Scoliosis detection apparatus, system and computer readable storage medium

Abstract

The application provides a scoliosis detection device, system and computer readable storage medium, the scoliosis detection device comprises a processor, the processor is configured to implement the following steps: acquiring a full body image of a user performing a preset action by using an image acquisition device, the preset action comprising a standing action; adopting a thinning algorithm to perform thinning line extraction on the full body image of the standing action to obtain a thinning line of a first type of preset joint of the user, the first type of preset joint comprising a spine joint, a shoulder joint and a hip joint; based on the thinning line of the first type of preset joint, obtaining posture information of the user, and calculating the similarity between the posture information of the user and standard posture information; when the similarity is less than a preset similarity threshold, generating a prompt information and sending it to a user device, the prompt information is used to indicate that the user has scoliosis. The application does not need manual screening, the accuracy of detection is higher, and can meet the large amount of scoliosis screening work.

Description

Technical Field

[0001] This application relates to the fields of machine vision inspection and medical testing equipment, and in particular to scoliosis detection devices, systems and computer-readable storage media. Background Technology

[0002] Scoliosis, also known as spinal curvature, is a three-dimensional deformity of the spine, including abnormalities in the coronal, sagittal, and axial planes. A normal spine should appear as a straight line from the back, with symmetrical sides of the trunk. If, from the front, the shoulders are uneven or the back appears uneven from side to side, scoliosis should be suspected. In this case, a standing full-spine X-ray should be taken. If the anteroposterior X-ray shows a lateral curvature of more than 10 degrees, scoliosis can be diagnosed. Mild scoliosis can be observed, while severe cases require surgical treatment. Mild scoliosis usually does not cause obvious discomfort, and there are no obvious physical deformities. More severe scoliosis can affect the growth and development of infants and adolescents, causing physical deformities. In severe cases, it can affect cardiopulmonary function and even involve the spinal cord, causing paralysis. Scoliosis is a common disease affecting adolescents and children; early detection and treatment are crucial.

[0003] Currently, most scoliosis screenings rely on manual visual inspection. After screening too many people within a certain time, the screening personnel are prone to fatigue, subjective errors, and individual differences may also lead to identification errors. This method cannot meet the needs of large-scale scoliosis screening.

[0004] Therefore, there is an urgent need to provide scoliosis detection devices, systems, and computer-readable storage media to improve existing technologies. Summary of the Invention

[0005] The purpose of this application is to provide a scoliosis detection device, system, and computer-readable storage medium that eliminates the need for manual screening, has a high accuracy rate, and can meet the needs of large-scale scoliosis screening.

[0006] The objective of this application is achieved through the following technical solution:

[0007] In a first aspect, this application provides a scoliosis detection device, the scoliosis detection device including a processor configured to perform the following steps:

[0008] The image acquisition device is used to acquire a full-body image of the user performing a preset action, including a standing action.

[0009] A thinning algorithm is used to extract thinning lines from the full-body image of the standing action to obtain the thinning lines of the user's first type of preset joints, which include the spinal joint, shoulder joint and hip joint.

[0010] Obtain the posture information of the user based on the refined lines of the first type of preset joints, and calculate the similarity between the posture information of the user and the standard posture information;

[0011] When the similarity is less than a preset similarity threshold, generate a prompt message and send it to the user device, and the prompt message is used to indicate that the user has scoliosis.

[0012] The beneficial effect of this technical solution is as follows: Use an image acquisition device to obtain a full-body image of the user doing a standing action, and adopt a refinement algorithm to extract the refined lines of the first type of preset joints in the full-body image. The first type of preset joints can be spinal joints, shoulder joints, and hip joints. In the standard posture information (corresponding to a user without scoliosis), the refined lines of the spinal joints, shoulder joints, and hip joints can be abstracted into the shape of the Chinese character "士". If the similarity between the posture information of the user doing a standing action and the standard posture information is relatively small, less than the preset similarity, it indicates that the user's spine may be laterally curved. Generate a prompt message and send it to the user device, thereby reminding the user that they have scoliosis and facilitating the user to take corresponding countermeasures in a timely manner.

[0013] This scoliosis detection device can automatically analyze and process the full-body image of the user using a refinement algorithm, and can automatically calculate the similarity between the posture information of the user and the standard posture information. It can judge whether the user has scoliosis based on the similarity, with a fast detection speed and no need for manual screening. The detection accuracy and efficiency are relatively high, and it can meet the needs of a large number of scoliosis screening tasks.

[0014] In some optional embodiments, the preset action further includes a first bending action and a second bending action. The first bending action is an action of bending forward the upper body, and the second bending action is an action of bending backward the upper body;

[0015] The processor is further configured to implement the following steps:

[0016] Obtain the corresponding first bending angle of the user based on the full-body image of the first bending action;

[0017] Obtain the corresponding second bending angle of the user based on the full-body image of the second bending action;

[0018] Obtain the scoliosis assessment information of the user based on the first bending angle and the second bending angle, and the scoliosis assessment information is used to indicate the degree of scoliosis of the user.

[0019] The beneficial effects of this technical solution are as follows: Generally speaking, compared with users without scoliosis, users with scoliosis will have a greater difference between the first bending angle and the second bending angle when performing the two movements of bending forward and bending backward. For example, if a user has scoliosis due to anterior pelvic tilt, bending forward may be more difficult than bending backward. By comparing the first bending angle and the second bending angle, the degree of scoliosis can be reflected. This non-contact method of detecting scoliosis is low in cost and the detection results are relatively accurate.

[0020] In some optional embodiments, the preset action further includes a third bending action and a fourth bending action, wherein the third bending action is a bending action of the upper body toward the left hip joint, and the fourth bending action is a bending action of the upper body toward the right hip joint.

[0021] The processor is also configured to perform the following steps:

[0022] Based on the full-body image of the third bending action, the third bending angle corresponding to the user is obtained;

[0023] Based on the full-body image of the fourth bending action, the fourth bending angle corresponding to the user is obtained;

[0024] The processor is configured to acquire the user's scoliosis assessment information in the following manner:

[0025] Based on the first bending angle, the second bending angle, the third bending angle, and the fourth bending angle, the user's scoliosis assessment information is obtained.

[0026] The beneficial effects of this technical solution are as follows: Generally speaking, for users without scoliosis, the difference in bending angles between bending to the left and right is relatively small. Compared to users without scoliosis, users with scoliosis will have a larger difference in the third and fourth bending angles when performing the two movements of bending the upper body to the left hip joint (left bending) and bending the upper body to the right hip joint (right bending). By comparing the first and second bending angles, and combining the comparison results of the first and second bending angles, the degree of scoliosis of the user can be further reflected, and the accuracy of the detection results can be improved.

[0027] In some alternative embodiments, the processor is further configured to perform the following steps:

[0028] The number of vibrations for each bending action performed by the user within a preset time period is obtained, and the balance degree corresponding to each bending action is obtained based on the number of vibrations for each bending action.

[0029] The processor is configured to acquire the user's scoliosis assessment information in the following manner:

[0030] Based on the first bending angle, the second bending angle, the third bending angle, the fourth bending angle, and the balance corresponding to each bending action, the user's scoliosis assessment information is obtained.

[0031] The beneficial effects of this technical solution are as follows: when users perform bending movements, it will cause muscle fatigue, which will produce a certain degree of shaking. Computer vision detection technology can be used to obtain the number of shakings of the user within a preset time. The fewer the number of shakings, the better the balance of the user in performing the movement. The more the number of shakings, the worse the balance of the user in performing the movement.

[0032] When a user has scoliosis, not only do the bending angles differ when performing different bending movements, but the degree of balance also varies. Balance can be calculated by counting the number of shakes during each bending movement within a preset time. By evaluating both balance and bending angle in each bending movement, the user's scoliosis assessment information can be obtained, further improving the accuracy of the detection results.

[0033] In some alternative embodiments, the processor is further configured to perform the following steps:

[0034] A first pressure sensor is used to obtain the first pressure corresponding to the user's left foot, and a second pressure sensor is used to obtain the second pressure corresponding to the user's right foot. The first pressure sensor is located on the sole of the user's left foot, and the second pressure sensor is located on the sole of the user's right foot.

[0035] Based on the first pressure and the second pressure, the user's scoliosis assessment information is obtained.

[0036] The beneficial effects of this technical solution are as follows: Generally speaking, the pressure on the two feet of a user with scoliosis is different. When the user is standing, by comparing the first pressure corresponding to the left foot and the second pressure corresponding to the right foot, the degree of scoliosis can be reflected. The detection process is relatively simple and easy to implement.

[0037] In some alternative embodiments, the processor is further configured to perform the following steps:

[0038] The infrared thermal image of the user was acquired using an infrared thermal imaging device;

[0039] Based on the infrared thermogram, the first temperature difference information on both sides of the user's spine is obtained, and the first temperature difference information is used to indicate the temperature difference value of symmetrical parts on both sides of the spine.

[0040] Based on the first temperature difference information, the user's scoliosis assessment information is obtained.

[0041] The beneficial effects of this technical solution are as follows: since the temperature of the inflamed area is higher than that of other areas, diseases can be diagnosed based on temperature information. Infrared thermal imaging detection technology is not affected by subjective or objective factors during examination and can visually reflect tissue damage and metabolic changes.

[0042] Generally, the infrared thermogram of a normal human body (without scoliosis) shows a symmetrical distribution of temperature along the spine, with the temperature decreasing from the midline to both sides. If a user has scoliosis, the temperature distribution will not be symmetrical, and there will be a large temperature difference between the symmetrical parts on both sides of the spine. Infrared thermal imaging equipment can be used to obtain the user's infrared thermogram, thereby obtaining the first temperature difference information between the two sides of the spine. The degree of scoliosis can be assessed based on the temperature difference between the symmetrical parts on both sides of the spine.

[0043] In some alternative embodiments, the processor is configured to acquire the user's scoliosis assessment information using the following steps:

[0044] Based on the infrared thermal image, the second temperature difference information of the user's second type of preset joint is obtained. The second temperature difference information is used to indicate the temperature difference between the second type of preset joint and its adjacent area. The second type of preset joint is any one of the following: shoulder joint, hip joint and knee joint.

[0045] Based on the first temperature difference information and the second temperature difference information, the user's scoliosis assessment information is obtained.

[0046] The beneficial effects of this technical solution are as follows: most scoliosis patients experience uneven stress on their limb joints, and some joints (shoulder joint, hip joint or knee joint) may suffer from strain, which can lead to inflammation and cause the body temperature at the site of inflammation to be higher. The degree of strain on the second-type preset joint can be judged based on the temperature difference between the second-type preset joint and its adjacent area. Combined with the temperature difference between the symmetrical parts on both sides of the spine, the degree of scoliosis of the user can be assessed.

[0047] Secondly, this application provides a scoliosis detection system, which includes an image acquisition device and any of the above-mentioned scoliosis detection devices, wherein the image acquisition device and the scoliosis detection device are electrically connected.

[0048] The image acquisition device is used to acquire full-body images of the user performing preset actions.

[0049] In some optional embodiments, the scoliosis detection system further includes an infrared thermal imaging device, a temperature sensor, a first pressure sensor, and a second pressure sensor;

[0050] The scoliosis detection device is electrically connected to the infrared thermal imaging device, the temperature sensor, the first pressure sensor, and the second pressure sensor, respectively.

[0051] The infrared thermal imaging device is used to acquire the infrared thermal image of the user, the temperature sensor is used to acquire ambient temperature information, the first pressure sensor is used to acquire the first pressure corresponding to the user's left foot, and the second pressure sensor is used to acquire the second pressure corresponding to the user's right foot.

[0052] Thirdly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the function of any of the above-mentioned scoliosis detection devices. Attached Figure Description

[0053] The present application will be further described below with reference to the accompanying drawings and embodiments.

[0054] Figure 1 This is a schematic flowchart of a scoliosis detection method provided in an embodiment of this application.

[0055] Figure 2 This is a structural block diagram of a scoliosis detection device provided in an embodiment of this application.

[0056] Figure 3 This is a structural block diagram of a scoliosis detection system provided in an embodiment of this application.

[0057] Figure 4 This is a structural block diagram of a program product provided in an embodiment of this application. Detailed Implementation

[0058] The present application will now be further described in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0059] In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, a and b and c, where a, b, and c can be single or multiple. It is worth noting that "at least one" can also be interpreted as "one or more".

[0060] It should also be noted that, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any implementation or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other implementations or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0061] See Figure 1 , Figure 1 This is a schematic flowchart of a scoliosis detection method provided in an embodiment of this application.

[0062] Step S101: Use an image acquisition device to acquire a full-body image of the user performing a preset action, the preset action including a standing action;

[0063] Step S102: Use a thinning algorithm to extract thinning lines from the full-body image of the standing action to obtain the thinning lines of the user's first type of preset joints, which include the spinal joint, shoulder joint and hip joint.

[0064] Step S103: Based on the thinning lines of the first type of preset joint, obtain the user's posture information and calculate the similarity between the user's posture information and the standard posture information;

[0065] Step S104: When the similarity is less than a preset similarity threshold, a prompt message is generated and sent to the user device. The prompt message is used to indicate that the user has scoliosis.

[0066] Thus, a full-body image of a user performing a standing action is obtained by using an image acquisition device. A thinning algorithm is used to extract the thinning lines of the first type of preset joints in the full-body image. The first type of preset joints can be spinal joints, shoulder joints, and hip joints. In the standard pose information (corresponding to a user without scoliosis), the thinning lines of the spinal joints, shoulder joints, and hip joints can be abstracted into the shape of the Chinese character "士". If the similarity between the pose information of the user performing the standing action and the standard pose information is relatively small, less than the preset similarity, it indicates that the user's spine may be laterally curved. A prompt message is generated and sent to the user device, thereby reminding the user that they have scoliosis and facilitating the user to take corresponding countermeasures in a timely manner.

[0067] This scoliosis detection device can automatically analyze and process the full-body image of the user by using a thinning algorithm, and can automatically calculate the similarity between the pose information of the user and the standard pose information. It judges whether the user has scoliosis based on the similarity, without manual screening, and the detection accuracy is relatively high, which can meet the large-scale scoliosis screening work.

[0068] The image acquisition device is not limited in the embodiments of this application. The image acquisition device is, for example, an optical camera, an infrared camera, or a depth camera. The full-body image refers to an image in which the user's entire body appears in the picture.

[0069] The thinning algorithm is an important image preprocessing method in digital image processing. The main process is to gradually delete boundary points without affecting the topological structure of the original image, and finally become an image with a single-pixel width, without generating new holes or new regions. The thinning line is also often called the central axis or the skeleton line. It is a low-dimensional representation of a two-dimensional object or a three-dimensional object, which can express the shape characteristics and topological structure of the object, greatly eliminating the繁杂 information in the image, and is commonly used in fields such as pattern recognition, data compression, and data storage.

[0070] The basic idea of the thinning algorithm is to traverse each pixel, judge whether the pixel is a boundary point to be deleted, delete the boundary point, judge the next pixel, and so on in a loop until convergence.

[0071] One iteration of the thinning algorithm consists of the following steps: 1. Mark the boundary points to be deleted; 2. Delete the marked points; 3. Continue to mark the remaining boundary points to be deleted; 4. Delete the marked points. Iterate repeatedly until there are no more deleted points, at which time the algorithm terminates and the skeleton of the region is generated. Applying the thinning algorithm to the extraction of the thinning lines of a human image can obtain the corresponding pose information.

[0072] The embodiments of this application do not limit the thinning algorithm. The thinning algorithm can be any of the following: median distance transformation thinning algorithm, ZS thinning algorithm, morphological thinning algorithm, 2.5D thinning algorithm and 3D thinning algorithm.

[0073] In some implementations, the thinning algorithm employs a 2.5D thinning algorithm, and the image acquisition device is, for example, a depth camera.

[0074] Compared to ordinary optical cameras, depth cameras can acquire not only planar images but also depth information of the subject, i.e., three-dimensional position and size information. Depth cameras are easy to set up and inexpensive. The data they provide is very attractive for motion tracking because depth images are not sensitive to lighting and surface color information, and even a single camera can provide rich geometric information, making it very convenient for background removal.

[0075] For 2.5D thinning algorithms, in a depth image, the grayscale value of each pixel represents the distance between the object and the camera, which plays a crucial role in segmentation or tracking. However, traditional thinning algorithms can only gradually remove contour points, failing to leverage the advantages of depth cameras and neglecting the provided depth information.

[0076] The specific process of the 2.5D refinement algorithm is as follows:

[0077] a. Search for each pixel in the depth map and calculate its binary template;

[0078] b. Match the binary template with the deletion table template;

[0079] c. Delete pixels that match the given information;

[0080] d. Iterate through steps a to c until no pixels can be modified. What remains are the thinning lines with depth information.

[0081] Similarity can be expressed as a number or a percentage; the higher the value, the higher the similarity.

[0082] This application does not limit the preset similarity threshold, which may be, for example, 80%, 90%, or 95%.

[0083] In some implementations, the similarity between the user's pose information and standard pose information is calculated as follows:

[0084] Acquire multiple similarity training data, each of which includes sample pose information, standard pose information, and labeled similarity between the two for training.

[0085] A preset deep learning model is trained using multiple similarity training data sets to obtain a similarity model;

[0086] The user's posture information and the standard posture information are input into the similarity model to obtain the similarity score.

[0087] Therefore, a pre-defined deep learning model can be trained based on similarity training data to obtain a similarity model. Simply input the user's pose information and standard pose information into the similarity model, and the corresponding similarity score can be automatically generated in real time, demonstrating a high degree of intelligence. By designing and establishing an appropriate number of neural computation nodes and a multi-layered computational hierarchy, and selecting suitable input and output layers, a pre-defined deep learning model can be obtained. Through learning and optimization of this pre-defined deep learning model, a functional relationship from input to output can be established. Although it cannot find a 100% accurate functional relationship between input and output, it can approximate the real-world correlation as closely as possible. The similarity model trained in this way can output the corresponding similarity score in real time, and the output results are highly reliable.

[0088] The embodiments of this application do not limit the user equipment, which may be, for example, a mobile phone, tablet computer, laptop computer, desktop computer, smart wearable device or other smart terminal device, or the user equipment may be a workstation or console.

[0089] In some implementations, the notification message can be one or more of text, image, video, and voice messages. The notification message can be sent via SMS, email, in-app push notifications, or phone calls, and the applications used may include WeChat, Alipay, or mini-programs.

[0090] In some optional embodiments, the preset action further includes a first bending action and a second bending action, wherein the first bending action is an upper body forward bending action and the second bending action is an upper body backward bending action;

[0091] The method may further include:

[0092] Based on the full-body image of the first bending action, the first bending angle corresponding to the user is obtained;

[0093] Based on the full-body image of the second bending action, the second bending angle corresponding to the user is obtained;

[0094] Based on the first bending angle and the second bending angle, the user's scoliosis assessment information is obtained, which is used to indicate the degree of the user's scoliosis.

[0095] Therefore, generally speaking, compared to users without scoliosis, users with scoliosis will have a greater difference between the first and second bending angles when performing forward bending and backward bending movements. For example, if a user has scoliosis due to anterior pelvic tilt, performing forward bending may be more difficult than performing backward bending. By comparing the first and second bending angles, the degree of scoliosis can be reflected. This non-contact method of scoliosis detection is low-cost and provides relatively accurate results.

[0096] In some implementations, the user device can display action prompts corresponding to preset actions to guide the user to perform the preset actions more correctly. The action prompts can be one or more of text, image, video, and voice information.

[0097] For example, when the preset movement is a forward bend, the text message "Stand in Mountain Pose with your hands on your hips; exhale and bend forward from your hips, not from your waist" is displayed on the user's device, along with an image or video of a person performing the forward bend.

[0098] When the preset action is an upper back bend, the text message "Stand upright with your feet together and straight; inhale, straighten your arms upward, keep your shoulders level, not one higher than the other; exhale, bend your body backward with your arms, push your hips forward, tuck your tailbone in, and extend your spine backward and upward" is displayed on the user's device, along with an image or video of a person performing the upper back bend.

[0099] When the preset action is to bend the upper body to the left hip joint, the user device will display the text message "Keep your legs together and straight, inhale, raise your arms from your sides, clasp your hands together, straighten your arms, exhale, slowly bend your upper body to the left, and perform a left flexion to fully extend your left waist", along with an image or video of a person bending their upper body to the left hip joint.

[0100] When the preset action is to bend the upper body to the right hip joint, the user device will display the text message "Keep your legs together and straight, inhale, raise your arms from your sides, clasp your hands together, straighten your arms, exhale, slowly bend your upper body to the right, and perform a right flexion to fully extend your right waist", along with an image or video of a person bending their upper body to the right hip joint.

[0101] In some optional embodiments, the preset action further includes a third bending action and a fourth bending action, wherein the third bending action is a bending action of the upper body toward the left hip joint, and the fourth bending action is a bending action of the upper body toward the right hip joint.

[0102] The method may further include:

[0103] Based on the full-body image of the third bending action, the third bending angle corresponding to the user is obtained;

[0104] Based on the full-body image of the fourth bending action, the fourth bending angle corresponding to the user is obtained;

[0105] The processor is configured to acquire the user's scoliosis assessment information in the following manner:

[0106] Based on the first bending angle, the second bending angle, the third bending angle, and the fourth bending angle, the user's scoliosis assessment information is obtained.

[0107] Therefore, generally speaking, for users without scoliosis, the difference in bending angles between bending to the left and right is smaller. Compared to users without scoliosis, users with scoliosis will have a larger difference in the third and fourth bending angles when performing the two movements of bending the upper body to the left hip joint (left bending) and bending the upper body to the right hip joint (right bending). By comparing the first and second bending angles, and combining the comparison results of the first and second bending angles, the degree of scoliosis of the user can be further reflected, and the accuracy of the test results can be improved.

[0108] In some implementations, the first bending angle can be the angle between the user's back and buttocks, the second bending angle can be the angle between the user's abdomen and thigh, the third bending angle can be the angle between the user's left waist and thigh, and the fourth bending angle can be the angle between the user's right waist and thigh.

[0109] In some optional embodiments, the method may further include:

[0110] Obtain the balance corresponding to each bending action;

[0111] The processor is configured to acquire the user's scoliosis assessment information in the following manner:

[0112] Based on the first bending angle, the second bending angle, the third bending angle, the fourth bending angle, and the balance corresponding to each bending action, the user's scoliosis assessment information is obtained.

[0113] In some alternative embodiments, the method may further include:

[0114] The number of vibrations for each bending action performed by the user within a preset time period is obtained, and the balance degree corresponding to each bending action is obtained based on the number of vibrations for each bending action.

[0115] The processor is configured to acquire the user's scoliosis assessment information in the following manner:

[0116] Based on the first bending angle, the second bending angle, the third bending angle, the fourth bending angle, and the balance corresponding to each bending action, the user's scoliosis assessment information is obtained.

[0117] Therefore, when users perform bending movements, it causes muscle fatigue, which in turn produces a certain degree of shaking. Computer vision detection technology can be used to obtain the number of shaking movements of the user within a preset time. The fewer the shaking movements, the better the user's balance in performing the movement; the more shaking movements, the worse the user's balance in performing the movement.

[0118] When a user has scoliosis, not only do the bending angles differ when performing different bending movements, but the degree of balance also varies. Balance can be calculated by counting the number of shakes during each bending movement within a preset time. By evaluating both balance and bending angle in each bending movement, the user's scoliosis assessment information can be obtained, further improving the accuracy of the detection results.

[0119] In one specific implementation, full-body images of the user's torso (upper body) bending in four directions (forward, backward, left, and right) are acquired respectively (i.e., the first bending action, the second bending action, the third bending action, and the fourth bending action). These full-body images are then processed into 360-degree multi-directional stereoscopic dynamic imaging and displayed as a three-dimensional view (three-dimensional model) on the corresponding display device to facilitate relevant analysis and judgment by doctors.

[0120] For example, a doctor can rotate the 3D view to observe the user's posture in different directions.

[0121] Scoliosis is characterized by the spine curving to one side. For example, if the lumbar spine curves to the right, it is called right scoliosis, and if the lumbar spine curves to the left, it is called left scoliosis.

[0122] For users with right scoliosis, when bending their upper body to the right, the bending angle will be larger because the direction is the same as the scoliosis, and the balance will be correspondingly higher (specifically, the frequency of body shaking will be lower). However, when bending their upper body to the left, the body will be twisted because the direction is opposite to the scoliosis, which will cause discomfort. The bending angle will be smaller, and the balance will be correspondingly lower (specifically, the frequency of body shaking will be higher).

[0123] The embodiments of this application do not limit the preset duration, which may be, for example, 1 minute, 2 minutes or 3 minutes.

[0124] Balance can be expressed as a score or a grade. A higher score or grade indicates that the user has a better balance ability when performing the preset action, while a lower score or grade indicates that the user has a worse balance ability when performing the preset action.

[0125] In a specific application, the degree of balance can be represented by a number between 0 and 1.

[0126] The process for obtaining the balance corresponding to each bending action is as follows:

[0127] If the number of shaking events within 1 minute is no more than 5, then the balance degree corresponding to this bending action is 1.

[0128] If the number of shaking events is greater than 5 but not more than 10 within 1 minute, the balance of the bending action is 0.5.

[0129] If the number of shaking events is greater than 10 within 1 minute, the balance of the bending action is 0.2.

[0130] Scoliosis assessment information can be expressed in terms of scores or grades. Higher scores or grades indicate a more severe degree of scoliosis, while lower scores or grades indicate a milder degree of scoliosis.

[0131] In some implementations, a user's scoliosis assessment information can be represented by a scoliosis score, and the process of calculating the scoliosis score is as follows:

[0132] Scoliosis score = Second bending angle × Balance corresponding to the second bending action - First bending angle × Balance corresponding to the first bending action + Fourth bending angle × Balance corresponding to the fourth bending action - Third bending angle × Balance corresponding to the third bending action

[0133] In a specific application, User A's first bending angle is 70 degrees, and the balance corresponding to the first bending action is 0.5; the second bending angle is 100 degrees, and the balance corresponding to the first bending action is 0.5; the third bending angle is 120 degrees, and the balance corresponding to the third bending action is 1; the fourth bending angle is 130 degrees, and the balance corresponding to the fourth bending action is 1. User Xiao Wang's scoliosis score = 100×0.5 - 70×0.5 + 130×1 - 120×1 = 25.

[0134] In some optional embodiments, the method may further include:

[0135] A first pressure sensor is used to obtain the first pressure corresponding to the user's left foot, and a second pressure sensor is used to obtain the second pressure corresponding to the user's right foot. The first pressure sensor is located on the sole of the user's left foot, and the second pressure sensor is located on the sole of the user's right foot.

[0136] Based on the first pressure and the second pressure, the user's scoliosis assessment information is obtained.

[0137] Therefore, generally speaking, the pressure on the two feet of a user with scoliosis is different. When the user is standing, by comparing the first pressure corresponding to the left foot and the second pressure corresponding to the right foot, the degree of scoliosis can be reflected. The detection process is relatively simple and easy to implement.

[0138] In some embodiments, the first and second pressure sensors can be flat-panel pressure sensors. The user stands upright on the ground with their shoulders and hips level with the ground and their feet shoulder-width apart. The first pressure sensor is located on the sole of the user's left foot, and the second pressure sensor is located on the sole of the user's right foot. The first and second pressure sensors detect the weight distribution of the user's two feet (the first pressure corresponding to the left foot and the second pressure corresponding to the right foot).

[0139] A user's scoliosis assessment information can be represented by a scoliosis score. The process of calculating the scoliosis score is as follows:

[0140] The pressure difference between the first pressure and the second pressure is obtained, and the user's scoliosis score is obtained based on the pressure difference.

[0141] Scoliosis scores are directly proportional to pressure gradients; the higher the pressure gradient, the higher the scoliosis score, and the more severe the user's scoliosis.

[0142] In some optional embodiments, the method may further include:

[0143] The infrared thermal image of the user was acquired using an infrared thermal imaging device;

[0144] Based on the infrared thermogram, the first temperature difference information on both sides of the user's spine is obtained, and the first temperature difference information is used to indicate the temperature difference value of symmetrical parts on both sides of the spine.

[0145] Based on the first temperature difference information, the user's scoliosis assessment information is obtained.

[0146] Therefore, since the temperature of the inflamed area is higher than that of other areas, diseases can be diagnosed based on temperature information. Infrared thermal imaging detection technology is not affected by subjective or objective factors during examination and can visually reflect tissue damage and metabolic changes.

[0147] Generally, the infrared thermogram of a normal human back (without scoliosis) shows a symmetrical distribution, with the temperature decreasing from the midline of the spine towards both sides. If a user reports scoliosis, the temperature distribution will not be symmetrical, and there will be a larger temperature difference between the symmetrical parts on both sides of the spine (the side with the higher temperature is the direction of scoliosis). Infrared thermal imaging equipment can be used to obtain the user's infrared thermogram, thereby obtaining the first temperature difference information between the two sides of the user's spine. The degree of scoliosis can be assessed based on the temperature difference between the symmetrical parts on both sides of the spine.

[0148] In some implementations, the infrared thermal imaging device can be an infrared thermal imager, which can achieve long-distance non-contact temperature measurement. Compared with thermopile measuring the temperature of a specific point (small area), the thermal imager measures the temperature of the entire phase surface (large area) and forms a temperature image (infrared thermal map), allowing the user to intuitively understand the temperature distribution of the object being measured.

[0149] An infrared thermal imager is a device that uses infrared thermal imaging technology to detect the infrared radiation of a target object and, through signal processing and photoelectric conversion, converts the temperature distribution of the target object into a visual image. The infrared thermal imager accurately quantifies the actual detected heat and images the entire target object in real time as a surface, thus accurately identifying suspected faulty areas that are overheating. Operators can use the image color and hotspot tracking display on the screen to make a preliminary judgment on the overheating situation and the location of the fault.

[0150] In some optional embodiments, obtaining the user's scoliosis assessment information may include:

[0151] Based on the infrared thermal image, the second temperature difference information of the user's second type of preset joint is obtained. The second temperature difference information is used to indicate the temperature difference between the second type of preset joint and its adjacent area. The second type of preset joint is any one of the following: shoulder joint, hip joint and knee joint.

[0152] Based on the first temperature difference information and the second temperature difference information, the user's scoliosis assessment information is obtained.

[0153] As a result, most scoliosis patients experience uneven stress on their limb joints, and some joints (shoulder, hip, or knee joints) may suffer from strain, leading to inflammation. This causes the body temperature at the site of inflammation to be higher. The degree of strain on the second-type preset joint can be determined by the temperature difference between the second-type preset joint and its adjacent area. Combined with the temperature difference between symmetrical parts on both sides of the spine, the degree of scoliosis of the patient can be assessed.

[0154] The embodiments of this application do not limit the adjacent area of ​​the second type of preset joint. The adjacent area can be an area with the center of the second type of preset joint as the center and the radius as a preset size. The preset size can be 1 cm, 2 cm or 3 cm.

[0155] Generally speaking, the greater the temperature difference between symmetrical parts on both sides of the spine, and / or the greater the temperature difference between the second-type preset joint and its adjacent area, the more severe the user's scoliosis.

[0156] In other embodiments, a thermopile sensor can be used to measure the temperature difference between the temperature of the second type of preset joint and its adjacent area.

[0157] A thermopile is a pyroelectric infrared sensor, which is a device composed of multiple thermocouples. Thermopile has been widely used as a temperature detection device in fields such as ear thermometers, radiation thermometers, electric ovens, and food temperature detection.

[0158] The structure of a thermopile sensor: The radiation receiving surface is divided into several blocks, each connected to a thermocouple. These blocks are connected in series to form a thermopile. Depending on the application, thermopile sensors can be made into filament or thin-film types, as well as multi-channel or array devices.

[0159] As a non-contact infrared temperature sensor, a thermopile can quickly measure the surface temperature of an object without direct contact. It can measure sensibly high-temperature, hazardous, or moving objects without contaminating or damaging them. Thermocouples, on the other hand, are widely used as temperature sensors due to their robustness, durability, low cost, ease of use, and wide temperature range.

[0160] Thermopile infrared sensors are a type of non-contact measurement application. Objects emit radiation that enters the thermopile, where a thermocouple on a silicon chip absorbs this infrared energy and generates and outputs an electrical signal. The higher the temperature of the object being measured, the more infrared energy is generated.

[0161] In some embodiments, the method may further include:

[0162] The preset rehabilitation training video corresponding to the scoliosis assessment information is pushed to the user device.

[0163] For users with mild scoliosis, targeted rehabilitation training every day can improve the symptoms of scoliosis.

[0164] This application also provides a detection process for scoliosis, the specific process of which is as follows:

[0165] 1. Collect the full-body image of the user performing a standing action, perform a linear transformation on the main body form of the full-body image, abstract the spine, shoulders, and waist and hips as the character "shi", and perform a comparison with the standard normal posture after processing.

[0166] 2. Respectively collect the full-body images of the user's torso (upper body) bending forward, backward, left, and right, and perform a secondary analysis based on the bending degree and balance of the bending action. The full-body image can be processed with 360-degree multi-directional stereoscopic dynamic imaging to form a three-dimensional view, which is convenient to provide to professional doctors for relevant analysis and judgment.

[0167] 3. Under the condition of the user's standing posture, with the feet shoulder-width apart, obtain the gravity distribution of the user's two feet through a flat pressure sensor respectively, perform a further analysis of the scoliosis degree, and obtain the scoliosis detection result (i.e., scoliosis evaluation information).

[0168] 4. As an auxiliary diagnostic method, adopt PIR directional thermopile infrared technology for local body temperature diagnosis to help judge the inflammation formed by local joint stress injury possibly caused by scoliosis (the body temperature of the inflamed part is on the high side).

[0169] The applicable population of the scoliosis detection method in the embodiments of the present application can be people under 18 years old. These people have the highest risk of scoliosis and require the greatest supervision. Of course, the scoliosis detection method can also be targeted at adult users, with a wide range of user groups, and the detection method is very simple. Teenagers and children can also easily get started, and the use of the software of the user device can also enable parents to pay attention to the health of their children in real time through remote detection.

[0170] The scoliosis detection method can not only detect a single individual, but also perform batch screening. For some schools, purchasing 2-3 spine detection devices and placing them in the cafeteria or hall can supervise the health of children in real time. For today's parents, the health and privacy of their children are of the utmost importance. Using the spine detection device can perform real-time sampling and analysis on adolescent scoliosis, achieve real-time monitoring, and变相 protect the privacy of children.

[0171] The embodiments of the present application also provide a scoliosis detection device. The specific implementation manner of the scoliosis detection device is the same as the implementation manner and the achieved technical effects recorded in the above method embodiments, and some contents will not be repeated.

[0172] The scoliosis detection device includes a processor, and the processor is configured to implement the following steps:

[0173] Use an image acquisition device to obtain the full-body image of the user performing a preset action, and the preset action includes a standing action;

[0174] A thinning algorithm is used to extract thinning lines from the full-body image of the standing action to obtain the thinning lines of the user's first type of preset joints, which include the spinal joint, shoulder joint and hip joint.

[0175] Based on the refinement lines of the first type of preset joints, the user's posture information is obtained, and the similarity between the user's posture information and the standard posture information is calculated.

[0176] When the similarity is less than a preset similarity threshold, a prompt message is generated and sent to the user's device. The prompt message is used to indicate that the user has scoliosis.

[0177] In some optional embodiments, the preset action further includes a first bending action and a second bending action, wherein the first bending action is an upper body forward bending action and the second bending action is an upper body backward bending action;

[0178] The processor is also configured to perform the following steps:

[0179] Based on the full-body image of the first bending action, the first bending angle corresponding to the user is obtained;

[0180] Based on the full-body image of the second bending action, the second bending angle corresponding to the user is obtained;

[0181] Based on the first bending angle and the second bending angle, the user's scoliosis assessment information is obtained, which is used to indicate the degree of the user's scoliosis.

[0182] In some optional embodiments, the preset action further includes a third bending action and a fourth bending action, wherein the third bending action is a bending action of the upper body toward the left hip joint, and the fourth bending action is a bending action of the upper body toward the right hip joint.

[0183] The processor is also configured to perform the following steps:

[0184] Based on the full-body image of the third bending action, the third bending angle corresponding to the user is obtained;

[0185] Based on the full-body image of the fourth bending action, the fourth bending angle corresponding to the user is obtained;

[0186] The processor is configured to acquire the user's scoliosis assessment information in the following manner:

[0187] Based on the first bending angle, the second bending angle, the third bending angle, and the fourth bending angle, the user's scoliosis assessment information is obtained.

[0188] In some alternative embodiments, the processor is further configured to perform the following steps:

[0189] The number of vibrations for each bending action performed by the user within a preset time period is obtained, and the balance degree corresponding to each bending action is obtained based on the number of vibrations for each bending action.

[0190] The processor is configured to acquire the user's scoliosis assessment information in the following manner:

[0191] Based on the first bending angle, the second bending angle, the third bending angle, the fourth bending angle, and the balance corresponding to each bending action, the user's scoliosis assessment information is obtained.

[0192] In some alternative embodiments, the processor is further configured to perform the following steps:

[0193] A first pressure sensor is used to obtain the first pressure corresponding to the user's left foot, and a second pressure sensor is used to obtain the second pressure corresponding to the user's right foot. The first pressure sensor is located on the sole of the user's left foot, and the second pressure sensor is located on the sole of the user's right foot.

[0194] Based on the first pressure and the second pressure, the user's scoliosis assessment information is obtained.

[0195] In some alternative embodiments, the processor is further configured to perform the following steps:

[0196] The infrared thermal image of the user was acquired using an infrared thermal imaging device;

[0197] Based on the infrared thermogram, the first temperature difference information on both sides of the user's spine is obtained, and the first temperature difference information is used to indicate the temperature difference value of symmetrical parts on both sides of the spine.

[0198] Based on the first temperature difference information, the user's scoliosis assessment information is obtained.

[0199] In some alternative embodiments, the processor is configured to acquire the user's scoliosis assessment information using the following steps:

[0200] Based on the infrared thermal image, the second temperature difference information of the user's second type of preset joint is obtained. The second temperature difference information is used to indicate the temperature difference between the second type of preset joint and its adjacent area. The second type of preset joint is any one of the following: shoulder joint, hip joint and knee joint.

[0201] Based on the first temperature difference information and the second temperature difference information, the user's scoliosis assessment information is obtained.

[0202] See Figure 2 , Figure 2 This is a structural block diagram of a scoliosis detection device 200 provided in an embodiment of this application.

[0203] The scoliosis detection device 200 includes at least one memory 210 and at least one processor 220. The scoliosis detection device 200 may also include a bus 230 for connecting different platform systems.

[0204] The memory 210 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 211 and / or cache memory 212, and may further include read-only memory (ROM) 213.

[0205] The memory 210 also stores a computer program, which can be executed by the processor 220 to enable the processor 220 to perform the functions of any of the above-mentioned devices or to perform the steps of any of the above-mentioned methods. The specific implementation method is consistent with the implementation method and the technical effect achieved in the above-mentioned method embodiments, and some contents will not be repeated.

[0206] The memory 210 may also include a utility 214 having at least one program module 215, such program module 215 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0207] Accordingly, processor 220 can execute the aforementioned computer program, and can also execute utility 214.

[0208] The processor 220 may employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0209] Bus 230 can be one or more of several types of bus structures, including memory bus or memory autonomous vehicle, peripheral bus, graphics acceleration port, processor, or local bus using any bus structure using multiple bus structures.

[0210] The scoliosis detection device 200 can also communicate with one or more external devices 240, such as a keyboard, pointing device, Bluetooth device, etc., and with one or more devices capable of interacting with the scoliosis detection device 200, and / or with any device that enables the scoliosis detection device 200 to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication can be performed via input / output interface 250. Furthermore, the scoliosis detection device 200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 260. Network adapter 260 can communicate with other modules of the scoliosis detection device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the scoliosis detection device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0211] See Figure 3 , Figure 3 This is a structural block diagram of a scoliosis detection system 100 provided in an embodiment of this application.

[0212] The specific implementation of the scoliosis detection system 100 is consistent with the implementation method and the technical effects achieved as described in the above method embodiments, and some details will not be repeated here.

[0213] The scoliosis detection system 100 includes an image acquisition device 300 and any of the above-mentioned scoliosis detection devices 200, wherein the image acquisition device 300 and the scoliosis detection device 200 are electrically connected.

[0214] The image acquisition device 300 is used to acquire full-body images of the user performing preset actions.

[0215] In some optional embodiments, the scoliosis detection system 100 further includes an infrared thermal imaging device 400, a first pressure sensor 500 disposed on the sole of the user's left foot, and a second pressure sensor 600 disposed on the sole of the user's right foot.

[0216] The scoliosis detection device 200 is electrically connected to the infrared thermal imaging device 400, the first pressure sensor 500, and the second pressure sensor 600, respectively.

[0217] The infrared thermal imaging device 400 is used to acquire the infrared thermal image of the user, the first pressure sensor 500 is used to acquire the first pressure corresponding to the user's left foot, and the second pressure sensor 600 is used to acquire the second pressure corresponding to the user's right foot.

[0218] This application also provides a computer-readable storage medium for storing a computer program. When the computer program is executed, it implements the steps of any of the above methods. The specific implementation method is consistent with the implementation method and the technical effect achieved in the above method embodiments, and some contents will not be repeated.

[0219] See Figure 4 , Figure 4 A schematic diagram of the structure of a program product provided in an embodiment of this application is shown.

[0220] The program product is used to implement any of the methods described above. The program product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this application, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0221] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, or any suitable combination thereof. Program code for performing operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code may be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0222] This application describes the invention from the perspectives of purpose, performance, progress, and novelty, and it meets the functional enhancement and use requirements emphasized by the Patent Law. The above description and drawings are merely preferred embodiments of this application and are not intended to limit this application. Therefore, all structures, devices, features, etc., that are similar to or identical to those of this application, i.e., all equivalent substitutions or modifications made in accordance with the scope of this patent application, shall fall within the scope of protection of this patent application.

Claims

1. A scoliosis detection device, characterized in that, The scoliosis detection device includes a processor configured to perform the following steps: The image acquisition device is used to acquire a full-body image of the user performing a preset action, including a standing action. A thinning algorithm is used to extract thinning lines from the full-body image of the preset action to obtain the thinning lines of the user's first type of preset joints, which include the spinal joint, shoulder joint and hip joint. Based on the refinement lines of the first type of preset joints, the user's posture information is obtained, and the similarity between the user's posture information and the standard posture information is calculated. When the similarity is less than a preset similarity threshold, a prompt message is generated and sent to the user's device. The prompt message is used to indicate that the user has scoliosis. The preset movements also include a first bending movement, a second bending movement, a third bending movement, and a fourth bending movement; the first bending movement is a forward bending movement of the upper body, the second bending movement is a backward bending movement of the upper body, the third bending movement is a bending movement of the upper body towards the left hip joint, and the fourth bending movement is a bending movement of the upper body towards the right hip joint. The processor is also configured to perform the following steps: Based on the full-body image of the first bending action, the first bending angle corresponding to the user is obtained; Based on the full-body image of the second bending action, the second bending angle corresponding to the user is obtained; Based on the full-body image of the third bending action, the third bending angle corresponding to the user is obtained; Based on the full-body image of the fourth bending action, the fourth bending angle corresponding to the user is obtained; The processor is also configured to perform the following steps: The number of vibrations for each bending action performed by the user within a preset time period is obtained, and the balance degree corresponding to each bending action is obtained based on the number of vibrations for each bending action. Based on the first bending angle, the second bending angle, the third bending angle, the fourth bending angle, and the balance corresponding to each bending action, the user's scoliosis assessment information is obtained; The user's scoliosis assessment information is represented by a scoliosis score: Scoliosis score = Second bending angle × Balance corresponding to the second bending action - First bending angle × Balance corresponding to the first bending action + Fourth bending angle × Balance corresponding to the fourth bending action - Third bending angle × Balance corresponding to the third bending action 2. The scoliosis detection device according to claim 1, characterized in that, The processor is also configured to perform the following steps: A first pressure sensor is used to obtain the first pressure corresponding to the user's left foot, and a second pressure sensor is used to obtain the second pressure corresponding to the user's right foot. The first pressure sensor is located on the sole of the user's left foot, and the second pressure sensor is located on the sole of the user's right foot. Based on the first pressure and the second pressure, the user's scoliosis assessment information is obtained.

3. The scoliosis detection device according to claim 1, characterized in that, The processor is also configured to perform the following steps: The infrared thermal image of the user was acquired using an infrared thermal imaging device; Based on the infrared thermogram, the first temperature difference information on both sides of the user's spine is obtained, and the first temperature difference information is used to indicate the temperature difference value of symmetrical parts on both sides of the spine. Based on the first temperature difference information, the user's scoliosis assessment information is obtained.

4. The scoliosis detection device according to claim 3, characterized in that, The processor is configured to acquire the user's scoliosis assessment information using the following steps: Based on the infrared thermal image, the second temperature difference information of the user's second type of preset joint is obtained. The second temperature difference information is used to indicate the temperature difference between the second type of preset joint and its adjacent area. The second type of preset joint is any one of the following: shoulder joint, hip joint and knee joint. Based on the first temperature difference information and the second temperature difference information, the user's scoliosis assessment information is obtained.

5. A scoliosis detection system, characterized in that, The scoliosis detection system includes an image acquisition device and a scoliosis detection apparatus according to any one of claims 1-4, wherein the image acquisition device and the scoliosis detection apparatus are electrically connected. The image acquisition device is used to acquire full-body images of the user performing preset actions.

6. The scoliosis detection system according to claim 5, characterized in that, The scoliosis detection system also includes an infrared thermal imaging device, a first pressure sensor, and a second pressure sensor. The scoliosis detection device is electrically connected to the infrared thermal imaging device, the first pressure sensor and the second pressure sensor, respectively. The infrared thermal imaging device is used to acquire the infrared thermal image of the user, the first pressure sensor is used to acquire the first pressure corresponding to the user's left foot, and the second pressure sensor is used to acquire the second pressure corresponding to the user's right foot.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the function of the scoliosis detection device according to any one of claims 1-4.

Images