Sitting posture detection system based on pressure partition

Abstract

The invention provides a sitting posture detection system based on pressure partitions, and the system comprises a seat which comprises a seat surface and a seat back, the seat surface is divided into a plurality of partitions, each partition is internally provided with a first pressure sensor used for detecting the pressure of the seat surface in the corresponding partition, and the seat back is provided with a second pressure sensor used for detecting the pressure of the seat back; the sitting posture distinguishing module is used for distinguishing whether the user is in an upright sitting posture or a backrest sitting posture according to the chair back pressure; the control module is used for analyzing whether the sitting posture of the user inclines leftwards and rightwards or forwards or not according to the pressure of the chair surface by adopting a first strategy in the upright sitting posture; in the backrest sitting posture, analyzing whether the sitting posture of the user is inclined left and right or not by adopting a second strategy on the chair surface pressure and the chair back pressure; the alarm is used for giving an alarm when judging that the sitting posture inclines leftwards and rightwards and / or inclines forwards. According to the application, the seat pressure in different subareas is analyzed, and whether a user on the seat tilts left and right or forwards can be judged.

Description

Technical Field

[0001] The present application relates to the technical field of sitting posture detection, and in particular to a sitting posture detection system based on pressure zoning. Background Art

[0002] As the times progress, more and more industries are moving into office buildings. This brings with it the fact that prolonged sitting at workstations has a significant impact on workers' health. This is especially true when adopting an unhealthy sitting posture, which can cause significant damage to the worker's cervical, shoulder, and lumbar spine, leading to a variety of illnesses.

[0003] In this case, workers are immersed in their work and often find it difficult to detect their poor sitting posture. Therefore, it is necessary to detect the worker's sitting posture through external detection and issue an alarm to the worker if a poor sitting posture is found.

[0004] A Chinese invention patent application, publication number CN116884083A, proposes a sitting posture detection method, medium, and device based on human key points. This method identifies and analyzes human key points in user images to determine whether the user is sitting with a tilted posture. However, during use, technicians discovered that this method relies heavily on the accuracy of the human key point extraction algorithm. This is particularly true in winter, when users are wearing thick clothing, making it difficult to identify certain human key points, such as the shoulders, resulting in inaccurate sitting posture detection results. Summary of the Invention

[0005] The present application provides a sitting posture detection method, medium and device based on key points of the human body to at least solve the above technical problems existing in the prior art.

[0006] According to a first aspect of the present application, a sitting posture detection system based on pressure zoning is provided, comprising: A seat, comprising a seat surface and a seat back, wherein the seat surface is divided into a plurality of partitions, each partition being provided with a first pressure sensor for detecting seat surface pressure within the corresponding partition, and the seat back being provided with a second pressure sensor for detecting seat back pressure; a sitting posture distinguishing module, which distinguishes whether the user is in an upright sitting posture or a back-rest sitting posture according to the chair back pressure; The control module is configured to analyze the seat surface pressure using a first strategy to determine whether the user's sitting posture is tilted left or right or tilted forward in the upright sitting posture; and to analyze the seat surface pressure and the seat back pressure together to determine whether the user's sitting posture is tilted left or right in the backrest sitting posture; The alarm sounds an alarm when it is determined that the sitting posture is tilted left to right and / or tilted forward.

[0007] In certain embodiments of the first aspect of the present application, the distinguishing method of the sitting posture distinguishing module is as follows: Obtain all chair back pressures measured in a recent first time period, count a first number of chair back pressures greater than a preset back pressure threshold, and divide the first number by the total number of chair back pressures to obtain a first ratio. If the first ratio is greater than a fixed ratio threshold, determine that the user is in a reclining sitting position; otherwise, determine that the user is in an upright sitting position.

[0008] In certain embodiments of the first aspect of the present application, there are four partitions, including a front left partition, a front right partition, a rear left partition, and a rear right partition.

[0009] In certain embodiments of the first aspect of the present application, in the upright sitting posture, a method for analyzing the pressure on the chair surface using a first strategy to determine whether the user's sitting posture is tilted left or right is as follows: Obtain all seat surface pressures within the first time period; Calculate the first difference between the pressure on the left and right sides of the seat ;

[0010] in, Represents the pressure on the left side of the chair seat; Represents the right side pressure of the chair seat; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, front left partition, rear right partition, and front right partition; Represents the first time period; Represents a time point in the first time period i the number of The first difference Compared with the set first threshold, if the first difference If the value is greater than the first threshold, it is determined that the user is leaning left or right; otherwise, it is determined that the user is keeping straight in front of the camera.

[0011] In certain embodiments of the first aspect of the present application, in the upright sitting posture, a method for analyzing the pressure on the chair surface using a first strategy to determine whether the user's sitting posture is tilted forward is as follows: Calculate the second difference between the pressure on the rear side and the pressure on the front side of the seat ;

[0012] in, Represents the pressure on the back of the chair seat; Represents the front pressure of the chair seat; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, rear right partition, front left partition, and front right partition; Represents the first time period; Represents a time point in the first time period i the number of The second difference Compared with the set second threshold, if the second difference If the value is less than the second threshold, it is determined that the user is leaning forward; otherwise, the user remains upright on the side.

[0013] In certain embodiments of the first aspect of the present application, when the user maintains correct posture both from the front and from the side, it is determined that the user's sitting posture is correct in the upright sitting position.

[0014] In certain embodiments of the first aspect of the present application, in the backrest sitting posture, a method for jointly analyzing the seat surface pressure and the seat back pressure using a second strategy to determine whether the user's sitting posture is in a left-right tilted sitting posture is as follows: Calculate the third difference between the pressure on the left and right sides of the seat ;

[0015] in, Represents the pressure on the left side of the chair seat; Represents the right side pressure of the chair seat; Represents chair back pressure; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, front left partition, rear right partition, and front right partition; represents the seat back pressure measured at time point i; Represents the correction factor of the pressure difference between the seat back and the left and right sides of the seat surface; Represents the first time period; Represents a time point in the first time period i the number of The third difference Compared with the set first threshold, if the third difference If the value is greater than the first threshold, it is determined that the user is leaning left or right; otherwise, it is determined that the user is sitting upright in a backrest sitting position.

[0016] In certain embodiments of the first aspect of the present application, the correction coefficient k ranges from 0.05 to 0.1.

[0017] In certain embodiments of the first aspect of the present application, before distinguishing between the upright sitting posture and the back-rest sitting posture, a determination is also made as to whether the user is sitting on the seat: Obtaining several seat surface pressure arrays measured within a recent second time period, each seat surface pressure array including seat surface pressures in all partitions; counting a second number of seat surface pressure arrays in which the seat surface pressures in all partitions are greater than a set surface pressure threshold; and dividing the second number by the total number of seat surface pressure arrays to obtain a second ratio. If the second ratio is greater than a fixed ratio threshold, it is determined that the user is sitting on the seat.

[0018] In certain embodiments of the first aspect of the present application, the partition division method is: with the center point of the chair surface as the intersection point, two mutually perpendicular straight lines are drawn respectively, thereby dividing the chair surface into a front left partition, a front right partition, a rear left partition, and a rear right partition.

[0019] Compared with the prior art, this application has the following beneficial effects: 1. This application uses pressure sensors to collect seat surface pressure within different sections of the seat surface and analyzes the pressure at a point in these sections to determine whether the user is leaning left or right or leaning forward. Compared to traditional sitting posture detection methods based on human key points, this eliminates the reliance on human key point detection algorithms, particularly avoiding the impact of heavy clothing on human key point recognition.

[0020] 2. This application divides sitting posture detection into two situations, upright sitting posture and backrest sitting posture, based on different chair back pressures, and adopts different strategies for analysis respectively, so as to avoid the situation where the seat surface pressure on the seat surface changes when the user leans on the chair back, thereby affecting the accuracy and sensitivity of the sitting posture detection.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an illustrative and non-limiting manner, in which: In the drawings, the same or corresponding reference numerals denote the same or corresponding parts.

[0023] Figure 1 A schematic diagram of the seat and pressure sensor installation of the present application is shown.

[0024] Figure 2 A schematic diagram of the system structure of this application is shown.

[0025] Figure 3 A schematic diagram of the chair seat partitions of the present application is shown.

[0026] Figure 4 A schematic diagram showing the different sitting postures of the present application is shown.

[0027] Figure 5 A schematic diagram of the sitting posture leaning forward of the present application is shown.

[0028] Figure 6 A schematic diagram of the sitting posture tilting left and right in this application is shown.

[0029] Description of reference numerals: 1. Seat; 11. Seat surface; 12. Seat back; 2. First pressure sensor; 3. Second pressure sensor. DETAILED DESCRIPTION

[0030] In order to make the purpose, features, and advantages of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0031] Example 1: This embodiment provides a sitting posture detection system based on pressure zoning. Figure 1 and Figure 2 , mainly including seat 1, sitting posture differentiation module, control module and alarm.

[0032] The seat 1 includes a seat surface 11 and a seat back 12. Figure 3 As shown, the seat surface 11 is divided into several partitions, each of which is provided with a first pressure sensor 2 for detecting the pressure of the seat surface 11 in the corresponding partition. Preferably, there are four partitions, namely, the front left partition fl, the front right partition fr, the rear left partition bl, and the rear right partition br.

[0033] It is worth mentioning that the partition division method is: with the center point of the seat surface as the intersection point, two mutually perpendicular straight lines are drawn respectively, thereby dividing the seat surface into the front left partition fl, the front right partition fr, the rear left partition bl, and the rear right partition br.

[0034] The seat back 12 is provided with a second pressure sensor 3 for detecting seat back pressure. The first pressure sensor 2 and the second pressure sensor 3 regularly detect corresponding pressure data (ie, seat surface pressure and seat back pressure) and upload them.

[0035] The sitting posture distinguishing module first determines whether the user is sitting on the seat. If the user is sitting on the seat, it then distinguishes whether the user is in an upright sitting posture or a back-rest sitting posture based on the seat back pressure. Figure 4 As shown, the solid line represents an upright sitting posture, where the user's upper body remains upright and has no contact with the chair back, while the dotted line represents a reclining sitting posture, where the user's upper body is in contact with the chair back.

[0036] As we all know, intermittent breaks are necessary during work, and the backrest of a chair provides support for the user's back during breaks, making them more comfortable. Because the backrest provides a certain amount of support, the pressure on the chair surface will change compared to an upright sitting position. Therefore, we first distinguish whether the user is in an upright or reclining sitting position, so that we can analyze different strategies later and achieve more accurate detection results.

[0037] Specifically, the distinguishing method of the sitting posture distinguishing module can be implemented according to the pressure of the chair back within a certain period of time, as follows: Get all the seat back pressures measured in the first time period T1 , calculate the seat back pressure Greater than the preset backpressure threshold The first quantity and the first number Divide by the total number of seat back pressures to get the first ratio , if the first ratio If the fixed ratio threshold is greater than 70%, it is considered that the user's back is leaning on the chair back for more than 70% of the time in the first time period T1, and the user is judged to be in a back-rest sitting position; otherwise, the user is judged to be in an upright sitting position.

[0038] Similarly, the determination of whether the user is sitting on the seat is similar to the analysis of the pressure on the seat back.

[0039] Obtaining several seat surface pressure arrays measured within a recent second time period, each seat surface pressure array including seat surface pressures in all partitions; counting a second number of seat surface pressure arrays in which the seat surface pressures in all partitions are greater than a set surface pressure threshold; and dividing the second number by the total number of seat surface pressure arrays to obtain a second ratio. If the second ratio is greater than a fixed ratio threshold, it is determined that the user is sitting on the seat.

[0040] If the second ratio If the pressure is greater than a fixed ratio threshold, the seat surface receives pressure for more than 70% of the time in the first time period T1, and it is considered that the user is sitting on the seat.

[0041] The control module, in the upright sitting posture, adopts a first strategy to analyze the seat surface pressure to determine whether the user's sitting posture is tilted left or right or forward; and adopts a second strategy to jointly analyze the seat surface pressure and seat back pressure to determine whether the user's sitting posture is tilted left or right in the backrest sitting posture.

[0042] This control module uses different strategies to analyze the two sitting postures distinguished above to determine whether the sitting posture is correct. The following is a detailed explanation of several situations.

[0043] 1. In the upright sitting posture, the method of using the first strategy to analyze the pressure of the chair surface to determine whether the user's sitting posture is tilted left or right is as follows: Obtain all seat surface pressures within the first time period T1.

[0044] Calculate the first difference between the pressure on the left and right sides of the seat .

[0045]

[0046] in, Represents the pressure on the left side of the chair seat; Represents the right side pressure of the chair seat; 、 、 、 Represents the time points i Measured seat surface pressures in the rear left partition, front left partition, rear right partition, and front right partition; Represents the first time period; Represents a time point in the first time period i The number of

[0047] like Figure 6 As shown in the figure, if the user's sitting posture is correct from the front, the pressure exerted by the human body on the chair surface should be roughly symmetrical. , that is, the first difference obtained It should be roughly 0, and as the user's sitting posture gradually shifts to the left or right, the first difference will also increase accordingly, therefore, according to the first difference It can be used to judge whether the sitting posture is correct.

[0048] Specifically, the first difference With the first threshold set In comparison, if the first difference If the value is greater than the first threshold, the user is judged to be tilted left or right, otherwise the user is judged to be standing upright. It is worth mentioning that the first threshold is preferably 50N.

[0049] Second, in the upright sitting posture, the method of using the first strategy to analyze the pressure on the chair surface to determine whether the user's sitting posture is leaning forward is as follows: Calculate the second difference between the pressure on the rear side and the pressure on the front side of the seat .

[0050]

[0051] in, Represents the pressure on the back of the chair seat; Represents the front pressure of the chair seat; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, rear right partition, front left partition, and front right partition; Represents the first time period; Represents a time point in the first time period i The number of

[0052] like Figure 5 As shown in the figure, through analysis, it can be seen that in a sitting position, the main weight of the upper body is applied to the back of the chair surface. Therefore, whether the user is sitting upright or leaning forward, the pressure applied to the front and back sides of the chair surface (i.e., the rear pressure) is and front pressure ) are not equal.

[0053] However, the difference will change uniformly, that is, the second difference calculated for the forward-leaning sitting posture compared to the upright sitting posture is It will decrease accordingly.

[0054] Therefore, the following method is used to distinguish: the second difference With the second threshold set In comparison, if the second difference If the value is less than the second threshold, it is determined that the user is leaning forward; otherwise, the user remains upright on the side.

[0055] It is worth mentioning that the second threshold is different from the first threshold. The second threshold is positively correlated with the body weight or the total pressure applied to the chair surface. For example, if a person weighing 70kg sits upright, the pressure difference between the front and back of the chair may be around 50-100N. Therefore, the second threshold is the user's weight or the total pressure on the chair surface. The weighted value of. Taking the total pressure as an example, ;priority It is 0.1-0.2.

[0056] In the above two cases, the user's sitting posture is correct only when the user maintains correct posture in both the front and side views.

[0057] 3. In the backrest sitting posture, the second strategy is used to analyze the seat surface pressure and the seat back pressure to determine whether the user's sitting posture is tilted left or right as follows: Since the user's upper body is leaning on the chair back in the backrest sitting posture, there is no need to judge whether the user is leaning forward, and only the left and right tilts need to be judged.

[0058] Calculate the third difference between the pressure on the left and right sides of the seat .

[0059]

[0060] in, Represents the pressure on the left side of the chair seat; Represents the right side pressure of the chair seat; Represents chair back pressure; 、 、 、 Represents the time points i Measured seat surface pressures in the rear left partition, front left partition, rear right partition, and front right partition; represents the seat back pressure measured at time point i; Represents the correction factor of the seat back pressure to the pressure difference between the left and right sides of the seat surface; Represents the first time period; Represents a time point in the first time period i The number of

[0061] Because the chair back provides a certain amount of support to the user, the pressure on the chair surface will change compared to the upright sitting posture. Specifically, the pressure on the left and right sides of the chair surface will be reduced as a whole. Therefore, compared with the first case, in order to maintain the same sensitivity and accuracy, the third difference A correction factor for seat back pressure has been added to the calculation of The correction coefficient k ranges from 0.05 to 0.1.

[0062] The judgment principle is similar to the first case, the third difference With the first threshold set In comparison, if the third difference If the value is greater than the first threshold, it is determined that the user is leaning left or right; otherwise, it is determined that the user is sitting upright in a backrest sitting position.

[0063] According to the above three situations, it can be analyzed whether the user has a sitting tilt in the two sitting postures.

[0064] The alarm device sounds an alarm when it determines that the sitting posture is tilted left and right and / or tilted forward. Preferably, the alarm device can be a buzzer or an app program installed on the terminal.

[0065] Example 2: This embodiment also proposes a sitting posture detection system that can integrate pressure zoning with gender factors.

[0066] In the second case of the above embodiment 1, when analyzing whether the user's sitting posture is tilted forward, the staff found that based on different genders, when men and women sit on the seat, the second difference between the pressure on the rear side and the pressure on the front side of the seat is Show obvious difference.

[0067] Based on this, this embodiment makes a correction based on the gender factor for the formula for calculating the second difference in the second case.

[0068] The specific replacement is as follows: each seat is configured with the user's gender and uploaded to the control module.

[0069] Calculate the second difference between the pressure on the rear side and the pressure on the front side of the seat .

[0070]

[0071] in, Represents the pressure on the back of the chair seat; Represents the front pressure of the chair seat; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, rear right partition, front left partition, and front right partition; Represents the first time period; Represents a time point in the first time period i the number of Preferably, when the user is male, the gender factor b=40N; when the user is female, the gender factor b=10N.

[0072] The second embodiment can eliminate the error caused by the difference in body shape between men and women in determining whether the sitting posture is tilted forward.

[0073] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved. This is not limited herein.

[0074] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0075] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A sitting posture detection system based on pressure zoning, characterized in that: include: A seat, comprising a seat surface and a seat back, wherein the seat surface is divided into a plurality of partitions, each partition being provided with a first pressure sensor for detecting seat surface pressure within the corresponding partition, and the seat back being provided with a second pressure sensor for detecting seat back pressure; a sitting posture distinguishing module, which distinguishes whether the user is in an upright sitting posture or a back-rest sitting posture according to the chair back pressure; The control module is configured to analyze the seat surface pressure using a first strategy to determine whether the user's sitting posture is tilted left or right or tilted forward in the upright sitting posture; and to analyze the seat surface pressure and the seat back pressure together to determine whether the user's sitting posture is tilted left or right in the backrest sitting posture; The alarm sounds an alarm when it is determined that the sitting posture is tilted left to right and / or tilted forward.

2. The sitting posture detection system based on pressure zoning according to claim 1, characterized in that: The distinguishing method of the sitting posture distinguishing module is as follows: Obtain all chair back pressures measured in a recent first time period, count a first number of chair back pressures greater than a preset back pressure threshold, and divide the first number by the total number of chair back pressures to obtain a first ratio. If the first ratio is greater than a fixed ratio threshold, determine that the user is in a reclining sitting position; otherwise, determine that the user is in an upright sitting position.

3. The sitting posture detection system based on pressure zoning according to claim 1, characterized in that: There are four partitions in total, including a front left partition, a front right partition, a rear left partition, and a rear right partition.

4. The sitting posture detection system based on pressure zoning according to claim 3, characterized in that: In the upright sitting posture, the method of using the first strategy to analyze the pressure of the chair surface to determine whether the user's sitting posture is tilted left or right is as follows: Obtain all seat surface pressures within the first time period; Calculate the first difference between the pressure on the left and right sides of the seat ; in, Represents the pressure on the left side of the chair seat; Represents the right side pressure of the chair seat; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, front left partition, rear right partition, and front right partition; Represents the first time period; Represents a time point in the first time period i the number of The first difference Compared with the set first threshold, if the first difference If the value is greater than the first threshold, it is determined that the user is leaning left or right; otherwise, it is determined that the user is keeping straight in front of the camera.

5. A sitting posture detection system based on pressure zoning according to claim 3 or 4, characterized in that: In the upright sitting posture, the method of using the first strategy to analyze the pressure of the chair surface to determine whether the user's sitting posture is tilted forward is as follows: Calculate the second difference between the pressure on the rear side and the pressure on the front side of the seat ; in, Represents the pressure on the back of the chair seat; Represents the front pressure of the chair seat; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, rear right partition, front left partition, and front right partition; Represents the first time period; Represents a time point in the first time period i the number of The second difference Compared with the set second threshold, if the second difference If the value is less than the second threshold, it is determined that the user is leaning forward; otherwise, the user remains upright on the side.

6. The sitting posture detection system based on pressure zoning according to claim 5, characterized in that: When the user maintains correct posture both in the front and side directions, the user is judged to be sitting in an upright position.

7. The sitting posture detection system based on pressure zoning according to claim 3, characterized in that: In the backrest sitting posture, the method of using the second strategy to jointly analyze the seat surface pressure and the seat back pressure to determine whether the user's sitting posture is in a left-right tilted sitting posture is as follows: Calculate the third difference between the pressure on the left and right sides of the seat ; in, Represents the pressure on the left side of the chair seat; Represents the right side pressure of the chair seat; Represents chair back pressure; 、 、 、 Represents the time points i The measured seat surface pressures in the rear left partition, front left partition, rear right partition, and front right partition; represents the seat back pressure measured at time point i; Represents the correction factor of the pressure difference between the seat back and the left and right sides of the seat surface; Represents the first time period; Represents a time point in the first time period i the number of The third difference Compared with the set first threshold, if the third difference If the value is greater than the first threshold, it is determined that the user is leaning left or right; otherwise, it is determined that the user is sitting upright in a backrest sitting position.

8. The sitting posture detection system based on pressure zoning according to claim 7, characterized in that: The correction coefficient k ranges from 0.05 to 0.

1.

9. The sitting posture detection system based on pressure zoning according to claim 2, characterized in that: Before distinguishing between upright sitting and reclining sitting, it is also determined whether the user is sitting on the seat: Obtaining several seat surface pressure arrays measured within a recent second time period, each seat surface pressure array including seat surface pressures in all partitions; counting a second number of seat surface pressure arrays in which the seat surface pressures in all partitions are greater than a set surface pressure threshold; and dividing the second number by the total number of seat surface pressure arrays to obtain a second ratio. If the second ratio is greater than a fixed ratio threshold, it is determined that the user is sitting on the seat.

10. The sitting posture detection system based on pressure zoning according to claim 3, characterized in that: The partitioning method is as follows: taking the center point of the chair surface as the intersection point, two mutually perpendicular straight lines are drawn respectively, thereby dividing the chair surface into a front left partition, a front right partition, a rear left partition, and a rear right partition.

Images