Posture evaluation device, posture evaluation system, posture evaluation method, and program

Abstract

To provide a posture evaluation device, a posture evaluation system, a posture evaluation method, and a program capable of evaluating a backward bending posture appropriately.SOLUTION: A posture evaluation device includes a feature amount calculation unit and a state estimation unit. The feature amount calculation unit calculates a feature amount indicating a feature of the inclination of the head at least with respect to the trunk on the basis of body information including the information showing at least the trunk inclination and the head inclination in the body of an object person in a backward bending state in which the object person is bending backward. The state estimation unit estimates at least a state of the backbone in the backward bending state on the basis of the calculated feature amount.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a posture evaluation device, a posture evaluation system, a posture evaluation method, and a program. [Background technology]

[0002] In recent years, with the spread of online training and self-training, there is a growing need for ordinary people without specialized knowledge to evaluate their own posture.

[0003] Patent Document 1 describes a posture measuring device that aims to simply measure the posture of a measured object. The measuring device described in Patent Document 1 estimates the position, size, and posture of a measured object in a posture measuring image, which is a camera image of the measured object. The measuring device includes a posture measuring means that obtains a center line of the contour of the measured object in the posture measuring image from the posture measuring image and the estimation result, and measures the posture of the measured object from the inclination of this center line. The posture measuring means includes an edge extracting means, a center line estimating means, and a center line determining means. The edge extracting means extracts edges of the posture measuring image to create an edge image. The center line estimating means estimates the center line of the contour of the measured object in the posture measuring image from the estimation result. The center line determining means receives the estimated center line from the center line estimating means and the edge image from the edge extracting means, and determines the center line from the edges in the edge image near the estimated center line. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2000-207568 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, with the measurement device described in Patent Document 1, it is not possible to measure and evaluate the backward bending posture of the measured object relatively easily and with high accuracy, especially when the subject is wearing clothes, because the clothes hide the actual shape of the back.

[0006] An object of the present disclosure is to provide a posture evaluation device, a posture evaluation system, a posture evaluation method, and a program that can appropriately evaluate a backward bending posture. [Means for solving the problem]

[0007] A posture assessment device according to a first aspect of the present disclosure includes a feature calculation unit that calculates a feature indicating at least a characteristic of the tilt of the head relative to the trunk based on physical information including information indicating at least a tilt of the trunk and a tilt of the head of a subject in a backward bending state, and a state estimation unit that estimates a state of at least the spine in the backward bending state based on the feature.

[0008] A posture evaluation system according to a second aspect of the present disclosure comprises a posture evaluation device and a terminal device capable of communicating with the posture evaluation device, wherein the posture evaluation device comprises a feature calculation unit that calculates a feature indicating at least a characteristic of the tilt of the head relative to the trunk based on physical information acquired by the terminal device, the feature including information indicating at least a tilt of the trunk and a tilt of the head of the subject's body when the subject is in a backward bending state, and a state estimation unit that estimates at least a state of the spine when in the backward bending state based on the feature.

[0009] A posture evaluation method according to a third aspect of the present disclosure includes a posture evaluation device that calculates features indicating at least the characteristics of the tilt of the head relative to the trunk based on physical information including information indicating at least the tilt of the trunk and the tilt of the head of a subject in a backward bending state, and estimates the state of at least the spine in the backward bending state based on the features.

[0010] A program according to a fourth aspect of the present disclosure is a program for causing a computer to execute a posture evaluation process in which, based on physical information including information indicating at least the inclination of the trunk and the inclination of the head of a subject in a backward bending state, a feature amount indicating at least the characteristics of the inclination of the head relative to the trunk is calculated based on physical information including information indicating at least the inclination of the trunk and the inclination of the head of a subject in a backward bending state, and, based on the feature amount, an estimate is made of at least the state of the spine in the backward bending state. Effect of the Invention

[0011] According to the present disclosure, it is possible to provide a posture evaluation device, a posture evaluation system, a posture evaluation method, and a program that can appropriately evaluate a backward bending posture. [Brief description of the drawings]

[0012] [Figure 1] 1 is a block diagram showing an example of the configuration of a posture assessment device according to the present disclosure. [Diagram 2] FIG. 13 is a block diagram showing another configuration example of a posture assessment device according to the present disclosure. [Diagram 3] 1 is a diagram showing an example of an image captured by an imaging unit of a posture evaluation device according to the present disclosure. FIG. [Figure 4] FIG. 1 is a diagram showing an example of key points according to the present disclosure. [Diagram 5] FIG. 13 is a diagram illustrating an example of a line segment connecting key points according to the present disclosure. [Figure 6] FIG. 1 is a diagram illustrating an example of a feature amount according to the present disclosure. [Figure 7] FIG. 13 is a diagram showing another example of feature amounts according to the present disclosure. [Figure 8] FIG. 13 is a diagram showing an example of a state label output as a state estimation result according to the present disclosure. [Figure 9] FIG. 2 is a diagram showing an example of an image displayed on a display unit according to the present disclosure. [Figure 10] FIG. 13 is a diagram showing another example of an image displayed on the display unit according to the present disclosure. [Figure 11] FIG. 13 is a diagram showing another example of an image displayed on the display unit according to the present disclosure. [Figure 12] FIG. 13 is a diagram showing another example of an image displayed on the display unit according to the present disclosure. [Figure 13] 1 is a flowchart illustrating a posture assessment method according to the present disclosure. [Figure 14] FIG. 1 is a diagram illustrating an example of a configuration of a posture evaluation system according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] First embodiment An example of the configuration of the posture evaluation device 1 will be described below with reference to FIG. As shown in FIG. 1, the posture evaluation device 1 includes a feature amount calculation unit 1a and a state estimation unit 1b.

[0014] The feature amount calculation unit 1a calculates a feature amount indicating at least the tilt of the head relative to the trunk based on body information including information indicating at least the tilt of the trunk and the tilt of the head in the subject's body in a backward bending state. The information indicating the tilt of a part such as the trunk or the head can be, for example, information indicating the angle of the part or the positions of both ends.

[0015] Here, the inclination refers to the inclination when the subject is viewed from the side, that is, the inclination in the sagittal plane, or in other words, the inclination in the direction along the sagittal plane, and the following description will be based on this premise, but processing may also be performed that includes the inclination in the coronal plane in the retroflexed state. Similarly, the position described below will be based on the premise that it refers to the position in the sagittal plane, but processing may also be performed that includes the position in the coronal plane in the retroflexed state.

[0016] The physical information may also include an image of the side of the subject's body in a retroflexed state. Taking an image of the side of the subject's body refers to taking an image of the subject from a direction perpendicular to the subject's sagittal plane. This image may be obtained by, for example, taking an image of the side of the subject's body with a camera such as a smartphone. In this way, the feature amount calculation unit 1a may calculate the feature amount using such an image. The image included in the physical information may include an image of the subject's body in a retroflexed state taken from the opposite side or from a side other than the side.

[0017] Alternatively, the body information may include information extracted from the image. That is, the feature calculation unit 1a may calculate the feature using the information extracted from the image. Examples of the extracted information include position information indicating the position of the body's skeleton, or a position indicating a key point other than the skeleton, or both of them. Of course, the body information may include both the image and the information extracted from the image. Examples of the image and the information extracted from the image will be described in the second embodiment, and examples of the information extracted from the image include position information indicating a position indicating a predetermined part that can be estimated from the skeleton.

[0018] The feature amount calculated by the feature amount calculation unit 1a may be at least a feature amount indicating the characteristics of the tilt of the head relative to the trunk. For example, the calculated feature amount may be expressed as a value such as the angle of the straight line of the tilt direction of the head relative to the straight line of the tilt direction of the trunk, or a level value when the angle is assigned to one of multiple levels by threshold processing or the like.

[0019] The feature calculation unit 1a may also calculate the feature by inputting physical information and outputting the feature using a learning model obtained by machine learning from data of many subjects. The algorithm of this learning model is not limited, and various types of algorithms such as a linear regression model and a support vector machine can be adopted.

[0020] The state estimation unit 1b estimates at least the state of the spine in a backward bending state, that is, at least the state of the spine in a backward bending posture, based on the feature amount calculated by the feature amount calculation unit 1a. The target of estimation may include, for example, the state of one or more parts among various parts such as the upper thoracic vertebrae, the lower thoracic vertebrae, the lumbar vertebrae, the lumbosacral junction, the hip joint, the upper limbs, the scapular spine, the anterior superior iliac spine, the knee joint, and the ankle joint. The estimation of the state of these parts will be exemplified in the second embodiment and onwards.

[0021] For example, the state estimation unit 1b may store in advance in an internal memory a correspondence table that associates features with the state of the spine, etc. in a backward bending posture, and may refer to the correspondence table to search for the state of the spine, etc. in a backward bending posture that corresponds to the feature received from the feature calculation unit 1a.

[0022] The state estimation unit 1b may estimate the state by inputting features and outputting the state of the spine, etc., in a retroflex state using a learning model obtained by machine learning from data of many subjects. The algorithm of this learning model is not limited, and various types of algorithms, such as a linear regression model or a support vector machine, can be adopted.

[0023] In this way, the posture evaluation device 1 is a device that evaluates the backward bending posture based on the physical information. Even when the subject is wearing clothes and the physical information does not include information on the tilt or position of the spine, the posture evaluation device 1 can estimate the state of the spine in the backward bending posture for the following reasons. That is, even in such a case, the posture evaluation device 1 can estimate the state of the spine in the backward bending posture based on alternative movements of parts other than the spine, such as the tilt of the trunk and head caused by the mobility of the spine.

[0024] In fact, the shape of the spine can be estimated using the shape of the back, which is easily observed from the body surface. However, if the subject is wearing clothes, the clothes will hide the shape of the back in the backward bending posture. In particular, if the clothes do not fit the subject, the sagging of the clothes will hide the shape of the back to a large extent. Therefore, in such a case, it is difficult to accurately evaluate the backward bending posture for evaluating the extension range of the spine, that is, the extension posture, by processing based on the shape of the back without adopting this embodiment. Therefore, in order to perform such an accurate evaluation without adopting this embodiment, expensive specialized equipment such as a method using a depth camera, a method using an acceleration sensor, a method of scanning a measuring probe along the spine, etc. is required. In other words, without using such expensive specialized equipment, the accuracy of the posture evaluation cannot be said to be sufficient compared to the accuracy of the posture evaluation by a specialist such as a therapist or trainer. However, a specialist such as a therapist or trainer evaluates the balance of the bending of the entire spine, and does not evaluate the position or inclination of each vertebra. Therefore, for the purpose of ordinary people evaluating their own posture at an expert level, there is no need to aim for the same level of accuracy as the methods that require the above-mentioned specialized equipment.

[0025] On the other hand, the posture evaluation device 1 estimates the state of the spine etc. in a backward bending state using information on the head and trunk which are easy to grasp from the outside and move in conjunction with the spine, rather than information on the spine which is difficult to estimate from the outside. In other words, the posture evaluation device 1 estimates the state of the spine based on compensatory movements that occur in parts other than the spine depending on the mobility of the spine, rather than on the shape of the spine itself.

[0026] In this way, the posture evaluation device 1 can estimate and evaluate at an expert level the state of the spine and other parts in a backward bending posture even from information that can be easily obtained as physical information. In other words, the posture evaluation device 1 can estimate and evaluate the state of the spine and other parts in a backward bending posture relatively easily and with high accuracy. Furthermore, with the spread of online training and self-training, there is an increasing need for ordinary people to evaluate their own posture and alignment, and this embodiment can also meet such needs.

[0027] In particular, by including the above-mentioned image or information extracted from the image in the physical information, it is possible to estimate at least the state of the spine in a backward bending posture from information obtained by imaging the side of the body with a camera of a smartphone or the like. This makes it possible for even non-experts such as trainers and therapists to use images obtained with a camera of a smartphone or the like to evaluate posture and alignment in a backward bending posture, particularly evaluation of each part of the spine. Therefore, in situations such as online training and self-training, it is possible to relatively easily and accurately evaluate the state of the spine in a backward bending posture.

[0028] In addition, this embodiment can be used for self-training or online training by a subject, regardless of whether or not there is advice from a trainer, therapist, etc. In addition, this embodiment can be used for simple screening of a subject by a trainer, therapist, etc. before treatment.

[0029] As described above, the posture evaluation device 1 is capable of evaluating the backward bending posture in particular. However, the posture evaluation device 1 may be equipped with a function for evaluating other postures such as the forward bending posture and the standing posture.

[0030] Embodiment 2 An example of the configuration of the posture evaluation device 100 will be described with reference to FIG. The posture evaluation device 100 shown in Fig. 2 is, for example, a user terminal such as a smartphone, a tablet terminal, or a personal computer owned by a user. The user includes both a subject whose posture is evaluated by the posture evaluation device 100 and an evaluator who evaluates the posture of others using the posture evaluation device 100. When a subject evaluates his / her own posture using the posture evaluation device 100 in self-training or the like, the subject is also the evaluator. When an evaluator evaluates the posture of others using the posture evaluation device 100, the evaluator is, for example, a therapist or a trainer.

[0031] 2, the posture evaluation device 100 includes an imaging unit 101, a skeleton extraction unit 102, a feature calculation unit 103, a state estimation unit 104, an image generation unit 105, a communication unit 106, an input unit 107, a display unit 108, and a storage unit 110. The input unit 107 and the display unit 108 may be integrated into a single touch panel display, or may be provided separately. The storage unit 110 stores a reference value list 111, a skeleton database (Database: DB) 112, a skeleton extraction model 113, and the like. The feature calculation unit 103 and the state estimation unit 104 are examples of the feature calculation unit 1a and the state estimation unit 1b, respectively.

[0032] The imaging unit 101 captures an image of the side of the body of a subject in a backward bending posture. FIG. 3 shows an example of an image of the side of the body of a subject captured by the imaging unit 101. The image shown in FIG. 3 shows the side of a person O corresponding to the subject bending backward. Here, the image captured by the imaging unit 101 is a two-dimensional image, and may be a two-dimensional RGB image. The imaging unit 101 inputs the captured image to the skeleton extraction unit 102.

[0033] The imaging unit 101 may also capture a moving image of the side of the body of the subject in a backward bending posture to obtain an image. In this case, the user may operate the input unit 107 to specify a time point at which the backward bending posture is evaluated. Then, the image at the time point specified by the user may be input to the skeleton extraction unit 102.

[0034] The skeleton extraction unit 102 extracts position information indicating the positions of, for example, the head, cervical vertebrae, and hip joints from the image captured by the imaging unit 101. Hereinafter, such positions of the extraction target are also referred to as "key points," and the position information indicating those positions is also referred to as "position information of key points."

[0035] Moreover, the position information on the image is, for example, image coordinates. Here, the image coordinates are coordinates for indicating the position of a pixel on a two-dimensional image, and are defined as coordinates in which, for example, the center of the pixel located at the leftmost and uppermost side of the two-dimensional image is the origin, the left-right direction or horizontal direction is the x direction, and the up-down direction or vertical direction is the y direction.

[0036] Examples of key points extracted by the skeleton extraction unit 102 will be given with reference to Figures 3 to 5. Figure 4 shows an example of key points P1 to P6 extracted by the skeleton extraction unit 102 from the image shown in Figure 3. In Figures 3 to 5, the symbol Sa indicates a sagging portion of the user's jacket.

[0037] In Figures 4 and 5, P1 is the key point of the eye, P2 is the key point of the ear, P3 is the key point of the vertebrae, P4 is the key point of the hip joint, and in Figures 4 and 5, P5 is the key point of the anterior superior iliac spine, and P6 is the key point of the knee joint.

[0038] Hereinafter, eye keypoints will be referred to as eye keypoints. Hereinafter, ear keypoints will be referred to as ear keypoints, and similar abbreviations will be used. Hereinafter, ear keypoints and eye keypoints are used as position information indicating the positions of two points on the head, but for example, a keypoint at the center of the head can also be used. Also, vertebral protuberance keypoints are used as position information indicating the position of the cervical vertebrae.

[0039] Thus, the position information of the cervical vertebrae on the image is described here as being the position information of the protuberance (C7), but it may be the position information of any of the seven vertebrae that make up the cervical vertebrae. The position information of the protuberance is, for example, the position information of a pixel located at the center of an image region on the image that corresponds to the protuberance. For other parts, the position information of a pixel located at the center of the part can be used in a similar manner. Also, for example, when a part has a size that cannot be represented by a single position, the position information of the part may be the position information indicating the position of a pixel at one or both ends of the part.

[0040] The skeleton extraction unit 102 uses the trained skeleton extraction model 113 to extract position information of, for example, key points P1 to P4 from the image captured by the imaging unit 101. In practice, the position of each key point is estimated by the skeleton extraction model 113, and position information indicating the position is extracted. The posture evaluation device 100 performs machine learning in advance using the skeleton extraction model 113, which is a machine learning model, and the skeleton database 112, which is teacher data, to generate the trained skeleton extraction model 113. The algorithm of the skeleton extraction model 113 is not important, and for example, a model using deep learning is used. Even if the eyes and ears are hidden by the arms in the image, the position information of the eye key points and ear key points can be extracted from the shape of the head.

[0041] The position information of the key points may be information expressed in three-dimensional coordinates defined by the z direction, which is the depth direction, in addition to the x direction, which is the left-right or horizontal direction, and the y direction, which is the up-down or vertical direction, of the two-dimensional image captured by the imaging unit 101. This is possible by using a skeleton extraction model 113 that extracts the position information of the key points expressed in three-dimensional coordinates from the two-dimensional image.

[0042] Furthermore, the body parts from which the skeleton extraction unit 102 extracts key points are not limited to the head, cervical vertebrae, hip joints, etc., as described above, and key points such as shoulder joints may be extracted. The positions of the extraction targets may be any of a plurality of parts from which information indicating at least the inclination of the trunk and the inclination of the head can be obtained.

[0043] Furthermore, the skeleton extraction unit 102 calculates information indicating at least the inclination of the trunk and the inclination of the head from the position information of the key points extracted in this manner, for example, by geometric calculation. Figure 5 shows an example of line segments connecting key points.

[0044] For example, the skeleton extraction unit 102 calculates the difference between the coordinates of the eye key point P1 and the ear key point P2 in the x and y directions, and obtains the difference value as information indicating the tilt of the head, or performs a geometric calculation from the difference value to obtain an angle θ1 indicating the tilt of the head. Similarly, the skeleton extraction unit 102 calculates the difference between the coordinates of the vertebral key point P3 and the hip joint key point P4 in the x and y directions, and obtains the difference value as information indicating the tilt of the trunk, or performs a geometric calculation from the difference value to obtain an angle θ2 indicating the tilt of the trunk.

[0045] Here, the angles θ1 and θ2 are both calculated as angles relative to the horizontal line, but they may be angles relative to a plumb line. A supplementary explanation will be given of how to calculate the plumb line and the horizontal line in an image, which can be used for calculating such angles and for calculating the feature amount described later. Assuming that the imaging unit 101 is fixed horizontally in the left-right direction and vertically in the front-back direction, the lines parallel to the left and right sides and the top and bottom sides of the image are respectively the plumb line and the horizontal line. At the same time as still image shooting or video shooting by the imaging unit 101, tilt information of the imaging unit 101 is obtained using a separately provided acceleration sensor or the like, and the plumb line and the horizontal line in the key point coordinate system are calculated using this information.

[0046] Furthermore, the key points may be specified by the user operating the input unit 107 while the image captured by the imaging unit 101 is displayed on the display unit 108. Then, position information of the key points specified by the user is input to the skeleton extraction unit 102, which calculates information indicating at least the inclination of the trunk and the inclination of the head.

[0047] Then, skeleton extraction unit 102 inputs physical information including at least information indicating the calculated inclination of the trunk and inclination of the head to feature calculation unit 103. In this manner, in this embodiment, skeleton extraction unit 102 extracts position information from the image, and passes the extracted position information to feature calculation unit 103 as at least a part of the physical information.

[0048] The feature amount calculation unit 103 calculates a feature amount indicating at least the inclination characteristic of the head relative to the trunk, based on the physical information input from the skeleton extraction unit 102. In this way, the feature amount calculation unit 103 does not need to calculate a feature amount for the spine that is the evaluation target in the posture evaluation device 100.

[0049] The feature amount calculation unit 103 calculates the feature amount as an angle between any two of a line segment connecting two key points, a line indicating the inclination of a specific portion, a vertical line in the image, and a horizontal line in the image.

[0050] An example of the feature calculated by the feature calculation unit 103 will be described with reference to Fig. 6. The feature calculation unit 103 calculates the feature as, for example, an angle θ5 between a line segment connecting key points P1 and P2 and a line segment connecting key points P3 and P4. The angle θ5 is a feature that indicates the characteristic of a line indicating the inclination of the head relative to a line indicating the inclination of the trunk.

[0051] Alternatively, the feature calculation unit 103 calculates the feature as, for example, the angle θ6 between the line segment connecting the key points P2 and P3 and the line segment connecting the key points P3 and P4. The angle θ6 is also a feature that indicates the characteristic of the line indicating the inclination of the head relative to the line indicating the inclination of the trunk.

[0052] In this way, the physical information used to calculate the feature amount can include information indicating the positions of at least the cervical vertebrae, hip joints, eyes, and ears of the user in the backward bending state (for convenience, referred to as first position information).The feature amount calculation unit 103 can then calculate the inclination of the trunk and the inclination of the head based on this first position information, and use the calculated inclination of the trunk and the inclination of the head to calculate a feature amount indicating at least the characteristics of the inclination of the head relative to the trunk.

[0053] The physical information may also include information indicating the position of the head with respect to the trunk in the user's body in the backward bending state, i.e., the relative position of the head with respect to the trunk. In this case, the feature amount calculation unit 103 calculates not only the feature amount of the head inclination with respect to the trunk, but also the feature amount indicating the feature amount of the head position with respect to the trunk.

[0054] Also in this example, the physical information can include the above-mentioned first position information. For example, the position of the trunk and the position of the head can be calculated using the eye key point P1, the ear key point P2, the vertebral protuberance key point P3, and the hip joint key point P4, respectively, as well as their inclinations. Then, the feature amount calculation unit 103 can calculate the inclination of the trunk, the inclination of the head, and the position of the head relative to the trunk based on this first position information, and calculate the following feature amounts. That is, the feature amount calculation unit 103 can calculate feature amounts indicating at least the characteristics of the inclination and position of the head relative to the trunk, using the calculated inclination of the trunk, the inclination of the head, and the position of the head relative to the trunk.

[0055] Furthermore, even if the subject is clothed, the shape of the front of the body can be known to some extent. Therefore, in this embodiment, the inclination of the pelvis and the shape of the trunk can be estimated using information on the front of the body, the shape of which is easy to grasp even when the subject is in a clothed, backward bending posture, and the estimation results can be used as features.

[0056] The feature amount calculation unit 103 estimates the inclination of the pelvis by the following method. That is, the feature amount calculation unit 103 obtains the inclination of the tangent to the edge of the front surface of the body at the position of the anterior superior iliac spine key point P5 as the inclination of the pelvis, and sets this inclination as the feature amount related to the pelvis. This inclination refers to the inclination of the tangent to the front surface edge of the user's body passing through the anterior superior iliac spine key point P5 in FIG. 5. This inclination is expressed, for example, by an angle θ3 indicating the inclination to the line segment connecting the vertebral protuberance key point P3 and the hip joint key point P4, or an angle θ4 indicating the inclination to the line segment connecting the hip joint key point P4 and the knee joint key point P6.

[0057] That is, in this example, the body information used to calculate the feature amount includes information indicating the edge of the front side (body front) of the user in the backward bending state, and the feature amount calculation unit 103 calculates at least the feature amount related to the pelvis based on the information indicating the edge of the body front. The edge of the body front here is different from the edge described in Patent Document 1, and particularly refers to the whole or part of the boundary between the body area and the non-body area in the image that is located in the front of the body. The boundary between the body area and the non-body area in the image may be obtained by estimating the body area and the non-body area in the image, respectively, using a trained area extraction model, for example. Alternatively, the boundary may be obtained by estimating the boundary located in the body front from an edge-enhanced image obtained by applying an edge-enhancing filter such as a Laplacian filter to the image. Alternatively, the boundary may be provided by the user via the input unit 107.

[0058] Alternatively, the feature amount calculation unit 103 obtains the inclination of the pelvis at the height of the hip joint key point P4, and regards this as the feature amount related to the pelvis. Note that instead of this inclination, the inclination of a line passing through the anterior superior iliac spine key point P5 and the posterior superior iliac spine key point (not shown) can be used, although this is not information on the front of the body.

[0059] In this way, the body information used to calculate the feature amount may include information indicating the positions of the anterior superior iliac spine and the posterior superior iliac spine of the user in the retroflexed state (for convenience, referred to as second position information). Then, the feature amount calculation unit 103 calculates at least the feature amount related to the pelvis based on this second position information.

[0060] The feature amount calculation unit 103 can also calculate the feature amount using the shape of the trunk. Shape information of the front of the body is easier to obtain than shape information of the rear of the body, but is easily affected by the shapes of the chest and abdomen. The shapes of the chest and abdomen that affect the front of the body can indicate the degree of obesity of the user. Therefore, the feature amount calculation unit 103 may estimate the shape of the trunk by the following method, and the estimated result may be used as the feature amount.

[0061] First, the feature amount calculation unit 103 obtains the edges of the front and rear surfaces of the trunk. i Line l passing through (i=1, ,n) (i,θ) and the intersection point p of the edges of the front and rear of the trunk (i,θ) (f) ,p (i,θ) (b) Here, l (i,θ) can be taken as an infinite number of values, but in implementation, the angle from the horizontal line can be defined as θ, and the angle can be limited to increments of 5 degrees, for example, as follows: θ={0°,5°,10°,...,175°}

[0062] The edges of the front and rear torso here, like the edges of the front body, differ from the edges described in Patent Document 1, and in particular refer to the whole or part of the boundary between the body area and the non-body area in the image, located on the front and rear of the torso, respectively. These can be obtained, for example, by a method similar to that for the edges of the front body.

[0063] Next, the feature amount calculation unit 103 calculates the intersection point {(p (i,θ) (f) ,p (i,θ) (b) )} (θ=0°,··,···,175°) Let p be the pair of intersections that has the smallest distance. i Finally, let N be a positive integer and let the set of N representative points {p i (f)} (i=1,···,n) The shape of the front surface of the body is determined by interpolating the shape of the front surface of the body by fitting an n-th order power function or a spline function. The feature amount calculation unit 103 then uses this shape of the front surface of the body to calculate the curvature and the angle between the tangent lines as feature amounts.

[0064] In this way, the feature amount calculation unit 103 can calculate at least the feature amount related to the spine based on the information indicating the edge of the front surface of the body. The feature amount calculation unit 103 can also calculate at least the feature amount related to the spine based on the above-mentioned second position information.

[0065] Here, an example of a feature calculated by the feature calculation unit 103 using key points will be described with reference to FIG. 7. The feature calculation unit 103 can calculate, as an angle θ7, an angle between a straight line passing through the vertebral prominence key point P3 and the hip joint key point P4 and a straight line passing through the shoulder joint key point P7 and the elbow joint key point P8, as a feature indicating an upper limb lift angle. The feature calculation unit 103 can also calculate, as an angle θ8, an angle between a line segment connecting the vertebral prominence key point P3 and the hip joint key point P4 and a vertical line passing through the hip joint key point P4 in the image, as a feature indicating a trunk backward inclination angle. This trunk backward inclination angle represents the angle of the trunk with respect to the vertical line.

[0066] The feature calculation unit 103 can calculate the angle between the line segment connecting the vertebral protuberance key point P3 and the hip joint key point P4 and the line segment connecting the hip joint key point P4 and the knee joint key point P6 as a feature indicating the hip joint angle, as indicated by the angle θ9. This hip joint angle represents the angle of the hip joint with respect to the trunk. The feature calculation unit 103 can calculate the angle between the line segment connecting the knee joint key point P6 and the ankle joint key point P9 and the line segment connecting the hip joint key point P4 and the knee joint key point P6 as a feature indicating the knee joint angle, as indicated by the angle θ10. Here, the angle θ10 indicates the angle between the line segment connecting the knee joint key point P6 and the ankle joint key point P9 and the line segment connecting the hip joint key point P4 and the knee joint key point P6. The knee joint key point P6 on the image is a key point indicating the position of any of the lower end of the femur, the patella, the upper end of the tibia, the upper end of the fibula, and the knee joint space, for example, a key point at the position of the lower end of the femur.

[0067] Furthermore, the feature calculation unit 103 can calculate the angle between the line segment connecting the knee joint key point P6 and the ankle joint key point P9 and the horizontal line passing through the ankle joint key point P9 in the image as the feature indicating the ankle joint angle, as indicated by the angle θ11. This ankle joint angle represents the angle of the ankle joint with respect to the horizontal line. Alternatively, the feature calculation unit 103 may calculate the angle between the line segment connecting the knee joint key point P6 and the ankle joint key point P9 and a line segment connecting a key point indicating the position of the toes and the ankle joint key point P9 (not shown) as the feature indicating the ankle joint angle. The key point indicating the toes can be, for example, a key point indicating the position of the distal phalanx of the third toe, but is not limited thereto.

[0068] The feature calculation unit 103 can also calculate the angle between the line segment connecting the hip joint key point P4 and the ankle joint key point P9 and the vertical line passing through the ankle joint key point P9 in the image as an angle θ12, as a feature indicating the position of the hip joint relative to the ankle joint. The feature calculation unit 103 can also calculate the angle between the line segment connecting the shoulder joint key point P7 and the ankle joint key point P9 and the vertical line passing through the ankle joint key point P9 in the image as an angle θ13, as a feature indicating the position of the shoulder joint relative to the ankle joint.

[0069] Next, the state estimation unit 104 will be described. The state estimation unit 104 estimates at least the state of the spine in the backward bending state based on the feature amount calculated by the feature amount calculation unit 103.

[0070] The state estimation unit 104 estimates the state of the spine in a backward bending posture based on a feature quantity indicating the inclination of at least the head relative to the trunk, such as at least one of the angles θ5 and θ6 described above. In other words, the state of the spine is estimated based on compensatory movements of parts other than the spine that occur according to the mobility of the spine, not on the shape of the spine itself. The state estimation unit 104 captures the compensation of the cervical vertebrae curving and extending according to the mobility of the upper thoracic vertebrae by using the position and inclination of the head, and indirectly estimates the state of the upper thoracic vertebrae. Specifically, at least one of the angles θ5 and θ6 is obtained, and the state of the upper thoracic vertebrae is estimated based on, for example, a reference value of the head angle or the neck angle.

[0071] In addition, the state estimation unit 104 can improve the accuracy of estimating the state of the upper thoracic vertebrae by using features other than the head angle and the neck angle, and can estimate the state of parts of the spine other than the upper thoracic vertebrae, such as the lower thoracic vertebrae, lumbar vertebrae, and the lumbar-sacral junction. The targets of estimation may include the hip joint, upper limbs, scapular spine, anterior superior iliac spine, knee joint, and ankle joint.

[0072] Moreover, the state estimation unit 104 stores in the storage unit 110 a reference value list 111 in which each feature amount is associated with its reference value. The reference value list 111 is an example of a correspondence table that associates the feature amount with the state of the spine, etc. in a backward bending posture, as described in the first embodiment. Here, the reference value is a value within a range that the feature amount can take when a body part such as the spine is normal. The state estimation unit 104 then refers to the reference value list 111 based on the feature amount input from the feature amount calculation unit 103, and estimates the state of the spine, etc., depending on whether the feature amount satisfies the reference value or not. For example, when a certain feature amount satisfies the reference value, the state estimation unit 104 estimates that the state of the feature amount is appropriate, when the reference value is exceeded, the state estimation unit 104 estimates that the extension, etc. during backward bending is excessive, and when the reference value is exceeded, the state estimation unit 104 estimates that the extension, etc. during backward bending is insufficient.

[0073] An example of the estimation result for each part output by the state estimation unit 104 will be given using FIG. 8. Here, an example will be given in which a state label is output as the estimation result. For example, as shown in FIG. 8, if the feature amount indicating the characteristics of the upper thoracic vertebrae is within a reference value, the state estimation unit 104 estimates that the extension is appropriate, and outputs a state label "1". An example of the feature amount indicating the characteristics of the upper thoracic vertebrae is, for example, a trunk backward tilt angle. Furthermore, if the feature amount indicating the characteristics of the upper thoracic vertebrae exceeds a reference value, the state estimation unit 104 estimates that the extension is excessive, and outputs a state label "0". Furthermore, if the feature amount indicating the characteristics of the upper thoracic vertebrae is below a reference value, the state estimation unit 104 estimates that the extension is insufficient, and outputs a state label "2".

[0074] The lower thoracic vertebrae, lumbar vertebrae, lumbar-sacral junction, and hip joints are also processed in the same manner as the upper thoracic vertebrae. Feature quantities indicative of the characteristics of the lower thoracic vertebrae and lumbar-sacral junction include, for example, the trunk posterior tilt angle. Feature quantities indicative of the characteristics of the lumbar vertebrae include, for example, the trunk posterior tilt angle. Feature quantities indicative of the characteristics of the hip joints include, for example, the hip joint angle.

[0075] If the feature quantity indicating the characteristics of the ankle joint is within a reference value, the state estimation unit 104 estimates that the dorsiflexion is appropriate, and outputs a state label "1." Examples of feature quantities indicating the characteristics of the ankle joint include the ankle joint angle. If the feature quantity indicating the characteristics of the ankle joint is below a reference value, the state estimation unit 104 estimates that the dorsiflexion is excessive, and outputs a state label "0." If the feature quantity indicates the characteristics of the ankle joint is above the reference value, the state estimation unit 104 estimates that the dorsiflexion is insufficient, and outputs a state label "2."

[0076] The reference values ​​for the upper limbs, scapular spine, anterior superior iliac spine, and knee joint can each be set to one threshold value. If the feature amount indicating the characteristics of the upper limbs is equal to or greater than the reference value, the state estimation unit 104 estimates that the fist is sufficiently raised and outputs a state label "1". If the feature amount is less than the reference value, the state estimation unit 104 estimates that the fist is not sufficiently raised and outputs a state label "2". An example of the feature amount indicating the characteristics of the upper limbs is the angle of the upper limbs being raised. If the feature amount indicating the characteristics of the scapular spine is equal to or greater than the reference value, the state estimation unit 104 estimates that the horizontal position of the scapular spine exceeds the horizontal position of the heel and outputs a state label "1". If the feature amount is less than the reference value, the state estimation unit 104 estimates that the horizontal position of the scapular spine does not exceed the horizontal position of the heel and outputs a state label "2". An example of the feature amount indicating the characteristics of the scapular spine is the position of the shoulder joint relative to the ankle joint.

[0077] If the feature amount indicating the characteristic of the anterior superior iliac spine is equal to or greater than a reference value, the state estimation unit 104 estimates that the horizontal position exceeds the horizontal position of the toes and outputs a state label "1". If the feature amount is less than the reference value, the state estimation unit 104 estimates that the horizontal position does not exceed the horizontal position of the toes and outputs a state label "2". An example of the feature amount indicating the characteristic of the anterior superior iliac spine is the hip joint position relative to the ankle joint. If the feature amount indicating the characteristic of the knee joint is equal to or less than a reference value, the state estimation unit 104 estimates that there is no flexion and outputs a state label "1". If the feature amount exceeds the reference value, the state estimation unit 104 estimates that there is flexion and outputs a state label "2". An example of the feature amount indicating the characteristic of the knee joint is the knee joint angle.

[0078] Furthermore, the state estimation unit 104 may use a state estimation model as a learning model generated by machine learning, input the feature amount to the state estimation model, and obtain the state estimation result as the output. When the state estimation unit 104 performs estimation using a state estimation model, the state estimation model may be stored in advance in the storage unit 110. The state estimation model may be a model that is machine-learned using a data set in which the feature amount is associated with a state label such as "excessive", "moderate", or "insufficient" as correct answer data. The state estimation unit 104 inputs the estimation result thus obtained to the image generation unit 105 .

[0079] The image generation unit 105 generates an estimation result display image to be displayed by the display unit 108, based on the estimation result input from the state estimation unit 104. This estimation result image may include an image obtained by normalizing the image captured by the imaging unit 101. Then, the image generation unit 105 inputs the generated image to the display unit 108.

[0080] The display unit 108 displays the estimation result display image input from the image generation unit 105. That is, the display unit 108 can display at least a part of the result estimated by the state estimation unit 104. The display unit 108 is configured with various display means such as an LCD (Liquid Crystal Display) and an LED (Light Emitting Diode). Figs. 9 to 12 show various examples of the estimation result display image displayed on the display unit 108.

[0081] 9, the display unit 108 of the posture evaluation device 100 displays an image portion G0 showing the estimation result of the backward bending posture, that is, the evaluation result of the backward bending posture. The image portion G0 includes a list of part names and the evaluation results of the corresponding states. In the image portion G0, the estimation results that indicate non-normality are highlighted with a star mark M, but it is preferable to display them in a display form different from that of normal parts, for example, by highlighting them in bold or red instead.

[0082] 10, the display unit 108 of the posture evaluation device 100 displays an image portion G1 in which the estimation result is superimposed on the image captured by the imaging unit 101. In the image portion G1, the rough areas of the parts where the estimation result shows that they are not normal are highlighted by being surrounded by a figure such as an ellipse or a circle. In addition, the image portion G1 also includes a sentence explaining that each area is not normal, such as "upper thoracic vertebrae: insufficient extension", "lower thoracic vertebrae: insufficient extension", and "knee joint: flexed".

[0083] 11, an image portion G2 in which line segments connecting key points related to calculation of each key point and angles, etc. are superimposed on an image captured by the imaging unit 101 is displayed on the display unit 108 of the posture evaluation device 100. The shape G21 of the front of the trunk estimated by the feature calculation unit 103 may also be displayed in the image portion G2. At least one of the image portion G0 in FIG. 9 and the image portion G1 in FIG. 10 may also be displayed on the display unit 108 together with the image portion G2.

[0084] Furthermore, the display unit 108 may display the image for correction input from the image generating unit 105, for example, by displaying the image portion G2 so that correction can be accepted. This allows, for example, when a key point extracted by the skeleton extracting unit 102 is incorrect, the user to correct the key point by dragging the target key point displayed on the screen requiring correction.

[0085] 12, an image selection area G3 is displayed on display unit 108 of posture evaluation device 100. Image selection area G3 is an image area in which a plurality of thumbnail images of a moving image input from imaging unit 101 are arranged along a time scale T1, and a designation bar T2 for designating a time point at which posture evaluation is to be performed is displayed so as to be movable along the time scale T1. Image generation unit 105 may generate image selection area G3 to be displayed on display unit 108, based on the image input from imaging unit 101.

[0086] Furthermore, the image generation unit 105 generates an image portion G2 by superimposing the estimation result on the image at the time point designated by the user in the image selection area G3 displayed on the display unit 108. The image generation unit 105 generates an image portion G0 by superimposing the estimation result on the image at the time point designated by the user in the image selection area G3 displayed on the display unit 108. Then, the image generation unit 105 inputs the generated image selection area G3, image portion G2, and image portion G0 to the display unit 108.

[0087] Display unit 108 displays image selection area G3, image portion G2, and image portion G0 input from image generation unit 105. In the example shown in Fig. 12, image selection area G3 is displayed on the lower side of display unit 108 of posture evaluation device 100, image portion G2 is displayed on the upper left side of display unit 108, and image portion G0 is displayed on the upper right side of display unit 108. In the example shown in Fig. 12, designation bar T2 is moved by the user in image selection area G3 to designate 0 minutes 11 seconds as the time point for posture evaluation.

[0088] The posture evaluation device 100 may also include a change unit that changes at least one of the display form and the display contents of the result based on the presentation target person to whom the estimated result is presented. The change unit may execute at least one of the display form and the display contents according to a user operation that accepts a user operation specifying the presentation target person from the input unit 107, or according to user information of the user who uses the posture evaluation device 100. For example, when the presentation target person is a user, a display form as shown in FIG. 10 that is easier to understand can be applied, and when the presentation target person is a trainer or the like, a display form as shown in FIG. 9, FIG. 11, or FIG. 12 that shows more information can be applied. Of course, the contents and display forms to be displayed on the display unit 108 are not limited to those exemplified in FIG. 9 to FIG. 12.

[0089] The communication unit 106 communicates with an external server, other terminal devices, etc. The communication unit 106 may include an antenna (not shown) for wireless communication, or may include an interface such as a NIC (Network Interface Card) for wired communication.

[0090] The input unit 107 receives operation instructions from a user. The input unit 107 may be configured with a keyboard or a touch panel display device. The input unit 107 may be configured with a keyboard or a touch panel connected to the posture evaluation device 100 main body.

[0091] The storage unit 110 stores a reference value list 111, a skeleton database 112, a skeleton extraction model 113, and the like. The storage unit 110 may include a non-volatile memory (e.g., a ROM (Read Only Memory)) in which various programs and various data required for processing are fixedly stored. The storage unit 110 may also use a HDD (Hard Disk Drive) or an SSD (Solid-State Drive). The storage unit 110 may further include a volatile memory, such as a RAM (Random Access Memory), used as a working area. The above programs may be read from a portable recording medium such as an optical disk or a semiconductor memory, or may be downloaded from a server device on a network.

[0092] The reference value list 111 is a list in which each feature amount in the backward bending posture is associated with its reference value. Note that the reference value list 111 can be prepared for each posture, such as a forward bending posture or a standing posture, in addition to the backward bending posture.

[0093] The skeleton database 112 is a database in which a plurality of images obtained by capturing an image of the side of the body in a backward bending posture are associated with position information of key points as correct labels.

[0094] The skeleton extraction model 113 is a learning model that extracts position information of key points from an image obtained by imaging the side of the body when the user is in a backward bending posture. In other words, the skeleton extraction model 113 is a learning model that infers and outputs position information of key points using an image obtained by imaging the side of the body of a user in a backward bending posture as an input. Note that in this specification, machine learning may be deep learning, but is not particularly limited to this.

[0095] Next, the posture evaluation method executed by the posture evaluation device 100 will be described with reference to Fig. 13. Only a simple flow will be described here, but the various examples described above can also be applied.

[0096] First, the imaging unit 101 captures an image of the side of the body (step S101), and inputs the obtained image to the skeleton extraction unit 102. Next, the skeleton extraction unit 102 extracts position information of key points from the image captured by the imaging unit 101 in step S101 (step S102). Next, the skeleton extraction unit 102 calculates information indicating at least the inclination of the trunk and the inclination of the head based on the extracted position information, and inputs the information to the feature calculation unit 103 (step S103).

[0097] Next, the feature amount calculation unit 103 calculates a feature amount indicating at least the inclination characteristic of the head relative to the trunk based on the information input from the skeleton extraction unit 102 (step S104). Then, the feature amount calculation unit 103 inputs the calculated feature amount to the state estimation unit 104.

[0098] Next, the state estimation unit 104 estimates the state of at least the spine, such as the upper thoracic vertebrae, the lower thoracic vertebrae, and the lumbar vertebrae, based on the feature amount input from the feature amount calculation unit 103 (step S105). Then, the state estimation unit 104 inputs the estimation result to the image generation unit 105.

[0099] Next, the image generating unit 105 generates an image to be displayed on the display unit 108 based on the image captured in step S101 and the states of the upper thoracic vertebrae, lower thoracic vertebrae, lumbar vertebrae, etc. estimated in step S105 (step S106). The image generated by the image generating unit 105 is then input to the display unit 108. Next, the display unit 108 displays the image generated in step S106 (step S107), and this process ends.

[0100] Note that, instead of the process of step S102, each key point may be specified by displaying an image captured by the imaging unit 101 on the display unit 108 and the user operating the input unit 107.

[0101] According to the second embodiment, similarly to the first embodiment, it is possible to relatively easily and accurately evaluate the backward bending posture even when the user is wearing clothes, and further, by performing the evaluation based on an image, it is not necessary to use expensive specialized equipment.

[0102] Moreover, according to the second embodiment, the accuracy of the evaluation can be improved by using key points that are relatively easy to extract, such as the eyes and ears. Moreover, according to the second embodiment, the physical information includes information indicating the position of the head relative to the trunk, thereby reducing the processing load required for calculating the feature amount and allowing accurate calculation of the feature amount. Moreover, according to the second embodiment, the physical information includes information indicating the edge of the front surface of the user's body, thereby allowing the use of information that is relatively easy to recognize from an image, thereby allowing the accuracy of the evaluation to be improved, and the evaluation of the pelvis can also be performed with high accuracy. Moreover, according to the second embodiment, the physical information includes information indicating the positions of the anterior superior iliac spine and the posterior superior iliac spine, thereby allowing the evaluation of not only the spine but also the pelvis with high accuracy.

[0103] Furthermore, by including the skeleton extraction unit 102 in the posture evaluation device 100, key points are extracted from an image captured by the imaging unit 101, eliminating the need for the user to specify key points on the image.

[0104] Furthermore, the skeleton extraction unit 102 may use the trained skeleton extraction model 113 to extract key points expressed in three-dimensional coordinates defined by the z direction, which is the depth direction, in addition to the x direction, which is the left-right or horizontal direction, and the y direction, which is the up-down or vertical direction, of the two-dimensional image captured by the imaging unit 101. This enables more precise posture evaluation.

[0105] Moreover, the display unit 108 displays an estimation result display image that displays the image captured by the imaging unit 101 and the estimation result by the state estimation unit 104, allowing the user to visually grasp the state of posture. Moreover, the posture evaluation device 100 is configured so that the display form, etc., can be changed in the display unit 108 according to the presentation target person, thereby making it possible to perform a display that matches the level of understanding of the presentation target person.

[0106] In addition, in this embodiment, the processing from only the image captured from one side has been described, but the image captured from the other side can also be used for at least one of the processes of extracting key points, calculating feature amounts, and estimating the spine, etc. In the simplest example, in any processing, the desired result can be obtained by calculating the average value of both the left and right sides. Furthermore, even if images from other directions such as the front and back are displayed together when presented to the user, information about the posture that cannot be obtained by simply checking the side of the body, such as whether the left and right sides of the body are moving evenly, can be confirmed. However, the images from the other directions may also be used for at least one of the processes of extracting key points, calculating feature amounts, and estimating the state of the spine, etc.

[0107] Third embodiment Next, a configuration example of the posture evaluation system 200 will be described with reference to Fig. 14. As shown in Fig. 14, the posture evaluation system 200 includes a posture evaluation device 100A and a subject terminal 300 capable of communicating with the posture evaluation device 100A. The posture evaluation device 100A and the subject terminal 300 are capable of communicating with each other via a network N. Also, as shown in Fig. 14, one or more subject terminals 300 may be capable of communicating with the posture evaluation device 100A. Moreover, the subject terminal 300 is a smartphone, tablet terminal, personal computer, or the like possessed by the subject.

[0108] The posture evaluation device 100A acquires an image of the side of the subject's body in a backward bending posture from the subject terminal 300. Therefore, the posture evaluation device 100A differs from the posture evaluation device 100 in Fig. 2 in that the imaging unit 101 may be omitted. In addition, the estimation result display image created by the image generation unit 105 of the posture evaluation device 100A may be transmitted to the subject terminal 300 and displayed on a display unit (not shown) of the subject terminal 300.

[0109] The subject terminal 300 includes an imaging unit (not shown) that images the side of the subject's body in a backward bending posture. The subject terminal 300 transmits the image to the posture evaluation device 100A.

[0110] Other embodiments In the above embodiment, the present disclosure has been described as a hardware configuration, but the present disclosure is not limited to this. The present disclosure can also be realized by having a CPU (Central Processing Unit) execute a computer program to perform the process steps shown in the flowchart of FIG. 13 and the process steps described in the other embodiments.

[0111] Moreover, the above-mentioned program includes a set of instructions (or software code) for making the computer perform one or more functions described in the embodiment when the program is read into the computer. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology. By way of example and not limitation, the computer-readable medium or tangible storage medium includes CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disk or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagating signals.

[0112] The present disclosure is not limited to the above-described embodiment, and can be modified as appropriate without departing from the spirit and scope of the present disclosure.

[0113] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-mentioned embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be appropriately combined with other embodiments.

[0114] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one particular embodiment, but to one or more other embodiments. As will be appreciated by those skilled in the art, various features or steps described with reference to any one drawing may be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0115] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes. (Appendix 1) a feature amount calculation unit that calculates a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information including information indicating at least a tilt of the trunk and a tilt of the head in the body of the subject in a backward bending state in which the subject is bending backward; A state estimation unit that estimates at least a state of the spine in the backward bending state based on the feature amount; A posture assessment device comprising: (Appendix 2) The body information includes an image of the subject's body in the flexed position, or information extracted from the image. 2. The posture assessment device of claim 1. (Appendix 3) The physical information includes information indicating a position of the head relative to the trunk in the subject's body in the backward bending state, the feature amount includes a feature amount indicating a feature amount of a position of the head relative to the trunk, 3. The posture assessment device according to claim 1 or 2. (Appendix 4) The physical information includes first position information indicating positions of at least the cervical vertebrae, hip joints, eyes, and ears of the subject in the backward bending state; the feature amount calculation unit calculates the inclination of the trunk and the inclination of the head based on the first position information, and calculates a feature amount indicating at least a characteristic of the inclination of the head relative to the trunk using the calculated inclination of the trunk and the inclination of the head. 3. The posture assessment device according to claim 1 or 2. (Appendix 5) The physical information includes first position information indicating positions of at least the cervical vertebrae, hip joints, eyes, and ears of the subject in the backward bending state; the feature amount calculation unit calculates the inclination of the trunk, the inclination of the head, and the position of the head relative to the trunk based on the first position information, and calculates feature amounts indicating characteristics of at least the inclination and position of the head relative to the trunk using the calculated inclination of the trunk, the inclination of the head, and the position of the head relative to the trunk; 4. A posture assessment apparatus as described in appended claim 3. (Appendix 6) the physical information includes information indicating a front edge of the subject in the backward bending state, the feature amount calculation unit calculates feature amounts related to at least a pelvis or a spine based on the information indicating the front side edge. 6. A posture evaluation device according to any one of claims 1 to 5. (Appendix 7) The physical information includes second position information indicating positions of the anterior superior iliac spine and the posterior superior iliac spine of the subject in the retroflexion state; The feature amount calculation unit calculates a feature amount related to at least a pelvis or a spine based on the second position information. 7. A posture evaluation device according to any one of claims 1 to 6. (Appendix 8) a display unit that displays at least a part of the result estimated by the state estimation unit; A change unit that changes at least one of a display form and a display content of the result based on a presentation target person to which the result is presented; 8. The posture evaluation device according to claim 1, further comprising: (Appendix 9) A posture evaluation device and a terminal device capable of communicating with the posture evaluation device, The posture evaluation device includes: a feature amount calculation unit that calculates a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information acquired by the terminal device, the feature amount including information indicating at least a tilt of the trunk and a tilt of the head of the subject in a backward bending state in which the subject is bending backward; A state estimation unit that estimates at least a state of the spine in the backward bending state based on the feature amount; A posture assessment system comprising: (Appendix 10) The posture evaluation device calculating a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information including information indicating at least a tilt of a trunk and a tilt of a head in a body of the subject in a backward bending state in which the subject is bending backward; estimating at least a state of the spine in the backward bending state based on the feature amount; Posture assessment methods. (Appendix 11) On the computer, calculating a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information including information indicating at least a tilt of a trunk and a tilt of a head in a body of the subject in a backward bending state in which the subject is bending backward; estimating at least a state of the spine in the backward bending state based on the feature amount; A program for executing posture evaluation processing.

[0116] Some or all of the elements (e.g., configurations and functions) described in Supplementary Note 2 to Supplementary Note 8 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Note 9, Supplementary Note 10, and Supplementary Note 11 in the same dependent relationship as Supplementary Note 2 to Supplementary Note 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods. [Explanation of symbols]

[0117] 1, 100, 100A Posture Evaluation Device 101 Imaging unit 102 Skeleton Extraction Unit 1a, 103 Feature calculation unit 1b, 104 State Estimation Unit 105 Image Generation Unit 106 Communications Department 107 Input section 108 Display section 110 Storage section 111 Reference Value List 112 Skeleton DB (Skeletal Database) 113 Skeleton Extraction Model 200 Posture Evaluation System 300 Target terminal

Claims

1. a feature amount calculation unit that calculates a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information including information indicating at least a tilt of the trunk and a tilt of the head in the body of the subject in a backward bending state in which the subject is bending backward; A state estimation unit that estimates at least a state of the spine in the backward bending state based on the feature amount; A posture assessment device comprising:

2. The body information includes an image of the subject's body in the flexed position, or information extracted from the image. The posture evaluation device according to claim 1 .

3. The physical information includes information indicating a position of the head relative to the trunk in the subject's body in the backward bending state, the feature amount includes a feature amount indicating a feature amount of a position of the head relative to the trunk, The posture evaluation device according to claim 1 .

4. The physical information includes first position information indicating positions of at least the cervical vertebrae, hip joints, eyes, and ears of the subject in the backward bending state; the feature amount calculation unit calculates an inclination of the trunk and an inclination of the head based on the first position information, and calculates a feature amount indicating at least a characteristic of the inclination of the head relative to the trunk using the calculated inclination of the trunk and the inclination of the head. The posture evaluation device according to claim 1 .

5. the physical information includes information indicating a front edge of the subject in the backward bending state, the feature amount calculation unit calculates feature amounts related to at least a pelvis or a spine based on the information indicating the front side edge. The posture evaluation device according to claim 1 .

6. The physical information includes second position information indicating positions of the anterior superior iliac spine and the posterior superior iliac spine of the subject in the retroflexion state; The feature amount calculation unit calculates a feature amount related to at least a pelvis or a spine based on the second position information. The posture evaluation device according to claim 1 .

7. a display unit that displays at least a part of the result estimated by the state estimation unit; a change unit that changes at least one of a display form and a display content of the result based on a presentation target person to which the result is presented; The posture evaluation device according to claim 1 or 2, comprising:

8. A posture evaluation device and a terminal device capable of communicating with the posture evaluation device, The posture evaluation device includes: a feature amount calculation unit that calculates a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information acquired by the terminal device, the feature amount including information indicating at least a tilt of the trunk and a tilt of the head of the subject in a backward bending state in which the subject is bending backward; A state estimation unit that estimates at least a state of the spine in the backward bending state based on the feature amount; A posture assessment system comprising:

9. The posture evaluation device calculating a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information including information indicating at least a tilt of a trunk and a tilt of a head in a body of the subject in a backward bending state in which the subject is bending backward; estimating at least a state of the spine in the backward bending state based on the feature amount; Posture assessment methods.

10. On the computer, calculating a feature amount indicating at least a feature of a tilt of the head relative to the trunk based on physical information including information indicating at least a tilt of a trunk and a tilt of a head in a body of the subject in a backward bending state in which the subject is bending backward; estimating at least a state of the spine in the backward bending state based on the feature amount; A program for executing posture evaluation processing.

Images