A posture correction method based on posture correction mirror and related components

Abstract

The present application relates to the field of medical devices, and discloses a posture correction method based on a posture correction mirror and related components, which are applied to a posture correction mirror including a control unit, a camera movably arranged in a preset track embedded between each rectangular lens, and an infrared sensor embedded on the surface of the rectangular lens. It includes: obtaining the part to be trained, the initial data collected by the infrared sensor and the target image collected by the camera, and determining the best target position for the camera to capture the training data of the part to be trained according to the target image. At preset time intervals, the camera is controlled to move to the current best target position according to the initial data to capture the training data. It can be seen that a single camera can move within the preset track, and the position of the collected data can be adjusted according to the user's body shape. At preset time intervals, the camera is controlled to move so as to adjust the position according to the user's current state, without the user having to maintain a different state, thereby improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of medical devices, and in particular to a posture correction method based on a posture correction mirror and related components. Background Art

[0002] The posture correction mirror is a mirror provided to patients with movement disorders, trauma recovery, Parkinson's syndrome and paralysis to correct abnormal body posture.

[0003] The current posture correction mirror uses a single camera to collect images of the user and analyzes the images to determine the parts to be trained. Since the camera is fixed in position, when there are differences in the height and body shape of the user, the camera still collects images at a fixed position, resulting in inaccurate data, which in turn leads to poor posture training results. Increasing the number of cameras will increase costs, and when any of the cameras fails, locating and troubleshooting the problem is time-consuming and laborious.

[0004] In addition, when using a single camera for training, when collecting data based on the user's movement, the user is required to maintain a certain state for a period of time before each collection, otherwise the collected data will be inaccurate, which brings a very poor user experience.

[0005] It can be seen that how to accurately correct the user's posture according to the user's current state based on a posture correction mirror including a single camera to improve the user experience is a problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0006] The purpose of the present application is to provide a posture correction method based on a posture correction mirror and related components, based on a posture correction mirror including a single camera, to accurately correct the user's posture according to the user's current state, thereby improving the user experience.

[0007] In order to solve the above technical problems, the present application provides a posture correction method based on a posture correction mirror, which is applied to a posture correction mirror including a plurality of rectangular lenses, a camera, an infrared sensor and a control unit, wherein the camera is movably arranged in a preset track embedded between each of the rectangular lenses, and the infrared sensor is embedded on the surface of the rectangular lenses, and the method comprises:

[0008] Acquire the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera;

[0009] Determining, according to the target image, an optimal target position for the camera to capture training data of the part to be trained;

[0010] After each preset time period, the camera is controlled to move to the current optimal target position according to the initial data, so that the camera can capture the training data of the part to be trained.

[0011] Preferably, determining the best target position for the camera to capture the training data of the part to be trained according to the target image comprises:

[0012] Parsing the target image to obtain a parsing result;

[0013] Determine the theoretical target position of the to-be-trained part mapped on the posture correction mirror according to the analysis result;

[0014] The optimal target position is determined according to the theoretical target position.

[0015] Preferably, determining the optimal target position according to the theoretical target position comprises:

[0016] When the theoretical target position is on the preset track, taking the theoretical target position as the optimal target position;

[0017] When the theoretical target position is on the rectangular lens, determining a first position and a second position of the theoretical target position that are closest to the preset track in the horizontal direction and the vertical direction;

[0018] The smaller one of the first position and the second position is taken as the optimal target position.

[0019] Preferably, controlling the camera to move to the current optimal target position according to the initial data comprises:

[0020] Determine the target center position of the user's geometric center position mapped on the posture correction mirror according to the initial data;

[0021] Determining the relative distance between the optimal target position and the target center position;

[0022] Obtaining the difference between the current relative distance and the relative distance at a previous moment;

[0023] When the difference exceeds a preset range, the camera is controlled to move to the current optimal target position.

[0024] Preferably, the posture correction method based on the posture correction mirror further comprises:

[0025] In the case where the initial data collected by the infrared sensor and / or the target image collected by the camera cannot be obtained, a prompt signal is issued.

[0026] Preferably, after controlling the camera to move to the current optimal target position according to the initial data after each preset time period so that the camera can capture the training data of the part to be trained, the method further includes:

[0027] When the training time reaches the preset time, the training of the current part to be trained is terminated, and a training result analysis graph is generated.

[0028] In order to solve the above technical problems, the present application also provides a posture correction mirror, including: a plurality of rectangular lenses, a camera, an infrared sensor and a control unit;

[0029] The rectangular lens is used to assist the user in posture correction;

[0030] The camera can be movably arranged in a preset track embedded between the rectangular lenses to capture the target image;

[0031] The infrared sensor is embedded on the surface of the rectangular lens and is used to collect initial data;

[0032] The control unit is connected to the camera and the infrared sensor respectively, and is used to obtain the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera, determine the optimal target position for the camera to capture the training data of the part to be trained according to the target image, and control the camera to move to the current optimal target position according to the initial data after each preset time period, so that the camera can capture the training data of the part to be trained.

[0033] In order to solve the above technical problems, the present application also provides a posture correction device based on a posture correction mirror, which is applied to a posture correction mirror including a plurality of rectangular lenses, a camera, an infrared sensor and a control unit, wherein the camera is movably arranged in a preset track embedded between each of the rectangular lenses, and the infrared sensor is embedded on the surface of the rectangular lenses, and the device comprises:

[0034] An acquisition module, used to acquire the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera;

[0035] A determination module, used to determine the best target position for the camera to capture the training data of the part to be trained according to the target image;

[0036] The control module is used to control the camera to move to the current optimal target position according to the initial data after each preset time period, so that the camera can capture the training data of the part to be trained.

[0037] In order to solve the above technical problems, the present application also provides a posture correction device based on a posture correction mirror, comprising a memory for storing a computer program;

[0038] A processor is used to implement the steps of the posture correction method based on the posture correction mirror when executing the computer program.

[0039] In order to solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the posture correction method based on the posture correction mirror are implemented.

[0040] The present invention provides a posture correction method based on a posture correction mirror, which is applied to a posture correction mirror including a plurality of rectangular lenses, a camera, an infrared sensor and a control unit, wherein the camera can be movably arranged in a preset track embedded between each rectangular lens, and the infrared sensor is embedded on the surface of the rectangular lens. The method comprises: obtaining the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera, and determining the best target position for the camera to capture the training data of the part to be trained according to the target image. After each preset time, the camera is controlled to move to the current best target position according to the initial data, so that the camera can capture the training data of the part to be trained. It can be seen that the technical solution provided by the present application is designed that a single camera can be moved within a preset track, and can be moved according to the user's body shape to obtain accurate data, and avoid the high cost brought by multiple cameras, and avoid the difficulty of camera fault location and elimination by using multiple cameras. In addition, after each preset time, the camera is controlled to move to the best target position to capture the training data of the part to be trained by the user, so as to continuously adjust the position of the camera to collect data according to the current state of the user, without the user having to maintain a different state before collecting data, thereby improving the user experience.

[0041] In addition, the present application also provides a posture correction device and medium based on a posture correction mirror, and a posture correction mirror, which correspond to the above-mentioned posture correction method based on the posture correction mirror and have the same effect as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1A flowchart of a posture correction method based on a posture correction mirror provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of a posture correction mirror provided in an embodiment of the present application;

[0045] Figure 3 A training diagram of a posture correction mirror provided by another embodiment of the present application;

[0046] Figure 4 A structural diagram of a posture correction device based on a posture correction mirror provided in an embodiment of the present application;

[0047] Figure 5 A structural diagram of a posture correction device based on a posture correction mirror provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The core of this application is to provide a posture correction method based on a posture correction mirror and related components. The user's posture is corrected by a posture correction mirror including a single movable camera, avoiding the high cost brought by multiple cameras. At the same time, the camera is controlled to adjust the position of the current data collection at preset time intervals, eliminating the need for the user to maintain a state for a period of time before collecting data, thereby improving the user experience.

[0050] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0051] The posture correction mirror is a mirror provided to patients with movement disorders, trauma recovery, Parkinson's syndrome and paralysis to correct abnormal body posture.

[0052] The current posture correction mirror uses a single camera to collect images of the user and analyzes the images to determine the parts to be trained. Since the camera is fixed in position, when there are differences in the height and body shape of the user, the camera still collects images at a fixed position, resulting in inaccurate data, which in turn leads to poor posture training results. Increasing the number of cameras will increase costs, and when any of the cameras fails, locating and troubleshooting the problem is time-consuming and laborious.

[0053] In addition, when using a single camera for training, when collecting data based on the user's movement, the user is required to maintain a certain state for a period of time before each collection, otherwise the collected data will be inaccurate, which brings a very poor user experience.

[0054] In order to realize a posture correction mirror based on a single camera, accurately correct the user's posture according to the user's current state and improve the user experience, an embodiment of the present application provides a posture correction method based on a posture correction mirror, by acquiring the part to be corrected, the initial data collected by the infrared sensor embedded in the surface of the rectangular lens, and the target image collected by the camera movably set in a preset track, wherein the preset track is a track embedded between each rectangular lens, and the optimal target position of the camera to capture the training data of the part to be trained is determined according to the acquired target image, and after each preset time period, the camera is controlled to move to the current optimal target position according to the acquired initial data to capture the training data. In this way, the camera position can be controlled to the optimal position for data collection according to the user's body shape. At the same time, the user does not need to maintain a state for a period of time before collecting data, thereby improving the user experience.

[0055] Figure 1 A flowchart of a posture correction method based on a posture correction mirror provided in an embodiment of the present application is provided. The method is applied to a posture correction mirror including a plurality of rectangular lenses, a camera, an infrared sensor and a control unit. The camera is movably arranged in a preset track embedded between each rectangular lens, and the infrared sensor is embedded on the surface of the rectangular lens, such as Figure 1 As shown, the method includes:

[0056] S10: Obtain the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera;

[0057] In a specific embodiment, the part to be trained selected by the user according to actual needs, as well as the initial data collected by the infrared sensor and the target image collected by the camera are obtained. Among them, the part to be trained can be one or more, which is not limited by this application. When there are multiple parts to be trained, training is performed once according to user needs. When each part to be trained reaches the preset training time, a prompt is issued and the training of the next part to be trained is directly entered.

[0058] It should be noted that the initial data collected by the infrared sensor includes the distance between the posture correction mirror and the ground, the distance from the point where the top of the user's head is mapped on the posture correction mirror to the bottom edge of the posture correction mirror, and the width of the user. The width of the user can be the shoulder distance or the longest distance in the horizontal direction of the user, which is not limited in this application.

[0059] In fact, the distance between users of different heights and the posture correction mirror will also affect the correction effect. Therefore, different distances from the posture correction mirror are set according to different heights. When users perform posture correction, they need to stand at a distance corresponding to their height from the posture correction mirror.

[0060] S11: determining the best target position for the camera to capture the training data of the part to be trained according to the target image;

[0061] After the target image captured by the camera is acquired according to step S10, the target image is analyzed, and then the theoretical target position of the part to be trained mapped on the posture correction mirror is determined based on the result of the analysis, that is, the theoretical target position of the part to be trained irradiated on the correction mirror.

[0062] It is understandable that the camera is set in a preset track, and the preset track is embedded between the rectangular lenses, so the part to be trained may be mapped on the rectangular lens or on the preset track. Therefore, the mapped position is called the theoretical target position, and the optimal target position for the camera to capture the training data of the part to be trained needs to be determined based on the theoretical target position.

[0063] When the theoretical target position is exactly on the preset track, the theoretical target position is used as the optimal target position for the camera to collect training data. When the theoretical target position is on a rectangular lens, the first position and the second position of the theoretical target position that are closest to the preset track in the horizontal direction and the vertical direction are further determined, and the smaller of the first position and the second position is used as the optimal target position. In other words, when the theoretical target position falls on one of the rectangular lenses, each side of the rectangular lens has a preset track, and the point where the theoretical target position is closest to the preset track on each side is determined, and this point is used as the optimal target position.

[0064] S12: After each preset time period, the camera is controlled to move to the current optimal target position according to the initial data, so that the camera can capture the training data of the part to be trained.

[0065] In practice, after obtaining the initial data collected by the infrared sensor, the position corresponding to the user's geometric center mapped on the posture correction mirror can be determined based on the initial data, and this position is called the target center position, that is, the position where the user's own center point is mapped on the posture correction mirror.

[0066] Further, after obtaining the target center position, determine the relative distance between the optimal target position obtained in step S11 and the target center position

[0067] It is understandable that in the process of posture correction, the user may move and other phenomena may cause the target center position and the optimal target position for the camera to collect training data to change. Therefore, it is necessary to adjust the position of the camera to collect training data after a preset time. That is, at every preset time, obtain the relative distance between the current optimal target position and the target center position, as well as the relative distance between the optimal target position and the target center position at the previous moment, and determine the difference between the current relative distance and the relative distance at the previous moment. When the difference exceeds the preset range, it is determined that the position of the camera currently collecting training data needs to be adjusted. At this time, according to the principle of the shortest path between the current optimal target position and the optimal target position at the previous moment, control the camera to move to the current optimal target position.

[0068] In fact, when the user moves during the training process, the target center position will also move, and the target center position obtained when the user initially stands in front of the mirror is the most accurate position. Therefore, before training, the camera can be moved to the target center position based on the initial data collected by the infrared sensor. After that, the position of the camera is adjusted based on the target center position during the training process.

[0069] During the training process, if the infrared sensor cannot collect initial data and / or the camera cannot normally collect the target image, the infrared sensor and camera may be malfunctioning, or the user may have deviated from the physical range of training. At this time, a prompt signal is issued to facilitate the user to troubleshoot.

[0070] When the training time reaches the preset time, the training is stopped and a dynamic analysis diagram of the corresponding part to be trained is generated so that the user can obtain the current training effect.

[0071] The posture correction method based on the posture correction mirror provided in the embodiment of the present application is applied to the posture correction mirror including multiple rectangular lenses, a camera, an infrared sensor and a control unit, wherein the camera can be movably arranged in a preset track embedded between each rectangular lens, and the infrared sensor is embedded on the surface of the rectangular lens. The method comprises: obtaining the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera, and determining the best target position for the camera to capture the training data of the part to be trained according to the target image. After each preset time, the camera is controlled to move to the current best target position according to the initial data, so that the camera can capture the training data of the part to be trained. It can be seen that the technical solution provided by the present application, the design that a single camera can move within a preset track, can be moved according to the user's body shape to obtain accurate data, and avoids the high cost brought by multiple cameras, and avoids the difficulty of camera fault location and elimination by using multiple cameras. In addition, after each preset time, the camera is controlled to move to the best target position to capture the training data of the part to be trained by the user, so as to continuously adjust the position of the camera to collect data according to the current state of the user, without the user having to maintain a different state before collecting data, thereby improving the user experience.

[0072] In a specific embodiment, when determining the optimal target position of the camera for capturing training data of the part to be trained based on the target image, the target image captured by the camera is first analyzed to obtain a analysis result, and the theoretical target position of the part to be trained mapped on the posture correction mirror is determined based on the analysis result.

[0073] It can be understood that the posture correction mirror provided in the present application is composed of multiple rectangular lenses, and preset tracks are set between the rectangular lenses. Therefore, when determining the theoretical target position of the part to be trained mapped on the posture correction mirror according to the analysis results, the theoretical target position may be mapped on the preset track or on the rectangular lens.

[0074] Therefore, it is necessary to determine the optimal target position based on the theoretical target position, that is, to determine the optimal position of the camera on the preset track based on the theoretical target position. When the theoretical target position is on the preset track, the theoretical target position is used as the optimal target position. When the theoretical target position is on the rectangular lens, the first position and the second position that are closest to the preset track in the horizontal direction and the vertical direction are determined, and the smaller of the first position and the second position is used as the optimal target position. Figure 2 Provide detailed explanation.

[0075] Figure 2 A schematic diagram of a posture correction mirror provided in an embodiment of the present application is shown in FIG. Figure 2As shown, assuming that the rectangular lens is a square, and the side length of each square lens is L, the width of the preset track is W, the camera can move within the preset track with a width of W, and a coordinate system is established with the center of the posture correction lens as the origin, wherein the coordinates of the user's geometric center position are (m, n).

[0076] The theoretical target position is horizontally closest to the left preset track as L_left, and is closest to the right preset track as L_right. In the vertical direction, the theoretical target position is vertically closest to the bottom preset track as L_bottom, and is closest to the top preset track as L_top.

[0077] Therefore, when determining the optimal target position, the position of the preset track corresponding to the smallest of L_left, L_right, L_bottom and L_top is used as the optimal target position. That is, the smaller of the first position and the second position that are closest to the preset track in the horizontal and vertical directions of the theoretical target position is used as the optimal target position.

[0078] It is worth noting that in the horizontal direction, the closest distance to the left preset track L_left = m-int(float(mw) / (L+W))*(L+W), the closest distance to the right preset track L_right = int(float(mw) / (L+W))*(L+W)-m, the closest distance to the lower preset track L_bottom = n-int(float(nw) / (L+W))*(L+W), and the closest distance to the upper preset track in the vertical direction L_top = int(float(nw) / (L+W))*(L+W)-n.

[0079] Therefore, if Figure 2 As shown, when the theoretical target position falls on the rectangular lens, the point closest to the preset tracks corresponding to the four sides is taken as the optimal target position, that is, the optimal position for the camera to collect training data.

[0080] It is understandable that when there are more rectangular lenses and the preset tracks are denser, the data collected by the control camera will be more accurate. Correspondingly, the visual effect given by the lenses will be relatively poor. Therefore, the width of the preset track and the shape, size and number of the rectangular lenses can be set according to actual needs.

[0081] The posture correction method based on the posture correction mirror provided in the embodiment of the present application, when determining the best target position for the camera to collect training big data, analyzes the target image to obtain the analysis result, and determines the theoretical target position of the part to be trained mapped on the posture correction mirror based on the analysis result. When the theoretical target position is on the preset track, the theoretical target position is used as the best target position. When the theoretical target position is on the rectangular lens, the first position and the second position of the theoretical target position closest to the preset track in the horizontal direction and the vertical direction are determined, and the smaller of the first position and the second position is used as the best target position. In this way, the camera is moved to the best position for collecting training data as much as possible, the accuracy of data collection is improved, and the effect of posture correction is improved.

[0082] Based on the above embodiment, the user's training data can be collected after the optimal target position of the camera is obtained. However, during the training process, it is inevitable that the user will move, causing the optimal target position to change. If the camera is always in one position for data collection, it will cause deviations in the collected data. Therefore, it is necessary to adjust the position of the camera in real time according to the user's movement.

[0083] Specifically, first determine the target center position of the user's geometric center position mapped on the posture correction mirror based on the initial data, and determine the relative distance between the optimal target position and the target center position, then obtain the difference between the current relative distance and the relative distance at the previous moment, and when the difference exceeds a preset range, control the camera to move to the current optimal target position.

[0084] It is worth noting that the initial data collected by the infrared sensor includes the distance between the posture correction mirror and the ground, the distance from the point where the user's head is mapped on the posture correction mirror to the bottom edge of the posture correction mirror, and the user's width. The user's width can be the shoulder distance or the longest distance in the horizontal direction of the user, which is not limited in this application.

[0085] Figure 3 A training diagram of a posture correction mirror provided in another embodiment of the present application is shown in FIG. Figure 3 As shown, when a user stands in front of a posture correction mirror for posture training according to his / her height, the distance from the posture correction mirror to the ground collected by the infrared sensor is a, the distance from the point on the top of the user's head mapped on the posture correction mirror to the bottom edge of the posture correction mirror is b, and the width of the user is c. The target center position of the user's geometric center position mapped on the posture correction mirror can be determined. For example, the target center position is located at 1 / (a+b), 1 / c.

[0086] It is understandable that when the user moves slightly, there is no need to adjust the position of the camera, so when the difference between the relative distance between the currently determined best target position and the target center position and the relative distance between the best target position and the target center position at the previous moment exceeds the preset range, it is determined that the position of the camera needs to be adjusted. At this time, all paths between the current best target position and the best target position at the previous moment are obtained, and the shortest path is selected to move the camera.

[0087] It should be noted that when the user moves, the target center position mapped on the posture correction mirror will inevitably change. Therefore, the target center position first obtained when the user initially stands in front of the posture correction mirror is used as the target center position during the entire training process.

[0088] In addition, it should be noted that in order to avoid the initial position of the camera being located far away from the center of the posture correction mirror, resulting in inaccurate initial image acquisition, before determining the optimal target position for the camera to capture the training data of the part to be trained based on the target image, the target center position of the user's geometric center mapped on the posture correction mirror can be determined based on the initial data collected by the infrared sensor, and the camera can be moved to the target center position.

[0089] The posture correction method based on the posture correction mirror provided in the embodiment of the present application controls the camera to move to the current optimal target position according to the initial data. First, the target center position of the user's geometric center position mapped on the posture correction mirror is determined according to the initial data. Then, the relative distance between the optimal target position and the target center position is determined, and the difference between the current relative distance and the relative distance at the previous moment is obtained. When the difference exceeds the preset range, it is determined that the camera needs to adjust the position of the training data collection. At this time, the camera is controlled to move to the current optimal target position. As a result, the user does not need to maintain a constant state before collecting data. The camera can continuously adjust the position of the camera to collect training data according to the user's current position and state, thereby improving the accuracy of data collection while improving the user experience.

[0090] In a specific embodiment, in order to further improve the accuracy of data collection and the effect of training, when the initial data collected by the infrared sensor and / or the target image collected by the camera cannot be obtained, it may be that the infrared sensor or the camera has malfunctioned, or the user has left the physical range of normal collection. At this time, a prompt signal is issued to facilitate the staff to troubleshoot the posture correction mirror or remind the user to move to the designated training range.

[0091] The posture correction method based on the posture correction mirror provided in the embodiment of the present application sends out a prompt signal when the initial data collected by the infrared sensor and / or the target image collected by the camera cannot be obtained, so as to facilitate the staff to troubleshoot in time, thereby improving the accuracy of data collection and the reliability of the posture correction mirror.

[0092] During implementation, in order to facilitate users to view the current training results and conduct a comprehensive analysis of the user's training in combination with historical training data, when the training time reaches the preset time, the training of the current part to be trained is ended and a training result analysis chart is generated.

[0093] The posture correction method based on the posture correction mirror provided in the embodiment of the present application generates a training result analysis diagram after the training of the training part is completed, so that the user can view the current training effect.

[0094] In the above embodiment, the posture correction method based on the posture correction mirror is described in detail, and the present application also provides an embodiment corresponding to the posture correction mirror. The posture correction mirror includes a plurality of rectangular lenses, a camera, an infrared sensor and a control unit, wherein the rectangular lenses are used to assist the user in posture correction, and the camera can be movably set in a preset track embedded between each rectangular lens to collect the target image. It should be noted that the present application does not limit the width of the preset track, the number, shape and size of the rectangular lenses.

[0095] In addition, an infrared sensor is embedded on the surface of the rectangular lens and is used to collect initial data. The control unit is respectively connected to the camera and the infrared sensor to obtain the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera, and the optimal target position for the camera to capture the training data of the part to be trained is determined according to the target image. After each preset time period, the camera is controlled to move to the current optimal target position according to the initial data so that the camera can capture the training data of the part to be trained.

[0096] The beneficial effects brought about by the posture correction mirror provided in the embodiment of the present application correspond to the beneficial effects brought about by the posture correction method based on the posture correction mirror in the above-mentioned embodiment, and will not be repeated here.

[0097] In the above embodiments, a posture correction method based on a posture correction mirror is described in detail, and the present application also provides an embodiment corresponding to a posture correction device based on a posture correction mirror. It should be noted that the present application describes the embodiments of the device part from two perspectives, one is based on the perspective of functional modules, and the other is based on the perspective of hardware structure.

[0098] Figure 4The structural diagram of a posture correction device based on a posture correction mirror provided in an embodiment of the present application is applied to a posture correction mirror including a plurality of rectangular lenses, a camera, an infrared sensor and a control unit. The camera can be movably arranged in a preset track embedded between each rectangular lens, and the infrared sensor is embedded on the surface of the rectangular lens, such as Figure 4 As shown, the device comprises:

[0099] The acquisition module 10 is used to acquire the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera;

[0100] A determination module 11 is used to determine the best target position for the camera to capture the training data of the part to be trained according to the target image;

[0101] The control module 12 is used to control the camera to move to the current optimal target position according to the initial data after each preset time period, so that the camera can capture the training data of the part to be trained.

[0102] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, which will not be repeated here.

[0103] The posture correction device based on the posture correction mirror provided in the embodiment of the present application is applied to the posture correction mirror including multiple rectangular lenses, a camera, an infrared sensor and a control unit, wherein the camera can be movably arranged in a preset track embedded between each rectangular lens, and the infrared sensor is embedded on the surface of the rectangular lens. It includes: obtaining the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera, and determining the best target position for the camera to capture the training data of the part to be trained according to the target image. After each preset time, the camera is controlled to move to the current best target position according to the initial data, so that the camera can capture the training data of the part to be trained. It can be seen that the technical solution provided by the present application, the design that a single camera can move within a preset track, can be moved according to the user's body shape to obtain accurate data, and avoids the high cost brought by multiple cameras, and avoids the difficulty of camera fault location and elimination by using multiple cameras. In addition, after each preset time, the camera is controlled to move to the best target position to capture the training data of the part to be trained by the user, so as to continuously adjust the position of the camera to collect data according to the current state of the user, without the user having to maintain a different state before collecting data, thereby improving the user experience.

[0104] Figure 5 A structural diagram of a posture correction device based on a posture correction mirror provided in another embodiment of the present invention, such as Figure 5As shown, the posture correction device based on the posture correction mirror includes: a memory 20 for storing a computer program;

[0105] The processor 21 is used to implement the steps of the posture correction method based on the posture correction mirror mentioned in the above embodiment when executing the computer program.

[0106] The posture correction device based on the posture correction mirror provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer or a desktop computer.

[0107] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of a digital signal processor (Digital Signal Processor, referred to as DSP), a field programmable gate array (Field-Programmable Gate Array, referred to as FPGA), and a programmable logic array (Programmable Logic Array, referred to as PLA). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (Central Processing Unit, referred to as CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a graphics processor (Graphics Processing Unit, referred to as GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an artificial intelligence (Artificial Intelligence, referred to as AI) processor, which is used to process computing operations related to machine learning.

[0108] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the posture correction method based on the posture correction mirror disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. Data 203 may include but is not limited to the relevant data involved in the posture correction method based on the posture correction mirror.

[0109] In some embodiments, the posture correction device based on the posture correction mirror may further include a display screen 22 , an input and output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .

[0110] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation on the posture correction device based on the posture correction mirror, and may include more or less components than those shown in the figure.

[0111] The posture correction device based on the posture correction mirror provided in the embodiment of the present application includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the following method: a posture correction method based on the posture correction mirror.

[0112] The posture correction device based on the posture correction mirror provided in the embodiment of the present application is designed with a single camera that can move within a preset track, and can be moved according to the user's body shape to obtain accurate data, and avoid the high cost brought by multiple cameras, and avoid the difficulty of locating and troubleshooting camera faults using multiple cameras. In addition, after every preset time period, the camera is controlled to move to the optimal target position to capture the training data of the user's training part, so as to continuously adjust the position of the camera to collect data according to the user's current state, without the user having to maintain a different state before collecting data, thereby improving the user experience.

[0113] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.

[0114] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program code.

[0115] The above is a detailed introduction to a posture correction method based on a posture correction mirror and related components provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

[0116] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A posture correction method based on a posture correction mirror, characterized in that: The method is applied to a posture correction mirror including a plurality of rectangular lenses, a camera, an infrared sensor and a control unit, wherein the camera is movably arranged in a preset track embedded between the rectangular lenses, and the infrared sensor is embedded on the surface of the rectangular lenses, and the method comprises: Acquire the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera; Determining, according to the target image, an optimal target position for the camera to capture training data of the part to be trained; After each preset time period, controlling the camera to move to the current optimal target position according to the initial data, so that the camera can capture the training data of the part to be trained; The controlling the camera to move to the current optimal target position according to the initial data comprises: Determine the target center position of the user's geometric center position mapped on the posture correction mirror according to the initial data; Determining the relative distance between the optimal target position and the target center position; Obtaining the difference between the current relative distance and the relative distance at a previous moment; When the difference exceeds a preset range, the camera is controlled to move to the current optimal target position.

2. The posture correction method based on the posture correction mirror according to claim 1, characterized in that: Determining the optimal target position for the camera to capture the training data of the part to be trained according to the target image includes: Parsing the target image to obtain a parsing result; Determine the theoretical target position of the to-be-trained part mapped on the posture correction mirror according to the analysis result; The optimal target position is determined according to the theoretical target position.

3. The posture correction method based on the posture correction mirror according to claim 2, characterized in that: Determining the optimal target position according to the theoretical target position comprises: When the theoretical target position is on the preset track, taking the theoretical target position as the optimal target position; When the theoretical target position is on the rectangular lens, determining a first position and a second position of the theoretical target position that are closest to the preset track in the horizontal direction and the vertical direction; The smaller one of the first position and the second position is taken as the optimal target position.

4. The posture correction method based on the posture correction mirror according to claim 1, characterized in that: Also includes: In the case where the initial data collected by the infrared sensor and / or the target image collected by the camera cannot be obtained, a prompt signal is issued.

5. The posture correction method based on the posture correction mirror according to claim 1, characterized in that: After controlling the camera to move to the current optimal target position according to the initial data after each preset time period so that the camera can capture the training data of the part to be trained, the method further includes: When the training time reaches the preset time, the training of the current part to be trained is terminated, and a training result analysis graph is generated.

6. A posture correction lens, characterized in that: include: multiple rectangular lenses, a camera, infrared sensor and control unit; The rectangular lens is used to assist the user in posture correction; The camera can be movably arranged in a preset track embedded between the rectangular lenses to capture the target image; The infrared sensor is embedded on the surface of the rectangular lens and is used to collect initial data; The control unit is connected to the camera and the infrared sensor respectively, and is used to obtain the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera, determine the best target position for the camera to capture the training data of the part to be trained according to the target image, and control the camera to move to the current best target position according to the initial data after each preset time period, so that the camera can capture the training data of the part to be trained; The method of controlling the camera to move to the current optimal target position according to the initial data includes: determining the target center position of the user's geometric center position mapped on the posture correction mirror according to the initial data; determining the relative distance between the optimal target position and the target center position; obtaining the difference between the current relative distance and the relative distance at the previous moment; and when the difference exceeds a preset range, controlling the camera to move to the current optimal target position.

7. A posture correction device based on a posture correction mirror, characterized in that: The device is applied to a posture correction mirror including a plurality of rectangular lenses, a camera, an infrared sensor and a control unit, wherein the camera is movably arranged in a preset track embedded between each of the rectangular lenses, and the infrared sensor is embedded on the surface of the rectangular lenses, and the device comprises: An acquisition module, used to acquire the part to be trained selected by the user, the initial data collected by the infrared sensor, and the target image collected by the camera; A determination module, used to determine the best target position for the camera to capture the training data of the part to be trained according to the target image; A control module is used to control the camera to move to the current optimal target position according to the initial data after each preset time period, so that the camera can capture the training data of the part to be trained; the control of the camera to move to the current optimal target position according to the initial data includes: determining the target center position of the user's geometric center position mapped on the posture correction mirror according to the initial data; determining the relative distance between the optimal target position and the target center position; obtaining the difference between the current relative distance and the relative distance at the previous moment; when the difference exceeds a preset range, controlling the camera to move to the current optimal target position.

8. A posture correction device based on a posture correction mirror, characterized in that: comprising a memory for storing a computer program; A processor, configured to implement the steps of the posture correction method based on a posture correction mirror as described in any one of claims 1 to 5 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the posture correction method based on the posture correction mirror as claimed in any one of claims 1 to 5 are implemented.

Images