WO2021042971A1

WO2021042971A1 - Surface electromyogram signal processing method and apparatus, and wearable device

Info

Publication number: WO2021042971A1
Application number: PCT/CN2020/109486
Authority: WO
Inventors: 田彦秀; 韩久琦; 牛天增
Original assignee: 北京海益同展信息科技有限公司
Priority date: 2019-09-03
Filing date: 2020-08-17
Publication date: 2021-03-11
Also published as: CN110420025B; CN110420025A

Abstract

A surface electromyogram signal processing method and apparatus, and a wearable device, which relate to the technical field of intelligent wearable devices. The surface electromyogram signal processing method comprises: acquiring a surface electromyogram signal (101); importing the surface electromyogram signal into a kernel function for equidistant integration so as to obtain a determination signal (102); and when the determination signal is greater than a predetermined threshold value, determining that the surface electromyogram signal corresponding to the determination signal is in an action stage. By means of the described method, a surface electromyogram signal may first be processed on the basis of a kernel function, a determination signal may be obtained after equidistant integration, and it may be determined according to the determination signal whether the surface electromyogram signal is in an action stage or not, thereby reducing the dependence of the detection of an action stage on the setting of a threshold value, and improving the accuracy of the detection of an action stage.

Description

Surface electromyography signal processing method, device and wearable device

Cross-references to related applications

This application is based on the application with the CN application number 201910825053.X and the filing date of September 3, 2019, and claims its priority. The disclosure of the CN application is hereby incorporated into this application as a whole.

Technical field

The present disclosure relates to the technical field of smart wearable devices, in particular to a surface EMG signal processing method, device and wearable device.

Background technique

The surface EMG signal is generally divided into resting potential segment and action potential segment. Action segment detection refers to determining the starting and ending positions of action potentials. Effectively distinguishing resting potentials and action potentials is one of the important steps in gesture recognition of EMG signals.

Summary of the invention

According to an aspect of some embodiments of the present disclosure, a surface EMG signal processing method is provided, which includes: obtaining a surface EMG signal; importing the surface EMG signal into a kernel function for isometric integration processing to obtain a determination signal, wherein, The kernel function includes the surface EMG signal before the current surface EMG signal in chronological order; when the determination signal is greater than a predetermined threshold, it is determined that the surface EMG signal corresponding to the determination signal is in the action segment.

In some embodiments, the isometric integration processing is performed according to the surface EMG signal imported into the kernel function, and obtaining the determination signal includes: importing a single surface EMG signal into the kernel function to update the kernel function; calculating the unit of the kernel function based on the trapezoidal method, etc. Distance integration, determine the judgment signal.

In some embodiments, importing the surface EMG signal into the kernel function to perform equidistant integration processing, and obtaining the determination signal further includes: initializing the kernel function to 0; according to the order of acquisition time from first to last, the surface EMG signal is concentrated The surface EMG signals are imported into the kernel function one by one. After each surface EMG signal is imported, the kernel function is updated, and isometric integration is performed to obtain the judgment signal corresponding to the current surface EMG signal; complete the import of each surface EMG signal in the surface signal concentration Then, the determination signal set corresponding to the surface signal set is obtained.

In some embodiments, obtaining the surface EMG signal includes: collecting initial surface EMG signal data; correcting the initial surface signal data based on a baseline threshold to obtain the surface EMG signal.

In some embodiments, correcting the initial surface signal data based on the predetermined baseline threshold includes: when the initial surface EMG signal is less than the baseline threshold, the surface EMG signal is 0; when the initial surface EMG signal is greater than or equal to the baseline threshold , The surface EMG signal is the collected initial surface signal data.

In some embodiments, the surface EMG signal processing method further includes: according to the formula:

thr=mean{MAV ₁ ,MAV ₂ ,MAV ₃ ,…,MAV _k }+A

Determine the baseline threshold thr, where MAV _i is the maximum value of the signal in the sliding window in the resting state data of the initial surface EMG signal data, i is a positive integer between 1 and k, k is the number of sliding windows, and A is The predetermined constant.

In some embodiments, determining that the surface EMG signal corresponding to the determination signal is in the action segment includes: when the previous one or more determination signals are less than or equal to a predetermined threshold, if the determination signal is switched to be greater than the predetermined threshold, then the current determination signal corresponds to The surface EMG signal of the action segment is the signal at the start point of the action segment; when the previous one or more determination signals are greater than the predetermined threshold, if the determination signal is switched to be less than the predetermined threshold, the surface EMG signal corresponding to the current determination signal is the end of the action segment Point signal.

According to an aspect of some embodiments of the present disclosure, a surface EMG signal processing device is provided, including: a signal acquisition unit configured to acquire a surface EMG signal; and a determination signal acquisition unit configured to import the surface EMG signal The kernel function performs equidistant integration processing to obtain the determination signal, where the kernel function includes the surface EMG signal before the current surface EMG signal in chronological order; the action segment determination unit is configured to determine when the signal is greater than a predetermined threshold In this case, it is determined that the surface EMG signal corresponding to the determination signal is in the action segment.

In some embodiments, the determination signal acquisition unit is configured to: import a single surface EMG signal into the kernel function, update the kernel function; calculate the unit isometric integral of the kernel function based on the trapezoid method, and determine the determination signal.

In some embodiments, the determination signal acquisition unit is further configured to: initialize the kernel function to 0; according to the order of acquisition time from first to last, import the concentrated surface EMG signals into the kernel function one by one. After a surface EMG signal is updated, the kernel function is updated and equidistant integration is performed to obtain the determination signal corresponding to the current surface EMG signal; after completing the import of each surface EMG signal in the surface signal set, the determination signal set corresponding to the surface signal set is obtained.

In some embodiments, the signal acquisition unit is configured to: collect initial surface EMG signal data; correct the initial surface signal data based on a baseline threshold to acquire the surface EMG signal.

In some embodiments, the signal acquisition unit is configured to: when the initial surface EMG signal is less than the baseline threshold, the surface EMG signal is 0; when the initial surface EMG signal is greater than or equal to the baseline threshold, the surface EMG signal is greater than or equal to the baseline threshold. The signal is the collected initial surface signal data.

In some embodiments, the signal acquisition unit is further configured to follow the formula:

thr=mean{MAV ₁ ,MAV ₂ ,MAV ₃ ,…,MAV _k }+A

In some embodiments, the action segment determination unit is configured to: in the case where the previous one or more determination signals are less than or equal to the predetermined threshold, if the determination signal is switched to be greater than the predetermined threshold, the surface EMG signal corresponding to the current determination signal is The signal of the starting point of the action segment; in the case that the previous one or more determination signals are greater than the predetermined threshold, if the determination signal is switched to be less than the predetermined threshold, the surface EMG signal corresponding to the current determination signal is the end point signal of the action segment.

According to an aspect of some embodiments of the present disclosure, a surface EMG signal processing device is provided, including: a memory; and a processor coupled to the memory, and the processor is configured to execute any one of the above based on instructions stored in the memory. A surface EMG signal processing method.

According to an aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the instructions are executed by a processor, the steps of any of the above surface EMG signal processing methods are realized.

In addition, according to an aspect of some embodiments of the present disclosure, a wearable device is provided, which includes: an electromyography signal acquisition device configured to collect surface electromyography signals; and any of the above surface electromyography signal processing devices.

In some embodiments, the electromyographic signal acquisition device includes a detector attached to the surface of the user's body to be detected.

Description of the drawings

The drawings described here are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The exemplary embodiments and descriptions of the present disclosure are used to explain the present disclosure, and do not constitute an improper limitation of the present disclosure. In the attached picture:

FIG. 1 is a flowchart of some embodiments of the surface EMG signal processing method of the present disclosure.

FIG. 2 is a flowchart of other embodiments of the surface EMG signal processing method of the present disclosure.

3A to 3C are schematic diagrams of some embodiments of surface EMG signal processing of the present disclosure.

FIG. 4 is a schematic diagram of some embodiments of the surface EMG signal processing device of the present disclosure.

FIG. 5 is a schematic diagram of other embodiments of the surface EMG signal processing device of the present disclosure.

FIG. 6 is a schematic diagram of still other embodiments of the surface EMG signal processing device of the present disclosure.

FIG. 7 is a schematic diagram of some embodiments of the wearable device of the present disclosure.

detailed description

There are several methods for detecting motion segments in related technologies:

(1) Moving average method: First find the average value of the surface EMG signal, then find the norm of the average value, and use the window function to perform moving average processing on the instantaneous energy of the surface EMG signal, and the obtained value and the appropriate threshold are judged , It is considered that the signal greater than the threshold is the action potential segment, and the signal less than the threshold is the resting potential segment.

(2) Standard deviation and absolute mean detection: use the standard deviation and absolute mean of the surface EMG signal to establish a single or double threshold for judgment.

(3) Wavelet transform method: use continuous wavelet transform decomposition to calculate the maximum value of a set of matched filter outputs at different scales, compare this value with a threshold, and determine the start and end positions of the action segment.

(4) Statistical criterion decision-making method: It is a model-based detection method of the active segment. The start of the active segment is used as a sudden change in the time-varying parameters of the statistical process model to adapt to the measured signal. The accuracy can be assessed by statistical models.

The inventor found that the motion segment detection in the related technology has the following problems:

1. The moving average method has a large amount of calculation, and the use of sliding window plus the running time of the algorithm itself will cause delay; the dependence on the threshold is relatively strong, if the amount of noise in the surface EMG signal is large, accurate detection cannot be achieved well The purpose of this, and the threshold universality caused by individual differences is not high.

2. Although the standard deviation and absolute mean detection is relatively simple, the detection accuracy is not high. When the amount of data in the sliding window is small, the abnormal value has a great influence on the detection accuracy of the active segment. When the data in the sliding window is large, it will cause delay and be more sensitive to noise.

3. The wavelet transform method is a time-frequency analysis method with a large amount of calculation. The decomposition of different scales depends on the choice of the mother wavelet function, which requires prior knowledge for verification.

4. The statistical criterion decision-making method needs to continuously obtain prior knowledge such as the current EMG signal level to establish a pre-model, and the amount of calculation is large.

The flowchart of some embodiments of the surface EMG signal processing method of the present disclosure is shown in FIG. 1.

In step 101, a surface EMG signal is acquired. In some embodiments, the surface EMG signal may be collected by an EMG signal collecting device attached to the surface of the user's body. In some embodiments, the directly collected signal can be used as the initial surface EMG signal data, and the surface EMG signal is obtained after correction processing.

In step 102, the surface EMG signal is introduced into the kernel function for isometric integration processing to obtain a determination signal. In some embodiments, the kernel function may be a data set including the preamble signal of the current surface EMG signal, the initial state of the kernel function is 0, and the data therein is gradually enriched during the signal processing. In some embodiments, each surface EMG signal corresponds to a decision signal.

In step 103, it is determined whether the determination signal is greater than a predetermined threshold. If it is determined that the signal is greater than the predetermined threshold, step 104 is executed; otherwise, it is determined that the surface EMG signal corresponding to the signal is in a resting state.

In step 104, it is determined that the surface EMG signal corresponding to the determination signal is in the action segment.

Through this method, the surface EMG signal can be processed based on the kernel function first, and then the judgment signal can be obtained after equidistant integration. According to the judgment signal, it can be determined whether it is in the action section, thereby reducing the threshold setting of the action section detection. Dependence improves the accuracy of motion segment detection.

The flowchart of other embodiments of the surface EMG signal processing method of the present disclosure is shown in FIG. 2.

In step 201, the initial surface EMG signal data is collected by a detector attached to the surface of the user to be detected. In some embodiments, the initial surface EMG signal data may be as shown in FIG. 3A, where the higher amplitude is the action segment, and the stable part between the active segments is the resting segment.

In step 202, a baseline threshold is determined according to the resting surface EMG signal data. In some embodiments, the detected user may be asked to be in a resting state and collect data, the data being confirmed resting state surface EMG signal data. In some embodiments, the baseline threshold thr can be determined according to a formula,

thr=mean{MAV ₁ ,MAV ₂ ,MAV ₃ ,…,MAV _k }+A

Among them, mean is the operator for averaging operation, MAV _i is the maximum value of the signal in the sliding window in the resting state data of the initial surface EMG signal data, i is a positive integer between 1 and k, and k is the number of sliding windows. Number, A is a predetermined constant. In some embodiments, a predetermined constant A may be set based on experience, and A may be adjusted during the measurement process to improve accuracy.

In step 203, the initial surface signal data is corrected based on the baseline threshold, and the surface EMG signal is obtained. In some embodiments, it can be set that when the initial surface EMG signal is less than the baseline threshold, the surface EMG signal is 0; when the initial surface EMG signal is greater than or equal to the baseline threshold, the surface EMG signal is collected Initial surface signal data. Such as based on formula

Correct the initial surface EMG signal data to obtain the surface EMG signal, where x _i is the collected initial surface EMG signal data, and thr is the baseline threshold of the initial EMG signal data.

In step 204, the surface EMG signal is imported into the kernel function, and the kernel function is updated. In some embodiments, the kernel function is a collection of data points and a data set including imported surface EMG signals.

In some embodiments, before the arrival of the first surface EMG signal, the initial kernel function is 0, and the form of the initial kernel function is kernel(j _k )=0, j ₁ , j ₂ , j ₃ ,..., j _n , Where 0, j ₁ ～j _n represent the data points in the kernel function; after the surface EMG signal s _{i is transferred} into the kernel function (assuming that no other surface EMG signal data has been imported before _{s i is imported), the kernel function is updated} Is kernel={j ₂ ,…,j _n ,s _i },j ₂ ,…,j _n ; after the next surface EMG signal s _i+1 in accordance with the time sequence is passed into the kernel function, the kernel function is updated to kernel ={j ₃ ,...,j _n ,s _i ,s _i+1 },j ₃ ,j ₄ ,...,j _n .

In step 205, the unit equidistant integral of the kernel function is calculated based on the trapezoidal method, and the determination signal is determined. In some embodiments, the kernel function is regarded as a one-dimensional time series, and isometric integral calculation is performed. For example, the surface EMG s _i after the introduction of a kernel function, the computing trapezoidal method based on the kernel function equally integral unit, to obtain a corresponding determination signal s _i Y _i; in accordance with the next timing of surface EMG signals s _i after passing ₊₁ kernel function, the integral is calculated to obtain a determination signal s _{i +} y _{i + ₁ 1} corresponds. In some embodiments, the determination signal determined for a series of surface EMG signals may be as shown in FIG. 3B.

In step 206, it is determined whether one or more signals before the current determination signal are less than or equal to a predetermined threshold. If it is less than or equal to the predetermined threshold, it means that it was in the resting state before, and step 207 is executed; otherwise, it means that it was in the active state before and step 210 is executed.

In step 207, it is determined whether the current determination signal is less than or equal to a predetermined threshold. If it is less than or equal to the predetermined threshold, go to step 208; otherwise, go to step 209.

In step 208, the currently detected user remains at rest. In the case where the currently processed determination signal also includes subsequent signals, step 213 is executed.

In step 209, the surface EMG signal corresponding to the current determination signal is the start point signal of the action segment, and the currently detected user switches from the resting state to the active state. In the case where the currently processed determination signal also includes subsequent signals, step 213 is executed.

In step 210, it is determined whether the current determination signal is less than a predetermined threshold. If it is less than the predetermined threshold, step 211 is executed, otherwise, step 212 is executed.

In step 211, the surface EMG signal corresponding to the current determination signal is the end point signal of the action segment, and the currently detected user is switched from the active state to the resting state. In the case where the currently processed determination signal also includes subsequent signals, step 213 is executed.

In step 212, the currently detected user remains at rest. In the case where the currently processed determination signal also includes subsequent signals, step 213 is executed.

Fig. 3C shows the relationship between the action segment and the resting segment distinguished based on the judgment signal below and the initial surface EMG signal corresponding to the upper side. It can be seen from the comparison in Figure 3C that the initial surface EMG signal data has a small amplitude when it just enters the action segment or just leaves the action segment, and it is difficult to distinguish from the resting segment data, and it is easy to misjudge, and its accuracy depends heavily on于 Threshold. The determination signal corresponding to the initial surface EMG signal has a large amplitude change when it just enters the action segment or just leaves the action segment, thereby improving the accuracy of the judgment.

In step 213, the buffered next surface EMG signal is obtained in the order of acquisition time from first to last, and step 204 is executed. In some embodiments, after collecting a piece of initial surface EMG signal data, centralized processing can be performed to obtain the corresponding surface EMG signal set, and the concentrated surface EMG signals of the surface EMG signal can be imported into the kernel function one by one; the surface is completed After each surface EMG signal in the signal set is imported, the determination signal set corresponding to the surface signal set is obtained.

In some embodiments, when the signal acquisition and analysis processing are executed simultaneously, after completing the operations of

steps

208, 209, 211, or 212, skip to step 201 to obtain the next initial surface EMG signal collected. .

Through this method, it is possible to perform baseline correction first, and then use the kernel function concept to obtain the judgment signal, which is equivalent to a secondary conversion of the original signal, which increases the small difference between the resting potential and the action potential, and improves the follow-up The accuracy of detection, and the algorithm adopts the concept of kernel function to reduce the time delay caused by the sliding window in identifying the starting point.

A schematic diagram of some embodiments of the surface EMG signal processing device of the present disclosure is shown in FIG. 4.

The signal acquisition unit 401 can acquire surface EMG signals. In some embodiments, the surface EMG signal may be collected by an EMG signal collecting device attached to the surface of the user's body. In some embodiments, the directly collected signal can be used as the initial surface EMG signal, and the surface EMG signal is obtained after the correction processing.

The determination signal acquisition unit 402 can import the surface EMG signal into the kernel function for equidistant integration processing to obtain the determination signal. In some embodiments, the kernel function may be a data set including the preamble signal of the current surface EMG signal, the initial state of the kernel function is 0, and the data therein is gradually enriched during the signal processing. In some embodiments, each surface EMG signal corresponds to a decision signal.

The action segment determination unit 403 can determine that the surface EMG signal corresponding to the determination signal is in the action segment when the determination signal is greater than the predetermined threshold; when the determination signal is not greater than the predetermined threshold, determine that the surface EMG signal corresponding to the determination signal is in the action segment. Resting segment.

In some embodiments, the action segment determining unit 403 can determine to maintain the resting state if the current determination signal is less than or equal to the predetermined threshold when the action segment determination unit 403 is in the resting state; if the current signal is greater than the predetermined threshold, determine the current determination signal The corresponding surface EMG signal is the signal of the starting point of the action segment, and the currently detected user switches from the resting state to the active state.

In some embodiments, the action segment determination unit 403 can determine to remain active if the current determination signal is greater than or equal to a predetermined threshold when the action segment determination unit 403 is previously active; if the current signal is less than the predetermined threshold, determine that the current determination signal corresponds to The surface EMG signal is the signal of the end point of the action segment, and the currently detected user switches from the active state to the resting state.

Such a surface EMG signal processing device can first process the surface EMG signal based on the kernel function, obtain a determination signal after equidistant integration, and determine whether it is in the action section according to the determination signal, thereby reducing the threshold value of the action section detection The dependence of the setting improves the accuracy of the motion segment detection.

In some embodiments, the process of processing the surface EMG signal by the determination signal acquisition unit 402 may include: importing a single surface EMG signal into the kernel function, updating the kernel function; calculating the unit isometric integral of the kernel function based on the trapezoid method, and determining Determine the signal.

In some embodiments, the method for constructing the kernel function may include:

The kernel function is initialized to 0, and the kernel function is initialized in the form of kernel(j _k )=0,j ₁ ,j ₂ ,j ₃ ,...,j _n ; after the surface EMG signal s _{i is} passed into the kernel function, the kernel function Update to kernel={j ₂ ,…,j _n ,s _i },j ₂ ,…,j _n =0, after the surface EMG signal s _{i is} passed into the kernel function, the unit equidistance of the kernel function is calculated based on the trapezoid method integrated to obtain a signal y _i s _i corresponding to the determination; in accordance with the following pass after a surface EMG kernel, the kernel update timing of s _{i + 1} is the _{kernel = {j 3, ...,} j n, s i ,s _i+1 },j ₃ ,j ₄ ,…,j _n =0, after the next surface EMG signal s _i+1 in accordance with the time sequence is passed into the kernel function, the integral is calculated to obtain the corresponding _{s i+1} The decision signal y _i+1 .

Such a surface EMG signal processing device can gradually construct a kernel function in the processing process, so that the kernel function has the intensity information of all the signals before the current signal, and increases the small difference between the resting potential and the action potential. Improve the accuracy of subsequent detection.

In some embodiments, the signal acquisition unit 401 can first collect the initial surface EMG signal data, and then correct the collected initial data to obtain the surface EMG signal. Such as based on formula

In some embodiments, the signal acquisition unit can also determine the baseline threshold according to the resting state data, such as according to the formula:

thr=mean{MAV ₁ ,MAV ₂ ,MAV ₃ ,…,MAV _k }+A

A schematic structural diagram of an embodiment of the surface EMG signal processing device of the present disclosure is shown in FIG. 5. The surface EMG signal processing device includes a memory 501 and a processor 502. Wherein: the memory 501 may be a magnetic disk, flash memory or any other non-volatile storage medium. The memory is used to store the instructions in the corresponding embodiment of the above surface EMG signal processing method. The processor 502 is coupled to the memory 501 and can be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller. The processor 502 is configured to execute the instructions stored in the memory, which can reduce the dependence of the action segment detection on the threshold setting, and improve the accuracy of the action segment detection.

In an embodiment, as shown in FIG. 6, the surface EMG signal processing device 600 includes a memory 601 and a processor 602. The processor 602 is coupled to the memory 601 through the BUS bus 603. The surface EMG signal processing device 600 can also be connected to an external storage device 605 through a storage interface 604 to call external data, and can also be connected to a network or another computer system (not shown) through a network interface 606. No more detailed introduction here.

In this embodiment, the memory stores the data instructions and the processor processes the above instructions, which can reduce the dependence of the action segment detection on the threshold setting and improve the accuracy of the action segment detection.

In another embodiment, a computer-readable storage medium has computer program instructions stored thereon, and when the instructions are executed by a processor, the steps of the surface EMG signal processing method corresponding to the method in the embodiment are realized. Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, an apparatus, or a computer program product. Therefore, the present disclosure may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. .

A schematic diagram of some embodiments of the wearable device of the present disclosure is shown in FIG. 7. The electromyographic signal collecting device 71 may be a detector attached to the surface of the user's body to be detected, and can collect the electromyographic signal of the user's surface. The surface EMG signal processing device 72 can be any of the above-mentioned ones. The surface EMG signal processing device 72 can be integrated in the terminal of the wearable device, and the detector can also send the detection data to the remote data processing side in a wired or wireless manner, and the surface EMG signal processing on the data processing side The device 72 executes the surface EMG signal processing method as mentioned above.

Such a wearable device can first process the surface EMG signal based on the kernel function, obtain a determination signal after equidistant integration, and determine whether it is in the action segment based on the determination signal, thereby reducing the threshold setting of the action segment detection Dependence improves the accuracy of motion segment detection.

The present disclosure is described with reference to flowcharts and/or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and/or block in the flowchart and/or block diagram and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

So far, the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure can be implemented by software, hardware, firmware or any combination of software, hardware, and firmware. The above-mentioned order of the steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless specifically stated otherwise. In addition, in some embodiments, the present disclosure can also be implemented as programs recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure and not to limit them; although the present disclosure has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that: The disclosed specific embodiments are modified or some technical features are equivalently replaced; without departing from the spirit of the technical solutions of the present disclosure, they should all be covered in the scope of the technical solutions claimed by the present disclosure.

Claims

A surface EMG signal processing method, including:

Obtain surface EMG signal;

Import the surface EMG signal into a kernel function, perform equidistant integration processing on the kernel function to obtain a determination signal, wherein the kernel function includes the surface EMG signal before the current surface EMG signal in chronological order; and When the determination signal is greater than the predetermined threshold, it is determined that the surface EMG signal corresponding to the determination signal is in the action segment.
The surface EMG signal processing method according to claim 1, wherein the importing a kernel function according to the surface EMG signal and performing equidistant integration processing on the kernel function to obtain the determination signal comprises:

Import a single surface EMG signal into the kernel function and update the kernel function; and

Calculate the unit equidistant integral of the kernel function based on the trapezoid method to determine the judgment signal.
The surface EMG signal processing method according to claim 2, wherein the importing the kernel function according to the surface EMG signal and performing equidistant integration processing on the kernel function to obtain the determination signal further comprises:

Initialize the kernel function to 0;

According to the order of acquisition time from first to last, import the concentrated surface EMG signals into the kernel function one by one, update the kernel function after each import of the surface EMG signal, and perform equidistant integration to obtain The judgment signal corresponding to the current surface EMG signal; and

After completing the import of each surface EMG signal in the surface signal set, the determination signal set corresponding to the surface signal set is obtained.
The surface EMG signal processing method according to claim 1, wherein said obtaining the surface EMG signal comprises:

Collect initial surface EMG signal data; and

The initial surface signal data is corrected based on the baseline threshold, and the surface EMG signal is obtained.
The surface EMG signal processing method according to claim 4, wherein said correcting said initial surface signal data based on a predetermined baseline threshold value comprises:

In the case that the initial surface EMG signal is less than the baseline threshold, the surface EMG signal is 0; and

In the case that the initial surface EMG signal is greater than or equal to the baseline threshold, the surface EMG signal is the collected initial surface signal data.
The surface EMG signal processing method according to claim 4 or 5, further comprising: determining the baseline threshold thr according to a formula,

thr=mean{MAV 1 ,MAV 2 ,MAV 3 ,…,MAV k }+A

Among them, MAV i is the maximum value of the signal in the sliding window in the resting state data of the initial surface EMG signal data, i is a positive integer between 1 and k, k is the number of sliding windows, and A is a predetermined constant.
The surface EMG signal processing method according to claim 1, wherein the determining that the surface EMG signal corresponding to the determination signal is in an action segment comprises:

In the case where the previous one or more determination signals are less than or equal to the predetermined threshold, if the determination signal is switched to be greater than the predetermined threshold, the surface EMG signal corresponding to the current determination signal is the starting point signal of the action segment; and

In the case where the previous one or more determination signals are greater than the predetermined threshold, if the determination signal is switched to be less than the predetermined threshold, the surface EMG signal corresponding to the current determination signal is the end point signal of the action segment.
A surface EMG signal processing device, including:

The signal acquisition unit is configured to acquire the surface EMG signal;

The determination signal acquisition unit is configured to import the surface EMG signal into the kernel function, perform equidistant integration processing on the kernel function, and obtain the determination signal, wherein the kernel function includes the current surface EMG signal in chronological order Previous surface EMG signal; and

The action segment determination unit is configured to determine that the surface EMG signal corresponding to the determination signal is in the action segment when the determination signal is greater than a predetermined threshold.
The surface EMG signal processing device according to claim 8, wherein the determination signal acquisition unit is configured to:

Import a single surface EMG signal into the kernel function and update the kernel function; and

Calculate the unit equidistant integral of the kernel function based on the trapezoidal method to determine the judgment signal.
The surface EMG signal processing device according to claim 9, wherein the determination signal acquisition unit is further configured to:

Initialize the kernel function to 0;

According to the order of acquisition time from first to last, import the concentrated surface EMG signals into the kernel function one by one, update the kernel function after each import of the surface EMG signal, and perform equidistant integration to obtain The judgment signal corresponding to the current surface EMG signal; and

After completing the import of each surface EMG signal in the surface signal set, the determination signal set corresponding to the surface signal set is obtained.
The surface EMG signal processing device according to claim 8, wherein the signal acquisition unit is configured to:

Collect initial surface EMG signal data; and

The initial surface signal data is corrected based on the baseline threshold, and the surface EMG signal is obtained.
A surface EMG signal processing device, including:

Memory; and

A processor coupled to the memory, the processor being configured to execute the method according to any one of claims 1 to 7 based on instructions stored in the memory.
A computer-readable storage medium having computer program instructions stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are realized.
A wearable device including:

An electromyographic signal acquisition device configured to collect surface electromyographic signals; and

The surface EMG signal processing device according to any one of claims 8-12.
The wearable device according to claim 14, wherein the electromyographic signal acquisition device comprises a detector attached to the surface of the user's body to be detected.