-09 | Running distance correction method based on three-axis sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110595501B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115253256A (en) * | 2021-04-30 | 2022-11-01 | 安徽华米健康科技有限公司 | Method and device for counting periods of periodic movement |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030018430A1 (en) * | 2001-04-23 | 2003-01-23 | Quentin Ladetto | Pedestrian navigation method and apparatus operative in a dead reckoning mode |
CN102654405A (en) * | 2011-03-04 | 2012-09-05 | 美新半导体(无锡)有限公司 | Gait counting method and device based on acceleration sensor |
US20130138394A1 (en) * | 2011-11-29 | 2013-05-30 | Seiko Epson Corporation | State detecting device, electronic apparatus, and program |
CN104713568A (en) * | 2015-03-31 | 2015-06-17 | 上海帝仪科技有限公司 | Gait recognition method and corresponding pedometer |
CN106108913A (en) * | 2016-07-25 | 2016-11-16 | 北京顺源开华科技有限公司 | Error count step removing method, device and wearable device |
WO2017000563A1 (en) * | 2015-06-30 | 2017-01-05 | 广州市香港科大霍英东研究院 | Real-time location method and system for intelligent device, and determination method for movement posture of mobile phone |
CN106767888A (en) * | 2016-11-15 | 2017-05-31 | 皖西学院 | A kind of meter based on Wave crest and wave trough detection walks algorithm |
CN107314775A (en) * | 2017-05-17 | 2017-11-03 | 浙江利尔达物联网技术有限公司 | A kind of switching at runtime based on 3-axis acceleration sensor calculates the step-recording method of axle |
CN107343789A (en) * | 2017-05-17 | 2017-11-14 | 浙江利尔达物联网技术有限公司 | A kind of step motion recognition method based on 3-axis acceleration sensor |
CN107462258A (en) * | 2017-07-13 | 2017-12-12 | 河海大学 | A kind of step-recording method based on mobile phone 3-axis acceleration sensor |
CN107588784A (en) * | 2016-07-08 | 2018-01-16 | 深圳达阵科技有限公司 | A kind of state recognition and the method, apparatus and terminal distinguished |
CN108981745A (en) * | 2018-09-30 | 2018-12-11 | 深圳个人数据管理服务有限公司 | A kind of step-recording method, device, equipment and storage medium |
-
2019
- 2019-10-09 CN CN201910952486.1A patent/CN110595501B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030018430A1 (en) * | 2001-04-23 | 2003-01-23 | Quentin Ladetto | Pedestrian navigation method and apparatus operative in a dead reckoning mode |
CN102654405A (en) * | 2011-03-04 | 2012-09-05 | 美新半导体(无锡)有限公司 | Gait counting method and device based on acceleration sensor |
US20130138394A1 (en) * | 2011-11-29 | 2013-05-30 | Seiko Epson Corporation | State detecting device, electronic apparatus, and program |
CN104713568A (en) * | 2015-03-31 | 2015-06-17 | 上海帝仪科技有限公司 | Gait recognition method and corresponding pedometer |
WO2017000563A1 (en) * | 2015-06-30 | 2017-01-05 | 广州市香港科大霍英东研究院 | Real-time location method and system for intelligent device, and determination method for movement posture of mobile phone |
CN107588784A (en) * | 2016-07-08 | 2018-01-16 | 深圳达阵科技有限公司 | A kind of state recognition and the method, apparatus and terminal distinguished |
CN106108913A (en) * | 2016-07-25 | 2016-11-16 | 北京顺源开华科技有限公司 | Error count step removing method, device and wearable device |
CN106767888A (en) * | 2016-11-15 | 2017-05-31 | 皖西学院 | A kind of meter based on Wave crest and wave trough detection walks algorithm |
CN107314775A (en) * | 2017-05-17 | 2017-11-03 | 浙江利尔达物联网技术有限公司 | A kind of switching at runtime based on 3-axis acceleration sensor calculates the step-recording method of axle |
CN107343789A (en) * | 2017-05-17 | 2017-11-14 | 浙江利尔达物联网技术有限公司 | A kind of step motion recognition method based on 3-axis acceleration sensor |
CN107462258A (en) * | 2017-07-13 | 2017-12-12 | 河海大学 | A kind of step-recording method based on mobile phone 3-axis acceleration sensor |
CN108981745A (en) * | 2018-09-30 | 2018-12-11 | 深圳个人数据管理服务有限公司 | A kind of step-recording method, device, equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
杨力等: "基于步态特征的移动平台持续认证方案", 《通信学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115253256A (en) * | 2021-04-30 | 2022-11-01 | 安徽华米健康科技有限公司 | Method and device for counting periods of periodic movement |
CN115253256B (en) * | 2021-04-30 | 2024-02-27 | 安徽华米健康科技有限公司 | Periodic motion period counting method and device |
Also Published As
Publication number | Publication date |
---|---|
CN110595501B (en) | 2022-10-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101252634B1 (en) | system for analyzing walking motion | |
Lee et al. | Estimation of attitude and external acceleration using inertial sensor measurement during various dynamic conditions | |
US9127947B2 (en) | State estimator for rejecting noise and tracking and updating bias in inertial sensors and associated methods | |
US20120101763A1 (en) | Positioning apparatus, positioning method and storage medium for positioning of pedestrian by autonomous navigation | |
CN102353383B (en) | Method for step counting and mileage reckoning based on single-axis gyroscope | |
CN110274592B (en) | Zero-speed interval determination method for information fusion of waist and foot inertia measurement units | |
JP2006175206A (en) | Apparatus, method and program for detecting physical condition | |
CN104197935B (en) | Indoor localization method based on mobile intelligent terminal | |
Cockcroft et al. | A novel complimentary filter for tracking hip angles during cycling using wireless inertial sensors and dynamic acceleration estimation | |
WO2015146048A1 (en) | Error estimation method, motion analysis method, error estimation device, and program | |
CN104897158A (en) | Indoor double-layered positioning method and indoor double-layered positioning system for walker | |
JP6804908B2 (en) | Estimator, estimation method and computer program | |
CN107941212A (en) | A kind of vision and inertia joint positioning method | |
CN112362057A (en) | Inertial pedestrian navigation algorithm based on zero-speed correction and attitude self-observation | |
CN104613964A (en) | Pedestrian positioning method and system for tracking foot motion features | |
JP5821513B2 (en) | Reference value generation method and reference value generation apparatus | |
CN110595501B (en) | Running distance correction method based on three-axis sensor | |
CN115655265A (en) | Pedestrian navigation indoor positioning method based on inertial sensing | |
KR101301462B1 (en) | Pedestiran dead-reckoning apparatus using low cost inertial measurement unit and method thereof | |
JP2009186244A (en) | Tilt angle estimation system, relative angle estimation system, and angular velocity estimation system | |
CN113229806A (en) | Wearable human body gait detection and navigation system and operation method thereof | |
CN107907127A (en) | A kind of step-size estimation method based on deep learning | |
JP2017029383A (en) | Display control device, method, and program | |
CN111307148B (en) | Pedestrian positioning method based on inertial network | |
Kao et al. | Step-length estimation using wrist-worn accelerometer and GPS |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |