WO2021139666A1

WO2021139666A1 - Posture detection method, apparatus and system, electronic device and storage medium

Info

Publication number: WO2021139666A1
Application number: PCT/CN2021/070407
Authority: WO
Inventors: 李红红; 崔丽华; 韩久琦
Original assignee: 京东数科海益信息科技有限公司
Priority date: 2020-01-07
Filing date: 2021-01-06
Publication date: 2021-07-15
Also published as: CN111241983A; CN111241983B

Abstract

The present application relates to a posture detection method, apparatus and system, an electronic device and a storage medium. Said method comprises: receiving motion data at a first sampling time; determining an envelope signal corresponding to the motion data; and analyzing the envelope signal to determine posture information at the first sampling time. According to the technical solution, the motion data is processed to obtain an envelope signal corresponding to the motion data, and a posture at a current time is determined by analyzing the envelope signal, thereby achieving quick detection of daily instantaneous posture of a person, such as sitting down or standing up, so as to facilitate the prompt feedback of a smart wearable device. This method can be widely applied in fields such as medical rehabilitation, man-machine interaction and virtual reality.

Description

Posture detection method, device, system, electronic equipment and storage medium

This application requires the priority of a Chinese patent application filed with the Chinese Patent Office, the application number is 202010014951.X, and the invention title is "a posture detection method, device, system, electronic equipment and storage medium" on January 7, 2020. The entire content is incorporated into this application by reference.

Technical field

This application relates to the field of data processing, and in particular to a posture detection method, device, system, electronic equipment, and storage medium.

Background technique

In the prior art, common human posture recognition is generally divided into two types: (1) Human body motion posture method based on image recognition. (2) Human motion posture detection method based on electromagnetic wave positioning Human motion posture monitoring based on electromagnetic wave positioning.

However, the above two methods still have shortcomings in the implementation process. For the method of image recognition: video monitoring is intelligently arranged in a fixed place for real-time monitoring. If the target does not appear in frequently active areas, video monitoring will not work, and May cause the personal privacy of the monitored person to be exposed. The human body motion posture detection method for electromagnetic wave positioning: the electromagnetic wave of the external environment (such as electronic products) is greatly interfered, and the data obtained is inaccurate.

Summary of the invention

In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a posture detection method, device, system, electronic device, and storage medium.

In the first aspect, this application provides a posture detection method, including:

Receiving the motion data at the first sampling moment;

Determine the envelope signal corresponding to the motion data;

The envelope signal is analyzed to determine the posture information at the first sampling moment.

Optionally, the motion data includes: motion data corresponding to at least one key part, wherein each key part corresponds to at least one motion data.

Optionally, the determining the envelope signal corresponding to the motion data includes:

Get the initialized kernel function;

Pass the motion data into the kernel function;

Integrating the kernel function after inputting the motion data to obtain the envelope signal corresponding to the motion data.

Optionally, the method further includes:

Acquiring posture information of an adjacent second sampling time, where the second sampling time is before the first sampling time;

When the posture information at the first sampling time is different from the posture information at the second sampling time, acquiring the time difference between the first sampling time and the second sampling time;

When the time difference is greater than the preset time difference, the posture identifier corresponding to the first sampling moment is updated.

Optionally, the motion data includes: acceleration in the direction of the gravitational acceleration of the thigh, the angular velocity in the sagittal plane of the thigh, and the three-axis combined angular velocity of the lower leg.

Optionally, the method further includes:

Obtain the acceleration in the gravitational acceleration direction of the thigh and the angular velocity in the sagittal plane direction of the thigh for N consecutive sampling moments, where N is an integer greater than 1;

The analyzing the envelope signal to determine the posture information at the first sampling moment includes:

Determining the motion state of the thigh according to the envelope signal of the acceleration in the gravitational acceleration direction of the thigh and the envelope signal of the angular velocity in the sagittal plane direction of the thigh at consecutive N sampling moments;

Determining the movement state of the calf according to the envelope signal of the three-axis combined angular velocity of the calf;

The posture information at the first sampling moment is determined based on the motion state of the thigh and the motion state of the calf.

Optionally, the determining the state of the thigh according to the envelope signal of the acceleration in the gravitational acceleration direction of the thigh and the envelope signal of the angular velocity in the sagittal plane direction of the thigh at consecutive N sampling moments includes:

Calculating the differential average value of the N envelope signals of the acceleration in the direction of the gravitational acceleration of the thigh;

Obtaining the first change trend of the thigh in the vertical direction through the difference average value;

Obtaining the second changing trend of the thigh in the sagittal direction according to the envelope signal of the angular velocity in the sagittal direction of the thigh;

The thigh movement state is determined based on the first change trend and the second change trend.

In the second aspect, the present application provides a posture detection device, including:

The receiving module is used to receive the motion data at the first sampling moment;

The determining module is used to determine the envelope signal corresponding to the motion data;

The analysis module is used to analyze the envelope signal to determine the posture information at the first sampling moment.

Optionally, the determining module includes:

The kernel function acquisition sub-module is used to acquire the initialized kernel function;

Data transfer sub-module for transferring the motion data into the kernel function;

The integration sub-module is used to integrate the kernel function after the motion data is input to obtain the envelope signal corresponding to the motion data.

Optionally, the device further includes an update module, and the update module is configured to:

A posture information acquisition sub-module, configured to acquire posture information of an adjacent second sampling time, the second sampling time being before the first sampling time;

A time difference acquisition submodule, configured to acquire the time difference between the first sampling time and the second sampling time when the posture information at the first sampling time is different from the posture information at the second sampling time;

The update sub-module is configured to update the posture identifier corresponding to the first sampling moment when the time difference is greater than the preset time difference.

Optionally, the device further includes a data acquisition module, and the data acquisition module is configured to:

The analysis module includes:

The thigh motion state sub-module is used to determine the thigh motion state according to the envelope signal of the acceleration in the direction of the gravitational acceleration of the thigh and the envelope signal of the angular velocity in the sagittal plane of the thigh at consecutive N sampling moments;

The calf motion state sub-module is used to determine the calf motion state according to the envelope signal of the three-axis combined angular velocity of the calf;

The posture information sub-module is configured to determine the posture information at the first sampling moment based on the motion state of the thigh and the motion state of the calf.

Optionally, the thigh motion state sub-module includes:

A calculating unit, configured to calculate the differential average value of the envelope signals of the acceleration in the direction of acceleration due to gravity acceleration of the N thighs;

The first change trend unit is configured to obtain the first change trend of the thigh in the vertical direction through the difference average value;

The second change trend unit is configured to obtain the second change trend of the thigh in the sagittal direction according to the envelope signal of the angular velocity in the sagittal direction of the thigh;

The thigh movement state unit is configured to determine the thigh movement state based on the first change trend and the second change trend.

In a third aspect, the present application provides a posture detection system, including: a motion sensor and a processor, and the motion sensor is in communication connection with the processor;

The motion sensor is configured to collect motion data at the first sampling moment, and send the motion data to the processor;

The processor is configured to receive motion data at a first sampling time, determine an envelope signal corresponding to the motion data, and analyze the envelope signal to determine posture information at the first sampling time.

In a fourth aspect, the present application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;

The memory is used to store computer programs;

The processor is used to implement the steps of the above method when the computer program is executed.

In a fifth aspect, the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method steps are implemented.

Compared with the prior art, the above-mentioned technical solutions provided by the embodiments of the present application have the following advantages: the envelope signal corresponding to the motion data is obtained by processing the motion data, and the posture at the current moment is determined by analyzing the envelope signal, thereby achieving In order to quickly detect the instantaneous posture of the daily human body such as sitting or standing up, so as to provide timely feedback from smart wearable devices. This method can be widely used in medical rehabilitation, human-computer interaction, virtual realization and other fields.

Description of the drawings

The drawings here are incorporated into the specification and constitute a part of the specification, show embodiments consistent with the present invention, and together with the specification are used to explain the principle of the present invention.

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, In other words, other drawings can be obtained based on these drawings without creative labor.

FIG. 1 is a schematic diagram of a posture detection system provided by an embodiment of the application;

FIG. 2 is a flowchart of a posture detection method provided by an embodiment of the application;

FIG. 3 is a flowchart of a posture detection method provided by another embodiment of this application;

FIG. 4 is a flowchart of a posture detection method provided by another embodiment of this application;

FIG. 5 is a block diagram of a posture detection device provided by an embodiment of the application;

FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments These are a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

This application provides a posture detection method, device, system, electronic equipment, and storage medium. The method provided in the embodiments of the present invention can be applied to any required electronic equipment. For example, it can be a server, a terminal, and other electronic equipment. There is no specific limitation, and for the convenience of description, it is referred to as electronic device in the following.

The following first introduces a posture detection method provided by an embodiment of the present invention.

FIG. 1 is a schematic diagram of a posture detection system provided by an embodiment of this application. As shown in FIG. 1, the system includes: at least one motion sensor 100 and a processor 101, and the motion sensor 100 is in communication connection with the processor 101.

The motion sensor 100 is used to collect the motion data at the first sampling moment, and send the motion data to the processor;

The processor 101 is configured to receive the motion data at the first sampling time, determine the envelope signal corresponding to the motion data, and analyze the envelope signal to determine the posture information at the first sampling time.

This embodiment takes the human body as an example. The motion sensor can be worn on the side of the human thigh and the human calf respectively. The motion data collected by the motion sensor includes: gyroscope data, acceleration data, angle data, etc. The communication method between the motion sensor and the processor can be Is it wired or wireless.

Fig. 2 is a flowchart of a posture detection method provided by an embodiment of the application. As shown in Figure 2, the method includes the following steps:

Step S11, receiving the motion data at the first sampling moment;

Step S12, determining the envelope signal corresponding to the motion data;

Step S13: Analyze the envelope signal to determine the posture information at the first sampling moment.

In this embodiment, the envelope signal corresponding to the motion data is obtained by processing the motion data, and the current posture is determined by analyzing the envelope signal, thereby realizing the rapid instantaneous posture of the daily human body such as sitting or standing up. Detection in order to provide timely feedback from smart wearable devices. This method can be widely used in medical rehabilitation, human-computer interaction, virtual realization and other fields.

In this embodiment, the received motion data at the first sampling moment includes: motion data corresponding to at least one key part, wherein each key part corresponds to at least one motion data, for example, the key parts may be: thigh, calf, shoulder, Elbows, etc., motion data includes: gyroscope data, acceleration data, angular velocity data, etc. of key parts.

Optionally, the envelope signal corresponding to the motion data is determined by the following methods: obtaining the initialized kernel function, passing the motion data into the kernel function, and integrating the kernel function after the motion data is transferred to obtain the motion data Corresponding envelope signal. The kernel function used in this embodiment may be: Gaussian kernel function, Marton kernel function, etc.

In this embodiment, judging the sitting and standing posture of the human body as an example, so the motion data that conforms to the changes in the human sitting and standing posture characteristics are extracted from the motion data. The extracted motion data includes the acceleration in the direction of gravitational acceleration of the thigh, the angular velocity of the thigh in the sagittal plane direction and The three-axis combined angular velocity of the calf. Among them, the three-axis combined angular velocity of the calf is calculated by the following formula:

In the formula, w ₁ x, w ₂ y, and w ₃ z are the angular velocities of the x, y, and z axes, respectively.

Then, the acceleration in the direction of the gravitational acceleration of the thigh, the angular velocity in the sagittal plane direction of the thigh and the three-axis combined angular velocity of the lower leg are smoothly filtered. Based on the processed gravitational acceleration of the thigh, the sagittal angular velocity of the thigh and the triaxial combined angular velocity of the lower leg are used to extract the envelope signal.

The extraction process of the envelope signal is as follows: Obtain the initialized first kernel function, kernel(jk)={j ₁ ,j ₂ ,j ₃ ...j _n }, where j ₁ ,j ₂ ,j ₃ .. .j _n = 0.

^{Pass the acceleration s i in the} direction of the gravitational acceleration of the thigh into the first kernel function, and obtain the second kernel function kernel(jk)={j ₂ ,j ₃ ...j _n ,s _i },j ₂ ,j ₃ ...j _n = 0, the second kernel function is integrated based on the trapezoidal algorithm envelope-Signal = sum{j ₂ ,...j _n ,s _i _{} ÷ 2, that is, the envelope signal y i} = envelope of the acceleration in the direction of the thigh's gravitational acceleration is obtained -Signal, where the second kernel function is the first kernel function after passing acceleration in the direction of the gravitational acceleration of the thigh.

Pass the angular velocity s _{i+1 in the} sagittal plane of the thigh into the second kernel function to obtain the third kernel function kernel(jk)={j ₃ ...j _n ,s _i ,s _i+1 },j ₃ .. .j _n =0, integrate the third kernel function based on the trapezoidal algorithm envelope-Signal=sum{j ₃ ,...j _n ,s _i ,s _i+1 }÷2, that is, the angular velocity of the thigh sagittal plane is obtained The envelope signal y _i+1 =envelope-Signal, where the third kernel function is the second kernel function after passing the angular velocity in the sagittal direction of the thigh.

Pass the three-axis combined angular velocity s _{i+2 of the} calf into the third kernel function to obtain the fourth kernel function kernel(jk)={j ₄ ...j _n ,s _i ,s _i+1 ,s _i+2 } ,j ₄ ...j _n =0, integrate the fourth kernel function based on the trapezoidal algorithm, that is, envelope-Signal=sum{j ₃ ,...j _n ,s _i ,s _i+1 ,s _i+2 }÷2 obtains the envelope signal y _i+2 =envelope-Signal of the three-axis combined angular velocity of the calf, where the fourth kernel function is the third kernel function after the three-axis combined angular velocity of the calf is passed in.

In this embodiment, analyzing the envelope signal to determine the posture information at the first sampling moment is specifically implemented in the following manner: obtaining the acceleration in the gravitational acceleration direction of the thigh and the angular velocity in the sagittal plane direction of the thigh for N consecutive sampling moments, where N is greater than 1. Integer.

Determine the motion state of the thigh according to the envelope signal of the acceleration in the direction of the gravitational acceleration of the thigh and the envelope signal of the angular velocity in the sagittal plane of the thigh at consecutive N sampling moments, and determine the motion state of the calf according to the envelope signal of the three-axis angular velocity of the lower leg, The motion state and the calf motion state determine the posture information at the first sampling moment.

Specifically, the thigh state is determined according to the envelope signal of the acceleration in the direction of the gravitational acceleration of the thigh and the envelope signal of the angular velocity in the sagittal direction of the thigh at consecutive N sampling moments. The difference average value of the network signal is used to obtain the first change trend of the thigh in the vertical direction through the difference average value, and the second change trend of the thigh in the sagittal direction is obtained according to the envelope signal of the angular velocity of the thigh in the sagittal plane.

Optionally, calculate the differential average value of the envelope signals of acceleration in the direction of gravity acceleration of the N thighs, and obtain the first change trend of the thigh in the vertical direction through the differential average value, which is obtained by taking the envelope signals of acceleration in the direction of gravity acceleration of the thighs The difference average value is compared with the first threshold value. If the difference average value is greater than the first threshold value, the first change trend of the thigh in the vertical direction is an upward trend. It is confirmed that the thigh is currently changed from a bent state to an upright state; if the difference average value is less than The first threshold, the first change trend of the thigh in the vertical direction is a downward trend, and it is confirmed that the thigh is currently changed from an upright state to a bent state.

Optionally, obtaining the second change trend of the thigh in the sagittal direction according to the envelope signal of the thigh sagittal angular velocity is by comparing the envelope signal of the thigh sagittal angular velocity with the second threshold, if The envelope signal of the angular velocity in the sagittal plane of the thigh is greater than the threshold, and the thigh movement is confirmed.

Then, the thigh movement state is determined based on the first change trend and the second change trend. For example, if the first change trend is an upward trend, and the thigh movement is confirmed according to the second change trend, it is confirmed that the thigh movement state changes from bent to upright. Or, if the second change trend is a downward trend, and the thigh movement is confirmed based on the second change trend, it is confirmed that the thigh movement state changes from erect to bent.

In this embodiment, the movement state of the calf is determined according to the envelope signal of the three-axis combined angular velocity of the calf, by comparing the three-axis combined angular velocity of the calf with a third threshold. When it is less than the third threshold, it is confirmed that the calf is in a static state. ; When it is greater than the third threshold, it is confirmed that the calf is in motion.

Finally, the posture information at the first sampling moment is determined based on the motion state of the thigh and the motion state of the calf. For example: when the thigh movement state changes from upright to bent, and the calf is in a static state, it is confirmed that the posture information of the human body is a sitting posture. The movement state of the thigh changes from bending to upright, and the calf is in a static state, and the posture information of the human body is confirmed to be a standing posture.

FIG. 3 is a flowchart of a posture detection method provided by another embodiment of this application. As shown in Figure 3, the method also includes the following steps:

Step S21: Obtain the posture information of the adjacent second sampling time, the second sampling time is before the first sampling time;

Step S22: when the posture information at the first sampling time is different from the posture information at the second sampling time, acquiring the time difference between the first sampling time and the second sampling time;

Step S23: When the time difference is greater than the preset time difference, update the posture identifier corresponding to the first sampling moment.

In this embodiment, acquiring the posture information of the adjacent second sampling time, the second sampling time is before the first sampling time, wherein acquiring the posture information of the adjacent second sampling time includes: acquiring the posture of the second sampling time Identification, the gesture information at the second sampling moment is determined according to the gesture identification.

When the posture information at the first sampling time is different from the posture information at the second sampling time, the time difference between the first sampling time and the second sampling time is acquired, and when the time difference is greater than the preset time difference, the posture identifier corresponding to the first sampling time is updated.

For example: the posture information at the second sampling time is a sitting posture, and the posture information obtained at the first sampling time is a standing posture. Determine whether the time difference between the first sampling time and the second sampling time is greater than the preset time difference, and if it is greater, confirm the first sampling time The posture information of is the standing posture, and the posture identifier corresponding to the first sampling moment is updated.

In another embodiment, a method for confirming posture information is also provided, and the maximum value and minimum value of the envelope signal of the acceleration in the direction of the gravitational acceleration of the thigh at the previous sampling time are obtained.

Among them, if the envelope signal of the acceleration in the direction of the thigh's gravitational acceleration at the first sampling time is greater than the maximum value, the maximum value is updated according to the envelope signal of the acceleration in the direction of the thigh's gravitational acceleration at the first sampling time; When the envelope signal of the acceleration in the acceleration direction is less than or equal to the maximum value, the maximum value at the previous sampling time is still used.

Then determine the maximum difference between the maximum value and the minimum value based on the maximum value and the minimum value. Calculate the difference between the envelope signal of the acceleration in the direction of gravitational acceleration of the thigh at the first sampling time and the minimum value at the second sampling time, and compare it with the minimum difference to obtain the ratio. The ratio can represent the change between the current moment and the instantaneous characteristics of the experience. The larger the ratio, the closer to the sitting posture, and the smaller the ratio, the closer to the standing posture.

As shown in FIG. 4, another embodiment of the present application provides a flow chart of a posture detection method. The method embodiment is specifically used to determine the instantaneous change of the sitting posture and the standing posture. The method includes:

Step S31, receiving the motion data at the current sampling moment;

In this embodiment, the motion data at the current sampling time includes: each key part corresponds to at least one motion data. For example, the key parts can be: thigh, calf, shoulder, elbow, etc., and the motion data includes: the gyroscope of the key part Data, acceleration data, angular velocity data, etc.

In this embodiment, the sitting posture and the standing posture are judged as an example, so the extracted motion data are: the acceleration in the gravitational acceleration direction of the thigh, the angular velocity in the sagittal plane of the thigh, and the three-axis combined angular velocity of the lower leg.

Step S32, determining the envelope signal corresponding to the motion data;

Specifically, the initialized kernel function is obtained, the motion data is transferred to the kernel function, and the kernel function after the motion data is transferred is integrated to obtain the envelope signal corresponding to the motion data.

Step S33, analyzing the envelope signal to determine the posture information at the current sampling moment;

Specifically, the thigh motion state is determined according to the envelope signal of the acceleration in the gravitational acceleration direction of the thigh and the envelope signal of the thigh sagittal angular velocity at consecutive N sampling moments, and the calf motion state is determined according to the envelope signal of the three-axis combined angular velocity of the lower leg , Determine the posture information at the current sampling moment based on the motion state of the thigh and the motion state of the calf.

Step S34, when the posture information conforms to the sitting posture characteristics, or the posture information conforms to the standing posture characteristics, confirm that the current sampling time has a posture change compared to the previous sampling time, and perform step S35;

When the posture information does not conform to the sitting posture characteristics, or the posture information does not conform to the standing posture characteristics, it is confirmed that the current sampling time has not changed from the previous sampling time, and step S36 is executed.

Compared with recognition methods such as image recognition, the gesture detection method provided by the embodiments of the present application shows the advantages of low power consumption, good portability, and low cost based on motion sensor behavior recognition. It can also be used in medical rehabilitation, human-computer interaction, and virtual realization. And other fields for a wide range of applications.

The detection method disclosed in this application is based on the transient judgment of human lower limb behavior based on wearable sensor motion information fusion, and can realize rapid response to daily human sitting or standing transients, so as to provide timely feedback from smart wearable devices.

Fig. 5 is a block diagram of a posture detection device provided by an embodiment of the application. The device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. As shown in Figure 5, the device includes:

The receiving module 401 is configured to receive the motion data at the first sampling moment;

The determining module 402 is used to determine the envelope signal corresponding to the motion data;

The analysis module 403 is used to analyze the envelope signal to determine the posture information at the first sampling moment.

An embodiment of the present application also provides an electronic device. As shown in FIG. 6, the electronic device may include: a processor 1501, a communication interface 1502, a memory 1503, and a communication bus 1504. The processor 1501, the communication interface 1502, and the memory 1503 pass through The communication bus 1504 completes mutual communication.

The memory 1503 is used to store computer programs;

The processor 1501 is configured to implement the steps of the foregoing embodiment when executing the computer program stored in the memory 1503.

The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (P C I) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the above-mentioned electronic device and other devices.

The memory may include random access memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk storage. Optionally, the memory may also be at least one storage device located far away from the foregoing processor.

The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processing, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

The present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned embodiments are implemented.

It should be noted that, for the foregoing device, electronic device, and computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiments.

It should be further noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply There is any such actual relationship or sequence between these entities or operations. Moreover, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or equipment that includes the element.

The above are only specific embodiments of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in this document, but should conform to the widest scope consistent with the principles and novel features applied for in this document.

Claims

A posture detection method, including:

Receiving the motion data at the first sampling moment;

Determine the envelope signal corresponding to the motion data;

The envelope signal is analyzed to determine the posture information at the first sampling moment.
The method according to claim 1, wherein the motion data comprises: motion data corresponding to at least one key part, wherein each key part corresponds to at least one motion data.
The method according to claim 1, wherein the determining the envelope signal corresponding to the motion data comprises:

Get the initialized kernel function;

Pass the motion data into the kernel function;

Integrating the kernel function after inputting the motion data to obtain the envelope signal corresponding to the motion data.
The method according to claim 1, further comprising:

Acquiring posture information of an adjacent second sampling time, where the second sampling time is before the first sampling time;

When the posture information at the first sampling time is different from the posture information at the second sampling time, acquiring the time difference between the first sampling time and the second sampling time;

When the time difference is greater than the preset time difference, the posture identifier corresponding to the first sampling moment is updated.
The method according to any one of claims 1 to 4, wherein the motion data includes: acceleration in the direction of gravitational acceleration of the thigh, angular velocity in the sagittal plane of the thigh, and triaxial combined angular velocity of the lower leg.
The method according to claim 5, further comprising:

Obtain the acceleration in the gravitational acceleration direction of the thigh and the angular velocity in the sagittal plane direction of the thigh for N consecutive sampling moments, where N is an integer greater than 1;

The analyzing the envelope signal to determine the posture information at the first sampling moment includes:

Determining the motion state of the thigh according to the envelope signal of the acceleration in the gravitational acceleration direction of the thigh and the envelope signal of the angular velocity in the sagittal plane direction of the thigh at consecutive N sampling moments;

Determining the movement state of the calf according to the envelope signal of the three-axis combined angular velocity of the calf;

The posture information at the first sampling moment is determined based on the motion state of the thigh and the motion state of the calf.
The method according to claim 6, wherein the determining the state of the thigh according to the envelope signal of the acceleration in the gravitational acceleration direction of the thigh and the envelope signal of the angular velocity in the sagittal plane direction of the thigh at consecutive N sampling moments comprises:

Calculating the differential average value of the N envelope signals of the acceleration in the direction of the gravitational acceleration of the thigh;

Obtaining the first change trend of the thigh in the vertical direction through the difference average value;

Obtaining the second changing trend of the thigh in the sagittal direction according to the envelope signal of the angular velocity in the sagittal direction of the thigh;

The thigh movement state is determined based on the first change trend and the second change trend.
A posture detection device includes:

The receiving module is used to receive the motion data at the first sampling moment;

The determining module is used to determine the envelope signal corresponding to the motion data;

The analysis module is used to analyze the envelope signal to determine the posture information at the first sampling moment.
The device according to claim 8, wherein the motion data comprises: motion data corresponding to at least one key part, wherein each key part corresponds to at least one motion data.
The apparatus according to claim 8, wherein the determining module comprises:

The kernel function acquisition sub-module is used to acquire the initialized kernel function;

Data transfer sub-module for transferring the motion data into the kernel function;

The integration sub-module is used to integrate the kernel function after the motion data is input to obtain the envelope signal corresponding to the motion data.
The device according to claim 8, the device further comprising an update module, the update module configured to:

A posture information acquisition sub-module, configured to acquire posture information of an adjacent second sampling time, the second sampling time being before the first sampling time;

A time difference acquisition submodule, configured to acquire the time difference between the first sampling time and the second sampling time when the posture information at the first sampling time is different from the posture information at the second sampling time;

The update sub-module is configured to update the posture identifier corresponding to the first sampling moment when the time difference is greater than the preset time difference.
The device according to any one of claims 8-11, wherein the motion data comprises: acceleration in the direction of the gravitational acceleration of the thigh, the angular velocity in the sagittal plane of the thigh, and the triaxial combined angular velocity of the lower leg.
The device according to claim 12, the device further comprising a data acquisition module, the data acquisition module being configured to:

Obtain the acceleration in the gravitational acceleration direction of the thigh and the angular velocity in the sagittal plane direction of the thigh for N consecutive sampling moments, where N is an integer greater than 1;

The analysis module includes:

The thigh motion state sub-module is used to determine the thigh motion state according to the envelope signal of the acceleration in the direction of the gravitational acceleration of the thigh and the envelope signal of the angular velocity in the sagittal plane of the thigh at consecutive N sampling moments;

The calf motion state sub-module is used to determine the calf motion state according to the envelope signal of the three-axis combined angular velocity of the calf;

The posture information sub-module is configured to determine the posture information at the first sampling moment based on the motion state of the thigh and the motion state of the calf.
The device according to claim 13, wherein the thigh motion state sub-module comprises:

A calculating unit, configured to calculate the differential average value of the envelope signals of the acceleration in the direction of acceleration due to gravity acceleration of the N thighs;

The first change trend unit is configured to obtain the first change trend of the thigh in the vertical direction through the difference average value;

The second change trend unit is configured to obtain the second change trend of the thigh in the sagittal direction according to the envelope signal of the angular velocity in the sagittal direction of the thigh;

The thigh movement state unit is configured to determine the thigh movement state based on the first change trend and the second change trend.
A posture detection system, comprising: a motion sensor and a processor, the motion sensor is in communication connection with the processor;

The motion sensor is configured to collect motion data at the first sampling moment, and send the motion data to the processor;

The processor is configured to receive the motion data at the first sampling time, determine the envelope signal corresponding to the motion data, and analyze the envelope signal to determine the posture information at the first sampling time.
An electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete mutual communication through the communication bus;

The memory is used to store computer programs;

The processor is configured to implement the method steps of any one of claims 1-7 when executing the computer program.
A computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method steps described in any one of claims 1-7 are realized.