Fatigue estimation system, fatigue estimation method, and program recording medium

Abstract

A fatigue estimation system (200) estimates a posture of a subject (11) for a prescribed period based on information output during the prescribed period, determines whether the estimated posture of the subject (11) conforms to a specific posture, and estimates fatigue of the subject (11) accumulated during the prescribed period as a calculated value obtained by accumulating unit fatigue degrees corresponding to periods during which the estimated posture of the subject (11) is determined to conform to the specific posture.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to a fatigue estimation system, a fatigue estimation method, and a program recording medium for estimating fatigue of a subject. BACKGROUND

[0002] In recent years, there are many cases of injuries and accidents due to accumulation of fatigue, which are represented by poor physical condition. In response to this, a technology for preventing injuries, accidents, and the like by estimating the degree of fatigue to prevent them from occurring is attracting attention. For example, as a fatigue estimation system for estimating fatigue degree corresponding to the degree of fatigue described above, a fatigue determination device that determines the presence or absence of fatigue and the type of fatigue based on force measurement and biological impedance measurement is disclosed (see Patent Literature 1).

[0003] PRIOR ART DOCUMENTS

[0004] PATENT LITERATURE

[0005] Patent Literature 1: Japanese Patent Application Publication No. 2017-023311 SUMMARY

[0006] PROBLEMS TO BE SOLVED BY THE INVENTION

[0007] However, the calculation processing for estimating fatigue degree is sometimes not properly performed. Therefore, in the present disclosure, a fatigue estimation system and the like that estimates fatigue degree of a subject by more appropriate calculation processing are provided.

[0008] MEANS FOR SOLVING THE PROBLEMS

[0009] A fatigue estimation system according to a technical solution of the present disclosure includes an information output device that outputs information related to a position of a body part of a subject; a storage device that stores posture fatigue information that is information that establishes a correspondence between a specific posture of the subject and a unit fatigue degree accumulated in the subject by maintaining the specific posture for a unit time; and an estimation device that estimates fatigue degree accumulated in the subject in a prescribed period, in which the estimation device estimates a posture of the subject in the prescribed period based on the information output in the prescribed period, determines whether the estimated posture of the subject conforms to the specific posture, and estimates fatigue degree accumulated in the subject in the prescribed period as a calculation value obtained by accumulating the unit fatigue degree for a period in which the estimated posture of the subject is determined to conform to the specific posture.

[0010] Further, a fatigue estimation method according to the present disclosure includes: an acquisition step of acquiring information regarding a position of a body part of a subject; a readout step of reading out posture fatigue information from a storage device, the posture fatigue information being information in which a specific posture of the subject is associated with a unit fatigue degree accumulated in the subject by maintaining the specific posture for a unit time; and an estimation step of estimating a fatigue degree accumulated in the subject in a prescribed period, in the estimation step, based on the information output in the prescribed period, a posture of the subject in the prescribed period is estimated, it is determined whether the estimated posture of the subject matches the specific posture, and a calculation value obtained by accumulating the unit fatigue degree for a period in which it is determined that the estimated posture of the subject matches the specific posture is estimated as the fatigue degree accumulated in the subject in the prescribed period.

[0011] Further, a fatigue estimation system according to the present disclosure can be realized as a non-transitory recording medium in which a program for causing a computer to execute the above-described fatigue estimation method is recorded.

[0012] Effects of Invention

[0013] A fatigue estimation system according to the present disclosure can estimate a fatigue degree of a subject by more appropriate calculation processing. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 is a schematic diagram that outlines a fatigue estimation system according to an embodiment.

[0015] Figure 2 is a block diagram that shows a functional structure of a fatigue estimation system according to an embodiment.

[0016] Figure 3 is a diagram for explaining posture fatigue information according to an embodiment.

[0017] Figure 4A is a first diagram for explaining a specific posture according to an embodiment.

[0018] Figure 4B is a second diagram for explaining a specific posture according to an embodiment.

[0019] Figure 4C is a third diagram for explaining a specific posture according to an embodiment.

[0020] Figure 5 is a diagram that shows a musculoskeletal model used in construction of posture fatigue information according to an embodiment.

[0021] Figure 6A is a first diagram for explaining a feature quantity according to an embodiment.

[0022] Figure 6B FIG. 2 is a graph illustrating a feature quantity of the embodiment.

[0023] Figure 7 FIG. 3 is a graph illustrating a feature quantity of the embodiment.

[0024] Figure 8 FIG. 4 is a graph illustrating a blank period of the embodiment.

[0025] Figure 9 FIG. 5 is a graph exemplifying information output from the fatigue estimation system of the embodiment.

[0026] Figure 10 FIG. 6 is a flowchart showing an operation of the fatigue estimation system of the embodiment. DETAILED DESCRIPTION

[0027] Hereinafter, the embodiment will be specifically described with reference to the drawings. In addition, the embodiment described below indicates an inclusive or specific example. The numerical value, shape, material, configuration element, arrangement position and connection form of the configuration element, step, order of the steps, and the like indicated in the following embodiment are one example, and are not intended to limit the present disclosure. Furthermore, regarding the configuration element among the configuration elements of the following embodiment, which is not described in the independent claim, it is described as an arbitrary configuration element.

[0028] In addition, each drawing is a schematic diagram, and is not necessarily strictly illustrated. Furthermore, in each drawing, for the substantially same configuration element, the same reference numeral is given, and there is a case where the repeated explanation is omitted or simplified.

[0029] (Embodiment)

[0030] [Structure of System]

[0031] First, with reference to Figure 1 and Figure 2 the overall structure of the fatigue estimation system of the embodiment will be described. Figure 1 FIG. 1 is a schematic diagram illustrating an outline of the fatigue estimation system of the embodiment. In Figure 1 , a situation where the fatigue degree of the subject 11 is estimated using the fatigue estimation system 200 is indicated. In Figure 1 the scene shown, the subject 11 sits on a chair 12 and operates a computer 100a placed on a desk 13.

[0032] In the present embodiment, the fatigue estimation system 200 performs estimation of the fatigue level of the subject 11 based on an image of the subject 11 captured in the imaging device 101. The image captured by the imaging device 101 is transmitted to the estimation device 100 via a network such as the Internet. The estimation device 100 is, for example, a computing processing device installed in a server device such as a cloud server, and performs estimation of the fatigue level of the subject 11 included in the image based on the image. The estimation result is transmitted to the computer 100a operated by the subject 11, for example, via the network, and displayed on the screen of the computer 100a.

[0033] In this way, the subject 11 can confirm the estimation result displayed on the same computer 100a in the work using the computer 100a. In the present embodiment, the example in which the estimation device 100 is realized by the server device as described above is explained, but the structure of the fatigue estimation system is not limited thereto. For example, the estimation device 100 can also be built in the computer 100a. That is, the computer 100a is the estimation device in other embodiments.

[0034] In the present disclosure, in the estimation device 100, when estimating the fatigue level of the subject 11 according to the posture of the subject 11, the calculation processing can be greatly reduced by using the posture fatigue information constructed in advance. Details of the posture fatigue information and the like are described later. With the above configuration, even if the calculation processing is performed using, for example, a computer 100a with low processing performance, the fatigue estimation system 200 can be realized.

[0035] In the case where the computer 100a is used as the estimation device, it is not necessary to have a network and a server device, so the fatigue estimation system 200 can be realized with a simple structure. Further, sometimes a camera is provided at a position of the computer 100a where the subject 11 can be captured, and by using the camera as the imaging device 101 described above, the fatigue estimation system can also be realized by only the computer 100a.

[0036] Further, if the fatigue estimation system 200 is realized using a server device with relatively high processing performance, the estimation result can be obtained at substantially the same time, so the subject 11 can perform work while always grasping the fatigue level of himself or herself.

[0037] Figure 2 is a block diagram showing the functional structure of the fatigue estimation system of the embodiment. As shown in Figure 2 The fatigue estimation system 200 of the present embodiment has the estimation device 100, the imaging device 101, the pressure sensor 102, and the display device 103.

[0038] As described above, the estimation device 100 is a processing device that estimates the fatigue degree accumulated in the subject, and is implemented by being installed to a server device. The estimation device 100 includes the first acquisition unit 21, the difference calculation unit 22, the second acquisition unit 23, the storage unit 24, the posture estimation unit 25, the determination unit 26, the fatigue estimation unit 27, and the output unit 28.

[0039] The first acquisition unit 21 is a communication module that acquires an image in which the subject 11 is photographed. The first acquisition unit 21 acquires an image photographed in the camera 101, for example, by communicating with the camera 101 via a network.

[0040] The camera 101 is a device that outputs by photographing an image including the subject 11, and is implemented by a camera provided on a facility such as a surveillance camera, a camera built in a computer 100a or a portable terminal, and a dedicated camera of the fatigue estimation system 200, for example. In addition, the image output from the camera 101 and acquired by the first acquisition unit 21 is a so-called moving image that is continuously photographed along a time series. The first acquisition unit 21 acquires such a moving image in parallel with the photographing by the camera 101. The first acquisition unit 21 outputs the acquired image to the posture estimation unit 25.

[0041] The posture estimation unit 25 is a processing unit that estimates the posture of the subject 11 based on the image output from the first acquisition unit 21. The posture estimation unit 25 is implemented by executing a prescribed program by a processor, a memory, and the like. As described above, since the image is a moving image constituted by images that are continuous in a time series, the posture estimation unit 25 estimates the posture of the subject 11 with respect to each image constituting the moving image. Thereby, the estimated posture of the subject 11 is output from the posture estimation unit 25 throughout the entire period during which the estimation of the fatigue degree is performed. However, when the subject 11 departs from the field of view angle of the camera 101, the posture estimation unit 25 can also stop estimating the posture of the subject 11.

[0042] The posture estimation unit 25 determines the joint positions within the image of the subject 11 included in the image by performing image processing by a prescribed program. The posture estimation unit 25 outputs a joint position model that represents by connecting two joints with a bone of a prescribed length according to the relative positions of the joints to each other, as a result of the posture estimation. In addition, since the joint position model corresponds one-to-one to the relative positions of the bones connecting the joints to each other, it can also be called a bone position model. In the estimation device 100, by comparing the joint position model output here as the posture of the subject 11 with the posture fatigue information saved in the storage unit 24, the estimation of the fatigue degree of the subject 11 is performed.

[0043] The storage section 24 is a storage device realized by a semiconductor memory, a magnetic storage medium, an optical storage medium, or the like. In the storage section 24, various kinds of information used in the estimation device 100, including the posture fatigue information, is saved. Each processing section of the estimation device 100 or the like uses the information by reading out the required information from the storage section 24, and newly writes information generated or the like into the storage section 24 as necessary.

[0044] The posture fatigue information will be described below with reference to Figure 3 and Figures 4A-4C . Figure 3 is a diagram for explaining the posture fatigue information of the embodiment. In Figure 3 , the storage section 24 and the posture fatigue information saved in the storage section 24 are illustrated. The posture fatigue information is information in which a specific posture is associated with a fatigue degree, i.e., a unit fatigue degree, accumulated in the subject 11 by maintaining the specific posture for a unit time.

[0045] In the present embodiment, the posture fatigue information includes information of a plurality of (three in the present embodiment) specific postures, which are referred to as posture A, posture B, and posture C for convenience. Figure 4A is a first diagram for explaining the specific postures of the embodiment, and the subject 11 corresponding to the posture A described above is indicated by a broken line. In addition, Figure 4B is a second diagram for explaining the specific postures of the embodiment, and the subject 11 corresponding to the posture B described above is indicated by a broken line. In addition, Figure 4C is a third diagram for explaining the specific postures of the embodiment, and the subject 11 corresponding to the posture C described above is indicated by a broken line. In addition, the posture fatigue information can include more specific postures.

[0046] For example, the information 24a of the posture A included in the posture fatigue information is a specific posture corresponding to the posture of the subject 11 illustrated in Figure 4A . As illustrated in Figure 3 and Figures 4A-4C , the specific postures in the posture fatigue information are defined by the relative positions of the joints (or the bones) of the subject 11 from each other by connecting the joints of the subject 11 indicated by black dots with the bones of the subject 11 indicated by straight lines. That is, the specific postures in the posture fatigue information are joint position models 11a having information equivalent to the output of the posture estimation section 25 described above. In addition, as illustrated in Figure 3 , a unit fatigue degree accumulated in the subject 11 per unit time (1 second in the present embodiment) is indicated in the posture fatigue information.

[0047] In the present embodiment, the unit fatigue degree of the posture A is set to different fatigue degrees for each part of the subject 11. Specifically, with respect to the posture A, a first unit fatigue degree of 0.24 accumulated on the shoulder as the first part of the subject 11, a second unit fatigue degree of 0.19 accumulated on the back as the second part, and a third unit fatigue degree of 0.32 accumulated on the waist as the third part are individually set for every unit time. That is, if the subject 11 maintains the posture A, different fatigue degrees are accumulated on the shoulder, the back, and the waist of the subject 11 every 1 second.

[0048] Further, the posture A of the present embodiment is a posture on the premise that the subject 11 is seated on the chair 12, and thus, when the posture of the subject 11 is collated, a determination is made as to whether or not the chair is present around the subject 11. In order to use this determination, the information 24a of the posture A includes information indicating that the chair 12 is present around the subject 11. Note that the surroundings of the subject 11 refer to a range that the subject 11 can contact, and mean a range that is physically conducive to maintaining the posture of the subject 11 by the presence of an object such as the chair 12. The surroundings of the subject 11, for example, indicate a range including a position contacted by the hands and feet when the subject 11 stretches the hands and feet.

[0049] As such, a specific posture is sometimes defined as a posture maintained with the intervention of an object such as the chair 12 and the table 13. Further, in contrast to this, a specific posture is sometimes defined as a posture maintained without the intervention of an object. For example, in the case where the subject 11 is standing, although it is difficult to estimate whether or not the subject 11 is carrying baggage and the like based on the joint position model, since the fatigue degree is greatly different depending on whether or not baggage is carried, it is necessary to distinguish between the case where baggage and the like is carried and the case where baggage and the like is not carried.

[0050] Thus, by making the above-described structure, in the case where baggage and the like is not present around the subject 11 as an object, the posture estimation section 25 is able to estimate that the subject 11 is simply maintaining a standing posture. In the present embodiment, a specific posture of the subject 11 is defined as such based on the presence or absence of an object around the subject 11, and thus, a distinction is made in dependence on the fatigue degree of the object, and thus, more correct estimation of the fatigue degree is able to be made.

[0051] Further, the object around the subject 11 is made based on the image acquired from the imaging device 101. That is, the image acquired by the first acquisition section can be said to be information including information used by the posture estimation section 25 in order to estimate the posture of the subject 11 and object detection information indicating the presence or absence of an object around the subject 11. With respect to the calculation processing of the fatigue degree of the subject 11 using the object detection information, the description will be given later together with the description of the determination section 26 and the fatigue estimation section 27.

[0052] Next, the description will be given with reference toFigure 5 The method of constructing the above posture fatigue information will be described. Figure 5 is a diagram showing a musculoskeletal model used in the construction of posture fatigue information in the embodiment. As the musculoskeletal model 11b shown in Figure 5 The musculoskeletal model 11b is able to numerically express the load on the joints and muscles acting to take a certain posture by causing the posture to be reproduced. Further, the deterioration of blood flow on the model is able to be numerically expressed when the posture is maintained for a certain time in the musculoskeletal model 11b.

[0053] Thus, by reproducing the estimated posture using the musculoskeletal model 11b, the muscle load, joint load, and degree of deterioration of blood flow after a certain time are able to be calculated. Since the muscle load, joint load, and degree of deterioration of blood flow have a close relationship with fatigue, the fatigue degree accumulated per certain time (i.e., the unit time described above) in the estimated posture is able to be quantified by using these values. However, the calculation for this quantification requires a large amount of calculation processing, so applying these calculation processes to all of the estimated postures requires time and processing performance, so it cannot be said to be realistic.

[0054] In the present embodiment, these calculation processes are performed in advance for each specific posture, and by using posture fatigue information that directly associates specific postures with fatigue degrees, the above calculation processes are able to be omitted. Thus, the fatigue degree of the subject 11 is able to be immediately estimated depending on whether the estimated posture matches a specific posture. Therefore, in the present embodiment, the estimation of the fatigue degree is able to be realized by the estimation device 100 having low processing performance and the immediacy of the estimation of the fatigue degree is able to be improved, so the fatigue degree of the subject is able to be estimated by more appropriate calculation processing.

[0055] The specific posture here is defined as a posture having a tolerance range including a reference posture as a reference and a posture in which the position of each joint deviates from the reference posture within a prescribed range. Thereby, a plurality of estimated postures are able to be included by one specific posture, so the calculation becomes easier. However, expanding the tolerance range of the specific posture causes the accuracy of the estimated fatigue degree to decrease, and on the other hand, narrowing the tolerance range of the specific posture forms a "hole" in which the posture cannot be estimated. Further, if many specific postures are included to construct the posture fatigue information in order to fill such a "hole", the amount of information becomes large, and the processing cost when comparing the estimated posture with the specific posture is able to be expanded.

[0056] Therefore, it is only necessary to set the allowable range of such specific postures in accordance with the accuracy of the estimated fatigue degree required by the manager or the like who sets the fatigue estimation system 200. In addition, the estimation device 100 can, for example, simply select the specific posture closest to the estimated posture from among the specific postures included in the posture fatigue information, and accumulate the unit fatigue degree associated with the selected specific posture. Alternatively, the estimation device 100 can, for example, assign an average fatigue degree as the unit fatigue degree and perform estimation of the fatigue degree for the posture that does not conform to the specific posture in the case where the estimated posture does not conform to the specific postures included in the posture fatigue information.

[0057] Further, in the present embodiment, the unit fatigue degree is corrected using the characteristic quantity of the estimated posture, and more accurate estimation of the fatigue degree is performed. As an example, the difference (i.e., the amount of deviation) of the estimated posture from the reference posture of the specific posture to which the estimated posture conforms is used as the characteristic quantity, and correction of the unit fatigue degree set for the specific posture is performed. This correction is mainly performed in the difference calculation section 22 and the second acquisition section 23.

[0058] Referring again to Figure 2 , the difference calculation section 22 is a processing section that calculates the difference of the reference posture from the estimated posture. The difference calculation section 22 is realized by executing a prescribed program by a processor and a memory or the like. Specifically, the difference calculation section 22 uses the specific posture found by comparison with the estimated posture in the determination section 26 and the fatigue estimation section 27 described later. In the specific posture, the reference posture is included as described above, and the difference calculation section 22 calculates the difference of the estimated posture from the reference posture.

[0059] The second acquisition section 23 is a processing section that acquires the amount of deviation as the calculated characteristic quantity and corrects the unit fatigue degree. The second acquisition section 23 is realized by executing a prescribed program by a processor and a memory or the like.

[0060] Hereinafter, the Figure 6A and Figure 6B will be described in more detail. Figure 6A is a first view for explaining the characteristic quantity of the embodiment. In Figure 6A , for the posture A described above, the estimated posture is represented by a dashed line and a joint position model 11c of hollow dots, and the reference posture is represented by a solid line and a joint position model 11a of black dots. Further, Figure 6B is a second view for explaining the characteristic quantity of the embodiment. In Figure 6B , the correlation of the difference of the reference posture from the estimated posture (here, the angle difference of the upper body with the waist joint as the axis) and the unit fatigue degree determined by correction is shown.

[0061] Here, for example, the difference calculating section 22 can also calculate the difference with respect to the body part having a dominant unit fatigue degree when calculating the unit fatigue degree of the specific posture to which the estimated posture conforms, separated into each body part. That is, in the posture A described above, the unit fatigue degree of the waist is the largest value, and it can be said that it is a dominant unit fatigue degree. Therefore, in the present embodiment, as shown in FIG. 3, the difference is calculated with the focus on the waist joint between the reference posture and the estimated posture. Here, in the case where the waist joint is the rotation axis, the difference calculating section 22 calculates the amount of rotation from the reference posture to the estimated posture on the upper body side from the waist joint as the difference. Figure 6A

[0062] For example, in the example in the figure, the estimated posture has an angle difference of -5° as the difference with respect to the reference posture. In addition, the positive and negative signs are arbitrarily assigned as signs indicating the direction of deviation, and the positive and negative signs can be replaced. In the figure, the negative sign indicates deviation in the forward inclination direction with respect to the reference posture, and the positive sign indicates deviation in the backward inclination direction with respect to the reference posture.

[0063] The 2nd acquisition section 23 calculates the corrected unit fatigue degree from the correlation between the angle difference and the unit fatigue degree using the angle difference. For example, in the case where the unit fatigue degree is a linear function of the angle difference, the 2nd acquisition section 23 calculates the corrected unit fatigue degree from the correlation between the angle difference and the unit fatigue degree using the angle difference. Figure 6B Figure 6B For example, in the case where the unit fatigue degree is a linear function of the angle difference, the 2nd acquisition section 23 calculates the corrected unit fatigue degree from the correlation between the angle difference and the unit fatigue degree using the angle difference.

[0064] Further, in the present embodiment, the pressure value acquired from the pressure sensor 102 is used as a feature quantity of the posture of the subject 11.

[0065] The pressure sensor 102 is a detector having a pressure-sensitive surface that detects the application of pressure to the pressure-sensitive surface and the magnitude of the applied pressure (i.e., the pressure value). The pressure-sensitive surface of the pressure sensor 102 is disposed, for example, on the seat surface and backrest of a chair 12 on which the subject 11 is seated, the ground on which the feet of the subject 11 are placed, the top plate of a table 13 on which the subject 11 places his or her hands, and the like.

[0066] In the present embodiment, the 2nd acquisition section 23 acquires the pressure value applied to the pressure-sensitive surface from the pressure sensor 102 by communicating with the pressure sensor 102. The 2nd acquisition section 23 corrects the unit fatigue degree using the pressure value acquired from the pressure sensor 102 as a feature quantity. Figure 7 FIG. 3 is a third diagram illustrating a feature quantity of the present embodiment. In the present embodiment, the pressure value acquired from the pressure sensor 102 is used as a feature quantity of the posture of the subject 11. Figure 7 ​​Fig. 6 shows an example of a correlation between the acquired pressure value and the corrected unit fatigue degree.

[0067] Here, depending on the body part corresponding to the contact position with the pressure-sensitive surface, there are cases where the correlation between the pressure value and the unit fatigue degree is positive and cases where it is negative. For example, if the pressure value of the top plate of the table 13 is large, it can be assumed that the hand of the subject 11 is placed on the table 13, and that there is a negative correlation in which the fatigue degree of the shoulder of the subject 11 decreases in correspondence with an increase in the pressure value. Further, for example, if the pressure value in front of the seat surface of the chair 12 is large, it can be assumed that the posture of the subject 11 is forward-leaning, and that there is a positive correlation in which the fatigue degree of the waist of the subject 11 increases in correspondence with an increase in the pressure value.

[0068] In addition to this, the 2nd acquisition unit 23 can correct the unit fatigue degree of the back and the waist using the pressure value detected by the pressure sensor 102 having the pressure-sensitive surface disposed on the backrest of the chair 12, or can correct the unit fatigue degree of the lower body such as the feet using the pressure value detected by the pressure sensor 102 having the pressure-sensitive surface disposed on the floor. Further, the 2nd acquisition unit 23 can acquire a plurality of pressure values detected by a plurality of pressure sensors 102 each having a pressure-sensitive surface disposed at a plurality of places, and use them in combination.

[0069] Referring again to Figure 2 , the determination unit 26 is a processing unit that determines whether the estimated posture matches a specific posture. The determination unit 26 is realized by executing a prescribed program by a processor and a memory or the like. In this way, the determination unit 26 performs a comparison between the specific posture included in the posture fatigue information and the estimated posture. The determination unit 26 outputs an accumulation instruction to the fatigue estimation unit 27 to accumulate the unit fatigue degree associated with the specific posture in a case where it is determined that the estimated posture matches the specific posture.

[0070] The fatigue estimation unit 27 is a processing unit that generates the result of the accumulation of the unit fatigue degree as the fatigue degree of the subject. The fatigue estimation unit 27 is realized by executing a prescribed program by a processor and a memory or the like. For example, the fatigue estimation unit 27 performs the accumulation of the unit fatigue degree in correspondence with the period during which the accumulation instruction is acquired. Thereby, the unit fatigue degree is accumulated in correspondence with the period during which the estimated posture is determined to match the specific posture, and it is possible to estimate the accumulated fatigue degree for the period during which the subject 11 continuously assumes the specific posture.

[0071] The fatigue estimation unit 27, after estimating the fatigue level of the subject 11 for a prescribed period, externally outputs the estimation result via the output unit 28. The prescribed period here can be a period set in advance such as one day, or can be a unit time that is the minimum period for updating the fatigue level of the subject 11 in the system configuration. Further, the fatigue estimation unit 27 can output the latest fatigue level accumulated each time the unit time elapses, and initialize the accumulated value at the time point when one day elapses. Thus, the subject 11 can easily grasp the fatigue level accumulated from the start of one day to the present.

[0072] In addition, the subject 11 does not necessarily stay in the area that can be photographed by the camera 101, for example, for the period of one day. Figure 8 is a view that explains a blank period of the embodiment. For example, as shown in Figure 8 if the subject 11 exits to outside the angle of view of the camera 101, a blank period is formed in which the image including the subject 11 cannot be photographed (cannot be output). For example, in such a case, if there is another camera at the moving destination of the subject 11, the fatigue estimation system 200 can also acquire the image from the other camera.

[0073] Further, the fatigue estimation system 200 can also cooperate with a schedule system that manages the action plan of the subject 11, based on the expected exit reason, accumulate the pre-set make-up fatigue level corresponding to the length of the blank period, and add the accumulated value to the fatigue level estimated in the fatigue estimation unit 27. For example, in the case where the exit reason is rest or the like, a negative make-up fatigue level corresponding to the length of the blank period can also be accumulated and added to the estimated fatigue level. Further, for example, in the case where the exit reason is work or the like, a positive make-up fatigue level corresponding to the length of the blank period can also be accumulated and added to the estimated fatigue level. Thus, for the blank period as well, the fatigue level can be made up based on the action of the subject 11, and the fatigue level of the subject 11 can be more correctly estimated even if a blank period is formed.

[0074] The output unit 28 is a processing unit that outputs the estimation result including the estimated fatigue level. The output unit 28 acquires the fatigue level of the subject estimated in the fatigue estimation unit 27, generates image data together with other information, and transmits it to the display device 103 via a network.

[0075] The display device 103 displays the received image data. Figure 9 is a view that illustrates the information output from the fatigue estimation system of the embodiment. The display device 103 is a display having a display module 103a such as a liquid crystal panel, and displays the received image data by driving the display module 103a.

[0076] For example, image data showing the current fatigue degree of the subject 11 is displayed in the graph. As shown in the graph, in the image data, the current fatigue degree of the subject 11 is shown for each body part. Specifically, in the image data, "shoulder stiffness degree" showing the fatigue degree of the shoulder of the subject 11, "back pain degree" showing the fatigue degree of the back, and "waist pain degree" showing the fatigue degree of the waist are separately displayed. In addition, the positions of the body parts having the fatigue degree on the dummy, the evaluation of the comprehensive fatigue degree, the situation of the estimation result of the fatigue degree, and the like are shown in the image data as additional information.

[0077] The display device 103 uses the display possessed by the computer 100a of the subject 11 as described above, but can be another display. For example, it can be a dedicated display for the fatigue estimation system 200.

[0078] [Operation]

[0079] Next, the operation of the fatigue estimation system 200 described above will be described with reference to Figure 10 The operation of the fatigue estimation system 200 described above will be described. Figure 10 is a flowchart showing the operation of the fatigue estimation system according to the embodiment.

[0080] In the fatigue estimation system 200 according to the embodiment, first, the posture estimation section 25 reads out the posture fatigue information stored in the storage section 24 (reading step S101). The posture fatigue information read out here is information in which a specific posture is associated with a unit fatigue degree.

[0081] The imaging device 101 starts operating in advance, and a plurality of images constituting a moving image are continuously output from the imaging device 101. The 1st acquisition section 21 starts acquiring the output images (acquisition step S102), and continuously continues acquiring the plurality of images until the fatigue estimation system 200 is stopped.

[0082] Here, the estimation device 100 starts measuring the period from the timing at which the image of the starting point is acquired (step S103). The posture estimation section 25 estimates the posture of the subject 11 based on the acquired images (step S104). The determination section 26 determines whether the posture of the subject 11 estimated by the posture estimation section 25 matches the specific posture included in the posture fatigue information (step S105). In addition, in the case where a plurality of specific postures are included, the determination of whether the estimated posture matches is performed for each of the plurality of specific postures in order.

[0083] In a case where the estimated posture does not match the specific posture, or in a case where the matching specific posture is not included in the plurality of specific postures (NO in step S105), the estimation device 100 returns to step S103 to start the measurement of the period from another timing. Further, the posture estimation section 25 estimates the posture of the subject at the other timing (step S104). In this way, the measurement of the period and the estimation of the posture are repeated until the estimated posture of the subject 11 matches the specific posture.

[0084] In a case where the estimated posture matches the specific posture, or in a case where the matching specific posture is included in the plurality of specific postures (YES in step S105), the difference between the reference posture calculated by the difference calculation section 22 and the posture of the subject 11 estimated is calculated, and the pressure value detected by the pressure sensor 102 is output. The 2nd acquisition section 23 acquires the calculated difference and the detected pressure value as the characteristic quantity (step S106).

[0085] The 2nd acquisition section 23 performs correction of the unit fatigue degree of the specific posture with which the estimated posture matches, based on the acquired characteristic quantity (step S107). The fatigue estimation section 27 accumulates the corrected unit fatigue degree corresponding to the measured period (i.e., the period during which the posture matching the specific posture is maintained), thereby estimating the fatigue degree of the subject 11 (step S108). Note that steps S105 to S108 are also referred to as estimation steps of estimating the fatigue degree accumulated in the subject.

[0086] Next, the posture estimation section 25 estimates the posture of the subject 11 (step S109). The determination section 26 again determines whether the estimated posture of the subject 11 matches the same specific posture as in step S105 (step S110). Thus, determination of whether the posture matching the specific posture is maintained is performed.

[0087] In a case where the estimated posture of the subject 11 matches the specific posture (YES in step S110), the process returns to step S106 to perform acquisition of the characteristic quantity again. For example, there is a case where the characteristic quantity changes although the same specific posture is matched due to a slight change in the posture. Therefore, by performing acquisition of the characteristic quantity again, the change in the fatigue degree due to the change in the posture can be captured more accurately. In this way, the estimation device 100 repeatedly performs steps S106 to S110 until the posture of the subject 11 no longer matches the specific posture, thereby continuously estimating the fatigue degree accumulated in the subject 11 as the period extends (i.e., time elapses).

[0088] On the other hand, in a case where the estimated posture of the subject 11 does not conform to the specific posture, the process returns to step S103, and the estimation device 100 starts the measurement of the period from another timing. Further, the posture estimation section 25 estimates the posture of the subject at the other timing (step S104). The same process is repeated thereafter. The estimation device 100 ends the operation after the lapse of a predetermined prescribed period.

[0089] In addition, when the determination in step S110 that the posture does not conform to the specific posture is made once, and then the determination in step S105 becomes "Yes" again, and step S108 is reached, the fatigue degree estimated in step S108 before step S110 is added to, and the fatigue degree is estimated by totaling, thereby enabling the estimation of the fatigue degree accumulated in the prescribed period while the subject 11 changes the posture.

[0090] Thus, without performing a complicated calculation process using a musculoskeletal model or the like for each estimated posture, the fatigue degree accumulated in the subject 11 can be estimated by an appropriate calculation process.

[0091] [Effects and the like]

[0092] As explained above, the fatigue estimation system 200 of the present embodiment is provided with an information output device (the imaging device 101 or the like) that outputs information on the position of the body part of the subject 11, a storage section 24 that stores posture fatigue information that is information that establishes a correspondence between a specific posture of the subject 11 and a unit fatigue degree accumulated in the subject 11 by maintaining the specific posture for a unit time, and an estimation device 100 that estimates the fatigue degree accumulated in the subject in a prescribed period; the estimation device 100 estimates the posture of the subject 11 in the prescribed period based on the information output from the above information output device in the prescribed period, determines whether the estimated posture of the subject 11 conforms to the specific posture indicated by the posture fatigue information stored in the storage device, and estimates and outputs the fatigue degree accumulated in the subject 11 in the prescribed period as a calculation value obtained by accumulating the unit fatigue degree corresponding to the period in which the estimated posture of the subject is determined to conform to the specific posture.

[0093] In such a fatigue estimation system 200, the fatigue degree accumulated in the maintenance of the estimated posture of the subject 11 is stored as posture fatigue information that is associated with the specific posture in advance, in accordance with the estimated posture of the subject 11. In order to estimate the fatigue degree from the posture, a large calculation process is usually involved, but by simply referring to the posture fatigue information in accordance with the pre-calculated association of the fatigue degree with the posture, the fatigue degree can be estimated from the posture. For example, such a calculation process can be implemented even with a system having low processing performance, so the fatigue estimation system 200 can be implemented with a simple structure. Further, on the other hand, if a system having high processing performance is used, the estimation of the fatigue degree from the posture can be performed promptly, so a fatigue estimation system 200 that can provide feedback in real time to the subject 11 or the like can be implemented. Thus, through a review of the calculation process, the fatigue degree of the subject can be estimated by an appropriate calculation process that matches the system.

[0094] Further, for example, in the posture fatigue information, a specific posture of the subject 11 can be associated with a first unit fatigue degree that is a part of the unit fatigue degree, the first unit fatigue degree being a unit fatigue degree accumulated in a first body part of the subject 11 by maintaining the specific posture for a unit time; and a second unit fatigue degree that is a part of the unit fatigue degree, the second unit fatigue degree being a unit fatigue degree accumulated in a second body part of the subject 11 by maintaining the specific posture for a unit time. The estimation device can estimate the fatigue degree accumulated in the first body part of the subject 11 in a predetermined period by accumulating the first unit fatigue degree corresponding to the period in which the estimated posture of the subject 11 is determined to match the specific posture, and estimate the fatigue degree accumulated in the second body part of the subject 11 in the predetermined period by accumulating the second unit fatigue degree corresponding to the period in which the estimated posture of the subject 11 is determined to match the specific posture.

[0095] Thus, the fatigue degree accumulated individually for each body part can be estimated. Further, in this estimation, a large calculation process is not involved, and the fatigue degree of the subject 11 can be estimated individually for each body part by a simple calculation process. Thus, the fatigue degree of the subject can be estimated by an appropriate calculation process.

[0096] Further, for example, the estimation device 100 can acquire a feature amount of the estimated posture of the subject 11 when the estimated posture of the subject 11 is determined to match the specific posture, and correct the unit fatigue degree using the feature amount, and estimate the fatigue degree accumulated in the subject 11 in a predetermined period by adding the corrected unit fatigue degree corresponding to the period in which the estimated posture of the subject 11 is determined to match the specific posture.

[0097] Thus, the degree of fatigue of the subject 11 can be more accurately estimated using the feature quantity. In this estimation, too, a large calculation process is not required, and the degree of fatigue of the subject 11 can be more accurately estimated by a simple calculation process. Thus, the degree of fatigue of the subject can be estimated by an appropriate calculation process.

[0098] Further, for example, the feature quantity can be a pressure value obtained from the pressure sensor 102 contacted by the body part of the subject corresponding to the first part, and the greater the pressure value, the greater the correction amount by which the estimation device 100 corrects the first unit degree of fatigue.

[0099] Thus, the degree of fatigue of the subject 11 can be more accurately estimated using the pressure value as the feature quantity. In this estimation, too, a large calculation process is not required, and the degree of fatigue of the subject 11 can be more accurately estimated by a simple calculation process. Thus, the degree of fatigue of the subject can be estimated by an appropriate calculation process.

[0100] Further, for example, the feature quantity can be a difference between the reference posture included in the range conforming to the specific posture and the estimated posture of the subject 11, and the greater the difference, the greater the correction amount by which the unit degree of fatigue is corrected.

[0101] Thus, the degree of fatigue of the subject 11 can be more accurately estimated using the difference between the reference posture and the estimated posture of the subject 11 as the feature quantity. In this estimation, too, a large calculation process is not required, and the degree of fatigue of the subject 11 can be more accurately estimated by a simple calculation process. Thus, the degree of fatigue of the subject can be estimated by an appropriate calculation process.

[0102] Further, for example, in the posture fatigue information, the specific posture of the subject 11 can be defined as a posture maintained by intervention of an object (chair 12 or the like), and the estimation device 100 obtains object detection information indicating the presence or absence of an object, and in a case where the presence of an object is indicated by the object detection information, it is determined whether the estimated posture of the subject 11 conforms to the specific posture.

[0103] Thus, the posture maintained by intervention of an object can be distinguished from the posture maintained without intervention of an object, and it can be determined whether or not the specific posture is conformed to. Thus, the degree of fatigue of the subject can be estimated by an appropriate calculation process.

[0104] Further, for example, in the posture fatigue information, the specific posture of the subject 11 can be defined as a posture maintained without intervention of an object (chair 12 or the like), and the estimation device 100 obtains object detection information indicating the presence or absence of an object, and in a case where the absence of an object is indicated by the object detection information, it is determined whether the estimated posture of the subject 11 conforms to the specific posture.

[0105] Thus, it is possible to distinguish between a posture maintained by the intervention of the object and a posture maintained without the intervention of the object, and determine whether or not the posture corresponds to the specific posture. Therefore, it is possible to estimate the fatigue level of the subject through appropriate calculation processing.

[0106] Further, for example, the estimation device 100 can accumulate a preset fill-in fatigue level corresponding to the length of the blank period, which is a period during which the information output device (the imaging device 101 or the like) cannot output information, in the blank period.

[0107] Thus, in a case where the subject 11 is not included in the image and the fatigue level cannot be estimated, it is possible to complete the fatigue level by the preset fill-in fatigue level, and it is possible to more accurately estimate the fatigue level accumulated in the prescribed period. Therefore, it is possible to estimate the fatigue level of the subject through appropriate calculation processing.

[0108] Further, for example, the specific posture of the subject 11 can be defined by a joint position model defined by the relative positions of each joint of the subject 11, and the estimation device 100 can output the joint position model as the estimation result of the posture of the subject 11 in the prescribed period.

[0109] Thus, by comparing the joint position models constructed from simple information with each other, it is possible to determine whether or not the estimated posture corresponds to the specific posture. Therefore, it is possible to estimate the fatigue level of the subject through appropriate calculation processing.

[0110] Further, the fatigue estimation method of the present embodiment includes the acquisition step S102 of acquiring information related to the position of the body part of the subject 11, the readout step S101 of reading out posture fatigue information from the storage device (the storage section 24), the posture fatigue information being information in which a specific posture of the subject 11 and a unit fatigue level accumulated in the subject 11 by maintaining the specific posture for a unit time are associated with each other, and the estimation step (steps S105 to S108, and the like) of estimating the fatigue level accumulated in the subject 11 in a prescribed period. In the estimation step, based on the information output in the prescribed period, the posture of the subject 11 in the prescribed period is estimated, it is determined whether or not the estimated posture of the subject 11 corresponds to the specific posture, and a calculation value obtained by adding the unit fatigue level corresponding to the period in which the estimated posture of the subject 11 is determined to correspond to the specific posture is estimated as the fatigue level accumulated in the subject 11 in the prescribed period.

[0111] Thus, it is possible to achieve the same effects as the fatigue estimation system 200 described above.

[0112] Further, the present embodiment can also be realized as a non-transitory recording medium that is readable by a computer and on which a program for causing a computer to execute the fatigue estimation method described above is recorded.

[0113] Thus, the same effects as the fatigue estimation method described above can be achieved using a computer.

[0114] (Other Embodiments)

[0115] The embodiments have been described above, but the present disclosure is not limited to the above-described embodiments.

[0116] For example, in the above-described embodiments, the processing performed by a specific processing section can be performed by another processing section. Further, the order of the plurality of processes can be changed, and the plurality of processes can be executed in parallel.

[0117] Further, the fatigue estimation system or the estimation device of the present disclosure can also be realized by a plurality of devices each having a part of the plurality of constituent elements, or by a single device having all of the plurality of constituent elements. Further, a part of the functions of the constituent elements can be realized as the functions of other constituent elements, and how to allocate each function to each constituent element can be changed. As long as a configuration having substantially all of the functions of the fatigue estimation system or the estimation device of the present disclosure can be realized, it is included in the present disclosure.

[0118] Further, in the above-described embodiments, each constituent element can be realized by executing a software program suitable for each constituent element. Each constituent element can be realized by a program execution section such as a CPU or a processor reading out and executing a software program recorded in a recording medium such as a hard disk or a semiconductor memory.

[0119] Further, each constituent element can be realized by hardware. For example, each constituent element can be a circuit (or an integrated circuit). These circuits can be a single circuit as a whole, or can be different circuits. Further, these circuits can be general-purpose circuits, or can be dedicated circuits.

[0120] Further, the global or specific technical solutions of the present disclosure can also be realized by a system, a device, a method, an integrated circuit, a computer program, or a recording medium such as a CD-ROM that is readable by a computer, or by any combination of a system, a device, a method, an integrated circuit, a computer program, and a recording medium.

[0121] Further, as a method of estimating the posture of the subject, the present disclosure can be implemented by using a configuration of a position sensor in addition to a configuration of an imaging device. Specifically, a sensor module including a position sensor and a potential sensor is used to estimate the posture of the subject. Here, the description is given assuming that the subject wears a plurality of sensor modules, but the number of sensor modules worn by the subject is not particularly limited. It is also possible that only one sensor module is worn by the subject.

[0122] Further, the wearing style of the sensor module is not particularly limited, and can be any style as long as the position of the prescribed body part of the subject can be measured. As an example, a plurality of sensor modules are worn by the subject by wearing a garment on which the plurality of sensor modules are mounted.

[0123] The sensor module is a device that is mounted on the prescribed body part of the subject and outputs information indicating the result of detection or measurement in conjunction with the prescribed body part. Specifically, the sensor module has a position sensor that outputs position information related to the spatial position of the prescribed body part of the subject, and a potential sensor that outputs potential information indicating the potential of the prescribed body part of the subject. In the drawings, a sensor module that simultaneously has a position sensor and a potential sensor is shown, but as long as the sensor module has a position sensor, the potential sensor is not necessary. The position sensor in such a sensor module is an example of an information output device that outputs position information as information related to the position of the body part of the subject. Thus, the information output is position information, which is information containing the relative or absolute position of the prescribed body part of the subject. Further, in the information output, for example, potential information can also be included. The potential information is information containing the value of the potential measured at the prescribed body part of the subject. As for the position information and the potential information, detailed description will be given below together with the position sensor and the potential sensor.

[0124] The position sensor is a detector that detects the relative position or absolute position in space of the prescribed body part of the subject wearing the sensor module, and outputs information related to the spatial position of the prescribed body part as a result of detection. The information related to the spatial position contains information that can determine the position of the body part within the space as described above and information that can determine the change in the position of the body part accompanying the body movement. Specifically, the information related to the spatial position contains the position of the joint and the bone within the space and information indicating the change in the position.

[0125] The position sensor is configured by combining various sensors such as an acceleration sensor, an angular velocity sensor, a geomagnetic sensor, and a distance measuring sensor. The position information output from the position sensor can approximate the spatial position of the prescribed body part of the subject, and thus the posture of the subject can be estimated based on the spatial position of the prescribed body part.

[0126] The potential sensor is a detector that measures the potential of the prescribed body part of the subject wearing the sensor module and outputs information indicating the potential of the prescribed body part as a measurement result. The potential sensor is a measurer having a plurality of electrodes and measuring the potential generated between the plurality of electrodes by a potentiometer. The potential information output from the potential sensor indicates the potential generated at the prescribed body part of the subject, which corresponds to the action potential of the muscle at the prescribed body part or the like, and thus the estimation accuracy of the posture of the subject estimated based on the action potential of the prescribed body part or the like can be improved.

[0127] In one aspect of the fatigue estimation system described herein, the estimated posture of the subject is used to estimate the fatigue degree of the subject as described above. In addition, the processing after the estimation of the posture of the subject is the same as in the above-described embodiments, and thus the description is omitted.

[0128] Further, the present disclosure can also be realized as a fatigue estimation method executed by the fatigue estimation system or the estimation device. The present disclosure can also be realized as a program for causing a computer to execute such a fatigue estimation method, and as a non-transitory recording medium readable by a computer on which such a program is recorded.

[0129] In addition to the above, aspects obtained by various modifications made on the basis of the embodiments by those skilled in the art, or aspects realized by arbitrarily combining the constituent elements and functions of the embodiments within a range that does not depart from the gist of the present disclosure are also included in the present disclosure.

[0130] Label Explanation

[0131] 11 Subject

[0132] 11a, 11c Joint position model

[0133] 24 Storage (storage device)

[0134] 100 Estimation device

[0135] 101 Imaging device (information output device)

[0136] 200 Fatigue estimation system

Claims

1. A fatigue prediction system, wherein, have: An information output device that outputs information related to the location of a part of the subject's body; The storage device stores posture fatigue information, which establishes a correspondence between a specific posture of the subject and a unit degree of fatigue accumulated in the subject by maintaining the specific posture for a unit of time. as well as The estimation device estimates the cumulative fatigue level of the aforementioned subject over a specified period. In the aforementioned speculative device, Based on the information output during the aforementioned period, the posture of the aforementioned subject during the aforementioned period is inferred. Determine whether the inferred posture of the aforementioned individual conforms to the specific posture described above. If the posture of the person suspected to be the above-mentioned object is consistent with the above-mentioned specific posture. Obtain the characteristic quantities of the inferred posture of the aforementioned objects. The aforementioned characteristic quantities are used to correct the unit fatigue level. The calculated value is extrapolated as the accumulated fatigue of the subject during the aforementioned specified period. This calculated value is obtained by adding the corrected unit fatigue values ​​corresponding to the period during which the extrapolated posture of the subject is determined to conform to the aforementioned specific posture. The aforementioned characteristic quantity is the difference between the reference posture within the range of the aforementioned specific posture and the inferred posture of the aforementioned subject. The larger the difference, the greater the correction amount for the aforementioned unit fatigue.

2. The fatigue prediction system as described in claim 1, wherein, In the above information on postural fatigue, A correspondence was established between the specific posture of the subject and a first unit of fatigue, which is part of the first unit of fatigue. The first unit of fatigue is the unit of fatigue accumulated in a first part of the subject's body by maintaining the specific posture for a unit of time. A correspondence was established between the specific posture of the subject and a second unit of fatigue, which is part of the first unit of fatigue. This second unit of fatigue is the unit of fatigue accumulated in a second part of the subject's body by maintaining the specific posture for a unit of time. In the aforementioned speculative device, The calculated value obtained by accumulating the first unit of fatigue corresponding to the period during which the posture of the person being predicted conforms to the specific posture is estimated to be the fatigue accumulated in the first part of the person being predicted during the specified period. The calculated value obtained by accumulating the second unit of fatigue corresponding to the period during which the posture of the subject is determined to conform to the specific posture is estimated as the fatigue accumulated in the second part of the subject during the specified period.

3. The fatigue prediction system as described in claim 2, wherein, The aforementioned characteristic quantity is the pressure value obtained from the pressure sensor that is in contact with the body part of the subject corresponding to the aforementioned first part. The greater the pressure value, the greater the correction amount the estimation device applies to the first unit fatigue.

4. The fatigue prediction system as described in claim 1, wherein, In the aforementioned postural fatigue information, the specific posture of the subject is defined as a posture maintained through the intervention of an object. In the aforementioned speculative device, Obtain object detection information indicating the presence or absence of the aforementioned objects. When the object detection information indicates the presence of the aforementioned object... Determine whether the inferred posture of the aforementioned subject conforms to the aforementioned specific posture.

5. The fatigue prediction system as described in claim 1, wherein, In the aforementioned postural fatigue information, the specific posture of the subject is defined as a posture maintained without the intervention of any object. In the aforementioned speculative device, Obtain object detection information indicating the presence or absence of the aforementioned objects. If the object detection information indicates that the object does not exist, then... Determine whether the inferred posture of the aforementioned subject conforms to the aforementioned specific posture.

6. The fatigue prediction system as described in claim 1, wherein, During the blank period, the aforementioned estimation device accumulates the pre-set filling fatigue level corresponding to the length of the blank period, which is the period during which the aforementioned information output device cannot output the aforementioned information within the specified period.

7. The fatigue prediction system according to any one of claims 1 to 6, wherein, The specific posture of the aforementioned subject is defined by a joint position model, which is defined by the relative position of each joint of the aforementioned subject. The aforementioned prediction device outputs the aforementioned joint position model as a prediction result of the posture of the aforementioned subject during the aforementioned specified period.

8. A fatigue prediction method, wherein, include: The acquisition step involves obtaining information related to the location of the subject's body parts; The reading step involves reading postural fatigue information from the storage device. This postural fatigue information is information that establishes a correspondence between a specific posture of the subject and the unit fatigue accumulated in the subject by maintaining the specific posture for a unit of time. as well as The estimation step involves estimating the cumulative fatigue level of the aforementioned individuals over a specified period. In the above inference steps, Based on the information output during the aforementioned period, the posture of the aforementioned subject during the aforementioned period is inferred. Determine whether the inferred posture of the aforementioned individual conforms to the specific posture described above. If the posture of the person suspected to be the above-mentioned object is consistent with the above-mentioned specific posture. Obtain the characteristic quantities of the inferred posture of the aforementioned objects. The aforementioned characteristic quantities are used to correct the unit fatigue level. The calculated value is extrapolated as the accumulated fatigue of the subject during the aforementioned specified period. This calculated value is obtained by adding the corrected unit fatigue values ​​corresponding to the period during which the extrapolated posture of the subject is determined to conform to the aforementioned specific posture. The aforementioned characteristic quantity is the difference between the reference posture within the range of the aforementioned specific posture and the inferred posture of the aforementioned subject. The larger the difference, the greater the correction amount for the aforementioned unit fatigue.

9. A program recording medium containing a program for causing a computer to execute the fatigue estimation method of claim 8.

Images