CN108960019A - Runner's identification and step-recording method based on treadmill - Google Patents
Runner's identification and step-recording method based on treadmill Download PDFInfo
- Publication number
- CN108960019A CN108960019A CN201710387941.9A CN201710387941A CN108960019A CN 108960019 A CN108960019 A CN 108960019A CN 201710387941 A CN201710387941 A CN 201710387941A CN 108960019 A CN108960019 A CN 108960019A
- Authority
- CN
- China
- Prior art keywords
- treadmill
- cloud server
- runner
- current value
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The runner's identification and step-recording method that the present invention provides a kind of based on treadmill, this method comprises: the 1, current value of acquisition treadmill at various speeds respectively；2, the current value is respectively sent in the database of the cloud server by the treadmill；3, the cloud server extracts the feature of the current value respectively, and the feature is normalized；4, the cloud server is trained based on the feature after normalization, obtains sorting parameter；5, the parameter is sent to the controller of the treadmill by the cloud server, and the controller identifies runner's identity according to the sorting parameter, and counts step number.The present invention improves the accuracy of runner's identification and step counting, enhances functions of treadmill, economical and practical.
Description
Technical field
The method of the present invention relates to a kind of runner's identification and step counting based on treadmill is more specifically logical
It crosses and the signal of running machine motor operating current is handled, with machine learning techniques, the identity of intelligent recognition runner, and
The method for realizing running step counting, belongs to body-building apparatus technical field.
Background technique
About the step counting technology of electric treadmill, conventional method mainly include the following types: (1) running channel two sides with just
A pair of of far infrared transceiver is installed to mode, number is blocked with signal and carrys out step counting；(2) increase pressure sensing on treadmill
Device, when being run on a treadmill according to people, foot solves to the pressure change of treadmill and walks number of running.This method needs to install special
Sensor therefore increase the complexity of running machine structure design, while improving production cost.(3) other classes are utilized
The signal that type sensor generates.Such as: " the intelligent step counting system for electric treadmill of Patent No. CN201420085472.7
System ", current of electric when acquiring treadmill work by closed-loop Hall current sensor, comparison electric current are compared with setting value,
If the numerical value of acquisition is greater than or equal to setting value, step number adds 1；Less than setting value, step number is constant.Although this scheme is from principle
It can be realized electric treadmill step counting.But since the speed of running people is different, weight is different or even running belt of running machine is elastic
It spends very big on the influence of the peak value of electric current；Secondly, the variation of electric current is also not the sine of a standard in completely walking, running
Wave, in fact it could happen that two different peak values, so simple go to calculate step number by a fixed current threshold, it is clear that in reality
Accurate step counting is unable to get in the application of border；Again, if not instead of people, an object, then this method above treadmill
Cannot be distinguished is not people, weight can be judged by accident and be run for people above；Finally, closed-loop Hall current sensor current acquisition
Precision is lower, and it is even more impossible to realize accurate note step for this scheme.Also, closed-loop Hall current sensor price is higher, increases race
The production cost of step machine.
About being run on a treadmill by runner, the identity of runner is identified, there are no similar technology and application,
But with the development of Internet of Things, Internet of Things treadmill is more and more common, if it is possible to the identity of automatic identification runner, automatically
Targetedly exercise guidance is provided, this will make treadmill become more intelligent and more practical, therefore related electric treadmill meter at present
One step process and technology need improve and perfect raising.
Summary of the invention
In view of the deficiency of above-mentioned various treadmill step-recording methods and technology, the present invention uses and acquires it in electric machine controller
The mode of operating current, when carrying out away race campaign on a treadmill by runner, due to the height, weight, gait of runner
Difference, lead to the amplitude of current of electric, the variation of curve, identify the identity of runner and carry out gait, step number statistics, provide
A kind of more accurate, more economical, more intelligent, more reliable scheme.Specifically:
The runner's identification and step-recording method, technical solution that the present invention provides a kind of based on treadmill are as follows:
A kind of runner's identification and step-recording method based on treadmill, the method are applied to a treadmill system,
The system comprises treadmill and cloud server, the cloud server includes database, and the treadmill includes controller,
It is characterized in that, which comprises
Step 1, the respectively current value of acquisition treadmill at various speeds；
The current value is respectively sent in the database of the cloud server by step 2, the treadmill；
Step 3, the cloud server extract the feature of the current value respectively, and place is normalized to the feature
Reason；
Step 4, the cloud server are trained based on the feature after normalization, obtain sorting parameter；
The parameter is sent to the controller of the treadmill by step 5, the cloud server, the controller according to
The sorting parameter identifies runner's identity, and counts step number.
Preferably, the state of the sorting parameter treadmill for identification, the state includes load condition, zero load
State；In the step 1,2 group current values of the treadmill under load condition and light condition are acquired.
Preferably, the method for normalizing in the step 3 are as follows:
Wherein D and D ' respectively indicates the value of the front and back of normalization, and max indicates the maximum value of this feature,
Min indicates the minimum value of this feature.
Preferably, the identity of parameter runner for identification；In the step 1, runner is acquired in friction speed
Under 1 group of current value.
Preferably, the step 1 further comprises carrying out shaping filter to the current value of acquisition and mean value being filtered
Wave.
Preferably, the step 3 further comprises: to filtered current value with trough be a wave starting point, under
One adjacent trough is the terminating point of the wave, and a trough reaches the current value between next trough and constitutes a wave, so
Afterwards, it is further analyzed again in the data to this wave, judges whether it meets a normal person and walk to run.
Preferably, the waveform number of the current value in specific time is calculated, a complete waveform corresponds to a step, statistics
Step number in the time.
Preferably, the cloud server includes training study module, the identity of runner and counts gait for identification
And step number.
Preferably, the treadmill is connect with the cloud server by wired or wireless way, carries out data exchange.
Preferably, the acquisition of the current value, for the work for directly acquiring treadmill by circuit in electric machine controller
Electric current obtains.
Compared with prior art, the beneficial effects of the present invention are:
1, economy.The present invention program acquires by motor control panel and uploads motor working current, aobvious using treadmill
Show that the arithmetic element on instrument board is calculated, without increasing any sensor and electronic component, constitutional detail, not will increase
Any cost.
2, accuracy.The present invention program acquires the running electric current of each runner, uploads to cloud server and is identified
Parameter calculates, and passes back to running generator terminal and identified that actively adapt to different runners, step counting precision is higher.
3, function is strong.The present invention program is not only able to step counting, and can identify different runners, is the calculating of energy consumption
Provide more parameters.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is runner's identification of the embodiment of the present invention and the implementation flow chart of step-recording method.
Specific embodiment
The embodiment of the present invention is described in detail with reference to the accompanying drawing.It will be appreciated that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
All other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Those skilled in the art should know it is further that following specific embodiments or specific embodiment, which are the present invention,
The set-up mode of series of optimum explaining specific summary of the invention and enumerating, and being between those set-up modes can be mutual
In conjunction with or it is interrelated use, unless clearly proposing some of them or a certain specific embodiment or embodiment party in the present invention
Formula can not be associated setting or is used in conjunction with other embodiments or embodiment.Meanwhile following specific embodiment or
Embodiment is only as the set-up mode optimized, and not as the understanding limited the scope of protection of the present invention.
In a specific embodiment, technical solution of the present invention can be accomplished by the following way: the technical program
It can identify the light condition or/and load condition of treadmill, and can be under treadmill load condition, in identification user's body
While part, implement to carry out step counting operation, specific as follows:
A, the technical program can be applied in the system of following framework, which includes running generator terminal and cloud server
Two parts, wherein running generator terminal is responsible for remained capacity and step counting identification；Cloud server is responsible for training study, calculates identification running
The identity of person simultaneously counts gait and step number；Running generator terminal is connect with cloud server by wired or wireless way, and data are carried out
Exchange；
B, the acquisition of current signal directly acquires the operating current of treadmill in electric machine controller by circuit；It is this
Not only acquisition precision is high for acquisition method, and it is reliable, complete to acquire current data；
C, treadmill is unloaded, loads intelligent recognition, passes through the method for machine learning, the operating condition of intelligent recognition treadmill
It is that steps are as follows for unloaded or remained capacity:
1. acquisition treadmill is empty at friction speed (such as 2km/h, 4km/h, 6km/h, 8km/h, 10km/h etc.) respectively
2 groups of current values when carrying and loading；Certainly, current value can also acquire more multiple groups, such as 3 groups, 4 groups, 5 groups etc., and/or every
The speed of group acquisition is set as more or less speed；
2. these current values are respectively transmitted in cloud server database by running generator terminal；
3. place is normalized as feature, and to feature in server extracts electric current respectively beyond the clouds mean value and variance
Reason.Method for normalizing is speciallyWherein D and D ' respectively indicates the value of the front and back of normalization, and max indicates the spy
The maximum value of sign, min indicate the minimum value of this feature；
4. the method that cloud server uses machine learning constructs unloaded load current model, and a large amount of according to acquisition
Unloaded load current data, these features of training, obtains the parameter that can classify to load condition and light condition；
5. the parameter that cloud server training obtains is transmitted to treadmill controller end, treadmill controller is according to acquisition
Electric current identifies that treadmill is in light condition or load condition in real time；
D, runner's gait intelligent recognition passes through the method for machine learning, the identity of intelligent recognition runner, identification step
It is as follows:
1. respectively acquisition runner at friction speed (2km/h, 4km/h, 6km/h, 8km/h, 10km/h) runner 1
Group current value；Certainly, current value can also acquire more multiple groups, such as the speed of 3 groups, 4 groups, 5 groups etc. and/or every group of acquisition
It is set as more or less speed；
2. these current values are respectively transmitted in cloud server database by running generator terminal；
3. cloud server extracts the characteristic value of the corresponding electric current of friction speed respectively, and trains these features, obtaining can
To identify the key parameter of runner's identity, these parameters include that current maxima minimum value under friction speed, electric current are average
Value, current cycle change T value, and the runner based on different weight and gait, these parameters are different characteristics, as body
The foundation of part identification；
4. the obtained key parameter of cloud server training is transmitted to treadmill controller end, treadmill controller is according to adopting
The electric current of collection determines the identity of current runner；
E, runner's step number counts, and steps are as follows:
1. treadmill carries out step number statistics while identifying runner's identity, integer filter is carried out to the primary current of acquisition
Wave and mean filter, to remove the burr above primary current；
2. the method using waveform partition carrys out step counting, in order to avoid the erroneous judgement of simple threshold value bring, step counting algorithm is used
The technology of waveform partition；To filtered current value with trough be a wave starting point, next adjacent trough be should
The terminating point of wave, a trough reaches the current value between next trough and constitutes a wave, then, in the data to this wave
It is further analyzed again, judges whether it meets a normal person and walk to run；
3. the method for utilizing this method, calculates the current value waveform number in this time, one of complete waveform
A corresponding step, and then reach the function of step counting.
Preferably, according to treadmill in the case where zero load, load, friction speed, different runners, the wave of current of electric
The difference of shape and wave amplitude is trained study by cloud server, extracts characteristic parameter and is issued to treadmill, treadmill root
It goes to identify different runners according to these characteristic parameters and counts step number.
In a specific embodiment, as shown in Figure 1, after treadmill starting, start to acquire treadmill driving motor
Current data under unloaded and load, when friction speed；The frequency acquisition of parameter preferably motor working current is 32 hertz；It is first
Low-pass filtering first is carried out to current of electric, burr is eliminated, then carries out median filtering again, identify the starting point of current waveform, so
After start to solve complete waveform, extract feature, be normalized；Finally by machine learning algorithm, calculating is known
Other parameter, from cloud server under pass identification parameter to treadmill and be written to treadmill control panel.
Treadmill is carried out unloaded and load first according to the electric current of fixed frequency acquisition driving motor by recognizer
Identification；If it is determined that the present load running of treadmill, then treadmill compare the characterisitic parameter of stored runner with just
The characterisitic parameter of runner after acquisition process carries out runner's identification judgement, determines the identity of runner；Pass through simultaneously
Step counting characterisitic parameter carry out on foot and running state identification, if being currently running state, number of running adds 1, if currently
Be walk line state then walk step number add 1.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those familiar with the art, all answers
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (10)
1. a kind of runner's identification and step-recording method based on treadmill, the method is applied to a treadmill system, institute
The system of stating includes treadmill and cloud server, and the cloud server includes database, and the treadmill includes controller,
It is characterized in that, which comprises
Step 1, the respectively current value of acquisition treadmill at various speeds；
The current value is respectively sent in the database of the cloud server by step 2, the treadmill；
Step 3, the cloud server extract the feature of the current value respectively, and the feature is normalized；
Step 4, the cloud server are trained based on the feature after normalization, obtain sorting parameter；
The parameter is sent to the controller of the treadmill by step 5, the cloud server, and the controller is according to
Sorting parameter identifies runner's identity, and counts step number.
2. the method according to claim 1, wherein the shape of the sorting parameter treadmill for identification
State, the state include load condition, light condition；In the step 1, treadmill is acquired under load condition and light condition
2 groups of current values.
3. being based on method as claimed in claim 2, which is characterized in that the method for normalizing in the step 3 are as follows:
Wherein D and D ' respectively indicates the value of the front and back of normalization, and max indicates the maximum value of this feature, min table
Show the minimum value of this feature.
4. the method according to claim 1, wherein the identity of parameter runner for identification；The step
In rapid 1, the 1 group of current value of acquisition runner at various speeds.
5. according to the method described in claim 4, it is characterized in that, the step 1 further comprises, to the electricity of acquisition
Flow valuve carries out shaping filter and mean filter.
6. according to the method described in claim 5, which is characterized in that the step 3 further comprises: to filtered current value with
Trough is the starting point of a wave, and next adjacent trough is the terminating point of the wave, trough reach next trough it
Between current value constitute a wave be then further analyzed again in the data to this wave, judge whether it is meeting one just
Ordinary person walks to run.
7. according to the method described in claim 6, it is characterized in that, calculate the waveform number of the current value in specific time,
One complete waveform corresponds to a step, counts the step number in the time.
8. being used for the method according to claim 1, wherein the cloud server includes training study module
It identifies the identity of runner and counts gait and step number.
9. the method according to claim 1, wherein the treadmill and the cloud server by wired or
Wireless mode connection, carries out data exchange.
10. the method according to claim 1, wherein the acquisition of the current value, is logical in electric machine controller
The operating current that oversampling circuit directly acquires treadmill obtains.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710387941.9A CN108960019A (en) | 2017-05-27 | 2017-05-27 | Runner's identification and step-recording method based on treadmill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710387941.9A CN108960019A (en) | 2017-05-27 | 2017-05-27 | Runner's identification and step-recording method based on treadmill |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108960019A true CN108960019A (en) | 2018-12-07 |
Family
ID=64494504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710387941.9A Pending CN108960019A (en) | 2017-05-27 | 2017-05-27 | Runner's identification and step-recording method based on treadmill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108960019A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109173147A (en) * | 2018-04-11 | 2019-01-11 | 北京慧动众人科技有限公司 | A kind of electric treadmill step-recording method |
-
2017
- 2017-05-27 CN CN201710387941.9A patent/CN108960019A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109173147A (en) * | 2018-04-11 | 2019-01-11 | 北京慧动众人科技有限公司 | A kind of electric treadmill step-recording method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103616034B (en) | A kind of network pedometer based on bluetooth and step-recording method | |
| CN106289309B (en) | Step-recording method and device based on 3-axis acceleration sensor | |
| CN106096662B (en) | Human motion state identification based on acceleration transducer | |
| CN104200234B (en) | Human action models and recognition methods | |
| CN104135911A (en) | Activity classification in a multi-axis activity monitor device | |
| CN104729507A (en) | Gait recognition method based on inertial sensor | |
| CN103455170A (en) | Sensor-based device and sensor-based method for recognizing motion of mobile terminal | |
| CN104007822A (en) | Large database based motion recognition method and device | |
| CN105797350A (en) | Intelligent method and system for body building posture recognition, evaluation, early-warning and intensity estimation | |
| CN103927851B (en) | A kind of individualized multi thresholds fall detection method and system | |
| CN108171278A (en) | A kind of recognizing model of movement method and system based on training data | |
| CN107588784A (en) | A kind of state recognition and the method, apparatus and terminal distinguished | |
| CN107644229A (en) | Indoor anomaly detection method based on multi-sensor information fusion | |
| CN105224104A (en) | Pedestrian movement's state identification method of mode is held based on smart mobile phone | |
| CN102445214A (en) | Step counting method based on 3D gravity sensor of smart phone | |
| CN102133103A (en) | Method for recognizing human walking gait cycle with electromyographic signal | |
| CN106156564A (en) | Driver's recognition methods based on smart mobile phone | |
| CN108008151A (en) | A kind of moving state identification method and system based on 3-axis acceleration sensor | |
| CN108334827A (en) | A kind of gait identity identifying method and intelligent shoe based on intelligent shoe | |
| CN106510658A (en) | Human body emotion judgment method based on bracelet | |
| CN106389074A (en) | Falling process stability predicting device and method based on plantar pressure sensing | |
| CN106644208A (en) | Riding capability analyzing system and riding capability analyzing method | |
| CN111931568A (en) | Human body falling detection method and system based on enhanced learning | |
| CN108960019A (en) | Runner's identification and step-recording method based on treadmill | |
| CN104850225B (en) | A kind of activity recognition method based on multi-level Fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Guangzhou elephant Health Technology Co., Ltd. Document name: Notification of Publication of the Application for Invention |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: GUANGZHOU DAXIANG HEALTH TECHNOLOGY Co.,Ltd. Document name: Notification of before Expiration of Request of Examination as to Substance |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Li Xueyun Document name: Deemed as a notice of withdrawal |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181207 |