Posture supervision method and device, equipment and computer readable storage medium

Abstract

The application discloses a posture supervision method and device, equipment and a computer readable storage medium, the posture supervision method comprises: acquiring a current posture graph, and detecting whether the current posture graph matches a preset standard posture graph; if not, determining a current error posture according to the current posture graph and the standard posture graph; and controlling the running state of a display terminal and outputting a reminder according to the current error posture. The application can determine whether the current posture of a user is consistent with the standard posture through the standard posture graph and the current posture graph, thereby monitoring whether the current posture is standard in real time. When the current error posture occurs, the current error posture is determined and timely reminded, and the running state of the display terminal is controlled to assist in correction, thereby realizing real-time supervision and reminding of the posture of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of posture supervision, and particularly relates to a posture supervision method, device and equipment and a computer readable storage medium. BACKGROUND

[0002] Long-term improper posture can have certain impact on health, especially for teenagers who are in the key period of physical development. No matter sitting posture, standing posture or lying posture, teenagers need to pay extra attention. A wrong posture for a long time can easily affect the vision of teenagers, cause myopia, and even cause spinal deformation and slight displacement, thereby affecting growth and development. The self-control of teenagers is often poor, and parents are also difficult to remind them at all times. Some wrong postures of teenagers have not been corrected in time. Therefore, how to supervise and remind the posture of a user in real time is a technical problem to be solved at present. SUMMARY

[0003] The main purpose of the present application is to provide a posture supervision method, device, equipment and computer readable storage medium, which aims to solve the technical problem of how to supervise and remind the posture of a user in real time.

[0004] To achieve the above purpose, the present application provides a posture supervision method, which comprises:

[0005] Obtaining a current posture graph and detecting whether the current posture graph matches a preset standard posture graph;

[0006] If not, determining a current error posture according to the current posture graph and the standard posture graph;

[0007] Controlling the running state of a display terminal and outputting a reminder according to the current error posture.

[0008] Optionally, the step of determining a current error posture according to the current posture graph and the standard posture graph comprises:

[0009] Obtaining a current posture height in the current posture graph and determining a standard posture height in the standard posture graph;

[0010] Calculating the difference between the standard posture height and the current posture height;

[0011] If the difference between the standard posture height and the current posture height exceeds a preset height difference value, and the current posture height is less than the standard posture height, it is determined that the current error posture is bending the waist and hunching the back.

[0012] Optionally, the step of determining a current error posture according to the current posture graph and the standard posture graph comprises:

[0013] determine standard skeleton key points according to the standard pose graph, and obtain current skeleton key points in the current pose graph;

[0014] determine a current error pose according to the current skeleton key points and the standard skeleton key points.

[0015] Optionally, the step of determining the current error pose according to the current skeleton key points and the standard skeleton key points comprises:

[0016] determine face feature key points in the current skeleton key points, the face feature key points comprising first face key points and second face key points;

[0017] obtain a first distance between the first face key points and the second face key points, and obtain a second distance between a user and a display terminal;

[0018] calculate a current face tilt angle according to the first distance and the second distance, and determine a standard face tilt angle according to the standard skeleton key points;

[0019] determine a current error pose according to the current face tilt angle and the standard face tilt angle.

[0020] Optionally, the step of determining the current error pose according to the current skeleton key points and the standard skeleton key points comprises:

[0021] determine current leg key points in the current skeleton key points, and obtain standard leg key points in the standard skeleton key points;

[0022] calculate a leg deviation value between the current leg key points and the standard leg key points;

[0023] determine a current error pose according to the leg deviation value.

[0024] Optionally, the step of determining the current error pose according to the leg deviation value comprises:

[0025] if the leg deviation value is greater than a preset leg deviation value, obtain a current relative position between a current left ankle key point and a current right ankle key point in the current leg key points;

[0026] obtain a standard relative position between a standard left ankle key point and a standard right ankle key point in the standard leg key points, and determine whether the current relative position is opposite to the standard relative position;

[0027] if the current relative position is opposite to the standard relative position, determine that the current error pose is cross-over legs.

[0028] Optionally, before the step of determining a current error posture according to the current posture graph and the standard posture graph, the method further comprises:

[0029] identifying current facial feature information, and matching the current facial feature information with preset facial feature information;

[0030] If target facial feature information matching the current facial feature information exists in the preset facial feature information, a preset standard posture graph corresponding to the target facial feature information is taken as the standard posture graph.

[0031] In addition, to achieve the above object, the present application further provides a posture supervision device, which comprises:

[0032] a picture matching module, configured to acquire a current posture graph and detect whether the current posture graph matches a preset standard posture graph;

[0033] a posture determination module, configured to determine a current error posture according to the current posture graph and the standard posture graph if the current posture graph does not match the standard posture graph;

[0034] a posture reminding module, configured to control the running state of a display terminal and output a reminder according to the current error posture.

[0035] In addition, to achieve the above object, the present application further provides a posture supervision device, which comprises a memory, a processor, and a posture supervision program stored in the memory and executable on the processor, and the posture supervision program implements the steps of the posture supervision method when executed by the processor.

[0036] In addition, to achieve the above object, the present application further provides a computer readable storage medium, which stores a posture supervision program, and the posture supervision program implements the steps of the posture supervision method when executed by the processor.

[0037] The present application provides a posture supervision method, device, equipment and computer readable storage medium, according to the current error posture control display terminal running state and output reminder by acquiring current posture graph, and further detecting whether the current posture graph matches the preset standard posture graph, if not matching, according to the current posture graph and the standard posture graph to determine the current error posture, so as to control the running state of the display terminal and output the reminder according to the current error posture. Through the matching between the standard posture graph and the current posture graph, it can be judged whether the current posture of the user is consistent with the standard posture, so that the current posture can be monitored in real time, and when the current error posture appears, the current error posture is determined and timely reminded, and the running state of the display terminal is controlled to assist in correcting, realizing the real-time supervision and reminding of the user posture. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 is the structural schematic diagram of the device of the hardware running environment related to the embodiment scheme of the present application.

[0039] Figure 2 is the flowchart of the first embodiment of the posture supervision method of the present application.

[0040] Figure 3 is the device structure schematic diagram of the posture supervision device of the present application.

[0041] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0042] It should be noted that the description of "first", "second" and the like in the present application is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the technical features indicated or implicitly indicating the number of technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor within the scope of protection required by the present application.

[0043] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0044] Referring to Figure 1 , Figure 1 is the structural schematic diagram of the device of the hardware running environment related to the embodiment scheme of the present application.

[0045] The embodiment of the present application can be set as PC (personal computer), portable computer, intelligent desk and intelligent desk lamp and other terminal devices.

[0046] As Figure 1As shown, the posture supervision device can include a processor 1001, such as a CPU (Central Processing Unit), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection communication between the components. The user interface 1003 can include a display, an input unit such as a keyboard, and optionally a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as WIreless-FIdelity (WI-FI)). The memory 1005 can be a high-speed random access memory (RAM) memory, or a stable non-volatile memory (NVM), such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0047] Those skilled in the art can understand that Figure 1 The structure shown in the figure does not constitute a limitation on the device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0048] As Figure 1 As shown, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and a posture supervision program.

[0049] In Figure 1 In the device shown, the network interface 1004 is mainly used to connect to a background server and communicate data with the background server; the user interface 1003 is mainly used to connect to a client (user end) and communicate data with the client; and the processor 1001 can be used to call the screen projection control program stored in the memory 1005 and perform the following operations:

[0050] Obtain a current posture graph and detect whether the current posture graph matches a preset standard posture graph;

[0051] If not, determine a current error posture according to the current posture graph and the standard posture graph;

[0052] Control the running state of the display terminal according to the current error posture and output a reminder.

[0053] Based on the above hardware structure, various embodiments of the posture supervision method are proposed.

[0054] The embodiment of the present application provides a posture supervision method, which is described with reference toFigure 2 , Figure 2 Figure 1 is a flowchart of a first embodiment of the posture supervision method of the present application.

[0055] In the embodiment, the posture supervision method comprises:

[0056] In step S10, a current posture graph is acquired, and it is detected whether the current posture graph matches a preset standard posture graph.

[0057] The execution subject of the embodiment can be a display terminal such as a smart TV, a smart desk or a personal computer. In the embodiment, the smart TV is taken as an example for illustration. The smart TV can comprise a camera. In the embodiment, the camera can be one or more. The current posture graph is acquired by the camera. In the embodiment, the standard posture graph can also be self-defined and input by the camera before the current posture graph is acquired. The input standard posture graph is taken as the preset standard posture graph. First, the standard posture graph is input by the camera. The standard posture graph is used as a reference for comparison with the subsequent current posture graph, and then the current posture graph is acquired. In the embodiment, a general standard posture graph can also be preset. The general standard posture graph is directly compared with the subsequent current posture graph. In the embodiment, the specific process of inputting the standard posture graph can comprise: if the user is using for the first time, a standard posture guide frame is output. The standard posture graph is input according to the prompt of the standard posture guide frame. The standard posture graph of multiple angles corresponding to different postures is input. The different postures comprise a standing posture and a sitting posture. The multiple angles can be set according to actual conditions. In the embodiment, the multiple angles comprise three angles of a front view, a left view and a right view of the user. The standard posture graph of different postures at different angles is acquired. The standard posture graph of multiple angles corresponding to different postures comprises a front view, a left view and a right view of the standing posture, and a front view, a left view and a right view of the sitting posture. Then, the posture information of the user can be acquired according to the standard posture graph, such as the contour information of the user and the distance between the user and the display terminal. When the user uses, the current posture graph is acquired. It is detected whether the current posture graph matches the standard posture graph. If the current posture graph matches the standard posture graph, it means that the current posture graph basically agrees with the standard posture graph, i.e. the current posture is a standard posture. At this time, it is continuously detected whether the current posture graph matches the standard posture graph. If the current posture graph does not match the standard posture graph, it means that the current posture graph deviates from the standard posture graph, i.e. the current posture is not a standard posture. At this time, the current error posture can be further determined according to the current posture graph and the standard posture graph.

[0058] In the embodiment, since there may be deviation due to different angles by single-frame picture comparison, for example, there is high and low shoulder, etc., the embodiment can obtain a more accurate three-dimensional standard posture graph through the standard posture graphs of multiple angles, thereby improving the accuracy of subsequent judgment of whether the current posture is correct according to the current posture graph and the standard posture graph, and in the embodiment, the standard posture of the user is recorded by the camera, different standard postures are obtained according to different body structures of the user, and the standard posture is self-defined, which is more flexible.

[0059] In step S20, if the current posture graph and the standard posture graph are not matched, the current error posture is determined according to the current posture graph and the standard posture graph.

[0060] In step S30, the running state of the display terminal is controlled according to the current error posture, and a reminder is output.

[0061] In the embodiment, the current posture graph of the user can be collected in real time by the camera, and the current posture graph and the standard posture graph are matched to determine whether the current posture is correct. If the current posture graph and the standard posture graph are matched, it indicates that the current posture is correct, and the current posture graph and the standard posture graph are continuously matched. If the current posture graph and the standard posture graph are not matched, it indicates that the current posture is incorrect, and the current error posture is determined. As a matching method, the user outlines in the current posture graph and the standard posture graph can be compared. If the deviation between the user outlines exceeds a preset value (for example, 10%), it is determined that the current posture graph and the standard posture graph are not matched, that is, the current posture is incorrect, and the current error posture is determined as a non-standard posture. At the same time, the running state of the display terminal is controlled and a reminder is output. In the embodiment, the process of controlling the running state of the display terminal and outputting the reminder according to the current error posture can be that the display terminal is controlled to pause running, the camera of the display terminal is controlled to be opened, and the standard posture graph and the correction reminder corresponding to the current error posture are output. When the user adjusts the current posture to coincide with the standard posture in the standard posture graph, the display terminal is controlled to normally run. The output correction reminder makes the user adjust to the standard posture again, so that the child forms a good posture habit. In another embodiment, before the step of controlling the running state of the display terminal and outputting the reminder according to the current error posture, the maintenance time length of the current error posture can be detected. When the maintenance time length exceeds a preset time length, the running state of the display terminal is controlled and a reminder is output. In the embodiment, the current posture can also be obtained by infrared or radar, etc.

[0062] In the embodiment, by inputting a standard posture picture, whether the current posture of the user is consistent with the standard posture can be determined by matching the standard posture picture with the current posture picture, so that whether the current posture is standard can be monitored in real time. If the current posture picture does not match the standard posture picture, it means that an error posture occurs, the current error posture is determined and a standard posture (sitting posture or standing posture) picture is output for prompting. After the posture of the user overlaps with the posture in the standard posture picture, the user can continue to watch the movie, so as to correct the sitting posture or standing posture and timely remind and control the running state of the display terminal to assist in correction, thereby realizing real-time supervision and reminding of the posture of the user.

[0063] Further, based on the first embodiment, the second embodiment of the posture supervision method is provided. In the embodiment, the step S20 includes the following steps:

[0064] Step A, acquiring the current posture height in the current posture picture and determining the standard posture height in the standard posture picture;

[0065] Step B, calculating the difference between the standard posture height and the current posture height;

[0066] Step C, if the difference exceeds the preset height difference and the current posture height is less than the standard posture height, determining that the current error posture is bending and hunching back.

[0067] In the embodiment, the current posture height in the current posture picture is acquired and the standard posture height in the standard posture picture is determined, and then the difference between the standard posture height and the current posture height is calculated. The current error posture can be determined according to the difference between the standard posture height and the current posture height. Specifically, if the difference exceeds the preset height difference and the current posture height is less than the standard posture height, it means that the height of the current posture of the user is less than the height of the corresponding standard posture, and the error posture of bending and hunching back may occur. Therefore, the current error posture is determined to be bending and hunching back, and a correction reminder corresponding to bending and hunching back is output. Specifically, the current posture height can include a current standing posture height and a current sitting posture height, and the standard posture height includes a standard standing posture height and a standard sitting posture height. The step of acquiring the current posture height in the current posture picture and determining the standard posture height in the standard posture picture can further include: judging the posture in the current posture picture; if the posture in the current posture picture is a standing posture, acquiring the current standing posture height, taking the current standing posture height as the current posture height, and determining the standard standing posture height, taking the standard standing posture height as the standard posture height; and if the posture in the current posture picture is a sitting posture, acquiring the current sitting posture height, taking the current sitting posture height as the current posture height, and determining the standard sitting posture height, taking the standard sitting posture height as the standard posture height.

[0068] In the embodiment, the height of the posture in the posture graph can be used to determine whether the user has a wrong posture of bending over, and the user can be reminded to correct the bad posture habit of bending over. In addition, the sitting and standing postures of the user are considered, and the posture of the user is supervised and reminded more comprehensively through various postures.

[0069] Further, based on the first embodiment, a third embodiment of the posture supervision method is provided. In the third embodiment, the step S20 of determining the current wrong posture according to the current posture graph and the standard posture graph includes:

[0070] Step D, determining the standard skeleton key point according to the standard posture graph, and obtaining the current skeleton key point in the current posture graph;

[0071] Step E, determining the current wrong posture according to the current skeleton key point and the standard skeleton key point.

[0072] In the embodiment, the human skeleton key point mainly includes the joints and facial features of the human body, and the human skeleton information can be described through the key point. The standard skeleton key point can be determined through the preset standard posture graph, and the current skeleton key point in the current posture graph can be obtained through the current posture graph. The head, neck, shoulder, elbow, wrist, waist, knee, ankle, and thigh root of the human body can be detected through the top-down detection and bottom-up detection methods. The current wrong posture can be determined according to the current skeleton key point and the standard skeleton key point. The deviation value between the current skeleton key point and the standard skeleton key point can be calculated, and the current posture can be determined according to the deviation value. If the current posture is determined to be incorrect, the current wrong posture is further determined. In the embodiment, the deviation between the current skeleton key point and the standard skeleton key point can be detected before the current wrong posture is determined according to the current skeleton key point and the standard skeleton key point. When the deviation is greater than or equal to the preset deviation, the current wrong posture is determined. If the deviation is less than the preset deviation, the current posture graph and the preset standard posture graph are continuously detected to determine whether they match, thereby avoiding the inconvenience caused by the user's slight action, the suspension of the running of the terminal, and the frequent reminders.

[0073] In the embodiment, the skeleton key point in the standard posture image can be determined to know the specific non-standard local posture details of the user, so that the user can develop a correct posture habit.

[0074] Further, the step E of determining the current wrong posture according to the current skeleton key point and the standard skeleton key point includes:

[0075] Step e1, determining face feature key points in the current skeleton key points, the face feature key points including a first face key point and a second face key point;

[0076] Step e2, obtaining a first distance between the first face key point and the second face key point, and obtaining a second distance between the user and the display terminal;

[0077] Step e3, calculating a current face tilt angle according to the first distance and the second distance, and determining a standard face tilt angle according to the standard skeleton key points;

[0078] Step e4, determining a current error posture according to the current face tilt angle and the standard face tilt angle.

[0079] In the embodiment, the current error posture can include a current error posture corresponding to the head. First, face feature key points in the current skeleton key points are determined, the face feature key points including a first face key point and a second face key point. A first distance between the first face key point and the second face key point is obtained, and a second distance between the user and the display terminal is obtained. A current face tilt angle is calculated according to the first distance and the second distance. The first face key point and the second face key point can be selected from the eyebrows, eyes, nose and mouth respectively. For example, the first face key point is the eye, and the second face key point is any one of the eyebrows, nose and mouth. A vertical line segment between the first face key point and the second face key point is obtained, and the length of the vertical line segment is taken as the first distance. A horizontal line segment between the user and the display terminal is obtained, and the length of the horizontal line segment is taken as the second distance. The angle between the display terminal and the first face key point and the second face key point is calculated by the Pythagorean theorem and the first distance and the second distance, and the angle is taken as the current face tilt angle. At the same time, a standard face tilt angle is determined according to the standard skeleton key points. The process of determining the standard face tilt angle according to the standard skeleton key points is similar to the process of determining the current face tilt angle according to the current skeleton key points, which is not described here. When the user bends down or looks up, the current face tilt angle deviates from the standard face tilt angle. Therefore, in the embodiment, the angle deviation value between the current face tilt angle and the standard face tilt angle is calculated. If the angle deviation value exceeds a preset angle deviation threshold, it is determined that the current error posture is bending down or looking up. In the embodiment, a neck key point and a head key point in the current skeleton key points can also be obtained. The distance between the neck key point and the head key point is calculated. If the distance between the neck key point and the head key point is less than a preset distance value, the closer the distance between the head and the neck, the greater the amplitude of the bending down. At this time, it can be determined that the current error posture is bending down.

[0080] In the embodiment, the step of determining the current error posture according to the current face tilt angle and the standard face tilt angle can further include: determining left eye key points and right eye key points in the current skeleton key points, and if the relative position between the left eye key points and the right eye key points is not horizontal, it indicates that there is an angle deviation between the left eye and the right eye, and the error posture of tilting the head can occur, and then it is determined that the current posture is incorrect, and the current error posture is determined as tilting the head. The current error posture of tilting the head can also be determined by determining left ear key points and right ear key points in the current skeleton key points, and the determination process is the same as that of determining the current error posture by the two eyes, which will not be described herein. In the embodiment, neck key points, head key points, left shoulder key points and right shoulder key points in the current skeleton key points can also be obtained, and if the distance between the neck key points or the head key points and the left shoulder key points and the right shoulder key points is too large or too small, it indicates that the head is tilted to the left shoulder or the right shoulder, and at this time, the current error posture can be determined as tilting the head.

[0081] In the embodiment, the face feature key points in the posture graph can be used to determine the current error posture of the head, so that the user can be reminded to correct the bad posture habits of tilting the head, lowering the head and raising the head in time.

[0082] Further, the detailed steps of step E of calculating the deviation value between the current skeleton key points and the standard skeleton key points and determining whether the current posture is correct according to the deviation value include:

[0083] Step e5, determining current leg key points in the current skeleton key points, and obtaining standard leg key points in the standard skeleton key points;

[0084] Step e6, calculating a leg deviation value between the current leg key points and the standard leg key points;

[0085] Step e7, determining the current error posture according to the leg deviation value.

[0086] In the embodiment, the current error posture can include the current error posture of the leg, the current leg key points in the current skeleton key points are determined, the standard leg key points in the standard skeleton key points are obtained, and then the leg deviation value between the current leg key points and the standard leg key points is calculated, and the current error posture is determined according to the leg deviation value. Specifically, the leg deviation value can be calculated by the current leg coordinate position of the current leg key points in the current posture graph and the standard leg coordinate of the standard leg key points in the standard posture graph, and if the deviation value between the current leg coordinate position and the standard leg coordinate position is greater than a preset leg deviation value, it is determined that the current posture is incorrect, and the current error posture is determined as the non-standard posture. The current leg key points and the standard leg key points can each include leg key points such as knee key points and ankle key points.

[0087] Further, the step e7 of determining the current error posture according to the leg deviation value comprises:

[0088] The step e71 of obtaining the current relative position between the current left ankle key point and the current right ankle key point in the current leg key point if the leg deviation value is greater than the preset leg deviation value;

[0089] The step e72 of obtaining the standard relative position between the standard left ankle key point and the standard right ankle key point in the standard leg key point, and determining whether the current relative position is opposite to the standard relative position;

[0090] The step e73 of determining the current error posture as cross-over legs if the current relative position is opposite to the standard relative position.

[0091] In the embodiment, the specific process of determining the current error posture according to the leg deviation value can be: if the leg deviation value is greater than the preset leg deviation value, it indicates that the current posture deviates from the standard posture, it is determined that the current posture is incorrect, and the current error posture is further determined. Therefore, the current relative position between the current left ankle key point and the current right ankle key point in the current leg key point can be obtained, the standard relative position between the standard left ankle key point and the standard right ankle key point in the standard leg key point can be obtained, and it is determined whether the current relative position is opposite to the standard relative position. If the current relative position is opposite to the standard relative position, it indicates that the left leg and the right leg appear a cross-over posture, and the current error posture is determined as cross-over legs. The left ankle key point and the right ankle key point in the current leg key point are determined, the relative position between the left ankle key point and the right ankle key point is determined according to the coordinates corresponding to the left ankle key point and the right ankle key point, and then it is directly determined whether the left leg and the right leg appear cross-over according to the relative position between the left ankle key point and the right ankle key point. If cross-over appears, the error posture of cross-over legs can appear, and the current posture is determined as cross-over legs, and it is determined that the current posture is incorrect.

[0092] In the embodiment, if the leg deviation value is greater than the preset leg deviation value, the first connecting line between the left ankle key point and the left knee key point in the current leg key point and the second connecting line between the right ankle key point and the right knee key point can also be obtained. It is determined whether the first connecting line and the second connecting line have an intersection point. If the first connecting line and the second connecting line have an intersection point, it indicates that the left leg and the right leg appear cross-over, and the current error posture is determined as cross-legged.

[0093] Further, the detailed step of determining the current error posture according to the current skeleton key point and the standard skeleton key point in the above step E can further comprise:

[0094] Step e8, a current shoulder key point in the current skeleton key point is obtained, and a standard shoulder key point in the standard skeleton key point is determined;

[0095] Step e9, a deviation value between the current shoulder key point and the standard shoulder key point is calculated, if the deviation value between the current shoulder key point and the standard shoulder key point exceeds a preset deviation value, a current left shoulder key point and a current right shoulder key point in the current shoulder key point are obtained;

[0096] Step e10, if a height between the current left shoulder key point and the current right shoulder key point is inconsistent, the current error posture is determined as body leaning.

[0097] In the embodiment, the current error posture can include a current error posture corresponding to the shoulder, a current shoulder key point in the current skeleton key point is obtained, a standard shoulder key point in the standard skeleton key point is determined, and then a deviation value between the current shoulder key point and the standard shoulder key point is calculated, if the deviation value between the current shoulder key point and the standard shoulder key point exceeds a preset deviation value, it indicates that the current posture deviates greatly compared with the standard posture, and then a current left shoulder key point and a current right shoulder key point in the current shoulder key point are further obtained, if a height between the current left shoulder key point and the current right shoulder key point is inconsistent, it indicates that the error posture of body leaning may occur, and the current error posture is determined as body leaning, and further, if horizontal positions of the left shoulder key point and the current right shoulder key point are inconsistent, the error posture of double shoulder forward and backward leaning may occur, and the current error posture is determined as double shoulder forward and backward leaning.

[0098] In the embodiment, a head key point and a shoulder key point in the current skeleton key point can also be obtained, a distance between the head key point and the shoulder key point is calculated, a standard distance between a standard head key point and a standard shoulder key point in the standard skeleton key point is obtained, if the distance between the head key point and the shoulder key point is less than the standard distance, it indicates that the error posture of head sinking or double shoulder lifting may occur, and the current error posture can be determined as shoulder lifting.

[0099] Further, before the step S20 of determining the current error posture according to the current posture graph and the standard posture graph, the step further includes:

[0100] Step F, a current face feature information is recognized, and the current face feature information is matched with preset face feature information;

[0101] Step G, if target face feature information matching the current face feature information exists in the preset face feature information, a preset standard posture graph corresponding to the target face feature information is taken as the standard posture graph.

[0102] In the embodiment, before determining the current error posture according to the current posture graph and the standard posture graph, the current facial feature information can be recognized first, and then the current facial feature information is matched with the preset facial feature information, the preset facial feature information is one or more facial ids and the preset standard posture graph corresponding to each facial id, if the target facial feature information matching the current facial feature information exists in the preset facial feature information, the preset standard posture graph corresponding to the target facial feature information is taken as the standard posture graph. For example, before monitoring the posture of user a, the current facial feature information of user a is recognized first, and then the current facial feature information of user a is matched with the preset facial feature information, if the target facial feature information (the facial id of user a) matching the current facial feature information of user a exists in the preset facial feature information, the target facial feature information can be the facial id, and then the preset standard posture graph corresponding to the facial id of user a is taken as the standard posture graph, so as to facilitate the subsequent step of determining the current error posture by the standard posture graph and the current posture graph.

[0103] Further, the embodiment can further acquire the distance between the current user and the display terminal according to the current posture graph, if the distance between the current user and the display terminal is less than the preset distance range, it is indicated that the user is too close to the display terminal, and the current error posture is determined as being too close.

[0104] Further, after determining the current error posture according to the current posture graph and the standard posture graph, the embodiment accumulates the occurrence frequency of the current error posture, if the preset frequency is exceeded within the preset time, a prompt message is automatically output to the mobile terminal, which can be the mobile phone of the parent bound with the display terminal (such as a smart television), the parent can select to control whether the current television allows the child to continue watching. The embodiment can realize remote management, when the user triggers the upper limit of the sitting or standing posture reminder, the prompt message is output to notify the parent, and the parent determines whether the child is allowed to continue watching the television, so as to assist the child to develop good posture habits. The embodiment inputs the standard posture of the child through the camera, and after the child watches the television, the posture of the child is automatically detected and compared with the standard posture, when the posture of the child is incorrect, the child is automatically paused and cannot continue to watch. When the child restores the normal posture, the television restores the playing. When the child triggers more than the preset reminding frequency in a day, the message is sent to the mobile phone bound with the parent, and the parent can control whether the television is locked to prevent the child from watching. In the long run, the purpose of ensuring the healthy development of the skeleton of the child is achieved.

[0105] The application also provides a posture supervision device, such as Figure 3The posture supervision device comprises a picture matching module A10, which is configured to acquire a current posture picture and detect whether the current posture picture matches a preset standard posture picture; a posture determination module A20, which is configured to determine a current error posture according to the current posture picture and the standard posture picture if the current posture picture does not match the standard posture picture; and a posture reminding module A30, which is configured to control a running state of a display terminal according to the current error posture and output a reminder of the posture supervision device. The specific embodiments of the posture supervision device are basically the same as those of the posture supervision method, and thus are not described herein again.

[0106] The posture supervision device comprises a memory, a processor, and a posture supervision program stored in the memory and executable on the processor, and the posture supervision program is configured to implement the steps of the posture supervision method according to any one of the above embodiments when executed by the processor. The specific embodiments of the posture supervision device are basically the same as those of the posture supervision method, and thus are not described herein again.

[0107] The posture supervision device comprises a memory, a processor, and a posture supervision program stored in the memory and executable on the processor, and the posture supervision program is configured to implement the steps of the posture supervision method according to any one of the above embodiments when executed by the processor. The specific embodiments of the posture supervision device are basically the same as those of the posture supervision method, and thus are not described herein again.

[0108] It can be understood that, in the description of the present specification, the description of the terms "an embodiment", "another embodiment", "other embodiments", or "a first embodiment to an Nth embodiment" means that the specific features, structures, materials or characteristics described in combination with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0109] It should be noted that, in this paper, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or system. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0110] The above embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0111] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, of course, can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk) as described above, and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in various embodiments of the present application.

[0112] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A pose supervision method, characterized in that, The posture supervision method comprises the steps of: obtaining a current posture graph and detecting whether the current posture graph matches a preset standard posture graph; if not, determining a current error posture according to the current posture graph and the standard posture graph; controlling the running state of a display terminal and outputting a reminder according to the current error posture; the step of determining the current error posture according to the current posture graph and the standard posture graph comprises: determining standard skeleton key points according to the standard posture graph and obtaining current skeleton key points in the current posture graph; determining the current error posture according to the current skeleton key points and the standard skeleton key points; the step of determining the current error posture according to the current skeleton key points and the standard skeleton key points comprises: obtaining a current shoulder key point in the current skeleton key points and determining a standard shoulder key point in the standard skeleton key points; calculating a deviation value between the current shoulder key point and the standard shoulder key point, if the deviation value between the current shoulder key point and the standard shoulder key point exceeds a preset deviation value, obtaining a current left shoulder key point and a current right shoulder key point in the current shoulder key point; if the height between the current left shoulder key point and the current right shoulder key point is inconsistent, determining that the current error posture is body tilting; if the horizontal positions of the left shoulder key point and the current right shoulder key point are inconsistent, determining that the current error posture is double-shoulder forward and backward tilting; obtaining a standard distance between a standard head key point and a standard shoulder key point in the standard skeleton key points, if the distance between the head key point and the shoulder key point is less than the standard distance, determining that the current error posture is shoulder raising; wherein, the input process of the preset standard posture graph comprises: inputting a standard posture graph corresponding to a plurality of angles of different postures according to the prompt of the standard posture guide frame, wherein the different postures include standing posture and sitting posture, and the plurality of angles include front, left side and right side of the user.

2. The pose supervision method of claim 1, wherein, The step of determining the current error posture according to the current posture graph and the standard posture graph comprises: obtaining a current posture height in the current posture graph and determining a standard posture height in the standard posture graph; calculating a difference value between the standard posture height and the current posture height; if the difference value exceeds a preset height difference value and the current posture height is less than the standard posture height, determining that the current error posture is bending and bending.

3. The pose supervision method of claim 1, wherein, The step of determining the current error posture according to the current skeleton key points and the standard skeleton key points further comprises: determining face feature key points in the current skeleton key points, the face feature key points comprising a first face key point and a second face key point; obtaining a first distance between the first face key point and the second face key point and obtaining a second distance between the user and the display terminal; calculating a current face tilt angle according to the first distance and the second distance, and determining a standard face tilt angle according to the standard skeleton key points; determining the current error posture according to the current face tilt angle and the standard face tilt angle.

4. The pose supervision method of claim 1, wherein, The step of determining the current error posture according to the current skeleton key points and the standard skeleton key points further comprises: determine a current leg key point in the current skeleton key points, and obtain a standard leg key point in the standard skeleton key points; calculate a leg deviation value between the current leg key point and the standard leg key point; determine a current error posture according to the leg deviation value.

5. The pose supervision method of claim 4, wherein, The step of determining the current error posture according to the leg deviation value comprises: if the leg deviation value is greater than a preset leg deviation value, obtain a current relative position between a current left ankle key point and a current right ankle key point in the current leg key point; obtain a standard relative position between a standard left ankle key point and a standard right ankle key point in the standard leg key point, and determine whether the current relative position is opposite to the standard relative position; if the current relative position is opposite to the standard relative position, determine that the current error posture is cross-over legs.

6. The pose supervision method of claim 1, wherein, Before the step of determining the current error posture according to the current posture graph and the standard posture graph, the method further comprises: recognize current facial feature information, and match the current facial feature information with preset facial feature information; if target facial feature information matching the current facial feature information exists in the preset facial feature information, take a preset standard posture graph corresponding to the target facial feature information as the standard posture graph.

7. A posture supervising apparatus characterized by comprising: The posture supervision device comprises: a picture matching module, configured to obtain a current posture graph, and detect whether the current posture graph matches a preset standard posture graph, wherein a preset standard posture graph recording process comprises: recording standard posture graphs corresponding to multiple angles according to a prompt of a standard posture guide frame, wherein different postures comprise a standing posture and a sitting posture, and the multiple angles comprise a front, a left side and a right side of a user; a posture determination module, configured to determine a current error posture according to the current posture graph and the standard posture graph if the current posture graph does not match the standard posture graph; a posture reminding module, configured to control an operation state of a display terminal and output a reminder according to the current error posture; The posture determination module is further configured to determine standard skeleton key points according to a standard posture graph, and obtain current skeleton key points in a current posture graph; and determine a current error posture according to the current skeleton key points and the standard skeleton key points. The posture determination module is further configured to obtain a current shoulder key point in the current skeleton key points, and determine a standard shoulder key point in the standard skeleton key points; calculate a deviation value between the current shoulder key point and the standard shoulder key point, obtain a current left shoulder key point and a current right shoulder key point in the current shoulder key point if the deviation value between the current shoulder key point and the standard shoulder key point exceeds a preset deviation value; determine that a current error posture is body tilting if a height between the current left shoulder key point and the current right shoulder key point is inconsistent; determine that the current error posture is double-shoulder front and back tilting if horizontal positions of the left shoulder key point and the current right shoulder key point are inconsistent; obtain a standard distance between a standard head key point and the standard shoulder key point in the standard skeleton key points, and determine that the current error posture is shoulder raising if a distance between the head key point and the shoulder key point is less than the standard distance.

8. A posture supervising apparatus characterized by comprising: The posture supervision device comprises a memory, a processor, and a posture supervision program stored on the memory and executable on the processor, the posture supervision program being configured to implement the steps of the posture supervision method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a posture supervision program, the posture supervision program being executable by the processor to implement the steps of the posture supervision method according to any one of claims 1 to 6.

Images