CN110108278A - It is landed determining method and device based on the foot of six axle sensors - Google Patents
It is landed determining method and device based on the foot of six axle sensors Download PDFInfo
- Publication number
- CN110108278A CN110108278A CN201910431342.1A CN201910431342A CN110108278A CN 110108278 A CN110108278 A CN 110108278A CN 201910431342 A CN201910431342 A CN 201910431342A CN 110108278 A CN110108278 A CN 110108278A
- Authority
- CN
- China
- Prior art keywords
- motion
- sporter
- foot
- data
- time
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/18—Stabilised platforms, e.g. by gyroscope
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
It lands determining method and device the invention discloses a kind of foot based on six axle sensors.Wherein, this method comprises: acquisition sporter exercise data during the motion, wherein exercise data is the motion characteristic data that six axle sensors detect in sporter's motion process and at the time of motion characteristic data corresponds to；Feature point extraction is carried out at the time of correspondence to motion characteristic data, obtains predetermined characteristic point；The motion characteristic data of time interval carries out characteristics extraction where at the time of correspondence to predetermined characteristic point, based on the feature vector for extracting target exercise data in obtained characteristic value generation exercise data；Determine that the foot of sporter during the motion lands mode based on feature vector.The present invention solves the lower technical problem of the mode reliability in the related technology for being detected to the foot mode of landing of sporter.
Description
Technical field
It lands identification technology field the present invention relates to foot, lands in particular to a kind of foot based on six axle sensors
Determine method and device.
Background technique
On foot, foot when running lands, and mode is extremely important for sporter, and the mode that lands of mistake not only influences
Achievement plays, and injury can be also brought to sporter.Currently, the inspection for the mode that is used to land to foot of the sporter when walking or running
Survey method is divided into view-based access control model and the human body attitude identification based on nonvisual means.Wherein, the human body attitude identification of view-based access control model
Method, the cost is relatively high, and more harsh to product structure design requirement, and is less suitable for outdoor activities.For example, in the patent No.
It is the human body attitude identification of view-based access control model means disclosed in file for CN106730770A, can be used for treadmill；Based on non-
The human body attitude identification of vision means has using acceleration transducer, pressure sensor and six axle sensors, such as in patent again
Number for CN107343789A file in disclose using three axis accelerometer the landing posture for determining foot；In addition, in patent
Number to disclose using the insole for having pressure sensor in the file of CN106621250B come the mode that lands that judges foot；Special
Benefit number knows otherwise human body attitude to disclose a kind of six axle sensors of use in the file of CN107303181A, tool
Body, the step in sporter's movement identifies, specifically, determines that foot lands the moment using resultant acceleration, is judging foot
The segment signal Y-axis magnitude of angular velocity after the moment is landed, is according to the relationship judgement between the numerical value such as maximum, minimum, average value
Front foot landing or rear foot landing.However above-mentioned view-based access control model and based on nonvisual means carry out human body attitude identification, Jin Erjin
The drawbacks of knowledge for the mode of landing of traveling far and wide is otherwise or there are higher costs or the drawback lower there are recognition efficiency,
It is unable to satisfy the demand of sporter.
It is lower for the above-mentioned mode reliability in the related technology for being detected to the foot mode of landing of sporter
Problem, currently no effective solution has been proposed.
Summary of the invention
It lands determining method and device the embodiment of the invention provides a kind of foot based on six axle sensors, at least to solve
The lower technical problem of the mode reliability for being used to detect the foot mode of landing of sporter in the related technology.
According to an aspect of an embodiment of the present invention, a kind of foot based on six axle sensors is provided to land determining method,
It include: to acquire the exercise data of sporter during the motion, wherein the exercise data is six axle sensors in the movement
At the time of the motion characteristic data and the motion characteristic data detected in person's motion process corresponds to；To the motion feature
Feature point extraction is carried out at the time of data correspond to, and obtains predetermined characteristic point；When where at the time of correspondence to the predetermined characteristic point
Between the motion characteristic data in section carry out characteristics extraction, to generate mesh in the exercise data based on extracting obtained characteristic value
Mark the feature vector of exercise data；Determine that the foot of the sporter during the motion lands mode based on described eigenvector.
Optionally, six axle sensor includes: three axis accelerometer and three-axis gyroscope, and the motion characteristic data is extremely
It less include: the acceleration in the motion process of the sporter detected by the three axis accelerometer, by three axis
The angular speed of the sporter that gyroscope detects during the motion.
Optionally, determine that the foot mode of landing of the sporter during the motion includes: logical based on described eigenvector
It crosses identification and classification model, determines that the foot of the sporter corresponding with described eigenvector during the motion lands mode,
In, the identification and classification model is obtained using multi-group data by machine learning training, every group in the multi-group data
Data include: feature vector, and the foot of the sporter corresponding with described eigenvector during the motion lands mode.
Optionally, by identification and classification model, determine that the sporter corresponding with described eigenvector is being moved through
Foot in journey lands before mode, and should be landed determining method based on the foot of six axle sensors further include: obtain historical time section
Multiple history feature vectors and multiple history feet land mode, wherein the multiple history foot mode of landing is according to
What multiple history feature vectors determined；To acquisition including the multiple history foot of the multiple history feature vector sum place
Formula is trained, and obtains the identification and classification model.
Optionally, at the time of the predetermined characteristic point includes: that the foot of the sporter leaves ground, the leg of the sporter
At the time of being raised to extreme higher position, at the time of the foot of the sporter touches ground, the sole of the sporter is all contacted
At the time of ground.
Optionally, after acquisition sporter exercise data during the motion, further includes: to the exercise data into
Row filtering, obtains filtered exercise data.
Optionally, the foot mode of landing includes following one: heelstrike, full sole lands, forward roll.
Another aspect according to an embodiment of the present invention additionally provides a kind of foot based on six axle sensors and lands determination
Device, comprising: acquisition unit, for acquiring the exercise data of sporter during the motion, wherein the exercise data is six
The motion characteristic data and the motion characteristic data that axle sensor detects in sporter's motion process are corresponding
Moment；Extraction unit carries out feature point extraction at the time of for corresponding to the motion characteristic data, obtain predetermined characteristic point；
Generation unit, the motion characteristic data of time interval where at the time of for corresponding to the predetermined characteristic point carry out characteristic value and mention
It takes, the feature vector of target exercise data in the exercise data is generated with the characteristic value obtained based on extraction；Determination unit is used
In determining that the foot of the sporter during the motion lands mode based on described eigenvector.
Optionally, six axle sensor includes: three axis accelerometer and three-axis gyroscope, and the motion characteristic data is extremely
It less include: the acceleration in the motion process of the sporter detected by the three axis accelerometer, by three axis
The angular speed of the sporter that gyroscope detects during the motion.
Optionally, the determination unit comprises determining that subelement, for passing through identification and classification model, the determining and spy
The foot of the corresponding sporter of sign vector during the motion lands mode, wherein the identification and classification model is using more
Group data are obtained by machine learning training, and every group of data in the multi-group data include: feature vector, with the spy
The foot of the corresponding sporter of sign vector during the motion lands mode.
Optionally, should foot based on six axle sensors land determining device further include: subelement is obtained, for by sentencing
Other disaggregated model, the foot of the determining sporter corresponding with described eigenvector during the motion land before mode, obtain
Multiple history feature vectors of historical time section and multiple history feet are taken to land mode, wherein the multiple history foot lands
Mode is determined according to the multiple history feature vector；Training subelement, for acquisition include the multiple history
Feature vector and the multiple history foot mode of landing are trained, and obtain the identification and classification model.
Optionally, at the time of the predetermined characteristic point includes: that the foot of the sporter leaves ground, the leg of the sporter
At the time of being raised to extreme higher position, at the time of the foot of the sporter touches ground, the sole of the sporter is all contacted
At the time of ground.
Optionally, should foot based on six axle sensors land determining device further include: filter element, for being moved in acquisition
After the exercise data of person during the motion, the exercise data is filtered, obtains filtered exercise data.
Optionally, the foot mode of landing includes following one: heelstrike, full sole lands, forward roll.
Another aspect according to an embodiment of the present invention, additionally provides a kind of storage medium, the storage medium includes
The program of storage, wherein described program execute it is any one of above-mentioned described in the foot based on six axle sensors land determination side
Method.
Another aspect according to an embodiment of the present invention, additionally provides a kind of processor, the processor is for running
Program, wherein described program executed when running it is any one of above-mentioned described in the foot based on six axle sensors land determination side
Method.
In embodiments of the present invention, using acquisition sporter exercise data during the motion, wherein exercise data is
At the time of the motion characteristic data and motion characteristic data that six axle sensors detect in sporter's motion process correspond to；It is right
Feature point extraction is carried out at the time of motion characteristic data corresponds to, and obtains predetermined characteristic point；At the time of institute is corresponded to predetermined characteristic point
Characteristics extraction is carried out in the motion characteristic data of time interval, mesh in exercise data is generated with the characteristic value obtained based on extraction
Mark the feature vector of exercise data；Based on feature vector determine the foot of sporter during the motion land mode mode to fortune
The foot mode of landing of dynamic person during the motion differentiates, the foot based on six axle sensors provided through the embodiment of the present invention
The feature obtained after being analyzed and processed based on the exercise data that six axle sensors collect may be implemented in the determining method that lands
Vector determines that the foot of sporter during the motion lands the purpose of mode, has reached and has improved to sporter during the motion
The technical effect that the mode that foot lands accurately is detected, and then solve and be used for the mode that lands to the foot of sporter in the related technology
The lower technical problem of the mode reliability detected.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is that the foot according to an embodiment of the present invention based on six axle sensors lands the flow chart of determining method；
Fig. 2 is that the foot according to an embodiment of the present invention based on six axle sensors lands the showing of feature point extraction in determining method
It is intended to
Fig. 3 is according to an embodiment of the present invention optionally to be landed the structure chart of determining system based on the foot of six axle sensors；
Fig. 4 is that the foot according to an embodiment of the present invention based on six axle sensors lands the schematic diagram of determining device.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Embodiment 1
According to embodiments of the present invention, a kind of the land method of determining method of the foot based on six axle sensors is provided to implement
Example, it should be noted that step shown in the flowchart of the accompanying drawings can be in the calculating of such as a group of computer-executable instructions
It is executed in machine system, although also, logical order is shown in flow charts, and it in some cases, can be to be different from
Sequence herein executes shown or described step.
Fig. 1 is that the foot according to an embodiment of the present invention based on six axle sensors lands the flow chart of determining method, such as Fig. 1 institute
Show, the determining method that should be landed based on the foot of six axle sensors is included the following steps:
Step S102, the exercise data of acquisition sporter during the motion, wherein exercise data is that six axle sensors exist
At the time of the motion characteristic data and motion characteristic data detected in sporter's motion process corresponds to.
It should be noted that here at the time of either relative instant, is also possible to the absolute moment.It specifically, can be with
Depending on according to the actual situation.
In an alternative embodiment, six axle sensors may include: three axis accelerometer and three-axis gyroscope, movement
Characteristic at least may include: the acceleration in the motion process of the sporter detected by three axis accelerometer, by three
The angular speed of the sporter that axis gyroscope detects during the motion.For example, above-mentioned motion characteristic data may include but
Be not limited to following several: the sensing data of three axis accelerometer and/or three-axis gyroscope, based on three axis accelerometer and/or
The angular transformation or motion profile that the sensing data of three-axis gyroscope converts.
Step S104 carries out feature point extraction at the time of correspondence to motion characteristic data, obtain predetermined characteristic point.
Wherein, at the time of above-mentioned predetermined characteristic point may include: that the foot of sporter leaves ground, the leg of sporter is raised to
At the time of extreme higher position, at the time of the foot of sporter touches ground, at the time of the sole of sporter all contacts ground.
As an optional embodiment of step S104, can also by motion characteristic data carry out slide window processing with
The one piece of data intercepted in motion characteristic data carries out characteristics extraction.Preferably, the motion characteristic data that above-mentioned interception obtains
Length be no less than a period of motion；Wherein, the period of motion here can include but is not limited to: the single step period, multiple to walk
Period.
Wherein, Fig. 2 is that the foot according to an embodiment of the present invention based on the six axle sensors characteristic point in determining method that lands mentions
The schematic diagram taken, in Fig. 2, horizontal axis is time shaft, and curve a indicates that resultant acceleration signal, curve b indicate to believe resultant acceleration
Signal after number being filtered, curve c indicate the signal for the three-axis gyroscope chosen.Wherein, the arrows in figure three
Several characteristic points in walking period, there is TC point, MS point, IC point and FC point, and respectively foot leaves ground
At the time of face (that is, at the time of the foot of sporter leaves ground), (that is, the leg of sporter at the time of leg is suspended in aerial extreme higher position
At the time of being raised to extreme higher position), at the time of (that is, at the time of the foot of sporter touches ground) foot has just contacted ground, sole
All at the time of contact ground (that is, at the time of the sole of sporter all contacts ground).
Step S106, the motion characteristic data of time interval where at the time of correspondence to predetermined characteristic point carry out characteristic value and mention
It takes, based on the feature vector for extracting target exercise data in obtained characteristic value generation exercise data.
In step S104 and step S106, the movement number that characteristic extracting module obtains data acquisition module can use
According to progress feature point extraction, and the motion characteristic data in the time interval at moment is corresponded to according to specific characteristic point and carries out characteristic value
It extracts, based on the feature vector for extracting target exercise data in obtained characteristic value generation exercise data.
Wherein, features described above value can include but is not limited to: the value of characterization motion characteristic data size and Axial changes, and three
Difference and variation of three number of axle between in axis accelerometer, difference and change of three number of axle between in three-axis gyroscope
Change, the angle or track of some axis or the corresponding synthesis axis of certain several axis in three axis accelerometer and three-axis gyroscope
(characteristic here can include but is not limited to characteristic: the minimum of angle or the maximum value of track, angle or track
Variance and/or variance, the intermediate value of angle or track of value, angle or the mean value of track (for synthesis axis), angle or track, angle
Degree or the ratio of track).
Step S108 determines that the foot of sporter during the motion lands mode based on feature vector.
Through the above steps, the exercise data of sporter during the motion can be acquired, wherein exercise data is six axis
At the time of the motion characteristic data and motion characteristic data that sensor detects in sporter's motion process correspond to；Then right
Feature point extraction is carried out at the time of motion characteristic data corresponds to, and obtains predetermined characteristic point；And at the time of correspondence to predetermined characteristic point
The motion characteristic data of place time interval carries out characteristics extraction, is generated in exercise data with the characteristic value obtained based on extraction
The feature vector of target exercise data；And determine that the foot of sporter during the motion lands mode based on feature vector.Phase
For there is at high cost, detection essence for being known otherwise to the foot mode of landing of sporter's motion process in the related technology
Low drawback is spent, the foot based on six axle sensors provided through the embodiment of the present invention the determining method that lands may be implemented based on six
The feature vector that the exercise data that axle sensor collects obtains after being analyzed and processed determines sporter during the motion
Foot land the purpose of mode, reached to improve and landed the skill that mode accurately detected to the foot of sporter during the motion
Art effect, and then the mode reliability solved in the related technology for being detected to the foot mode of landing of sporter is lower
Technical problem.
In step S108, determine that the foot mode of landing of sporter during the motion may include: based on feature vector
By identification and classification model, determine that the foot of sporter corresponding with feature vector during the motion lands mode, wherein differentiation
Disaggregated model is obtained using multi-group data by machine learning training, and every group of data in multi-group data include: feature
Vector, the foot of sporter corresponding with feature vector during the motion land mode.
Wherein, Fig. 3 is according to an embodiment of the present invention optionally to be landed the knot of determining system based on the foot of six axle sensors
Composition, as shown in figure 3, the system may include: data acquisition module, characteristic extracting module, feature recognition module, model training
Module and result output module.Wherein, data acquisition module here can be used to obtain the collected fortune of six axle sensors
The exercise data of dynamic person during the motion.In addition, feature recognition module here can be used to using model training module life
At identification and classification model operation and Classification and Identification are carried out to feature vector, obtain classification results, wherein classification results here
Can include but is not limited to: heelstrike, full sole lands, forward roll.As a result output module is used to feature identifying mould
The output of classification results that block obtains, wherein output form can include but is not limited to: the foot in single walking period lands mode,
Foot in a period of time lands mode.
Above-mentioned identification and classification model is the functional module in above-mentioned Fig. 3 in model training module, model training mould here
The feature vector that block can be used to obtain using characteristic extracting module carries out model training and optimization, generates identification and classification model.
It should be noted that model training module here is usually to use in the training pattern stage.In addition, being carried out using feature vector
Training, is including but not limited to trained to drag: neural network model, decision-tree model, SVM model, random forest
Model, deep learning model.
In addition, by identification and classification model, the foot of sporter corresponding with feature vector during the motion is determined
Before ground mode, the determining method that should be landed based on the foot of six axle sensors can also include: to obtain the multiple of historical time section to go through
History feature vector and multiple history feet land mode, wherein multiple history foot modes of landing be according to multiple history features to
Amount determination；What it is to acquisition includes that the multiple history foot modes of landing of multiple history feature vector sums are trained, and obtains differentiating and divide
Class model.
In addition, the history foot in identification and classification model training stage lands mode, in addition to that can pass through above-mentioned multiple history
Feature vector determines, is also possible to by artificially marking or automatic marking obtains.
In an alternative embodiment, after acquiring the exercise data of sporter during the motion, further includes: right
Exercise data is filtered, and obtains filtered exercise data.By being filtered to exercise data, can make for fortune
The result that the foot mode of landing of dynamic person is determined is more accurate.
In embodiments of the present invention, the foot mode of landing may include following one: heelstrike, full sole lands, front foot
The palm lands.
Embodiment 2
Another aspect according to an embodiment of the present invention additionally provides a kind of foot based on six axle sensors and lands determination
Device, Fig. 4 are that the foot according to an embodiment of the present invention based on six axle sensors lands the schematic diagram of determining device, as shown in figure 4,
The foot based on the six axle sensors determining device that lands includes: acquisition unit 41, extraction unit 43, generation unit 45 and is determined
Unit 47.The foot based on the six axle sensors determining device that lands is described in detail below.
Acquisition unit 41, for acquiring the exercise data of sporter during the motion, wherein exercise data is six axis biography
At the time of the motion characteristic data and motion characteristic data that sensor detects in sporter's motion process correspond to.
Extraction unit 43 carries out feature point extraction at the time of for corresponding to motion characteristic data, obtain predetermined characteristic point.
Generation unit 45, the motion characteristic data of time interval carries out special where at the time of for corresponding to predetermined characteristic point
Value indicative is extracted, based on the feature vector for extracting target exercise data in obtained characteristic value generation exercise data.
Determination unit 47, for determining that the foot of sporter during the motion lands mode based on feature vector.
Herein it should be noted that above-mentioned acquisition unit 41, extraction unit 43, generation unit 45 and determination unit 47 are right
Should be in the step S102 to S108 in embodiment 1, above-mentioned module is identical as example and application scenarios that corresponding step is realized,
But it is not limited to the above embodiments 1 disclosure of that.It should be noted that above-mentioned module can be all as a part of of device
As a group of computer-executable instructions computer system in execute.
From the foregoing, it will be observed that in embodiments of the present invention, can use the fortune of acquisition unit acquisition sporter during the motion
Dynamic data, wherein exercise data is the motion characteristic data and fortune that six axle sensors detect in sporter's motion process
At the time of dynamic characteristic corresponds to；And feature point extraction is carried out at the time of correspondence using extraction unit to motion characteristic data, it obtains
To predetermined characteristic point；Next the motion feature number of time interval where at the time of correspondence using generation unit to predetermined characteristic point
According to characteristics extraction is carried out, based on the feature vector for extracting target exercise data in obtained characteristic value generation exercise data；
And in such a way that determination unit determines that the foot of sporter during the motion lands based on feature vector.Relative to the relevant technologies
In there is drawback at high cost, that detection accuracy is low otherwise for being known to the foot mode of landing of sporter's motion process,
The foot based on six axle sensors provided through the embodiment of the present invention the determining device that lands may be implemented to adopt based on six axle sensors
Collect the feature vector obtained after obtained exercise data is analyzed and processed determine the foot of sporter during the motion place
The purpose of formula, has reached to improve and has landed the technical effect that mode accurately detected to the foot of sporter during the motion, into
And solves the lower technical problem of the mode reliability for being used to detect the foot mode of landing of sporter in the related technology.
As a kind of optional embodiment, six axle sensors include: three axis accelerometer and three-axis gyroscope, motion feature
Data include at least: the acceleration in the motion process of the sporter detected by three axis accelerometer, by three-axis gyroscope
Detect the angular speed of obtained sporter during the motion.
As a kind of optional embodiment, determination unit comprises determining that subelement, for passing through identification and classification model, really
The fixed foot of sporter corresponding with feature vector during the motion lands mode, wherein identification and classification model is uses multiple groups
Data are obtained by machine learning training, and every group of data in multi-group data include: feature vector, corresponding with feature vector
Sporter's foot during the motion land mode.
As a kind of optional embodiment, should foot based on six axle sensors land determining device further include: it is single to obtain son
Member, for by identification and classification model, determining that the foot of sporter corresponding with feature vector during the motion lands mode
Before, multiple history feature vectors of historical time section are obtained and multiple history feet lands mode, wherein multiple history feet
The mode of landing is determined according to multiple history feature vectors；Training subelement, for acquisition include multiple history features
The multiple history foot modes of landing of vector sum are trained, and obtain identification and classification model.
As a kind of optional embodiment, at the time of predetermined characteristic point includes: that the foot of sporter leaves ground, sporter's
At the time of leg is raised to extreme higher position, at the time of the foot of sporter touches ground, the sole of sporter all contacts ground
Moment.
As a kind of optional embodiment, should foot based on six axle sensors land determining device further include: filter element,
For being filtered to exercise data, obtaining filtered fortune after acquiring the exercise data of sporter during the motion
Dynamic data.
As a kind of optional embodiment, the foot mode of landing includes following one: heelstrike, full sole lands, front foot
The palm lands.
Embodiment 3
Another aspect according to an embodiment of the present invention, additionally provides a kind of storage medium, and storage medium includes storage
Program, wherein program executes any one of above-mentioned foot based on six axle sensors and lands determining method.
Embodiment 4
Another aspect according to an embodiment of the present invention additionally provides a kind of processor, and processor is used to run program,
Wherein, any one of above-mentioned foot based on six axle sensors is executed when program is run to land determining method.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of unit, can be one kind
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of unit or module,
It can be electrical or other forms.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple units
On.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of step of each embodiment method of the present invention
Suddenly.And storage medium above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
The above is only the preferred embodiment of the present invention, it is noted that those skilled in the art are come
It says, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should be regarded as
Protection scope of the present invention.
Claims (10)
- A kind of determining method 1. foot based on six axle sensors lands characterized by comprisingAcquire the exercise data of sporter during the motion, wherein the exercise data is six axle sensors in the movement At the time of the motion characteristic data and the motion characteristic data detected in person's motion process corresponds to；Feature point extraction is carried out at the time of correspondence to the motion characteristic data, obtains predetermined characteristic point；The motion characteristic data of time interval carries out characteristics extraction where at the time of correspondence to the predetermined characteristic point, to be based on Extract the feature vector that obtained characteristic value generates target exercise data in the exercise data；Determine that the foot of the sporter during the motion lands mode based on described eigenvector.
- 2. the method according to claim 1, wherein six axle sensor includes: three axis accelerometer and three Axis gyroscope, the motion characteristic data include at least: by the fortune for the sporter that the three axis accelerometer detects Acceleration during dynamic, the angular speed of the sporter detected by the three-axis gyroscope during the motion.
- 3. the method according to claim 1, wherein determining that the sporter is moving based on described eigenvector The foot mode of landing in the process includes:By identification and classification model, determine the foot of the sporter corresponding with described eigenvector during the motion it is local Formula, wherein the identification and classification model is obtained using multi-group data by machine learning training, in the multi-group data Every group of data include: feature vector, the foot of the sporter corresponding with described eigenvector during the motion place Formula.
- 4. according to the method described in claim 3, it is characterized in that, by identification and classification model, it is determining with the feature to The foot of the corresponding sporter during the motion is measured to land before mode, further includes:The multiple history feature vectors and multiple history feet for obtaining historical time section land mode, wherein the multiple history The foot mode of landing is determined according to the multiple history feature vector；What it is to acquisition includes that the multiple history foot mode of landing of the multiple history feature vector sum is trained, and is obtained described Identification and classification model.
- 5. the method according to claim 1, wherein predetermined characteristic point include: the sporter foot from At the time of opening ground, at the time of the leg of the sporter is raised to extreme higher position, the foot of the sporter touch ground when It carves, at the time of the sole of the sporter all contacts ground.
- 6. the method according to claim 1, wherein acquisition sporter exercise data during the motion it Afterwards, further includes: the exercise data is filtered, filtered exercise data is obtained.
- 7. method according to any one of claim 1 to 6, which is characterized in that the foot mode of landing include it is following it One: heelstrike, full sole lands, forward roll.
- The determining device 8. a kind of foot based on six axle sensors lands characterized by comprisingAcquisition unit, for acquiring the exercise data of sporter during the motion, wherein the exercise data is six axis sensing At the time of the motion characteristic data and the motion characteristic data that device detects in sporter's motion process correspond to；Extraction unit carries out feature point extraction at the time of for corresponding to the motion characteristic data, obtain predetermined characteristic point；Generation unit, the motion characteristic data of time interval carries out feature where at the time of for corresponding to the predetermined characteristic point Value is extracted, and the feature vector of target exercise data in the exercise data is generated with the characteristic value obtained based on extraction；Determination unit, for determining that the foot of the sporter during the motion lands mode based on described eigenvector.
- 9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution Benefit is landed determining method described in requiring any one of 1 to 7 based on the feet of six axle sensors.
- 10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run Benefit is landed determining method described in requiring any one of 1 to 7 based on the feet of six axle sensors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431342.1A CN110108278B (en) | 2019-05-22 | 2019-05-22 | Foot landing determination method and device based on six-axis sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431342.1A CN110108278B (en) | 2019-05-22 | 2019-05-22 | Foot landing determination method and device based on six-axis sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110108278A true CN110108278A (en) | 2019-08-09 |
| CN110108278B CN110108278B (en) | 2021-07-09 |
Family
ID=67491737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910431342.1A Active CN110108278B (en) | 2019-05-22 | 2019-05-22 | Foot landing determination method and device based on six-axis sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110108278B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104406586A (en) * | 2014-12-04 | 2015-03-11 | 南京邮电大学 | Pedestrian navigation device and pedestrian navigation method based on inertial sensor |
| US20160151696A1 (en) * | 2016-01-15 | 2016-06-02 | Inxpar Inc. | System for analyzing golf swing process and method thereof |
| CN106823347A (en) * | 2017-01-18 | 2017-06-13 | 深圳市爱康伟达智能医疗科技有限公司 | A kind of attitude detection display device and method |
| CN107303181A (en) * | 2017-05-17 | 2017-10-31 | 浙江利尔达物联网技术有限公司 | A kind of step motion recognition method based on six axle sensors |
| CN109663323A (en) * | 2018-12-20 | 2019-04-23 | 出门问问信息科技有限公司 | A kind of motion state monitoring method and wearable device based on wearable device |
-
2019
- 2019-05-22 CN CN201910431342.1A patent/CN110108278B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104406586A (en) * | 2014-12-04 | 2015-03-11 | 南京邮电大学 | Pedestrian navigation device and pedestrian navigation method based on inertial sensor |
| US20160151696A1 (en) * | 2016-01-15 | 2016-06-02 | Inxpar Inc. | System for analyzing golf swing process and method thereof |
| CN106823347A (en) * | 2017-01-18 | 2017-06-13 | 深圳市爱康伟达智能医疗科技有限公司 | A kind of attitude detection display device and method |
| CN107303181A (en) * | 2017-05-17 | 2017-10-31 | 浙江利尔达物联网技术有限公司 | A kind of step motion recognition method based on six axle sensors |
| CN109663323A (en) * | 2018-12-20 | 2019-04-23 | 出门问问信息科技有限公司 | A kind of motion state monitoring method and wearable device based on wearable device |
Non-Patent Citations (2)
| Title |
|---|
| 熊赟等: "《大数据挖掘》", 30 April 2016, 上海科学技术出版社 * |
| 肖茜: "便携式移动电子设备的步行者航位推算技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|---|
| CN110108278B (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104729507B (en) | A kind of gait recognition method based on inertial sensor | |
| CN109579853B (en) | Inertial navigation indoor positioning method based on BP neural network | |
| CN101894252B (en) | Walking movement classification method based on triaxial acceleration transducer signals | |
| CN103976739B (en) | It is wearable to fall down dynamic realtime detection method and device | |
| CN110334573B (en) | Human motion state discrimination method based on dense connection convolutional neural network | |
| CN105310696B (en) | A kind of fall detection model building method and corresponding fall detection method and device | |
| CN103988233B (en) | Posture estimation device and posture estimation method | |
| CN106981174A (en) | A kind of Falls Among Old People detection method based on smart mobile phone | |
| CN106705968A (en) | Indoor inertial navigation algorithm based on posture recognition and step length model | |
| CN105224104B (en) | Pedestrian movement's state identification method based on smart mobile phone grip mode | |
| CN108021888A (en) | A kind of fall detection method | |
| JP6724984B2 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN107662613B (en) | A kind of extreme driving behavior recognition methods and system based on mobile intelligent perception | |
| CN109976526A (en) | A kind of sign Language Recognition Method based on surface myoelectric sensor and nine axle sensors | |
| CN108008151A (en) | A kind of moving state identification method and system based on 3-axis acceleration sensor | |
| KR20180058999A (en) | System and method for gait analyzing and computer readable record medium thereof | |
| CN107122711A (en) | A kind of night vision video gait recognition method based on angle radial transformation and barycenter | |
| CN114881079A (en) | Human body movement intention abnormity detection method and system for wearable sensor | |
| CN110108278A (en) | It is landed determining method and device based on the foot of six axle sensors | |
| Wang et al. | Recognition of the Gait Phase Based on New Deep Learning Algorithm Using Multisensor Information Fusion. | |
| CN107016411B (en) | Data processing method and device | |
| CN113008230B (en) | Intelligent wearable device and gesture direction recognition method and device thereof | |
| KR20210046121A (en) | Apparatus and method for identify patients with parkinson's disease and patients with podarthritis by performing neural network analysis by various detection information | |
| KR102194313B1 (en) | Apparatus and method for identifying individuals by performing neural network analysis for various detection information | |
| KR20210011097A (en) | Apparatus and method for classification of gait type by performing neural network analysis for various detection information |
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 |