CN105833508A - Intelligent gloves capable of measuring calorie consumption and monitoring hand posture identification as well as estimation method and system - Google Patents
Intelligent gloves capable of measuring calorie consumption and monitoring hand posture identification as well as estimation method and system Download PDFInfo
- Publication number
- CN105833508A CN105833508A CN201610155558.6A CN201610155558A CN105833508A CN 105833508 A CN105833508 A CN 105833508A CN 201610155558 A CN201610155558 A CN 201610155558A CN 105833508 A CN105833508 A CN 105833508A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- glove
- wisdom
- calorie consumption
- 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
-
- 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
-
- A—HUMAN NECESSITIES
- A41—WEARING APPAREL
- A41D—OUTERWEAR; PROTECTIVE GARMENTS; ACCESSORIES
- A41D19/00—Gloves
-
- A—HUMAN NECESSITIES
- A41—WEARING APPAREL
- A41D—OUTERWEAR; PROTECTIVE GARMENTS; ACCESSORIES
- A41D19/00—Gloves
- A41D19/0024—Gloves with accessories
- A41D19/0027—Measuring instruments, e.g. watch, thermometer
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0062—Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
-
- 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
-
- 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
- A63B2220/50—Force related parameters
- A63B2220/51—Force
-
- 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
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/83—Special sensors, transducers or devices therefor characterised by the position of the sensor
- A63B2220/833—Sensors arranged on the exercise apparatus or sports implement
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2230/00—Measuring physiological parameters of the user
- A63B2230/75—Measuring physiological parameters of the user calorie expenditure
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to intelligent monitoring and improved devices for the fitness movements, and discloses intelligent gloves capable of measuring calorie consumption and monitoring hand posture identification. Each intelligent glove comprises a processor module, a storage module, a communication module, a sensing module, an early warning prompting module, a display module, a power module, a switch module and a cloud server, wherein the storage module, the communication module, the sensing module, the early warning prompting module, the display module, the power module, the switch module and the cloud server are respectively connected with the processor module. The intelligent gloves have the advantages that the calorie measurement and the hand posture identification are carried out on the basis of the existing sensor technology, an efficient data processing method and an efficient algorithm model are adopted, and the intelligent gloves can be widely applied to strength training, so that a good reference is provided for the fitness enthusiasts, and the recommendation for the later-period food match and nutrition balance can be provided.
Description
Technical field
The present invention relates to intellectual monitoring and the improvement device of body-building action, particularly relate to a kind of calorie consumption and hand appearance
The method and system of gesture identification.
Background technology
Nowadays, along with the theory of healthy living becomes more and more popular, increasing fitness enthusiasts wants to survey
Measure caloric consumption when participating in strength building and dietary adjustments afterwards, but, in traditional acquisition motor process
The energy expenditure of human body not only program is loaded down with trivial details, and also needs to extra equipment, and therefore we need to find the one can be square in a hurry
Just and effectively caloric consumption during detection strength building and the method for action recognition.
During daily body-building, especially during strength building, human body will consume substantial amounts of calorie, in order to contribute to training
After nutritional supplementation and meals collocation, accurately do not estimate human body calorie consumption in the training process again;Meanwhile,
Correct posture is the essential condition of any training program.This is because correct posture contributes to alleviating even eliminates any diving
Training sick and wounded, contribute to the healthy of trainer.
In order to realize the detection of the preparation to action during body-building and caloric consumption, there has been proposed and utilize treadmill, from
Driving, running shoes detect the method for caloric consumption, but the detecting system itself using these methods to build all also exists
All deficiencies, these systems all take the computing module of special exercise to detect caloric consumption, are utilizing these specific
Computing module carry out caloric calculate when, measurement module is not moveable, it is impossible to reach accomplish veritably to wear
Wearing, in current research and commercial production, a kind of equipment is capable of above-mentioned function, the existing method of the latter by
Particularity in module can not be widely applied to this scene.
Summary of the invention
In order to solve problem of the prior art, the present invention provides a kind of calorie to consume and the system of hand positions identification,
Solve prior art obtains the problem that the energy expenditure program of human body in motor process is loaded down with trivial details and increases extras.
The present invention is achieved by the following technical solutions: a kind of measurement calorie consumption and monitoring hand positions identification
Wisdom glove, including: processor module, memory module, communication module, sensing module, early warning module, display module,
Power module, switch module and Cloud Server, described memory module, communication module, sensing module, early warning module, display
Module, power module, switch module are connected with processor module respectively with Cloud Server, and wherein, described sensing module includes
Pressure transducer and IMU inertance element, described pressure transducer and IMU inertance element are respectively used to be responsible for sensing user for body-building mistake
Hand pressurized strength size in journey and IMU data, and then collect source data for user's strength building, and by described source data
Send processor module to;Described processor module is responsible for the pretreatment to source beginning data;Described memory module is responsible at storage
The result managing device pretreatment and the result passed back from Cloud Server;Described communication module is responsible for source data, pretreatment
After data reach Cloud Server, for Cloud Server make further data process and analyze, and be responsible for by Cloud Server process
Result be transmitted back to wisdom glove;Described early warning module is then responsible for during body-building abnormal conditions sending warning to user;Described
Display module be responsible for user for body-building during type of action, the result that consumes calorie and posture standard degree shows.
Invention also provides a kind of estimation calorie consumption and monitoring hand positions knows method for distinguishing, have employed described
Measure calorie consumption and the wisdom glove of monitoring hand positions identification, and comprise the following steps: step S1, utilize thin film
Pressure transducer and IMU inertance element gather initial data during strength building;Step S2, by original data transmissions to processing
Device module processes;Step S3, carries out ETL analysis by the pressure transducer received and IMU inertance element data, described
ETL process be by ETL technology, the data obtained by step S2 are extracted, transposition, the process that loads and pay;And,
Step S4, estimates the calorie of consumption, sets up disaggregated model by support vector machine, the source data beyond strength building is made
For subject performance class, other as non-targeted action class;Then the threshold value of strength building is seen if fall out, if then sending
Alerting signal, if otherwise transferring data to movable equipment to carry out record, and recommended dietary recipe, nutrition arrangement and training meter
Draw.
As a further improvement on the present invention: in step sl, whole system is opened by user by button or switch, intelligence
One or more pressure transducer it is provided with on the sensing module of intelligent glove.
As a further improvement on the present invention: comprise the following steps in step s 2:
Step S21, gathers pressure data and athletic posture data, based on wearable by pressure transducer and IMU inertance element
The data of the acceleration transducer of acquisition, Magnetic Sensor and gyroscope are carried out slip mean filter by computing technique, to eliminate the back of the body
Scape noise, the sliding window width of described slip mean filter is adjusted (as equal in described slip according to user's practical situation
The sliding window width of value filter is 7);
Step S22, uses the mode of complementary filter to realize the standard of glove attitude the reading of acceleration transducer and gyroscope
Really estimating, this complementary filter is for combining acceleration transducer for the estimated value of glove attitude angle and gyroscope for glove
The estimated value of attitude angle;
Step S23, after using the mode of complementary filter to estimate glove attitude angle in motor process, according to mechanics principle
Eliminate gravity projection component in the wisdom glove direction of motion, extract and add produced by wisdom glove displacement
Velocity amplitude, it is achieved acceleration is calibrated;
Step S24, obtain through calibration after acceleration information, use an integration mode get wisdom glove motion speed
Angle value;
Step S25, after integration obtains the velocity amplitude of wisdom glove motion, originates in resting state according to wisdom glove and terminates
In the motion feature of resting state, the speed of wisdom glove motion is calibrated;
Step S26, carries out an integration, thus obtains the displacement size of wisdom glove motion gained velocity amplitude;Step S27,
In conjunction with the above results, the track of body-building action is reconstructed, thus the movement locus of hand during obtaining user for body-building.
As a further improvement on the present invention: described step S4 comprises the following steps:
Step S41A, the shift value obtained by integrating step S2, the reading of combination film pressure transducer, through the place of step S3
Reason, calculates glove motion work done, and the relational model consumed according to the merit set up and calorie calculates calorie consumption;
Step S42B, records caloric consumption, and carries out meals collocation and prompting balanced in nutrition;
Step S42A, pre-builds high dimensional feature model based on Statistical Learning Theory, and described high dimensional feature model is to set space
In the abnormal patterns of information change that causes due to every pose deviation action as training sample;
Step S41B, maps to abnormal patterns, in the high dimensional feature model of one-class support vector machine, isolate subject performance class,
And judge whether athletic posture deviates, if then sending alarm signal.
The present invention again provides a kind of system estimating calorie consumption and monitoring hand positions identification, have employed described
Estimation calorie consume and monitoring hand positions knows method for distinguishing, and include with lower module:
Signal acquisition and computing module, the signal in time collecting wisdom glove kinestate, and assess movement state information and add
With primary Calculation;
Abnormality detection module, for the exception whether changed by Outlier Detection Algorithm identification signal;
Action judge module, for one-class support vector machine subject performance class and other action classes made a distinction, to exceed
The abnormal patterns that strength building threshold value is caused is as subject performance class, and judges whether the exercise attitudes of wisdom glove occurs appearance
Gesture deviates;
And, alarm modules, for sending alarm signal when judging to occur pose deviation.
As a further improvement on the present invention: described signal acquisition and computing module include with lower unit:
Inductive pick-up unit, is used for opening whole system and collecting exercise data, and the exercise data of collection includes strength building side
Exercise data in power upwards and three-dimensional coordinate all directions;
Data processing unit, for trying to achieve meansigma methods to the power on each direction and movable information, using this meansigma methods as fortune
Dynamic status information;
Smooth unit, carries out ETL analysis for the data obtained by data processing unit, and by moving average method to motion
Status information is smoothed.
As a further improvement on the present invention: described abnormality detection module includes with lower unit:
Abnormal computing unit, obtains subsequence for the time series of movement state information is implemented data segmentation, calculates sub-sequence
The local anomaly data of row;
Abnormal output unit, for when described abnormal data is more than or equal to predetermined threshold value, using subsequence as abnormal mould
Formula exports.
As a further improvement on the present invention: described action judge module includes with lower unit:
Set up model unit, for based on Statistical Learning Theory preset set up high dimensional feature model, described high dimensional feature model with
Set the abnormal patterns causing movement state information to change due to every human action in space as training sample;
Action recognition unit, for mapping to the higher-dimension of one-class support vector machine by the abnormal patterns that abnormal output unit is exported
In characteristic model, isolate subject performance class.
As a further improvement on the present invention: also include feedback module, for feedback for hand positions alarm signal
Response message, adjusts the high dimensional feature model of one-class support vector machine.
Beneficial effects of the present invention: during carrying out strength building, the Detection accuracy of detected action is 84%-
94%, rate of false alarm is low, and caloric measurement accuracy rate is up to 90%, it is possible to send police after realizing judging hand positions deviation
The number of notifying, and utilize the self-learning function of system to process wrong report situation, reduce rate of false alarm further;The present invention is in existing sensing
On the basis of device technology, carry out caloric measurement and the work of hand positions identification, use efficient data processing method and
Algorithm model, can apply in strength building widely, provides good reference for fitness enthusiasts, and can provide later stage meals
Collocation and recommendation balanced in nutrition.
Accompanying drawing explanation
Fig. 1 is the module diagram of the wisdom glove of an embodiment of the present invention;
Fig. 2 is the fundamental diagram of another kind embodiment of the present invention;
Fig. 3 is the workflow schematic diagram of another kind embodiment of the present invention;
Fig. 4 is the functional block diagram of another embodiment of the present invention.
Detailed description of the invention
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
A kind of wisdom glove measuring calorie consumption and monitoring hand positions identification, including: processor module, storage mould
Block, communication module, sensing module, early warning module, display module, power module, switch module and Cloud Server, described in deposit
Storage module, communication module, sensing module, early warning module, display module, power module, switch module and Cloud Server divide
Not being connected with processor module, wherein, described sensing module includes pressure transducer and IMU inertance element, and described pressure passes
Sensor and IMU inertance element are respectively used to the hand pressurized strength size during responsible sensing user for body-building and IMU data, enter
And collect source data for user's strength building, and send described source data to processor module;Described processor module is born
The duty pretreatment to source beginning data;Described memory module is responsible for storing the result of processor pretreatment and passing back from Cloud Server
Result;Described communication module is responsible for source data, pretreated data are reached Cloud Server, for Cloud Server make into
The data of one step process and analyze, and are responsible for the result of Cloud Server process is transmitted back to wisdom glove;Described early warning mould
Block be then responsible for body-building abnormal conditions (as when user action is nonstandard, motion excess or stress improper) time send police to user
Show;Described display module be responsible for user for body-building during type of action, the result that consumes calorie and posture standard degree shows
Illustrate.
Invention also provides a kind of estimation calorie consumption and monitoring hand positions knows method for distinguishing, have employed described
Measure calorie consumption and the wisdom glove of monitoring hand positions identification, and comprise the following steps: step S1, utilize pressure
The diaphragm pressure sensor of sensor and IMU inertance element collect source data during strength building;Step S2, passes source data
It is passed to processor module process;Step S3, by the data acquired in the pressure transducer received and IMU inertance element
Carry out ETL process, carry out ETL analysis, described ETL process be by ETL technology, the data obtained by step S2 are extracted,
Transposition, the process loading and paying;And, step S4, calculate the calorie of consumption, set up classification by support vector machine
Model, using the source data beyond strength building as subject performance class, other as non-targeted action class;Then judge whether
Beyond the threshold value of strength building, if then sending alerting signal, if otherwise transferring data to movable equipment to carry out record, and
Recommended dietary recipe, nutrition arrangement and training plan.
In step sl, whole system is opened by user by button or switch, and the sensing module of wisdom glove is arranged
There is one or more pressure transducer.
Comprise the following steps in step s 2:
Step S21, gathers pressure data and athletic posture data, based on wearable by pressure transducer and IMU inertance element
The data of the acceleration transducer of acquisition, Magnetic Sensor and gyroscope are carried out slip mean filter by computing technique, to eliminate the back of the body
Scape noise, the sliding window width of described slip mean filter is 7;
Step S22, uses the mode of complementary filter to realize the standard of glove attitude the reading of acceleration transducer and gyroscope
Really estimating, this complementary filter is for combining acceleration transducer for the estimated value of glove attitude angle and gyroscope for glove
The estimated value of attitude angle;
Step S23, after using the mode of complementary filter to estimate glove attitude angle in motor process, according to mechanics principle
Eliminate gravity projection component in the wisdom glove direction of motion, extract and add produced by wisdom glove displacement
Velocity amplitude, it is achieved acceleration is calibrated;
Step S24, obtain through calibration after acceleration information, use an integration mode get wisdom glove motion speed
Angle value;
Step S25, after integration obtains the velocity amplitude of wisdom glove motion, originates in resting state according to wisdom glove and terminates
In the motion feature of resting state, the speed of wisdom glove motion is calibrated;
Step S26, carries out an integration, thus obtains the displacement size of wisdom glove motion gained velocity amplitude;Step S27,
In conjunction with the above results, the track of body-building action is reconstructed, thus the movement locus of hand during obtaining user for body-building.
Described step S4 comprises the following steps:
Step S41A, the shift value obtained by integrating step S2, the reading of combination film pressure transducer, through the place of step S3
Reason, calculates glove motion work done, and the relational model consumed according to the merit set up and calorie calculates calorie consumption;
Step S42B, records caloric consumption, and carries out meals collocation and prompting balanced in nutrition;
Step S42A, pre-builds high dimensional feature model based on Statistical Learning Theory, and described high dimensional feature model is to set space
In the abnormal patterns of information change that causes due to every pose deviation action as training sample;
Step S41B, maps to abnormal patterns, in the high dimensional feature model of one-class support vector machine, isolate subject performance class,
And judge whether athletic posture deviates, if then sending alarm signal.
The present invention again provides a kind of system estimating calorie consumption and monitoring hand positions identification, have employed described
Estimation calorie consume and monitoring hand positions knows method for distinguishing, and include with lower module:
Signal acquisition and computing module, the signal in time collecting wisdom glove kinestate, and assess movement state information and add
With primary Calculation;
Abnormality detection module, for the exception whether changed by Outlier Detection Algorithm identification signal;
Action judge module, for one-class support vector machine subject performance class and other action classes made a distinction, to exceed
The abnormal patterns that strength building threshold value is caused is as subject performance class, and judges whether the exercise attitudes of wisdom glove occurs appearance
Gesture deviates;
And, alarm modules, for sending alarm signal when judging to occur pose deviation.
Described signal acquisition and computing module include with lower unit:
Inductive pick-up unit, is used for opening whole system and collecting exercise data, and the exercise data of collection includes strength building side
Exercise data in power upwards and three-dimensional coordinate all directions;
Data processing unit, for trying to achieve meansigma methods to the power on each direction and movable information, using this meansigma methods as fortune
Dynamic status information;
Smooth unit, carries out ETL analysis for the data obtained by data processing unit, and by moving average method to motion
Status information is smoothed.
Described abnormality detection module includes with lower unit:
Abnormal computing unit, obtains subsequence for the time series of movement state information is implemented data segmentation, calculates sub-sequence
The local anomaly data of row;
Abnormal output unit, for when described abnormal data is more than or equal to predetermined threshold value, using subsequence as abnormal mould
Formula exports.
Described action judge module includes with lower unit:
Set up model unit, for based on Statistical Learning Theory preset set up high dimensional feature model, described high dimensional feature model with
Set the abnormal patterns causing movement state information to change due to every human action in space as training sample;
Action recognition unit, for mapping to the higher-dimension of one-class support vector machine by the abnormal patterns that abnormal output unit is exported
In characteristic model, isolate subject performance class.
Also include feedback module, for feedback for the response message of hand positions alarm signal, adjust a class support to
The high dimensional feature model of amount machine.
Embodiment 1:
As it is shown in figure 1, this example provides a kind of wisdom glove measuring calorie consumption and monitoring hand positions identification, including: place
Reason device module, memory module, communication module, sensing module, early warning module, display module, power module, switch module and
Cloud Server, described memory module, communication module, sensing module, early warning module, display module, power module, switching molding
Block is connected with processor module respectively with Cloud Server, and wherein, described sensing module includes pressure transducer and IMU inertia list
The hand pressurized strength that unit, described pressure transducer and IMU inertance element are respectively used to during responsible sensing user for body-building is big
Little and IMU data, and then collect source data for user's strength building, and send described source data to processor module;Institute
State processor module and be responsible for the pretreatment to source beginning data;Described memory module be responsible for store processor pretreatment result and
The result passed back from Cloud Server;Described communication module is responsible for source data, pretreated data are reached Cloud Server,
Make further data for Cloud Server to process and analyze, and be responsible for the result of Cloud Server process is transmitted back to wisdom glove;
Described early warning module is then responsible for when user action is nonstandard, motion excess or stress not in the middle of any one situation time give
User sends warning;Described display module be responsible for user for body-building during type of action, consume calorie and posture standard
The result of degree shows.
Wisdom glove described in this example can be also simply referred to as glove;Be provided with on the sensing module of described wisdom glove one or
Plural pressure transducer, described pressure transducer is arranged at palm grip, and described IMU inertance element is arranged on wrist
Place, it is simple to client is easy to use;Described memory module includes built-in mass storage and external memory interface, it is simple to use
The storage of family exercise data and calling;Described source data is good for for being respectively induced user by pressure transducer and IMU inertance element
Hand pressurized strength size during body and the collection data corresponding to IMU data.
The use process of this example, all postures are done several times by the posture being first according to standard, and the posture of described standard is permissible
Aside instruct with reference to instructional video or coach, then extracted source data and each action of user by sensing module
Movement locus, and preserve as reference;Then, when user carries out body building, by user's body-building hand exercise now
Track contrasts with reference to track, such as contrasts by the way of similarity-rough set, when can judge user movement
Posture whether standard, and standard degree, described standard degree namely with the similarity degree of reference locus;When subscriber card road
In consume and hand positions and reach certain limit with reference to the difference between data, when namely having exceeded default threshold values, institute
State early warning module and send the alarms such as sound, light or vibrations;Described threshold values presets according to user's request, example
As, may be configured as 5.
Embodiment 2:
As shown in Figures 2 and 3, this example also provides for a kind of estimation calorie consumption and monitoring hand positions knows method for distinguishing, uses
Wisdom glove described in embodiment 1, and comprise the following steps:
Step S1, utilizes the diaphragm pressure sensor of pressure transducer and IMU inertance element to collect source number during strength building
According to;
Step S2, is transferred to processor module by source data and processes;
Data acquired in the pressure transducer received and IMU inertance element are carried out ETL process, carry out ETL and divide by step S3
Analysis, described ETL process be by ETL technology, the data obtained by step S2 are extracted, transposition, the mistake that loads and pay
Journey;
And, step S4, calculate the calorie of consumption, set up disaggregated model by support vector machine, will be beyond strength building
Source data as subject performance class, other as non-targeted action class;Then the threshold value of strength building is seen if fall out,
If then sending alerting signal, if otherwise transferring data to movable equipment to carry out record, and recommended dietary recipe, nutrition are taken
Join and training plan.
In described step S3, TL process refers to extract, Transform and load of data, i.e. data are extracted,
Data are carried out the important step of pretreatment by transposition, the process loading and paying before referring to data process;In step S4, root
According to the computation model arranged, human body mechanical power of externally output in motor process can be existed by a transforming factor and human body
The calorie consumed during this connects, and reading and reconstruct gained movement locus in conjunction with force cell calculate
Merit, thus calculate the calorie of consumption and one-class support vector machine subject performance class and other action classes made a distinction;
Beyond strength building as subject performance class, and the threshold value of strength building will be seen if fall out, the most then send prompting letter
Number;This step S4 transfers data to movable equipment, carries out record, it is recommended that meals recipe, nutrition arrangement and training plan,;
Described threshold values can carry out self-defined setting according to the demand of user, as use barbell time, by the size of the power pre-set,
Referred to as threshold value, if it exceeds this size pre-set, then sends signal.
In actual applications, receive pressure transducer by processor module and IMU inertance element measures required fortune
Dynamic data, set up out motor message and the relation of strength building action, it is only necessary to use simple sensor i.e. can pass through quilt
The caloric consumption of tester and the identification of hand positions, it is judged that whether detected person occurs the deviation of hand positions to go forward side by side
Row is reported to the police, and decreases the dependence that heaviness is measured equipment, will greatly improve the accuracy of hand positions identification;Specifically
In motion, calorie consumption amount can be gone out by movable equipment terminal demonstration and meals collocation is recommended.
In this example, the pressure transducer quantity of described wisdom glove is more than one or two, described processor die
The number of the central processing unit included by block is one, as shown in Figure 1, detected wisdom glove carries two class sensings
Device: pressure transducer and IMU inertance element, this two classes sensor will collect exercise data through complementary filter, Mean value of index
Being transferred in central processing unit with the process such as ETL, the method further according to the computation model arranged and machine learning carries out hand appearance
The identification of gesture.
This example in step sl, preferably opened by user by button or switch by whole system, and described button and switch can
To be the button and switch realized by touch inductor, described button and switch can be arranged on IMU inertance element adnexa,
So that user operation.
Step S2 described in this example utilizes the exception of the movable information acquired in Outlier Detection Algorithm identification to be different based on local
The time series Outlier Detection Algorithm of constant factor, comprises the following steps in step S2:
Step S21, gathers pressure data and athletic posture data, based on wearable by pressure transducer and IMU inertance element
The data of the acceleration transducer of acquisition, Magnetic Sensor and gyroscope are carried out slip mean filter by computing technique, to eliminate the back of the body
Scape noise, the sliding window width of described slip mean filter is 7;
Step S22, uses the mode of complementary filter to realize the standard of glove attitude the reading of acceleration transducer and gyroscope
Really estimating, this complementary filter is for combining acceleration transducer for the estimated value of glove attitude angle and gyroscope for glove
The estimated value of attitude angle;
Step S23, after using the mode of complementary filter to estimate glove attitude angle in motor process, according to mechanics principle
Eliminate gravity projection component in the wisdom glove direction of motion, extract and add produced by wisdom glove displacement
Velocity amplitude, it is achieved acceleration is calibrated;
Step S24, obtain through calibration after acceleration information, use an integration mode get wisdom glove motion speed
Angle value;
Step S25, after integration obtains the velocity amplitude of wisdom glove motion, originates in resting state according to wisdom glove and terminates
In the motion feature of resting state, the speed of wisdom glove motion is calibrated;
Step S26, carries out an integration, thus obtains the displacement size of wisdom glove motion gained velocity amplitude.
In step S22, realized the analyzing and processing of data by complementary filter, object attitude in space, can be by adding
Speed and angular velocity combine corresponding and then reach the purpose accurately estimated, therefore, described step S22 is combined by complementary filter
The estimated value of the glove attitude angle that the estimated value of the glove attitude angle that acceleration transducer is measured and gyroscope are measured, and then obtain
The accurate estimation of glove posture.In step S23, extract accekeration produced by wisdom glove displacement, the most just
Be intended to the component of acceleration filtering out wisdom glove on three directions of three-dimensional coordinate, this point can by complementary filter or
The modes such as Kalman Filtering realize.In step 24, for the speed drift after less integration, integration moves just for corresponding to glove
Time accekeration, to this end, Mean value of index (EMA) is adopted as judging the glove accekeration resting state corresponding to glove
Or kinestate;When in sliding window, Mean value of index is more than threshold value, the acceleration in this window is judged as corresponding to hands
The kinestate of set;Otherwise, then the resting state corresponding to glove it is judged as;After judge process completes, integration is only made
Accekeration under corresponding glove kinestate, thus obtain corresponding velocity amplitude, and corresponding under glove resting state
Accekeration be then considered null value;Described threshold value is in data processing, in conjunction with sensor, algorithm and user's request
Comprehensively determining, in the case of difference, this threshold value can be different.In described step S25, use the finger described in step S24
Number average (EMA) judges the kinestate of glove, when being judged to static, then forces to be set to 0 by corresponding velocity amplitude.
This example also includes the high dimensional feature adjusting one-class support vector machine for calorie consumption and hand positions identification
Model, described step S4 comprises the following steps:
Step S41A, the shift value obtained by integrating step S2, the reading of combination film pressure transducer, through the place of step S3
Reason, calculates glove motion work done, and the relational model consumed according to the merit set up and calorie calculates calorie consumption;
Step S42B, records caloric consumption, and carries out meals collocation and prompting balanced in nutrition;
Step S42A, pre-builds high dimensional feature model based on Statistical Learning Theory, and described high dimensional feature model is to set space
In the abnormal patterns of information change that causes due to every pose deviation action as training sample;
Step S41B, maps to abnormal patterns, in the high dimensional feature model of one-class support vector machine, isolate subject performance class,
And judge whether athletic posture deviates, if then sending alarm signal.
Described relational model is to pass through transforming factor and human body according to human body mechanical power of externally output in motor process
The calorie consumed in this course connects, and reading and reconstruct gained movement locus in conjunction with force cell calculate
Merit, thus calculate the calorie of consumption and then subject performance class and other action classes are made a distinction.
This example constructs model according to the relation between the acting of glove posture and calorie, thus carries out calculating point
Analysis, between merit and energy, available motion state represents, embodies the instantaneous of motion start time, motion finish time and motion
Speed;Because not every interior energy is used for doing work, can be due to heat consumption in a part, blood flows and is lost, human body
Interior can be according to certain rate conversion success.The metering that energy runs off calculates according to below equation: during human motion
Externally mechanical power=calorie the consumption of output consumes high calorie during transferring the efficiency * human motion of mechanical power to.
Relevant knowledge based on machine learning, constructs the relationship model between acting and calorie consumption.Wearable meter
Calculation is measured mechanical power, it is common that measure movement locus thus calculate human body work done.Further, movement locus is measured
It is to realize with some common sensor such as acceleration transducers and gravity sensor.
Embodiment 3:
As shown in Figure 4, this example also provides for a kind of system estimating calorie consumption and monitoring hand positions identification, have employed enforcement
Estimation calorie described in example 2 consumes and monitoring hand positions knows method for distinguishing, and includes with lower module:
Signal acquisition and computing module 41, signal during for collecting wisdom glove kinestate, and assess movement state information
Primary Calculation in addition;
Abnormality detection module 42, for the exception whether changed by Outlier Detection Algorithm identification signal;
Action judge module 43, for one-class support vector machine subject performance class and other action classes made a distinction, with super
Go out abnormal patterns that strength building threshold value caused as subject performance class, and judge whether the exercise attitudes of wisdom glove occurs
Posture deviates;
And, alarm modules 44, for sending alarm signal when judging to occur pose deviation.
Signal acquisition described in this example and computing module 41 include with lower unit:
Inductive pick-up unit 411, is used for opening whole system and collecting exercise data, and the exercise data of collection includes strength building
Power on direction and the exercise data in three-dimensional coordinate all directions;
Data processing unit 412, for the power on each direction and movable information are tried to achieve meansigma methods, using this meansigma methods as
Movement state information;
Smooth unit 413, carries out ETL analysis for the data obtained by data processing unit 412, and by moving average method
Movement state information is smoothed.
The three-dimensional coordinate of described inductive pick-up unit 411 is the x-axis of the kinestate determining object on solid space, y
Axle and z-axis.
Described in this example, abnormality detection module 42 includes with lower unit:
Abnormal computing unit 421, obtains subsequence for the time series of movement state information is implemented data segmentation, calculates son
The local anomaly data of sequence;
Abnormal output unit 422, for when described abnormal data is more than or equal to predetermined threshold value, using subsequence as exception
Pattern exports.
Preferably, this example utilizes time series Outlier Detection Algorithm, can limit by more accurately detecting standard, will mark
Accurate and abnormal time series corresponding to two kinds of postures is separated, and gets rid of the abnormal mould that these two kinds of common human actions cause
Formula.
Described abnormality detection module 42 uses multidimensional space data distinguished number based on support vector machine, and this is abnormal
Detection module 42 carries out abnormal posture Cleaning Principle: all postures are done several times by the posture being first according to standard, described standard
Posture be referred to instructional video or coach aside instructs, then extract the source data of user and each action
Movement locus, and preserve as reference;Then, when user carries out body building, by user's body-building hand exercise rail now
Mark contrasts with reference to track, such as contrasts by the way of similarity-rough set, when can judge user movement
Posture whether standard, and standard degree, described standard degree namely with the similarity degree of reference locus;The data obtained are
Produce over time, namely time series models, for ease of realizing data analysis and process, this example data to obtaining
Split, and subsequence refers to intercept one section is obtained by sensing module and through the data of ETL process, as subsequence
Length and data volume, can self-defined be arranged according to the disposal ability of system;Described local anomaly data refer in subsequence,
Calculating according to the method for support vector machine, part data are substantially and other data data devious of this subsequence;Described pre-
If threshold values is the threshold values pre-set, it is in data processing, carries out comprehensively in conjunction with sensor, algorithm and user's request
Determining, in the case of difference, this threshold value can be different.
Described in this example, action judge module 43 includes with lower unit:
Set up model unit 431, set up high dimensional feature model, described high dimensional feature model for presetting based on Statistical Learning Theory
To set the abnormal patterns causing movement state information to change due to every human action in space as training sample;
Action recognition unit 432, for mapping to one-class support vector machine by the abnormal patterns that abnormal output unit 422 is exported
High dimensional feature model in, isolate subject performance class.
This example further preferably includes feedback module 45, for feedback for the response message of hand positions alarm signal, adjusts
The high dimensional feature model of one-class support vector machine.
The data that this example obtains are as the time and produce, and namely time series models divide for ease of realizing data
Analysis and process, the data obtained are split by this example, and subsequence refers to intercept one section and obtained by sensing module and pass through
The data of ETL process, as length and the data volume of subsequence, can self-defined be arranged according to the disposal ability of system;Described
Local anomaly data refer in subsequence, calculate according to the method for support vector machine, and part data are obvious and this subsequence
Other data data devious;Described pre-set threshold value is the threshold values pre-set, and is in data processing, in conjunction with sensing
Device, algorithm and user's request comprehensively determine, in the case of difference, this threshold value can be different.
After completing abnormality detection module 42, componental movement action is by because causing the significant change quilt of movement state information
Detect and export the abnormal patterns of correspondence.Then, these abnormal patterns will be entered motion analysis, thus judge abnormal patterns
It is belonging to which kind of action.In order to distinguish abnormal operation from these patterns, this example employs to be extracted from abnormal patterns
The multi-class support vector machine (multi-class Support Vector Machine, multi-class SVM) of feature;
Multiclass SVM is the algorithm of support vector machine of a kind of extension, and in multiclass SVM, all of sample is divided into target class and other classes;For
The problem understanding linear classification by no means, is mapped to a dimensional images by input sample.In this example, the exception of non-standard posture
Pattern is considered subject performance class, and the abnormal patterns of other actions is regarded as other action classes.The exception of nonstandard action
Pattern has been mapped to a dimensional images the most in advance.By utilizing multiclass SVM to judge, can from previous step output different
Norm formula isolates abnormal operation, depends on by the abnormal patterns exported and selected model, thus determine what there occurs
Plant action.
This example further preferably includes the high dimensional feature model for adjusting and improving one-class support vector machine, it is provided that can optimize inspection
Survey and the system feedback of decision making algorithm.If alarm is closed the most in time, other equipment that system then can be associated by signal
Send help information to other people, such as send instant messages or note etc. by third-party application and seek help.
Above content is being expanded on further of combining that the present invention does by specific implementation, and should not assert that the present invention's is concrete
Realization is confined to described above.For those skilled in the art, without departing from the inventive concept of the premise,
Some simple deduction or replace can also be made, be regarded as protection domain that the claim that the present invention submitted to determines it
In.
Claims (10)
1. the wisdom glove measuring calorie consumption and monitoring hand positions identification, it is characterised in that including: processor die
Block, memory module, communication module, sensing module, early warning module, display module, power module, switch module and cloud service
Device, described memory module, communication module, sensing module, early warning module, display module, power module, switch module and cloud
Server is connected with processor module respectively, and wherein, described sensing module includes pressure transducer and IMU inertance element, institute
State pressure transducer and IMU inertance element be respectively used to be responsible for the hand pressurized strength size during sensing user for body-building and
IMU data, and then collect source data for user's strength building, and send described source data to processor module;Described place
Reason device module is responsible for the pretreatment to source beginning data;Described memory module is responsible for storing the result of processor pretreatment and from cloud
The result that server is passed back;Described communication module is responsible for source data, pretreated data are reached Cloud Server, for cloud
Server is made further data and is processed and analyze, and is responsible for the result of Cloud Server process is transmitted back to wisdom glove;Described
Early warning module is then responsible for during body-building abnormal conditions sending warning to user;Described display module is responsible for user for body-building process
In type of action, the result that consumes calorie and posture standard degree shows.
2. an estimation calorie consumption and monitoring hand positions know method for distinguishing, it is characterised in that have employed claim 1 institute
That states measures calorie consumption and the wisdom glove of monitoring hand positions identification, and comprises the following steps: step S1, utilizes pressure
The diaphragm pressure sensor of force transducer and IMU inertance element collect source data during strength building;Step S2, by source data
It is transferred to processor module process;Step S3, by the number acquired in the pressure transducer received and IMU inertance element
According to carrying out ETL process, carrying out ETL analysis, described ETL process is to be taken out the data obtained by step S2 by ETL technology
Take, transposition, the process that loads and pay;And, step S4, calculate the calorie of consumption, set up by support vector machine and divide
Class model, using the source data beyond strength building as subject performance class, other as non-targeted action class;Then judgement is
The no threshold value beyond strength building, if then sending alerting signal, if otherwise transferring data to mobile device to carry out record, and
Recommended dietary recipe, nutrition arrangement and training plan.
Estimation calorie consumption the most according to claim 2 and monitoring hand positions know method for distinguishing, it is characterised in that
In step S1, whole system is opened by user by button or switch, and the sensing module of wisdom glove is provided with one or two
Individual above pressure transducer.
Estimation calorie consumption the most according to claim 2 and monitoring hand positions know method for distinguishing, it is characterised in that
Step S2 comprises the following steps:
Step S21, gathers pressure data and athletic posture data by pressure transducer and IMU inertance element, by adding of obtaining
The data of velocity sensor, Magnetic Sensor and gyroscope carry out slip mean filter, to eliminate background noise, and described slip average
The sliding window width of wave filter is adjusted according to user's practical situation;
Step S22, uses the mode of complementary filter to realize the standard of glove attitude the reading of acceleration transducer and gyroscope
Really estimating, this complementary filter is for combining acceleration transducer for the estimated value of glove attitude angle and gyroscope for glove
The estimated value of attitude angle;
Step S23, after using the mode of complementary filter to estimate glove attitude angle in motor process, according to mechanics principle
Eliminate gravity projection component in the wisdom glove direction of motion, extract and add produced by wisdom glove displacement
Velocity amplitude, it is achieved acceleration is calibrated;
Step S24, obtain through calibration after acceleration information, use an integration mode get wisdom glove motion speed
Angle value;
Step S25, after integration obtains the velocity amplitude of wisdom glove motion, originates in resting state according to body-building action and terminates
In the motion feature of resting state, the speed of wisdom glove motion is calibrated;
Step S26, carries out an integration, thus obtains the displacement size of wisdom glove motion gained velocity amplitude;
Step S27, in conjunction with the above results, is reconstructed the track of body-building action, thus hand during obtaining user for body-building
Movement locus.
Estimation calorie consumption the most according to claim 2 and monitoring hand positions know method for distinguishing, it is characterised in that institute
State step S4 to comprise the following steps:
Step S41A, the shift value obtained by integrating step S2, the reading of combination film pressure transducer, through the place of step S3
Reason, calculates glove motion work done, and the relational model consumed according to the merit set up and calorie calculates calorie consumption;
Step S42B, records caloric consumption, and carries out meals collocation and prompting balanced in nutrition;
Step S42A, pre-builds high dimensional feature model based on Statistical Learning Theory, and described high dimensional feature model is to set space
In the abnormal patterns of information change that causes due to every pose deviation action as training sample;
Step S41B, maps to abnormal patterns, in the high dimensional feature model of one-class support vector machine, isolate subject performance class,
And judge whether athletic posture deviates, if then sending alarm signal.
6. one kind estimate calorie consumption and monitoring hand positions identification system, it is characterised in that have employed claim 2 to
Calorie consumption and hand positions described in 5 any one know method for distinguishing, and include with lower module:
Signal acquisition and computing module, the signal in time collecting wisdom glove kinestate, and assess movement state information and add
With primary Calculation;
Abnormality detection module, for the exception whether changed by Outlier Detection Algorithm identification signal;
Action judge module, for one-class support vector machine subject performance class and other action classes made a distinction, to exceed
The abnormal patterns that strength building threshold value is caused is as subject performance class, and judges whether the exercise attitudes of wisdom glove occurs appearance
Gesture deviates;
And, alarm modules, for sending alarm signal when judging to occur pose deviation.
Estimation calorie consumption the most according to claim 6 and the system of monitoring hand positions identification, it is characterised in that institute
State signal acquisition and include with lower unit with computing module:
Inductive pick-up unit, is used for opening whole system and collecting exercise data, and the exercise data of collection includes strength building side
Exercise data in power upwards and three-dimensional coordinate all directions;
Data processing unit, for trying to achieve meansigma methods to the power on each direction and movable information, using this meansigma methods as fortune
Dynamic status information;
Smooth unit, carries out ETL analysis for the data obtained by data processing unit, and by moving average method to motion
Status information is smoothed.
Estimation calorie consumption the most according to claim 6 and the system of monitoring hand positions identification, it is characterised in that institute
State abnormality detection module and include with lower unit:
Abnormal computing unit, obtains subsequence for the time series of movement state information is implemented data segmentation, calculates sub-sequence
The local anomaly data of row;
Abnormal output unit, for when described abnormal data is more than or equal to predetermined threshold value, using subsequence as abnormal mould
Formula exports.
Estimation calorie consumption the most according to claim 8 and the system of monitoring hand positions identification, it is characterised in that institute
State action judge module and include with lower unit:
Set up model unit, for based on Statistical Learning Theory preset set up high dimensional feature model, described high dimensional feature model with
Set the abnormal patterns causing movement state information to change due to every human action in space as training sample;
Action recognition unit, for mapping to the higher-dimension of one-class support vector machine by the abnormal patterns that abnormal output unit is exported
In characteristic model, isolate subject performance class.
Estimation calorie consumption the most according to claim 6 and the system of monitoring hand positions identification, it is characterised in that
Also include feedback module, for feedback for the response message of hand positions alarm signal, adjust multi-category support vector machines
High dimensional feature model.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610155558.6A CN105833508A (en) | 2016-03-18 | 2016-03-18 | Intelligent gloves capable of measuring calorie consumption and monitoring hand posture identification as well as estimation method and system |
PCT/CN2016/080734 WO2017156834A1 (en) | 2016-03-18 | 2016-04-29 | Intelligent gloves for measuring calorie consumption and monitoring hand gesture recognition, and estimation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610155558.6A CN105833508A (en) | 2016-03-18 | 2016-03-18 | Intelligent gloves capable of measuring calorie consumption and monitoring hand posture identification as well as estimation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105833508A true CN105833508A (en) | 2016-08-10 |
Family
ID=56587457
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610155558.6A Pending CN105833508A (en) | 2016-03-18 | 2016-03-18 | Intelligent gloves capable of measuring calorie consumption and monitoring hand posture identification as well as estimation method and system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105833508A (en) |
WO (1) | WO2017156834A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107875621A (en) * | 2017-11-28 | 2018-04-06 | 杨佰振 | A kind of automatic intelligent digital moving body building management system |
WO2018094978A1 (en) * | 2016-11-23 | 2018-05-31 | 深圳大学 | Limb movement state determination method and device |
CN108270658A (en) * | 2017-01-02 | 2018-07-10 | 郑洪� | Information-pushing method, pusher and supplying system |
CN109011508A (en) * | 2018-07-30 | 2018-12-18 | 三星电子(中国)研发中心 | A kind of intelligent coach system and method |
CN109646902A (en) * | 2017-10-10 | 2019-04-19 | 齐新旺 | A kind of body building metering method based on identification equipment |
CN109830278A (en) * | 2019-01-15 | 2019-05-31 | 深圳和而泰智能控制股份有限公司 | Anaerobic exercise body-building recommended method, device, anaerobic exercise equipment and storage medium |
CN110660411A (en) * | 2019-09-17 | 2020-01-07 | 北京声智科技有限公司 | Body-building safety prompting method, device, equipment and medium based on voice recognition |
CN113952700A (en) * | 2021-11-22 | 2022-01-21 | 深圳市天鹏宇科技有限公司 | Intelligent fitness interaction system and intelligent fitness remote guidance system |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647942B (en) * | 2018-07-27 | 2024-03-15 | 重庆爱鸽者智能科技有限公司 | Distributed racing pigeon cutting system based on universal mobile terminal |
CN111696646A (en) * | 2019-03-13 | 2020-09-22 | 青岛海尔电冰箱有限公司 | Method and device for recommending menu for refrigerator |
CN112762895B (en) * | 2020-10-30 | 2022-07-15 | 四川写正智能科技有限公司 | Method for judging read-write posture based on sensor |
CN112580587A (en) * | 2020-12-29 | 2021-03-30 | 西安精密机械研究所 | Bone joint damage information evaluation system and evaluation method based on vibration noise signals |
CN114886387B (en) * | 2022-07-11 | 2023-02-14 | 深圳市奋达智能技术有限公司 | Method and system for calculating walking and running movement calorie based on pressure sensation and storage medium |
CN115487477A (en) * | 2022-08-11 | 2022-12-20 | 安徽中飞星梦体育文化发展有限公司 | Creeping tunnel and system suitable for different crowds |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020194668A1 (en) * | 2001-05-24 | 2002-12-26 | Seung-Woo Kwon | Functional golf gloves |
CN102698425A (en) * | 2012-05-28 | 2012-10-03 | 吴江科沃客机械设备有限公司 | Sporting glove |
CN202751769U (en) * | 2012-05-31 | 2013-02-27 | 靖守禹 | Multifunctional boxing glove |
CN104888444A (en) * | 2015-05-20 | 2015-09-09 | 深圳大学 | Intelligent gloves, method and system for calorie consumption and hand posture recognition |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9192335B2 (en) * | 2013-04-12 | 2015-11-24 | Michael Linderman | Athletic glove providing feedback regarding grip to a wearer |
-
2016
- 2016-03-18 CN CN201610155558.6A patent/CN105833508A/en active Pending
- 2016-04-29 WO PCT/CN2016/080734 patent/WO2017156834A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020194668A1 (en) * | 2001-05-24 | 2002-12-26 | Seung-Woo Kwon | Functional golf gloves |
CN102698425A (en) * | 2012-05-28 | 2012-10-03 | 吴江科沃客机械设备有限公司 | Sporting glove |
CN202751769U (en) * | 2012-05-31 | 2013-02-27 | 靖守禹 | Multifunctional boxing glove |
CN104888444A (en) * | 2015-05-20 | 2015-09-09 | 深圳大学 | Intelligent gloves, method and system for calorie consumption and hand posture recognition |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018094978A1 (en) * | 2016-11-23 | 2018-05-31 | 深圳大学 | Limb movement state determination method and device |
US11134893B2 (en) | 2016-11-23 | 2021-10-05 | Shenzhen University | Limb movement gesture judgment method and device |
CN108270658A (en) * | 2017-01-02 | 2018-07-10 | 郑洪� | Information-pushing method, pusher and supplying system |
CN108270658B (en) * | 2017-01-02 | 2021-04-06 | 郑洪� | Information pushing method, pushing device and pushing system |
CN109646902A (en) * | 2017-10-10 | 2019-04-19 | 齐新旺 | A kind of body building metering method based on identification equipment |
CN107875621A (en) * | 2017-11-28 | 2018-04-06 | 杨佰振 | A kind of automatic intelligent digital moving body building management system |
CN107875621B (en) * | 2017-11-28 | 2019-08-27 | 杨佰振 | A kind of automatic intelligent digital moving body building management system |
CN109011508A (en) * | 2018-07-30 | 2018-12-18 | 三星电子(中国)研发中心 | A kind of intelligent coach system and method |
CN109830278A (en) * | 2019-01-15 | 2019-05-31 | 深圳和而泰智能控制股份有限公司 | Anaerobic exercise body-building recommended method, device, anaerobic exercise equipment and storage medium |
CN110660411A (en) * | 2019-09-17 | 2020-01-07 | 北京声智科技有限公司 | Body-building safety prompting method, device, equipment and medium based on voice recognition |
CN110660411B (en) * | 2019-09-17 | 2021-11-02 | 北京声智科技有限公司 | Body-building safety prompting method, device, equipment and medium based on voice recognition |
CN113952700A (en) * | 2021-11-22 | 2022-01-21 | 深圳市天鹏宇科技有限公司 | Intelligent fitness interaction system and intelligent fitness remote guidance system |
Also Published As
Publication number | Publication date |
---|---|
WO2017156834A1 (en) | 2017-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105833508A (en) | Intelligent gloves capable of measuring calorie consumption and monitoring hand posture identification as well as estimation method and system | |
CN104888444B (en) | Wisdom gloves, the method and system of a kind of calorie of consumption and hand positions identification | |
CN105797350A (en) | Intelligent method and system for body building posture recognition, evaluation, early-warning and intensity estimation | |
Johnston et al. | Smartwatch-based biometric gait recognition | |
CN104135911B (en) | Activity classification in multi-axial cord movement monitoring device | |
US9700241B2 (en) | Gait analysis system and method | |
CN103954295B (en) | A kind of step-recording method based on acceleration transducer | |
EP3058442A1 (en) | Calculating pace and energy expenditure from athletic movement attributes | |
CN103699795A (en) | Exercise behavior identification method and device and exercise intensity monitoring system | |
WO2016180653A1 (en) | Pedometer and method for analyzing motion data | |
CN107966161A (en) | Walking detection method based on FFT | |
CN105224104A (en) | Pedestrian movement's state identification method of mode is held based on smart mobile phone | |
CN106405384A (en) | Simulation circuit health state evaluation method | |
CN109078318A (en) | Full crowd's outdoor body-building equipment intelligent terminal system based on big data | |
CN108827290A (en) | A kind of human motion state inverting device and method | |
US20110288784A1 (en) | Monitoring Energy Expended by an Individual | |
Wenyuan et al. | From Lens to Prism: Device-free modeling and recognition of multi-part activities | |
Luqian et al. | Human activity recognition using time series pattern recognition model-based on tsfresh features | |
Mo et al. | Multi-sensor ensemble classifier for activity recognition | |
Liu et al. | A lightweight double-channel depthwise separable convolutional neural network for multimodal fusion gait recognition | |
CN105105757B (en) | A kind of wearable human motion posture track record and assessment device | |
CN109646902A (en) | A kind of body building metering method based on identification equipment | |
CN114341947A (en) | System and method for exercise type recognition using wearable devices | |
CN107692984A (en) | A kind of fatigue detection method and device | |
Pramanick et al. | Defatigue: Online non-intrusive fatigue detection by a robot co-worker |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160810 |
|
RJ01 | Rejection of invention patent application after publication |