CN115251902B - Training action recognition method, device, equipment and medium - Google Patents
Training action recognition method, device, equipment and medium Download PDFInfo
- Publication number
- CN115251902B CN115251902B CN202210784162.3A CN202210784162A CN115251902B CN 115251902 B CN115251902 B CN 115251902B CN 202210784162 A CN202210784162 A CN 202210784162A CN 115251902 B CN115251902 B CN 115251902B
- Authority
- CN
- China
- Prior art keywords
- action
- change
- rate
- training
- signal
- 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.)
- Active
Links
- 230000009471 action Effects 0.000 title claims abstract description 455
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000008859 change Effects 0.000 claims abstract description 347
- 210000003205 muscle Anatomy 0.000 claims abstract description 13
- 210000003414 extremity Anatomy 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 210000002310 elbow joint Anatomy 0.000 claims description 4
- 210000000629 knee joint Anatomy 0.000 claims description 4
- 210000003857 wrist joint Anatomy 0.000 claims description 4
- 210000004247 hand Anatomy 0.000 claims description 2
- 230000008569 process Effects 0.000 description 14
- 238000005452 bending Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 210000001513 elbow Anatomy 0.000 description 3
- 210000003127 knee Anatomy 0.000 description 3
- 210000000707 wrist Anatomy 0.000 description 3
- 208000012661 Dyskinesia Diseases 0.000 description 2
- 208000006011 Stroke Diseases 0.000 description 2
- 230000001939 inductive effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 208000016285 Movement disease Diseases 0.000 description 1
- 208000029549 Muscle injury Diseases 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 230000004064 dysfunction Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000003183 myoelectrical effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb using a particular sensing technique
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6804—Garments; Clothes
- A61B5/6806—Gloves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H1/00—Apparatus for passive exercising; Vibrating apparatus; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
- A61H1/02—Stretching or bending or torsioning apparatus for exercising
- A61H1/0237—Stretching or bending or torsioning apparatus for exercising for the lower limbs
- A61H1/024—Knee
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H1/00—Apparatus for passive exercising; Vibrating apparatus; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
- A61H1/02—Stretching or bending or torsioning apparatus for exercising
- A61H1/0274—Stretching or bending or torsioning apparatus for exercising for the upper limbs
- A61H1/0277—Elbow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H1/00—Apparatus for passive exercising; Vibrating apparatus; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
- A61H1/02—Stretching or bending or torsioning apparatus for exercising
- A61H1/0274—Stretching or bending or torsioning apparatus for exercising for the upper limbs
- A61H1/0285—Hand
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2505/00—Evaluating, monitoring or diagnosing in the context of a particular type of medical care
- A61B2505/09—Rehabilitation or training
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
- A61B2560/04—Constructional details of apparatus
- A61B2560/0462—Apparatus with built-in sensors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/12—Driving means
- A61H2201/1253—Driving means driven by a human being, e.g. hand driven
- A61H2201/1261—Driving means driven by a human being, e.g. hand driven combined with active exercising of the patient
- A61H2201/1269—Passive exercise driven by movement of healthy limbs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/16—Physical interface with patient
- A61H2201/1602—Physical interface with patient kind of interface, e.g. head rest, knee support or lumbar support
- A61H2201/1635—Hand or arm, e.g. handle
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5007—Control means thereof computer controlled
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Epidemiology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Physical Education & Sports Medicine (AREA)
- Pain & Pain Management (AREA)
- Rehabilitation Therapy (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Geometry (AREA)
- Rehabilitation Tools (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the invention relates to the technical field of limb joint rehabilitation treatment, and discloses a training action recognition method, device, equipment and medium. The method comprises the steps of controlling muscles of a target training part to train according to guiding actions, and obtaining training action identification data in real time, wherein the training action identification data comprise a plurality of training action identification semaphores, obtaining the change rate of the training action identification semaphores according to the plurality of training action identification semaphores, and identifying training actions according to the change rate of the training action identification semaphores. According to the embodiment of the invention, the training actions are identified through the change rate of the action identification semaphore, the tedious operation of calibrating the voltage value of the guiding actions is avoided, and the operation burden of patients and medical staff can be greatly reduced.
Description
Technical Field
The invention relates to the technical field of limb joint rehabilitation, in particular to a training action recognition method, device, equipment and medium.
Background
According to the research of related documents, the number of cerebral apoplexy patients in China is up to 7000 ten thousand at present, and more than 200 ten thousand are newly increased each year. More than 50% of stroke patients may have different degrees of limb dysfunction, such as hand dyskinesia.
The clinical rehabilitation of the hand dyskinesia can be realized by a hand functional rehabilitation training instrument. The hand function rehabilitation training device comprises a rehabilitation training host, training gloves and sensor gloves. Mirror image training is a rehabilitation training method adopted by a hand function rehabilitation training instrument, namely, the bending and stretching actions of the healthy side hand (serving as a guiding hand) wearing the sensor glove are identified, and then the training instrument controls the active side hand wearing the training glove to perform active and passive training according to the guiding actions of the guiding hand. In the mirror image training method, the identification of the action of the leading hand is the key to the success of the method.
At present, a training instrument on the market is used for identifying the motion of a guide hand, the motion data of the guide hand is acquired through a flexible resistance sensor arranged on the guide glove, the guide glove bends and stretches along with the guide hand when the guide hand bends and stretches, the absolute value of voltage output by the flexible resistance sensor can represent the bending and stretching degree, so that the voltage value of the middle process of the complete opening and closing of the hand and the opening to the closing of the hand can be acquired, and then the hand motion identification of the guide hand is realized according to the acquired voltage value. At present, when the motion of the leading hand is identified, voltage values are required to be calibrated one by one according to different bending and stretching degrees in the motion process of the hand at each time, and then the training motion of the training hand is identified according to the calibrated voltage values, so that the operation and the use are troublesome, and great inconvenience is brought to doctors and patients.
Disclosure of Invention
The embodiment of the invention aims to provide a training action recognition method, device, equipment and medium, which are used for recognizing training actions through the change rate of action recognition signal quantity, and discarding the tedious operation of calibrating the voltage value of the guiding action, so that the operation burden of patients and medical staff can be greatly reduced.
In order to solve the above technical problems, in a first aspect, an embodiment of the present invention provides a training motion recognition method, which is applied to rehabilitation training of a limb joint muscle, including:
the muscle of the target training part is controlled to train according to the guiding action, and training action recognition data are obtained in real time, wherein the training action recognition data comprise a plurality of training action recognition semaphores;
obtaining the change rate of the training motion recognition signal according to the plurality of training motion recognition signal;
And identifying the training action according to the change rate of the training action identification signal quantity and the relation between the change rate of the action identification signal quantity and the action.
The training motion recognition method for recognizing the training motion based on the rate of change of the training motion recognition signal and the relationship between the rate of change of the motion recognition signal and the motion includes:
If the change rates of the training motion recognition semaphores are all larger than 0 in the first preset duration, the change rates of the training motion recognition semaphores are all in a first reference value interval, and the number of the change rates of the training motion recognition semaphores is larger than or equal to a first threshold value, determining that the training motion is a buckling motion.
In addition, the method for recognizing the training action according to the change rate of the training action recognition signal quantity and the relation between the change rate of the action recognition signal quantity and the action further comprises the following steps:
And if the change rates of the training motion recognition semaphores are smaller than 0 in the second preset time period, absolute values of the change rates of the training motion recognition semaphores are in a second reference value interval, and the number of the change rates of the training motion recognition semaphores is larger than a second threshold value, determining that the training motion is an extension motion.
In addition, the method for recognizing the training action according to the change rate of the training action recognition signal quantity and the relation between the change rate of the action recognition signal quantity and the action further comprises the following steps:
And determining the completion degree of the training action according to the change rate of the training action recognition signal quantity and the calibration change rate determined based on the guiding action signal quantity.
In addition, the determining the completion of the training motion according to the change rate of the training motion recognition signal amount and the calibration change rate determined based on the guiding motion signal amount includes:
calculating the ratio of the change rate of each training action recognition signal quantity to the calibration change rate;
And determining the completion degree of the training action according to the ratio.
In addition, the method further comprises:
the calibration change rate is obtained by adopting the following modes:
The method comprises the steps of collecting guide action identification data, wherein the guide action identification data comprises identification data of a plurality of guide actions, and the identification data of each guide action comprises at least one signal quantity of the guide action;
Obtaining the change rate of the signal quantity of each guiding action according to at least one signal quantity of each guiding action;
Obtaining the calibration change rate according to the change rate of the signal quantity of the multiple guiding actions;
Optionally, the calibration rate of change is an average of rates of change of the signal quantity of the plurality of guiding actions.
In addition, the first reference value interval and the second reference value interval are updated by adopting a preset strategy;
The method further includes updating the rate of change boundary values for the first reference value interval and the second reference value interval as follows:
Recording the maximum value and the minimum value of the change rate of the signal quantity of each buckling action in the buckling action and the maximum value and the minimum value of the change rate of the signal quantity of each stretching action in the stretching action;
If the maximum value of the change rate of the signal quantity of each buckling action in the buckling actions counted for K times is smaller than the maximum value of the change rate of the first reference value interval in the previous time, or the minimum value of the change rate of the signal quantity of each buckling action in the buckling actions counted for K times is larger than the minimum value of the change rate of the first reference value interval in the previous time, taking the average value of the maximum value of the change rate of the signal quantity of the buckling action counted for K times as the maximum value of the change rate of the first reference value interval after updating, and taking the average value of the minimum value of the change rate of the signal quantity of the buckling action counted for K times as the minimum value of the change rate of the first reference value interval after updating;
If the maximum value of the change rate of the signal quantity of each stretching action in the stretching actions counted for K times is smaller than the maximum value of the change rate of the second reference value interval before, or the minimum value of the change rate of the signal quantity of each stretching action in the stretching actions counted for K times is larger than the minimum value of the change rate of the first reference value interval before, taking the average value of the maximum value of the change rate of the signal quantity of the stretching action counted for K times as the maximum value of the change rate of the second reference value interval after updating, and taking the average value of the minimum value of the change rate of the signal quantity of the stretching action counted for K times as the minimum value of the change rate of the second reference value interval after updating;
optionally, the method further comprises:
the method comprises the steps of collecting guide action identification data, wherein the guide action identification data comprises identification data of a plurality of guide actions, and the identification data of each guide action comprises a plurality of signal quantities of buckling actions and a plurality of signal quantities of stretching actions;
obtaining the maximum value and the minimum value of the change rate of the signal quantity of each buckling action according to a plurality of signal quantities of the buckling action, and obtaining the maximum value and the minimum value of the change rate of a first initial reference value interval of the first reference value interval according to the maximum value and the minimum value of the change rate of the signal quantity of the plurality of buckling actions;
Obtaining maximum and minimum values of the change rate of the signal quantity of each stretching action according to the plurality of signal quantities of the stretching action, and obtaining maximum and minimum values of the change rate of a second initial reference value interval of the second reference value interval according to the maximum and minimum values of the change rate of the signal quantity of the plurality of stretching actions;
optionally, the target training site includes a hand, a wrist, an elbow, or a knee;
optionally, the motion recognition signal quantity is a voltage signal capable of varying with the flexion and extension of the target training site.
In a second aspect, an embodiment of the present invention provides a training motion recognition device applied to rehabilitation training of a limb joint and a muscle, including:
The system comprises a signal acquisition module, a training action recognition module and a training action recognition module, wherein the signal acquisition module is used for controlling muscles of a target training part to train according to guiding actions and acquiring training action recognition data in real time;
The change rate calculation module is used for obtaining the change rate of the training action recognition semaphore according to the plurality of training action recognition semaphores;
and the recognition module is used for recognizing the training action according to the change rate of the training action recognition signal quantity and a preset judgment strategy.
In a third aspect, the embodiment of the invention also provides training action recognition equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor runs the computer program to realize the training action recognition method.
In a fourth aspect, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a training action recognition method according to any embodiment of the present invention.
Compared with the prior art, the technical scheme provided by the embodiment of the invention has at least the following positive effects:
according to the embodiment of the invention, the training action recognition data is obtained in real time, the training action recognition data comprises a plurality of training action recognition semaphores, the change rate of the training action recognition semaphores is obtained according to the plurality of training action recognition semaphores, and then the training actions are recognized according to the change rate of the training action recognition semaphores, so that the problem of complicated semaphore calibration when the actions are recognized directly according to the training action recognition semaphores is solved, and the operation burden of patients and medical staff is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being understood that the drawings in the following description are only embodiments of the present invention and that other drawings may be obtained according to the drawings provided without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a training action recognition method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a training motion recognition device according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a training motion recognition device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described by means of implementation examples with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The inventor finds that the current hand function rehabilitation training instrument is required to calibrate voltage values one by one for different bending and stretching degrees of hand actions when performing mirror image rehabilitation training, then identifies training actions of the training hand according to the calibrated voltage values, and one-by-one calibration voltage value operation is complex, so that great inconvenience is brought to doctors and patients. Therefore, the inventor proposes to perform motion recognition according to the relationship between the change rate and the motion by calculating motion recognition data, such as the change rates of a plurality of voltage values, and abandons a mode of performing motion recognition directly through calibrating the voltage values, so that the burden of patients and medical staff can be greatly reduced.
The training action recognition method provided by the embodiment of the invention is suitable for limb joint muscle rehabilitation training, and is particularly suitable for a mirror image training method. The limb joints include, but are not limited to, limb joint parts where movement disorder exists due to muscle injury, such as hands, wrists, elbows or knees. The method is applicable to related training devices including, but not limited to, hand function myoelectric stimulation rehabilitation training devices. Referring to fig. 1, the training action recognition method of the present embodiment includes the following steps:
And 101, controlling muscles of a target training part to train according to the guiding action, and acquiring training action identification data in real time.
In the mirror image training method, the guiding motion may be a training guiding motion performed by a healthy side hand of the patient, but not limited thereto, and the guiding motion may be obtained by other means. The method for controlling the target training site to perform mirror image training according to the guiding action is known to those skilled in the art, and will not be described herein.
The target training part can be a limb joint needing training such as a hand, an elbow joint, a wrist joint or a knee joint. This embodiment takes hand training as an example.
In order to monitor the training motion of the hand, training motion recognition data during the hand motion needs to be acquired. The training motion recognition data includes a plurality of training motion recognition semaphores. The training motion recognition signal may be a voltage signal that is capable of varying with flexion and extension of the target training site.
Specifically, the sensor glove can be used for collecting training motion identification data of the hand, for example, a voltage value which changes along with the training motion of the hand can be obtained through a flexible resistance sensor in the sensor glove. Preferably, the inductive sensor glove provided by the applicant in the patent with the application number 2021114250623 named glove for hand rehabilitation training and coil inductor for hand rehabilitation training can be used for collecting training action identification data, and different voltage values generated along with the training action can be collected. The inductive sensor glove has the advantages of high response speed of output signals, low cost, easiness in installation and the like.
Step 102, obtaining the change rate of the training motion recognition signal quantity according to the plurality of training motion recognition signal quantities.
The training motion recognition signal quantity takes the voltage value collected by the glove as an example, the voltage is continuously increased in the process of fully opening the hand to fully making a fist, otherwise, the voltage is gradually reduced in the process of fully making the fist to fully opening the hand, the curve shape of the voltage value of the complete fist making motion and the opening motion, which changes along with time, is similar to smooth sawtooth waves, the waveform shape can change along with the different motion speeds, the waveform is steep when the motion speed is high, and the waveform is gentle when the motion speed is low. If motion is paused during flexion and extension, the waveform remains constant.
The calculation mode of the change rate of the training action recognition signal quantity is to calculate the ratio of the difference between the signal quantity acquired at the later time and the signal quantity acquired at the previous time to the time between the front time and the back time.
Specifically, the voltage of the sensing signal output by the glove sensor is recorded as u, the voltage value acquired at any time i-1, i, i+1 is recorded as u i-1、ui、ui+1, wherein the value of i is 1 to N, the change rate (i.e. slope) at the time i is recorded as k i,Wherein the method comprises the steps ofIs the sampling time interval.
In step 102, the change rate of the training motion recognition signal amount may be calculated in real time according to the training motion recognition signal amount obtained in real time.
And 103, identifying the training action according to the change rate of the training action identification signal quantity and the relation between the change rate of the action identification signal quantity and the action.
The training motion recognition signal is based on the voltage value collected by the glove as an example to describe the relationship between the change rate of the motion recognition signal and the motion. In the process from full fist opening to full fist opening, the voltage is continuously increased, the change rate of the motion recognition signal quantity of the hand motion is always more than 0, and in the process, the voltage is gradually reduced, and in the process, the change rate of the motion recognition signal quantity of the hand motion is always less than 0. When the change rate is changed from more than 0 to less than 0, the fist-making action is ended to switch to the opening action, whereas when the change rate is changed from less than 0 to more than 0, the fist-making action is switched to the opening action. The rate of change may fluctuate over a range of intervals during the fist making and opening actions. When the sign of the change rate changes, the number of the change rate in a certain period TS can be counted, so that the number of the change rate larger than 0 in the action process of making a fist and the number of the change rate smaller than 0 in the opening process can be counted. Therefore, the hand motion can be recognized as the bending and stretching motion and the opening motion by the number of the change rate which is larger or smaller than 0 and the change rate and whether the change rate is in a certain range of the value interval, and the completion degree of the hand motion, such as the completion degree of fist making or the completion degree of opening, can be further recognized.
Specifically, the training actions are identified based on the change rate of the training action identification semaphore and the relation between the change rate of the action identification semaphore and the actions, wherein the change rate of the training action identification semaphore is larger than 0 in a first preset time period, the change rate of the training action identification semaphore is in a first reference value interval, the number of the change rates of the training action identification semaphore is larger than or equal to a first threshold value, and the training actions are determined to be buckling actions.
The first preset duration may be a duration of the guiding action to complete the buckling action. The first reference value interval may be determined from a rate of change of the motion recognition signal amount when the guiding motion completes the buckling motion. The numerical range of the first reference value interval may specifically be determined according to a numerical range of a rate of change of the motion recognition signal amount when the guiding motion completes the buckling motion. Similarly, the first threshold may be determined based on the number of change rates of the motion recognition signal amounts when the guide motion completes the buckling motion, that is, when the sampling frequencies of the motion recognition signal amounts of the training motion and the guide motion are identical, the motion recognition may be performed in accordance with the principle that the number of change rates of the two are identical.
The training actions may be identified based on the rate of change of the training action recognition semaphore and the relationship between the rate of change of the action recognition semaphore and the action, and may further include determining that the training actions are extension actions if the rate of change of the training action recognition semaphore is less than 0 in a second preset time period, absolute values of the rate of change of the training action recognition semaphore are within a second reference value interval, and the number of rates of change of the training action recognition semaphore is greater than a second threshold. The determining manners of the second preset time length, the second reference value interval and the second threshold value are similar to those of the first preset time length, the first reference value interval and the second threshold value, and accordingly the determining is performed according to the opening action of the guiding hand, and the details are omitted here.
Specifically, after detecting that the sign of the change rate of the training motion recognition semaphore changes, for example, the change rate changes from less than 0 to more than 0, the number of the change rates of the training motion recognition semaphore in a certain time period TS (first preset duration) is calculated, meanwhile, the magnitude of the change rate value is judged, and if the number of the change rate value is greater than or less than a first threshold value n_kt and the change rate value is in a first reference value interval, the hand is considered to execute the fist holding motion. When the opening hand is executed, the judging method is similar, and the details are not repeated here.
Identifying the training action based on the rate of change of the training action recognition semaphore and the relationship between the rate of change of the action recognition semaphore and the action may further include determining a completion of the training action based on the rate of change of the training action recognition semaphore and a calibrated rate of change determined based on the pilot action semaphore.
The determination of the completion of the training actions from the rate of change of the training action recognition semaphore and the calibrated rate of change determined based on the pilot action semaphore may include calculating a ratio of the rate of change of each training action recognition semaphore to the calibrated rate of change, and determining the completion of the training actions from the ratio.
The judgment of the completion degree of the training motion is to judge whether the amplitude, speed and the like of the fist making or opening motion of the training hand are consistent with the amplitude, speed and the like of the guiding hand. Of course, the degree of completion of the motion may be the consistency between the motion range of the training hand and the motion range of the guiding hand.
The method further comprises the steps of acquiring guide action identification data, wherein the guide action identification data comprise identification data of a plurality of guide actions, the identification data of each guide action comprise at least one signal quantity of the guide action, obtaining the change rate of the signal quantity of each guide action according to the at least one signal quantity of each guide action, and obtaining the calibration change rate according to the change rate of the signal quantity of the plurality of guide actions. Optionally, the calibration rate of change is an average of rates of change of the signal quantity of the plurality of pilot actions.
The calibration rate of change is illustrated as follows:
a. Performing calibration, performing the motion from full open to full fist making by the healthy side hand of the patient, recording the change rate of the signal quantity during the motion, and recording as a maximum value k max_l, wherein the calculation formula is Wherein the value of l is 0 to M-1;k max_l, which is the change rate of the signal quantity of one complete fist making action.
B. repeatedly executing the step a and the step M for a plurality of times, and sequentially marking the change rate of each time as k max_0、kmax_1、…、kmax_(M-1);
c. The nominal rate of change is equal to the average of the rates of change k max_l, k max_mean＝(kmax_0+kmax_1+…+kmax_(M-1))/M, where M is any positive integer.
After the calibration change rate is obtained, the action completion degree p is obtained in the training process by adopting the following modes:
p= |100×k i/kmax_mean |, where p is the action completion degree parameter.
Further, the first reference value interval and the second reference value interval may be updated by a preset policy. The range of the bending and stretching angle of the hand-operated training device is correspondingly reduced along with the increase of the fatigue degree of the hand during the training process, so that the boundary value of the reference value interval, namely the maximum value and the minimum value of the value interval, can be dynamically adjusted during the training process.
Wherein the method may further comprise updating the change rate boundary values of the first reference value interval and the second reference value interval in the following manner:
The maximum and minimum values of the rate of change of the signal quantity for each of the buckling movements and the maximum and minimum values of the rate of change of the signal quantity for each of the stretching movements are recorded.
If the maximum value of the change rate of the signal quantity of each buckling action in the continuously counted K buckling actions is smaller than the maximum value of the change rate of the previous first reference value interval, or the minimum value of the change rate of the signal quantity of each buckling action in the continuously counted K buckling actions is larger than the minimum value of the change rate of the previous first reference value interval, taking the average value of the maximum value of the change rate of the signal quantity of the buckling action counted K times as the maximum value of the change rate of the updated first reference value interval and taking the average value of the minimum value of the change rate of the signal quantity of the buckling action counted K times as the minimum value of the change rate of the updated first reference value interval.
If the maximum value of the change rate of the signal quantity of each stretching action in the continuous K times of counted stretching actions is smaller than the maximum value of the change rate of the signal quantity of the previous second reference value interval, or the minimum value of the change rate of the signal quantity of each stretching action in the continuous K times of counted stretching actions is larger than the minimum value of the change rate of the previous first reference value interval, taking the average value of the maximum value of the change rate of the signal quantity of the stretching action counted for K times as the maximum value of the change rate of the updated second reference value interval and taking the average value of the minimum value of the change rate of the signal quantity of the stretching action counted for K times as the minimum value of the change rate of the updated second reference value interval. K is a natural number greater than 1.
The method can further comprise the steps of collecting guide action identification data, wherein the guide action identification data comprise identification data of multiple guide actions, the identification data of each guide action comprise a plurality of signals of a buckling action and a plurality of signals of an extending action, obtaining the maximum value and the minimum value of the change rate of the signals of each buckling action according to the plurality of signals of the buckling action, obtaining the maximum value and the minimum value of the change rate of the first initial reference value interval of the first reference value interval according to the maximum value and the minimum value of the change rate of the signals of the plurality of buckling actions, obtaining the maximum value and the minimum value of the change rate of the signals of each extending action according to the plurality of signals of the extending action, and obtaining the maximum value and the minimum value of the change rate of the second initial reference value interval of the second reference value interval according to the maximum value and the minimum value of the change rate of the signals of the extending action.
In the training process, the recognition of the fist making and opening actions is repeated continuously.
Compared with the prior art, the embodiment of the invention recognizes the training actions through the change rate of the action recognition signal quantity, and the complicated operation of calibrating the voltage value of the guiding action is abandoned, so that the operation burden of patients and medical staff can be greatly reduced.
The embodiment of the invention provides a training action recognition device which is applied to limb joint muscle rehabilitation training and can be configured in training action recognition equipment. As shown in fig. 2, the device comprises a signal acquisition module 301, a change rate calculation module 302 and an identification module 303.
The signal acquisition module 301 is configured to control muscles of a target training site to train according to a guiding motion, and acquire training motion recognition data in real time, where the training motion recognition data includes a plurality of training motion recognition semaphores.
The change rate calculation module 302 is configured to obtain a change rate of the training motion recognition semaphore according to the plurality of training motion recognition semaphores;
The recognition module 303 is configured to recognize the training action according to the rate of change of the training action recognition signal and a preset judgment policy.
Optionally, the identifying module 303 is specifically configured to determine that the training action is a buckling action if the change rates of the training action identifying semaphores are all greater than 0 within a first preset duration, the change rates of the training action identifying semaphores are all within a first reference value interval, and the number of the change rates of the training action identifying semaphores is greater than or equal to a first threshold.
The identifying module 303 is further configured to determine that the training motion is the stretching motion if the change rates of the training motion identification semaphores are all less than 0 within a second preset duration, absolute values of the change rates of the training motion identification semaphores are all within a second reference value interval, and the number of the change rates of the training motion identification semaphores is greater than a second threshold.
The recognition module 303 is further configured to determine the degree of completion of the training action based on the rate of change of the training action recognition semaphore and the calibrated rate of change determined based on the pilot action semaphore.
The recognition module 303 is specifically configured to calculate a ratio of a change rate of the recognition signal amount of each training motion to the calibration change rate, and determine the completion degree of the training motion according to the ratio.
Optionally, the device further comprises a change rate calibration module, wherein the calibration change rate is obtained by collecting guide action identification data, the guide action identification data comprise identification data of a plurality of guide actions, the identification data of each guide action comprise at least one signal quantity of the guide action, the change rate of the signal quantity of each guide action is obtained according to the at least one signal quantity of each guide action, and the calibration change rate is obtained according to the change rate of the signal quantity of the plurality of guide actions.
Optionally, the calibration rate of change is an average of rates of change of the signal quantity of the plurality of guiding actions.
Optionally, the apparatus may further include a reference value interval updating module, configured to update the first reference value interval and the second reference value interval with a preset policy.
The reference value interval updating module is specifically configured to update the change rate boundary values of the first reference value interval and the second reference value interval by recording a maximum value and a minimum value of a change rate of a signal quantity of each buckling action in the buckling action and a maximum value and a minimum value of a change rate of a signal quantity of each extending action in the extending action; if the maximum value of the change rate of the signal quantity of each buckling action in the buckling actions counted for K times is smaller than the maximum value of the change rate of the interval of the first reference value, or the minimum value of the change rate of the signal quantity of each buckling action in the buckling actions counted for K times is larger than the minimum value of the change rate of the interval of the first reference value, taking the average value of the maximum value of the change rate of the signal quantity of the buckling actions counted for K times as the maximum value of the change rate of the interval of the first reference value after updating, and taking the average value of the minimum value of the change rate of the signal quantity of the buckling actions counted for K times as the minimum value of the change rate of the interval of the first reference value after updating, if the maximum value of the change rate of the signal quantity of each stretching action in the extending actions counted for K times is smaller than the maximum value of the interval of the second reference value before extending action, or the average value of the change rate of the signal quantity of each extending action counted for K times is smaller than the maximum value of the interval of the first reference value after updating, and taking an average value of the minimum values of the signal quantity change rates of the K times of statistics of the stretching actions as the minimum value of the change rate of the updated second reference value interval, wherein K is a natural number larger than 1.
The device can further comprise an initial reference value interval acquisition module, wherein the initial reference value interval acquisition module is used for acquiring guide action identification data, the guide action identification data comprise identification data of multiple guide actions, the identification data of each guide action comprise a plurality of signal quantities of a buckling action and a plurality of signal quantities of an extending action, the maximum value and the minimum value of the change rate of the signal quantity of each buckling action are obtained according to the plurality of signal quantities of the buckling action, the maximum value and the minimum value of the change rate of the first initial reference value interval of the first reference value interval are obtained according to the maximum value and the minimum value of the change rate of the signal quantity of the multiple buckling action, the maximum value and the minimum value of the change rate of the signal quantity of each extending action are obtained according to the plurality of signal quantities of the extending action, and the maximum value and the minimum value of the change rate of the second initial reference value interval of the second reference value interval are obtained according to the maximum value and the minimum value of the change rate of the signal quantity of the plurality of extending actions.
Optionally, the target training site includes a hand, a wrist, an elbow, or a knee.
Optionally, the motion recognition signal quantity is a voltage signal capable of varying with the flexion and extension of the target training site.
Compared with the prior art, the device provided by the embodiment of the invention can identify the training action through the change rate of the action identification signal quantity, abandon the complicated operation of calibrating the voltage value of the guiding action, and can greatly reduce the operation burden of patients and medical staff.
Fig. 3 is a schematic structural diagram of training motion recognition equipment according to a third embodiment of the present invention. The training action recognition device 30 comprises a memory 31, a process 32 and a computer program stored on the memory 31 and executable on the processor 32, wherein the processor 32 implements the technical solution as described in the previous method when executing the program.
Compared with the prior art, the device provided by the embodiment of the invention can identify the training action through the change rate of the action identification signal quantity, abandon the complicated operation of calibrating the voltage value of the guiding action, and can greatly reduce the operation burden of patients and medical staff.
A fourth embodiment of the present invention provides a computer-readable storage medium having stored thereon a computer program for performing the technical solutions of any of the method embodiments when executed by a computer processor.
From the above description of embodiments, it will be clear to a person skilled in the art that the present invention may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk, or an optical disk of a computer, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a grid device, etc.) to execute the method according to the embodiments of the present invention.
It should be noted that, in the embodiment of the training action recognition device, each unit and module included are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented, and the specific names of the functional units are only for convenience of distinguishing each other, and are not used for limiting the protection scope of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (24)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210784162.3A CN115251902B (en) | 2022-07-05 | 2022-07-05 | Training action recognition method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210784162.3A CN115251902B (en) | 2022-07-05 | 2022-07-05 | Training action recognition method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115251902A CN115251902A (en) | 2022-11-01 |
| CN115251902B true CN115251902B (en) | 2025-02-28 |
Family
ID=83763154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210784162.3A Active CN115251902B (en) | 2022-07-05 | 2022-07-05 | Training action recognition method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115251902B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111984119A (en) * | 2020-08-18 | 2020-11-24 | 哈尔滨工业大学（深圳） | Gesture recognition model establishing method, gesture recognition method and device and data glove |
| CN114099239A (en) * | 2021-11-26 | 2022-03-01 | 上海格润科技有限公司 | Hand function rehabilitation training method and device, rehabilitation training instrument and medium |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4732990B2 (en) * | 2006-09-19 | 2011-07-27 | 日本電信電話株式会社 | Impedance detection device, impedance detection method, biometric recognition device, and fingerprint authentication device |
| CA2795767C (en) * | 2010-04-08 | 2018-08-21 | Topera, Inc. | Methods, system and apparatus for the detection, diagnosis and treatment of biological rhythm disorders |
| US11309081B2 (en) * | 2010-10-13 | 2022-04-19 | Gholam A. Peyman | Telemedicine system with dynamic imaging |
| JP5892506B2 (en) * | 2011-07-04 | 2016-03-23 | 国立大学法人岩手大学 | Healthy side information feedback type walking assist device |
| KR102170321B1 (en) * | 2013-06-17 | 2020-10-26 | 삼성전자주식회사 | System, method and device to recognize motion using gripped object |
| CN104107134B (en) * | 2013-12-10 | 2017-08-01 | 中山大学 | Method and system for upper limb training based on electromyographic feedback |
| US9880632B2 (en) * | 2014-06-19 | 2018-01-30 | Thalmic Labs Inc. | Systems, devices, and methods for gesture identification |
| CN113144535B (en) * | 2021-04-30 | 2023-06-23 | 扬州大学 | A hand rehabilitation training system capable of remote monitoring |
| CN113425291A (en) * | 2021-06-24 | 2021-09-24 | 东北大学秦皇岛分校 | Ring formula collection system based on MEMS sensor |
| CN113963385B (en) * | 2021-09-30 | 2023-09-19 | 天津极豪科技有限公司 | Fingerprint image acquisition method and device and electronic equipment |
| CN114053097A (en) * | 2021-11-26 | 2022-02-18 | 上海格润科技有限公司 | Gloves for hand rehabilitation training and coil inductors for hand rehabilitation training |
-
2022
- 2022-07-05 CN CN202210784162.3A patent/CN115251902B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111984119A (en) * | 2020-08-18 | 2020-11-24 | 哈尔滨工业大学（深圳） | Gesture recognition model establishing method, gesture recognition method and device and data glove |
| CN114099239A (en) * | 2021-11-26 | 2022-03-01 | 上海格润科技有限公司 | Hand function rehabilitation training method and device, rehabilitation training instrument and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115251902A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104107134B (en) | Method and system for upper limb training based on electromyographic feedback | |
| Kanitz et al. | Classification of transient myoelectric signals for the control of multi-grasp hand prostheses | |
| US6413190B1 (en) | Rehabilitation apparatus and method | |
| US20200323460A1 (en) | System And Method For Post-Stroke Rehabilitation And Recovery Using Adaptive Surface Electromyographic Sensing And Visualization | |
| CN203564250U (en) | Data gloves for function rehabilitation training and assessment of hands and monitoring method thereof | |
| CN106422203B (en) | A kind of rehabilitation training of upper limbs method of the multi-modal feedback of photoelectricity based on mirror image therapy | |
| JP2001286451A (en) | Method of calculating standard value of normalization of electromuscular signal, method of calculating standard value of intrinsic force, method of calculating contraction degree, method of calculating intrinsic force, and device for the calculations | |
| CN106714685B (en) | System for rehabilitation using haptic devices and brain-computer interface | |
| CN111436942A (en) | Auxiliary rehabilitation device, system and method for hand surgery rehabilitation training | |
| JP5234542B2 (en) | Musculoskeletal model creation apparatus and method, musculoskeletal system control apparatus, and musculoskeletal system | |
| CN117472183A (en) | Personalized dynamic rehabilitation man-machine interaction method and related equipment | |
| CN108229283B (en) | Electromyographic signal acquisition method and device | |
| CN111367399B (en) | Surface electromyographic signal gesture recognition method | |
| CN115251902B (en) | Training action recognition method, device, equipment and medium | |
| JP2019084130A (en) | Walking motion evaluation device, walking motion evaluation method and program | |
| CN114669025B (en) | Application method of coronary heart disease PCI postoperative finger trainer | |
| WO2013164364A1 (en) | Training apparatus | |
| WO2021241676A1 (en) | Movement analysis device, system, storage medium, and rehabilitation system | |
| JP6870733B2 (en) | Information processing equipment, information processing systems, and information processing methods | |
| Bhardwaj et al. | Electromyography in physical rehabilitation: a review | |
| KR101797287B1 (en) | Method and apparatus for assessments of upper-limb functionality for neurological patients using multiple sensors | |
| CN114099239A (en) | Hand function rehabilitation training method and device, rehabilitation training instrument and medium | |
| JP6661123B2 (en) | Attitude transmission control device, attitude transmission device, attitude transmission method, and program | |
| Arjunan et al. | Recognition of finger/hand grip mechanism by computing s-transform features of surface electromyogram signal from healthy and amputee | |
| Rulaningtyas et al. | Elbow angle estimation from emg signals based on monte carlo simulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |