Concentration measurement device

Abstract

To provide a concentration degree measurement device and the like capable of measuring a concentration degree with high accuracy.SOLUTION: A concentration degree measurement device includes: an acquisition section 11 for acquiring an image in which a subject 101 is captured; a body part recognition section 13 for recognizing a position for each of parts of two or more portions of a body of the subject 101 in the acquired image and calculating a subject position relationship which is each position relationship from the positions of two or more portions of the body of the recognized subject 101; a concentration habit determination section 15 for determining whether or not the subject 101 is in a concentration state on the basis of the subject position relationship and a habit which can be taken when a person is in the concentration state; and a concentration degree calculation section 17 for calculating a concentration degree of the subject 101 using a determination result by the concentration habit determination section 15.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a focus measurement device and a focus measurement method. [Background technology]

[0002] Conventionally, information processing devices that calculate a person's concentration level are known. For example, the information processing device described in Patent Document 1 calculates the concentration level by setting the maximum concentration level at 100 and subtracting the sum of the amount of change in facial expression and the amount of change in movement multiplied by the face direction ratio. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2014-120137 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the conventional information processing device, the more the subject concentrates on one object, the higher the calculated concentration level becomes. However, in reality, the subject who is looking at one object does not necessarily have a high concentration level, and the subject who is looking at multiple objects does not necessarily have a low concentration level. For example, when a subject who is doing intellectual work such as learning or office work is engrossed in watching television, the conventional information processing device calculates a high concentration level, even though it cannot be said that the subject is concentrating. Also, when the subject is looking alternately at a reference book and a notebook during learning, the conventional information processing device calculates a low concentration level, even though it can be said that the subject is concentrating on learning. Thus, the conventional information processing device has a problem that the accuracy of the calculated concentration level is low.

[0005] Therefore, the present disclosure provides a concentration measurement device and a concentration measurement method that can measure the concentration level with high accuracy. [Means for solving the problem]

[0006] In order to solve the above problem, a focus measurement device according to an aspect of the present disclosure includes an acquisition unit that acquires an image of a subject, and a focus measurement device that recognizes the positions of two or more parts of the subject's body in the image acquired by the acquisition unit, and The shortest distance is expressed as the coordinates on the image. a body part recognition unit that calculates the body part recognition position; Shortest distance and a habit that can be taken when a person is in a state of concentration, which is determined by the relative positions of two or more parts of the person's body. The shortest distance in and a concentration degree calculation unit that calculates a concentration degree of the subject using a result of the determination by the concentration habit determination unit. R .

[0007] A concentration measurement method according to one aspect of the present disclosure is a concentration measurement method executed by a computer, the concentration measurement method including: acquiring an image of a subject; recognizing positions of two or more parts of the subject's body in the image acquired in the acquiring step; The shortest distance is expressed as the coordinates on the image. a recognition step of calculating the Shortest distance and a habit that can be taken when a person is in a state of concentration, which is determined by the relative positions of two or more parts of the person's body. The shortest distance in A determination step of determining whether the subject is in a state of concentration based on the result of the determination step, and a calculation step of calculating a concentration level of the subject using the result of the determination step. nothing .

[0008] Moreover, one aspect of the present disclosure can be realized as a program for causing a computer to execute the above-described concentration measurement method, or as a computer-readable recording medium storing the program. Effect of the Invention

[0009] According to the present disclosure, the concentration level can be measured with high accuracy. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating a focus measurement device according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram showing a configuration of the focus measurement device according to the first embodiment. [Diagram 3] FIG. 3 is a flowchart showing the concentration measurement method according to the first embodiment. [Figure 4] FIG. 4 is a diagram for explaining determination of the concentration state according to the first embodiment. [Diagram 5] FIG. 5 is a diagram illustrating calculation of the concentration degree according to the first embodiment. [Figure 6] FIG. 6 is a flowchart illustrating storage of habit information in the storage unit according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating the relationship between the task performance of the subject and the habits of the subject according to the first embodiment. [Figure 8] FIG. 8 is a diagram showing an example of a standard habit. [Figure 9] FIG. 9 is a diagram illustrating a processing table according to the first embodiment. [Figure 10] FIG. 10 is a flowchart illustrating storage of habit information in a storage unit according to a modification of the first embodiment. [Figure 11] FIG. 11 is a block diagram showing a configuration of a focus measurement device according to the second embodiment. [Figure 12] FIG. 12 is a flowchart illustrating storage of habit information in the storage unit according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] (Knowledge that led to this disclosure) As shown in Patent Document 1, an information processing device that calculates a person's concentration level is known. The information processing device disclosed in Patent Document 1 can calculate the concentration level only in a specific situation. Specifically, the more the person concentrates on looking at one object, the higher the calculated concentration level becomes. Therefore, in order to use the information processing device on a person who is working and to calculate the subject's concentration level for the work, the work performed by the subject needs to be done while gazing at one object, and the device can only be applied to limited uses.

[0012] In addition, there are individual differences in the actions that a subject can take when concentrating on a task, and it is difficult for the information processing device to accommodate such individual differences. Therefore, it cannot be said that the concentration level calculated using the information processing device is highly accurate.

[0013] The present disclosure has been made in consideration of the above circumstances, and provides a concentration measurement device that can be applied to a wide range of applications and can be adapted to the actions of each subject when concentrating. According to the present disclosure, a concentration measurement device and the like that can measure the concentration level of subjects in various situations with high accuracy are provided.

[0014] Hereinafter, the embodiments of the present disclosure will be described with reference to the drawings. Note that the embodiments described below all show comprehensive or specific examples of the present disclosure. Therefore, the numerical values, components, the arrangement and connection of the components, as well as the steps and the order of the steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Therefore, among the components in the following embodiments, components that are not described in the independent claims of the present disclosure will be described as optional components.

[0015] In addition, each figure is a schematic diagram and is not necessarily precisely illustrated. Therefore, the scales and the like are not necessarily the same in each figure. In each figure, the same reference numerals are given to substantially the same configurations, and duplicated explanations are omitted or simplified.

[0016] (Embodiment 1) [Concentration measurement device] First, the focus measurement device according to the first embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining the focus measurement device according to the first embodiment.

[0017] 1, the focus measurement device 100 in this embodiment is implemented, for example, as being built into a computer or the like used by a subject 101. By implementing the focus measurement device 100 in a form built into a computer or the like used by the subject 101, a camera, a display, and the like mounted on the computer can be used.

[0018] That is, the input to the concentration measurement device 100 can be obtained using a camera, and the output from the concentration measurement device 100 can be presented using a display. Furthermore, when the work performed by the subject 101 is a work that uses a computer, the concentration level of the subject 101 can be calculated in parallel with the work, using the computer used for the work.

[0019] The focus measurement device 100 in the present disclosure is a device that uses an image of the subject 101 to calculate the focus level of the subject 101 in the image. Therefore, as long as the focus measurement device 100 can obtain an image of the subject 101, it can calculate the focus level of the subject 101 regardless of the state the subject 101 is in. In other words, the focus measurement device 100 can be applied to a wide range of subjects 101.

[0020] In addition, the concentration measurement device 100 judges whether the subject 101 is in a state of concentration by using a habit that the subject 101 may have when he or she is in a state of concentration. For example, the subject 101 shown in the figure has a habit of touching a part 101a of the face with a hand 101b when he or she is in a state of concentration. As shown in the example in the figure, each subject 101 has a different habit. The concentration measurement device 100 in this embodiment calculates the concentration level by using the habit of the subject 101. This makes it possible to suppress a decrease in accuracy based on individual differences, as seen in the conventional case where the concentration level is calculated by focusing on a specific movement, and to measure the concentration level for each individual with higher accuracy.

[0021] Next, the focus measurement device 100 according to the present embodiment will be described in detail with reference to Fig. 2. Fig. 2 is a block diagram showing the configuration of the focus measurement device according to the first embodiment.

[0022] 2, concentration measurement device 100 in this embodiment includes acquisition unit 11, body part recognition unit 13, concentration habit determination unit 15, and concentration calculation unit 17. Acquisition unit 11 is a communication interface that acquires an image of subject 101. Acquisition unit 11 is connected to input unit 201, for example, and acquires an image of subject 101 via input unit 201. Input unit 201 is, for example, a camera, and an image is captured by input unit 201.

[0023] Note that input unit 201 may be realized in any manner as long as it can provide an image to acquisition unit 11. For example, input unit 201 may be an external storage device. An image stored in advance in the external storage device may be acquired by acquisition unit 11, and the concentration level of subject 101 may be measured using the image. Therefore, the measurement of the concentration level by concentration measurement device 100 does not need to be instantaneous. Acquisition unit 11 transmits the acquired image to body parts recognition unit 13.

[0024] Body part recognition unit 13 recognizes the position of each of two or more parts of the body of subject 101 in the image acquired by acquisition unit 11. Body part recognition unit 13 is a processing device that calculates a target positional relationship, which is a positional relationship between each of the recognized positions of two or more parts of the body of subject 101. Body part recognition unit 13 is realized by, for example, a processor, a storage device, and a program stored in the storage device.

[0025] The body part recognition unit 13 identifies the body of the subject 101 from the rest on the image received from the acquisition unit 11 by image recognition. The body part recognition unit 13 also identifies each part of the identified body of the subject 101, and recognizes the position of each part on the image. In this way, an object positional relationship is calculated, which is the positional relationship between two or more parts of the body of the subject 101 on the image. Here, the positional relationship between two or more parts is indicated by the distance between the two or more parts. For example, if the two or more parts are "a part of the face of the subject 101" and "the hand of the subject 101", the body part recognition unit 13 calculates the object positional relationship as "a part of the face and the hand are within a specific distance".

[0026] The concentration habit determination unit 15 is a processing device that determines whether the subject 101 is in a concentration state based on the object positional relationship and the habits of the subject 101. The concentration habit determination unit 15 is realized, for example, by a processor, a storage device, and a program stored in the storage device.

[0027] Concentration habit determination unit 15 knows the habits of subject 101 in advance, and determines whether or not the object positional relationship calculated by body parts recognition unit 13 is a habit of subject 101. If the object positional relationship matches the habit of subject 101, it can be determined that subject 101 is performing an action that can be taken when in a state of concentration. In other words, concentration habit determination unit 15 can determine that subject 101 is in a state of concentration because subject 101 is performing the relevant action.

[0028] In this specification, a habit is a movement that a person may take when he or she is in a state of concentration, and is a movement that is estimated from the positional relationship (i.e., distance) of two or more parts of the person's body. Therefore, a habit can be defined as the positional relationship of two or more parts of the person's body, or a movement that is estimated from the positional relationship.

[0029] The concentration degree calculation unit 17 is a processing device that calculates the concentration degree of the subject 101 using the result of the determination by the concentration habit determination unit 15 as to whether or not the subject 101 is in a concentration state. The concentration degree calculation unit 17 is realized by, for example, a processor, a storage device, and a program stored in the storage device. The concentration habit determination unit 15 determines whether or not the subject 101 is in a concentration state for each image of the subject 101 acquired by the acquisition unit 11.

[0030] A plurality of images are acquired, and for each of them, a determination is made as to whether or not the subject 101 is in a state of concentration. More specifically, the images acquired by the acquisition unit 11 are moving images in which the images are arranged continuously in a time series. Therefore, the concentration habit determination unit 15 determines whether or not the subject 101 is in a state of concentration for each frame of the image included in the moving image. That is, the concentration habit determination unit 15 outputs, based on the determination, a numerical sequence in which values ​​indicating either a state of concentration or a non-concentration state that is not a state of concentration, which corresponds to the moving image captured by the subject 101, are arranged continuously in a time series.

[0031] The concentration level calculation unit 17 calculates the ratio of the time during which the subject 101 was in a state of concentration to a preset time range as the concentration level of the subject 101, using the numerical sequence output by the concentration habit determination unit 15. For example, if the total time during which the subject 101 was in a state of concentration was 4 minutes out of a 5-minute video, the concentration level is calculated as 4 / 5=0.8. Alternatively, for example, the concentration level calculation unit 17 may calculate the concentration level as 0.8×100=80% using a percentage.

[0032] The above results are output by the output unit 202 connected to the concentration degree calculation unit 17. The output unit 202 is, for example, a display device such as a display provided in a computer. The output unit 202 displays the calculated concentration degree on a screen, thereby presenting it to the subject 101 or an administrator who manages the subject 101. The output unit 202 may be a server device. When the output unit 202 is a server device, the calculated concentration degree is stored in a storage device of the output unit 202. The subject 101 or an administrator who manages the subject 101 can refer to the stored concentration degree by communicating with the server device.

[0033] Furthermore, the concentration measurement device 100 in this embodiment may include a storage unit 21, a concentration state determination unit 25, and a task record acquisition unit 23. These are components for acquiring in advance the habits of the subject 101 and storing them in the storage unit 21, so that the concentration habit determination unit 15 can compare the habits with the target positional relationship calculated by the body parts recognition unit 13.

[0034] The memory unit 21 is a storage device in which habit information relating to the positional relationship of two or more parts of a person's body that defines a habit is stored in advance. That is, the memory unit 21 stores information on habitual actions that a person may take when he or she is in a state of concentration. Therefore, the concentration habit determination unit 15 may acquire the habit information stored in the memory unit 21 by referring to the memory unit 21, and determine whether or not the subject 101 is in a state of concentration based on the subject positional relationship and the habit information.

[0035] The task achievement acquisition unit 23 is a processing device that acquires achievements of a task performed by the subject 101. The task achievement acquisition unit 23 is realized, for example, by a processor, a storage device, and a program stored in the storage device. A task is an intellectual activity that may cause concentration when performed, such as a calculation problem or a quiz. The achievements of a task are quantified values ​​for evaluating the performance of a task by the subject 101, such as the progress speed of the task, the amount of processing, the score, and the accuracy rate. Therefore, the task achievement acquisition unit 23 has a different form depending on the task performed by the subject 101 and the evaluation method thereof. The task achievement acquisition unit 23 is realized, for example, by an input device such as a touch panel and a keyboard, a camera, a weight sensor, and a communication interface for communicating with an external terminal for performing a task.

[0036] For example, when the task performed by the subject 101 is performed on a computer, the task result acquisition unit 23 may be realized as a user interface that performs input to the computer for performing the task. In this case, the task result acquisition unit 23 may acquire the input performed by the subject 101 using an input device for performing the task as the task result.

[0037] The concentration state determination unit 25 is a processing device that determines whether or not the subject 101 is in a concentration state based on the track record of a task performed by the subject 101. The concentration state determination unit 25 is realized by, for example, a processor, a storage device, and a program stored in the storage device. For example, the concentration state determination unit 25 determines that the subject 101 is in a concentration state when the progress speed of the task performed by the subject 101 acquired by the task track record acquisition unit 23 is greater than a predetermined speed.

[0038] [Method of measuring concentration level] A concentration measurement method for measuring the concentration of subject 101 using focus measurement device 100 described above will be described below with reference to Fig. 3. Fig. 3 is a flowchart showing the focus measurement method according to the first embodiment.

[0039] The acquisition unit 11 in this embodiment acquires an image of the subject 101 by receiving the image via the connected input unit 201, and performs an acquisition step (S101). The acquisition unit 11 also transmits the acquired image to the body part recognition unit 13.

[0040] Next, body part recognition unit 13 distinguishes between the body of subject 101 and other parts of the image received from acquisition unit 11 by image recognition, and further distinguishes the body of subject 101 by part. Body part recognition unit 13 recognizes the position on the image for each part of the body of subject 101. Body part recognition unit 13 further performs a recognition step (S102) of calculating, from the recognized positions, a target positional relationship, which is the positional relationship between each combination of two or more parts of the body of subject 101 on the image.

[0041] Next, the concentration habit determination unit 15 performs a determination step of determining whether or not the subject 101 is in a concentration state based on the target positional relationship in the acquired image and the positional relationship of two or more parts of the body that define the habit of the subject 101. The concentration habit determination unit 15 acquires the positional relationship of two or more parts of the body that define the habit of the subject 101, for example, by using habit information of the subject 101 stored in the storage unit 21. The concentration habit determination unit 15 further performs a determination of whether or not the subject 101 is in a concentration state by determining whether or not the positional relationship that corresponds to the habit of the subject 101 is included in the target positional relationship calculated from the image (S103).

[0042] For example, if the positional relationship corresponding to the habit of the subject 101 corresponds (matches or can be considered equivalent to) the target positional relationship calculated from the image (Yes in S103), the concentration habit determination unit 15 determines that the subject 101 is in a concentration state (S104). Also, for example, if the positional relationship corresponding to the habit of the subject 101 does not correspond to the target positional relationship calculated from the image (No in S103), the concentration habit determination unit 15 determines that the subject 101 is not in a concentration state (S105).

[0043] The determination of whether the subject 101 is in a state of concentration in the concentration habit determination unit 15 will be described in more detail with reference to FIG. 4. FIG. 4 is a diagram for explaining the determination of the state of concentration according to the first embodiment. FIG. 4(a) is a diagram showing an image of the subject 101 captured when in a state of concentration. FIG. 4(b) is a diagram showing an image of the subject 101 captured when not in a state of concentration. Note that the habit of the subject 101 when concentrating here is the action of touching the chin (i.e., part of the face 101a) with the hand 101b. In the following description, the chin will be referred to by the same reference symbol 101a as the part of the face.

[0044] As shown in (a) of FIG. 4, the body part recognition unit 13 recognizes the positions of the chin 101a, which is one part of the body, and the hand 101b, which is another part, of the subject 101 on the image as coordinates on the image. Furthermore, based on the action of touching the chin 101a with the hand 101b, which is a habit of the subject 101 when concentrating, the concentration habit determination unit 15 determines whether the shortest distance between the chin 101a and the hand 101b is 0 or within a distance that can be considered equivalent to 0. In (a) of FIG. 4, the shortest distance between the chin 101a and the hand 101b on the image coordinates of the subject 101 is 0. Therefore, the subject 101 in (a) of FIG. 4 is determined to be in a state of concentration, which indicates a habit when concentrating.

[0045] On the other hand, as shown in Fig. 4(b), the position of only the chin 101a, which is one part of the body of the subject 101 in the image, is recognized as the coordinates on the image by the body part recognition unit 13. Because the hand 101b is not recognized in the image, the distance between the chin 101a and the hand 101b is not calculated, and the action of touching the chin 101a with the hand 101b, which is a habit of the subject 101 when concentrating, is not shown. Therefore, the subject 101 in Fig. 4(b) is determined not to be in a state of concentration, which is a habit when concentrating.

[0046] Returning to Fig. 3, concentration habit determination section 15 determines whether or not subject 101 is in a concentration state for each frame of image acquired by acquisition section 11. Here, concentration measurement device 100 in this embodiment calculates the concentration level of subject 101 in a preset time range. In other words, concentration habit determination section 15 determines whether or not subject 101 is in a concentration state for a predetermined number (number of frames) of images corresponding to a preset time range.

[0047] Therefore, the concentration habit judgment unit 15 judges whether or not the number of images for which judgment has been performed reaches a predetermined number (S106), and if the predetermined number has not been reached (No in S106), repeats the acquisition step (S101) to step (S106). As a result, the concentration habit judgment unit 15 acquires images and judges whether or not the subject 101 in the images is in a concentration state until the number of images for which judgment has been performed reaches the predetermined number.

[0048] When the number of images for which the determination has been performed reaches a predetermined number (Yes in S106), the concentration calculation unit 17 performs a calculation step (S107) of calculating the concentration level of the subject 101 using the determination results of whether the subject 101 is in a concentration state, which are determined for the predetermined number of images. This allows the concentration measurement device 100 to quantify the degree to which the subject 101 was concentrated within a preset time range. The concentration calculation unit 17 transmits information related to the calculated concentration level of the subject 101 to the output unit 202. This allows the subject 101 or an administrator or the like who manages the subject 101 to check the concentration level measured by the concentration measurement device 100.

[0049] The calculation of the concentration level will be described below with reference to Fig. 5. Fig. 5 is a diagram for explaining the calculation of the concentration level according to the first embodiment. Each of the rectangles shown in Fig. 5 represents one acquired image, and each includes an imaged subject 101. Each rectangle is divided into a hatched rectangle and a white rectangle, and each rectangle indicates a frame in which the subject 101 included in the hatched rectangle is determined to be in a concentration state, and the subject 101 included in the white rectangle is determined to not be in a concentration state.

[0050] For example, if the aforementioned time range is 5 minutes (300 seconds) and the image capture interval is 30 frames / second, the focus measurement device 100 calculates the focus level using images of 300 (seconds) x 30 (frames / second) = 9000 frames. The longer the time range, the more errors in determining the focus state due to momentary erroneous detections and the like are reduced, and the shorter the time range, the more immediate the focus level is output. Therefore, the time range may be set arbitrarily by the user of the focus measurement device 100 according to the purpose.

[0051] Furthermore, for example, after 9,000 frames of images from frames 1 to 9,000 have been acquired, the concentration level may be calculated based on images of a length of 9,000 frames for each frame, such as frames 2 to 9001, frames 3 to 9002, and frames 4 to 9003.

[0052] As described above, the concentration measurement device 100 in this embodiment measures the concentration level of the subject 101 using an image of the subject 101. At this time, the concentration measurement device 100 measures the concentration level based on a determination of whether or not the subject 101 is in a state of concentration, using the habit of the subject 101 that appears in the image. If the concentration measurement device 100 can obtain an image of the habitual movement exhibited by the subject 101, it can measure the concentration level of the subject 101 regardless of the work the subject 101 is performing. Therefore, the concentration measurement device 100 can be applied to a wide range of applications.

[0053] Furthermore, by measuring the concentration level based on a determination of whether or not the subject 101 is in a state of concentration using the habits of the subject 101, the concentration measurement device 100 in this embodiment can measure the concentration level tailored to each subject 101. Therefore, the concentration measurement device 100 in this embodiment can reduce individual differences in movements during concentration and measure the concentration level of the subject 101 with high accuracy.

[0054] [Storing habit information in memory] The storage of habit information in the storage unit 21 will be further described below with reference to Figs. 6 to 9. Fig. 6 is a flowchart for explaining the storage of habit information in the storage unit according to the first embodiment. Fig. 6(a) shows a flowchart for acquiring a task progress speed as the task achievement. Fig. 6(b) shows a flowchart for acquiring a task score as the task achievement.

[0055] When measuring the concentration level of the subject 101, the concentration measurement device 100 can store in advance in the storage unit 21 a target positional relationship that is a positional relationship between two or more parts of the subject 101's body that defines the subject 101's habits. By storing the target positional relationship in the storage unit 21 in advance, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy. In order to store the target positional relationship in the storage unit 21 in advance, it is necessary to acquire an image of the subject 101 in a state of concentration. For this reason, the concentration measurement device 100 acquires an image of the subject 101 in a situation in which the subject 101 can concentrate. The situation in which the subject 101 can concentrate is, for example, a situation in which the subject 101 is performing a task.

[0056] In the following, an example will be described in which an image of the subject 101 in a state of concentration is acquired by acquiring an image while the subject 101 is performing a task. Other examples of situations in which the subject 101 may be concentrating will be described later using modified examples.

[0057] In order to store the object positional relationship in the storage unit 21, the acquisition unit 11 acquires an implementation image in which the subject 101 performing the task is captured (S201). Furthermore, the task result acquisition unit 23 acquires the results of the task being performed by the subject 101. In this embodiment, based on the acquired task results, the habit of the subject 101 is calculated as the object positional relationship from the implementation image when the subject 101 is in a concentration state.

[0058] FIG. 7 is a diagram for explaining the relationship between the task performance of a subject and the subject's habits according to the first embodiment. FIG. 7 shows a graph of the fluctuation of the task performance against the elapsed time for a task performed by subject 101. As shown by the dashed line in FIG. 7, a threshold is set in advance for the task performance. The threshold may correspond to the acquired task performance. For example, when the task progress speed is acquired as the task performance, the threshold is a predetermined speed. Also, for example, when the task score is acquired as the task performance, the threshold is a predetermined value.

[0059] In the figure, it is shown that the subject 101 performed the habit of touching his / her chin with his / her hand at at least three points (points surrounded by thin dashed circles) where the task performance of the subject 101 is greater than a predetermined speed or a predetermined value and the task performance shows an upward convex peak. It is also shown that the subject 101 did not perform the above-mentioned habit at other points including at least three points (points surrounded by long dashed circles) where the task performance shows a downward convex peak. In this way, the concentration state determination unit 25 determines whether the subject 101 is in a concentration state depending on whether the acquired task performance is greater than a threshold such as a predetermined speed or a predetermined value.

[0060] Returning to Fig. 6, for example, in (a) of Fig. 6, the task result acquisition unit 23 acquires the progress speed of the task as the result of the task (S202). Also, for example, in (b) of Fig. 6, the task result acquisition unit 23 acquires the score of the task as the result of the task (S202a).

[0061] Next, the concentration measurement device 100 judges whether the subject 101 is in a state of concentration based on the acquired task performance as described in FIG. 7. For example, in (a) of FIG. 6, it is judged whether the acquired task progress speed is higher than a predetermined speed (S203). The predetermined speed may be a statistical progress speed set in consideration of the age and sex of the subject 101, or a progress speed experimentally determined in advance. The predetermined speed may be determined from an average speed of the progress speed of the task while the subject 101 is performing the task. In other words, an average speed calculated from the progress speed of a part of the task that has been performed among the tasks being performed may be set as the predetermined speed, and may be used to judge whether the subject 101 is in a state of concentration in the other part that has not been performed. In other words, the predetermined speed may be an average speed of the progress speed of the task by the subject 101.

[0062] Also, for example, in (b) of Fig. 6, it is determined whether or not the score of the acquired task is higher than a predetermined value (S203a). The predetermined value may be a statistical score set in consideration of the age and sex of the subject 101, or may be a score experimentally determined in advance. For example, the predetermined value may be an average value of the scores of one or more tasks previously performed by the subject 101.

[0063] For example, when the concentration state determination unit 25 determines that the progress speed of the subject 101 in the task is greater than a predetermined speed (Yes in S203), the body part recognition unit 13 calculates the target positional relationship in the implementation image at the time when the progress speed was acquired (S204). Furthermore, the habit information including the information indicating the calculated target positional relationship is stored in the storage unit 21 (S205).

[0064] On the other hand, if the concentration state determination unit 25 determines that the task progress speed of the subject 101 is equal to or lower than the predetermined speed (No in S203), the concentration measurement device 100 ends the process. The above process is repeatedly performed every time the task result acquisition unit 23 acquires the progress speed, which is the task result.

[0065] Also, for example, when the concentration state determination unit 25 determines that the task score of the subject 101 is higher than a predetermined value (Yes in S203a), the body part recognition unit 13 calculates the target positional relationship in the actual image at the time when the score was acquired (S204). Furthermore, the habit information including the information indicating the calculated target positional relationship is stored in the storage unit 21 (S205).

[0066] On the other hand, if the concentration state determination unit 25 determines that the task score of the subject 101 is equal to or less than the predetermined value (No in S203a), the concentration measurement device 100 ends the process.

[0067] Through the above process, the storage unit 21 stores habit information including information indicating the object positional relationship calculated in the implementation image acquired when the object 101 is in a state of concentration while performing a task.

[0068] Note that the habit information stored in storage unit 21 does not have to be habit information regarding the positional relationship between two or more parts of the body of subject 101 that defines the habit of subject 101. More specifically, information indicating the positional relationship between two or more parts of a person's body that defines a standard habit obtained by statistically processing the habits of multiple people may be stored in storage unit 21 as habit information.

[0069] FIG. 8 is a diagram showing an example of a standard habit. FIG. 8(a) illustrates the habit of touching the chin with the hand. FIG. 8(a) illustrates the action of touching the chin, which is a part of the face, with the hand as an example of a standard behavior pattern of a person when concentrating. FIG. 8(b) illustrates the habit of touching the area around the mouth with the hand. FIG. 8(b) illustrates the action of touching the area around the mouth, which is a part of the face, with the hand as an example of a standard behavior pattern of a person when concentrating. FIG. 8(c) illustrates the habit of stroking the neck with the hand. FIG. 8(c) illustrates the action of stroking the neck as if covering it with the hand as an example of a standard behavior pattern of a person when concentrating. FIG. 8(d) illustrates the habit of touching the forehead with the hand. FIG. 8(d) illustrates the habit of touching the forehead, which is a part of the face, with the hand as an example of a standard behavior pattern of a person when concentrating.

[0070] FIG. 8(e) illustrates the habit of clasping both hands together. FIG. 8(e) illustrates an example of a standard behavioral pattern of a person when concentrating, in which the person touches the area around the mouth, which is a part of the face, with the hands and clasps both hands in front of the face. FIG. 8(f) illustrates the habit of touching the hair with the hands. FIG. 8(f) illustrates an example of a standard behavioral pattern of a person when concentrating, in which the person clasps both hands and touches the hair with the hands. FIG. 8(g) illustrates the habit of touching the eyebrows with the hands. FIG. 8(g) illustrates an example of a standard behavioral pattern of a person when concentrating, in which the person touches the eyebrows, which is a part of the face, with the hands. FIG. 8(h) illustrates the habit of clasping both arms. FIG. 8(h) illustrates an example of a standard behavioral pattern of a person when concentrating, in which the person clasps both arms.

[0071] Information indicating the positional relationship between two or more parts of a person's body that specifies a standard habit as exemplified above may be stored as habit information in the storage unit 21. This makes it possible to measure the concentration level of the subject 101 using a habit that a person may generally adopt when concentrating. There is no need to perform a process of storing a habit specific to the subject 101 in the storage unit 21 in advance, and it is possible to measure the concentration level of the subject 101 more easily. Furthermore, even if a habit that a person may generally adopt when concentrating is used, the habit of the subject 101 can be sufficiently included because the habit is a statistically obtained habit.

[0072] Furthermore, the concentration measurement device 100 may store a plurality of habits that a person may generally adopt when concentrating in the memory unit 21. In other words, it is sufficient that any one of the plurality of habits stored in the memory unit 21 matches the habit of the subject 101, and by storing a plurality of habits in the memory unit 21, the possibility that the habits match the habit that the subject 101 may adopt increases. In other words, the concentration measurement device 100 can measure the concentration of a wider variety of subjects 101.

[0073] The operation of the concentration habit determination unit 15 in the case where habit information indicating a plurality of habits is stored in the storage unit 21 will be described. Fig. 9 is a diagram illustrating a processing table according to the first embodiment. The processing table in Fig. 9 shows "class number", "action pattern name", and "habit flag during concentration".

[0074] 9 shows a plurality of behavior patterns (i.e., habits) as specific behavior names corresponding to the habit information indicating the plurality of habits. Note that, in reality, the processing table is data used for processing inside the focus measurement device 100, so the portion for the behavior pattern name stores information indicating the positional relationship of two or more parts of the body that define each behavior pattern.

[0075] Moreover, the "class number" shown in the processing table of FIG. 9 is a serial number corresponding to each behavior pattern.

[0076] 9 is binary data indicating whether the target positional relationship matches the behavioral pattern included in the processing table. More specifically, when the target positional relationship in the acquired image matches the positional relationship of two or more parts of a person's body defined in the behavioral pattern, 1 is recorded in the "concentration habit flag," and otherwise 0 is recorded in the "concentration habit flag."

[0077] Here, one processing table corresponds to one image, and a binary judgment result of whether the subject 101 is in a state of concentration or a state of non-concentration is obtained from each image. Therefore, even if 1 is recorded in the "habit flag during concentration" for multiple behavioral patterns in one processing table, only one value indicating that the corresponding image is in a state of concentration is output as a judgment result. More specifically, for example, when the image shown in (e) of FIG. 8 is acquired, and even if 1 is recorded in the "habit flag during concentration" for both "touching around the mouth" and "putting hands together" with "class numbers" of 0 and 5 in the processing table as shown in FIG. 9, only the judgment result that the corresponding image is simply in a state of concentration is obtained.

[0078] As described above, when the habit information stored in the storage unit 21 stores information indicating the positional relationship of two or more parts of a person's body in each of a plurality of habits, the target positional relationship is compared with the positional relationship of two or more parts of a person's body in each of a plurality of habits for each acquired image. This generates information on "class numbers" in which 0 or 1 is recorded in the "habit flag during concentration" for each acquired image. For an image corresponding to the processing table in which 1 is recorded in the "habit flag during concentration" for at least one "class number," it is determined that the subject 101 is in a state of concentration. By tallying up the determination results in a preset time range, the concentration level of the subject 101 in that time range is calculated.

[0079] In addition, by directly tallying up the processing table for each image, output may be made regarding the contents of the habits of the subject 101, such as which "behavior pattern name" was detected more frequently.

[0080] [Effects, etc.] As described above, one aspect of the concentration measurement device 100 in this embodiment includes an acquisition unit 11 that acquires an image of the subject 101, a body part recognition unit 13 that recognizes the position of each of two or more parts of the subject 101's body in the image acquired by the acquisition unit 11 and calculates a target positional relationship, which is the positional relationship between the two or more parts of the subject 101's body that have been recognized, a concentration habit determination unit 15 that determines whether or not the subject 101 is in a state of concentration based on the target positional relationship calculated by the body part recognition unit 13 and a habit that a person may have when in a state of concentration, which habit is defined by the positional relationship of two or more parts of the person's body, and a concentration calculation unit 17 that calculates the concentration level of the subject 101 using the determination result by the concentration habit determination unit 15.

[0081] According to this, an image of the subject 101 for which the concentration level is to be measured can be acquired, and the positions of two or more parts of the subject 101's body included in the image can be recognized to calculate the positional relationship of each part. Using the habits of the person in a state of concentration, which are defined by the positional relationship of two or more parts of the body, and the calculated positional relationship of the subject 101, it can be determined whether the subject 101 is in a state of concentration. Since the determination of whether the subject 101 is in a state of concentration is made based on the habits of the person in a state of concentration, it is possible to determine whether the subject 101 is in a state of concentration regardless of the actions that the subject 101 can take when in a state of concentration. Therefore, it is possible to determine with high accuracy whether the subject 101 is in a state of concentration without depending on the actions that the subject 101 can take when in a state of concentration. Therefore, the concentration level measurement device 100 can measure the concentration level with high accuracy using the determination result of the state of concentration, which is determined with high accuracy.

[0082] In addition, for example, the concentration measurement device 100 may further include a memory unit 21 in which habit information regarding the positional relationship of two or more parts of a person's body that defines a habit is pre-stored, and the concentration habit determination unit 15 may determine whether the subject is in a state of concentration based on the target positional relationship and the habit information stored in the memory unit 21.

[0083] According to this, information on the positional relationship of two or more parts of a person's body that defines a habit, which is stored in advance in storage unit 21, can be used to determine the concentration state of subject 101. Therefore, since there is no need to obtain new information on the positional relationship of two or more parts of a person's body that defines a habit from outside when determining the concentration state of subject 101, concentration measurement device 100 can be realized as a single device.

[0084] Furthermore, for example, the habit information stored in the memory unit 21 may include information indicating the positional relationship between two or more parts of a person's body that defines a standard habit obtained by statistically processing the habits of multiple people.

[0085] According to this, the habits stored in advance in the storage unit 21 can be made into more generalized standard habits. Therefore, in a situation where the habits of the subject 101 are not specified, the concentration state of the subject 101 can be determined using general habits. Therefore, since the concentration state can be determined even for the subject 101 whose habits are not specified, the concentration measurement device 100 can be applied to a wide range of subjects 101.

[0086] Also, for example, the habit information stored in memory unit 21 may indicate the positional relationship of two or more parts of a person's body in at least one of standard habitual actions, such as a person touching part of their face with their hand, stroking their neck with their hand, bringing their hands together, touching their hair with their hands, and folding their arms.

[0087] According to this, the concentration state of the subject 101 can be determined using at least one of standard habitual actions, such as touching part of the face with the hand, stroking the neck with the hand, clasping the hands together, touching the hair with the hands, and folding the arms. Therefore, even for subjects 101 whose habits are not specified, the concentration state can be determined based on any of these actions, so the concentration measurement device 100 can be applied to a wide range of subjects 101.

[0088] In addition, for example, the concentration measurement device 100 further includes a task performance acquisition unit 23 that acquires the performance of the task performed by the subject 101, and a concentration state determination unit 25 that determines whether the subject 101 is in a state of concentration based on the task performance, and the acquisition unit 11 acquires an implementation image of the subject 101 performing the task as an image, and the habit information stored in the memory unit 21 may include information indicating the target position relationship calculated in the implementation image acquired when the concentration state determination unit 25 determines that the subject 101 is in a state of concentration.

[0089] According to this, an implementation image is acquired in which the subject 101 performing the task is captured at the time when the subject 101 is determined to be in a state of concentration based on the results of the task performed by the subject 101. The subject 101 in the implementation image is in a state of concentration, so it is presumed that the subject 101 is performing an action that can be taken when in a state of concentration. Therefore, the positional relationship of two or more parts of the body of the subject 101 in the implementation image is considered to define the habit of the subject 101. The positional relationship of two or more parts of the body due to the habit of the subject 101 can be stored in advance in the storage unit 21, and the concentration state of the subject 101 can be determined using this. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the habit of the subject 101 himself.

[0090] Also, for example, the task performance acquisition unit 23 may acquire the progress speed of the task performed by the subject 101 as the task performance, and the concentration state determination unit 25 may determine that the subject 101 is in a concentration state when the task progress speed is greater than a predetermined speed.

[0091] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task progress speed acquired as the task performance. If the task progress speed is faster than a predetermined speed, it is determined that the subject 101 is in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body in the implementation image acquired at this time. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the subject 101's own habits.

[0092] Also, for example, the predetermined speed may be an average speed at which the subject 101 progresses through the task.

[0093] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task progress speed acquired as the task performance. If the task progress speed is faster than the average speed, it is determined that the subject 101 is in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body in the implementation image acquired at this time. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the subject 101's own habits.

[0094] Also, for example, the task performance acquisition unit 23 may acquire the score of a task performed by the subject 101 as the task performance, and the concentration state determination unit 25 may determine that the subject 101 is in a concentration state when the task score is higher than a predetermined value.

[0095] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task score acquired as the task performance. If the task score is greater than a predetermined value, the subject 101 is determined to be in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body in the implementation image acquired at this time. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the habits of the subject 101 himself / herself.

[0096] Also, for example, the predetermined value may be an average of the scores of one or more tasks performed by the subject 101.

[0097] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task score acquired as the task performance. If the task score is higher than the average value, the subject 101 is determined to be in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body in the implementation image acquired at this time. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the habits of the subject 101 himself / herself.

[0098] Furthermore, one aspect of the concentration measurement method in this embodiment includes an acquisition step of acquiring an image of a subject, a recognition step of recognizing the position of each of two or more parts of the subject's body in the image acquired in the acquisition step and calculating a target positional relationship, which is the positional relationship between the two or more parts of the subject's body that have been recognized, a determination step of determining whether or not the subject is in a state of concentration based on the target positional relationship calculated in the recognition step and a habit that a person may have when in a state of concentration, which habit is defined by the positional relationship of two or more parts of the person's body, and a calculation step of calculating the subject's concentration level using the determination result in the determination step.

[0099] According to this, an image of the subject 101 for which the concentration level is to be measured can be acquired, and the positions of two or more parts of the subject 101's body included in the image can be recognized to calculate the positional relationship of each part. Using the habits of the person in a state of concentration, which are defined by the positional relationship of two or more parts of the body, and the calculated positional relationship of the subject 101, it can be determined whether the subject 101 is in a state of concentration. Since the determination of whether the subject 101 is in a state of concentration is made based on the habits of the person in a state of concentration, it is possible to determine whether the subject 101 is in a state of concentration regardless of the actions that the subject 101 can take when in a state of concentration. Therefore, it is possible to determine with high accuracy whether the subject 101 is in a state of concentration without depending on the actions that the subject 101 can take when in a state of concentration. Therefore, the concentration level measurement device 100 can measure the concentration level with high accuracy using the determination result of the state of concentration, which is determined with high accuracy.

[0100] Furthermore, for example, the above-described concentration measurement method may be implemented as a program for causing a computer to execute the method.

[0101] This makes it possible to cause a computer to execute the above-described concentration measurement method.

[0102] [Variations] Next, a modified example of the first embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart for explaining the storage of habit information in a storage unit according to a modified example of the first embodiment. Fig. 10(a) shows a flowchart for acquiring a task progress speed as the task performance. Fig. 10(b) shows a flowchart for acquiring a task score as the task performance.

[0103] In this modification, an operation of the concentration measurement device 100 that stores the object positional relationship in the storage unit 21 based on a determination of whether the subject 101 is in a concentration state when the subject 101 interrupts a task being performed will be described. Therefore, the process of the concentration measurement device 100 corresponding to the storage of habit information in the storage unit 21, which was described in the above first embodiment using FIG. 6, will be described, and the rest will be omitted or simplified.

[0104] First, when the task record acquisition unit 23 detects that the subject 101 has interrupted the performance of the task, the acquisition unit 11 acquires an interruption image capturing the subject 101 interrupting the performance of the task (S401). After that, the task record acquisition unit 23 determines whether the interruption time of the subject 101's task performance is equal to or longer than a second time (S402).

[0105] Here, it is presumed that the subject 101 who has suspended the performance of the task is in a thinking state for performing the task. Since the subject 101 who is in a thinking state is highly likely to be in a concentration state, it is presumed that the subject 101 who has suspended the performance of the task is in a concentration state. At this time, in order to distinguish a case where the subject 101 has suspended the performance of the task due to other reasons such as poor physical condition, the concentration state determination unit 25 further determines whether the subject 101 is in a concentration state or not by using the task performance after the task is resumed.

[0106] If the subject 101 was in a thinking state for performing the task when the performance of the task was interrupted, it is expected that the performance of the task after the task is resumed will be greater than a threshold such as a predetermined speed or a predetermined value. Therefore, when the performance of the task is interrupted and the performance of the task after the task is resumed is greater than a threshold such as a predetermined speed or a predetermined value, the concentration state determination unit 25 determines that the subject 101 was in a concentration state when the performance of the task was interrupted.

[0107] If it is determined that the interruption time is shorter than the second time (No in S402), the correlation between the interruption of the task and the concentration state of the subject 101 is uncertain, so the concentration measurement device 100 ends the process. Note that the second time is a sufficient time for the subject 101 to be considered capable of thinking about performing the task. The second time may be set individually for each subject 101, or a standard time may be set for each task content.

[0108] On the other hand, if it is determined that the interruption time is the second time or more (Yes in S402), it is determined whether or not the subject 101 is in a concentration state. That is, the concentration state determination unit 25 determines whether or not the subject 101 who has interrupted the performance of the task for the second time or more is in a concentration state by using an interruption image captured.

[0109] First, the task result acquisition unit 23 acquires the task result when the subject 101 resumes the task. The task result is the task progress speed or the task score, as in the above-mentioned first embodiment. For example, in (a) of FIG. 10, the task result acquisition unit 23 acquires the task progress speed as the task result (S403). Also, for example, in (b) of FIG. 10, the task result acquisition unit 23 acquires the task score as the task result (S403a).

[0110] Next, the concentration state determination unit 25 determines whether the subject 101 is in a concentration state based on the acquired track record of the task. For example, in (a) of FIG. 10, it determines whether the progress speed of the acquired task is greater than a predetermined speed (S404). The predetermined speed may be set in the same manner as in the first embodiment, or may be set based on the track record of the task before the performance of the task is interrupted. Moreover, the predetermined speed may be an average speed of the progress speed of the subject 101 in the task.

[0111] Also, for example, in (b) of Fig. 10, it is determined whether or not the score of the acquired task is higher than a predetermined value (S404a). The predetermined value may be set in the same manner as in the first embodiment, or may be set based on the performance of the task before the performance of the task is interrupted. The predetermined value may also be an average value of the scores of one or more tasks previously performed by the subject 101.

[0112] For example, when the concentration state determination unit 25 determines that the progress speed of the task of the subject 101 is greater than a predetermined speed (Yes in S404), the body part recognition unit 13 calculates the target positional relationship in the acquired interrupted image (S405). Furthermore, the habit information including the information indicating the calculated target positional relationship is stored in the storage unit 21 (S406).

[0113] On the other hand, if the concentration state determination unit 25 determines that the task progress speed of the subject 101 is equal to or lower than the predetermined speed (No in S404), the concentration measurement device 100 ends the process.

[0114] Also, for example, when the concentration state determination unit 25 determines that the task score of the subject 101 is higher than a predetermined value (Yes in S404a), the body part recognition unit 13 calculates the target positional relationship in the acquired interrupted image (S405). Furthermore, habit information including information indicating the calculated target positional relationship is stored in the storage unit 21 (S406).

[0115] On the other hand, if the concentration state determination unit 25 determines that the task score of the subject 101 is equal to or less than the predetermined value (No in S404a), the concentration measurement device 100 ends the process.

[0116] By the above process, the memory unit 21 stores habit information including information indicating the target positional relationship calculated in the interrupted image acquired when the subject 101 interrupted the task to perform the task and was in a state of concentration. Therefore, the concentration measurement device 100 in this modification can measure the concentration level of the subject 101 based on the determination of whether the subject 101 is in a state of concentration by using the habit of the subject 101 when measuring the concentration level of the subject 101, and can be applied to a wide range of applications. Furthermore, the concentration measurement device 100 can reduce individual differences in the actions during concentration and measure the concentration level of the subject 101 with high accuracy.

[0117] As described above, for example, the concentration measurement device 100 further includes a task performance acquisition unit that acquires the performance of a task performed by the subject, and a concentration state determination unit that determines whether the subject is in a state of concentration based on the task performance, wherein the acquisition unit acquires an interruption image capturing the subject who has interrupted the performance of the task for more than a second hour, and the habit information stored in the memory unit may include information indicating the subject positional relationship calculated in the interruption image when it is determined that the subject is in a state of concentration during the interruption of the task, based on the task performance of the subject who resumed the task after interrupting the performance of the task.

[0118] According to this, an interruption image is acquired in which the subject 101, who has interrupted the task and is determined to be in a state of concentration for thinking, is captured based on the task performance after the subject 101 has interrupted the task. The subject 101 in the interruption image is in a state of concentration, and therefore it is presumed that the subject 101 is performing an action that can be taken when in a state of concentration. Therefore, the positional relationship of two or more parts of the body of the subject 101 in the interruption image is considered to define the habit of the subject 101. The positional relationship of two or more parts of the body due to the habit of the subject 101 can be stored in advance in the storage unit 21, and the concentration state of the subject 101 can be determined using this. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the habit of the subject 101 himself.

[0119] Also, for example, the task performance acquisition unit may acquire the progress speed of a task performed by the subject as the task performance, and the concentration state determination unit may determine that the subject is in a concentration state while the task is interrupted if the task progress speed is greater than a predetermined speed.

[0120] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task progress speed acquired as the task performance. If the task progress speed is faster than a predetermined speed, it is determined that the subject 101 in the interruption image is in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the subject 101's own habits.

[0121] Furthermore, for example, the predetermined speed may be an average speed at which the subject progresses through the task.

[0122] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task progress speed acquired as the task performance. If the task progress speed is faster than the average speed, it is determined that the subject 101 in the interruption image is in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the subject 101's own habits.

[0123] Also, for example, the task performance acquisition unit may acquire the performance of a task performed by the subject as the task performance, and the concentration state determination unit may determine that the subject is in a concentration state while the task is interrupted if the task performance is higher than a predetermined value.

[0124] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task score acquired as the task performance. If the task score is greater than a predetermined value, it is determined that the subject 101 in the interruption image is in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the subject 101's own habits.

[0125] Also, for example, the predetermined value may be an average of performance in one or more tasks previously performed by the subject.

[0126] According to this, when the subject 101 performs a task, whether or not he / she is in a state of concentration can be determined based on the task score acquired as the task performance. If the task score is higher than the average value, it is determined that the subject 101 in the interruption image is in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body. Therefore, the concentration measurement device 100 can measure the concentration level of the subject 101 with higher accuracy based on the subject 101's own habits.

[0127] (Embodiment 2) Next, the second embodiment will be described with reference to Fig. 11 and Fig. 12. Fig. 11 is a block diagram showing the configuration of a concentration measurement device according to the second embodiment. Fig. 12 is a flowchart showing the storage of habit information in a storage unit according to the second embodiment.

[0128] In this embodiment, in order to store the object positional relationship in advance in the storage unit 21, another example of a situation in which the subject 101 may concentrate will be described when imaging the subject 101 in a state of concentration. Therefore, the concentration measurement device 100a in this embodiment has components that can handle another example of a situation in which the subject 101 may concentrate. Below, differences from the above-mentioned embodiment 1 will be described, and parts that are substantially the same as those in embodiment 1 will be omitted or simplified.

[0129] 11, the focus measurement device 100a in this embodiment differs from the first embodiment in that it includes a detection unit 27 and a focus state determination unit 25a. Also, the focus measurement device 100a in this embodiment differs from the first embodiment in that it does not include a task result acquisition unit 23 and a focus state determination unit 25.

[0130] The detection unit 27 is a processing device that detects the facial direction of the subject 101. The detection unit 27 is realized by, for example, a processor, a storage device, and a program stored in the storage device. The detection unit 27 is connected to the acquisition unit 11, and receives an image of the subject 101 acquired by the acquisition unit 11. The detection unit 27 detects the facial direction of the subject 101 in the received image.

[0131] The concentration state determination unit 25a is a processing device that determines whether the target person 101 is in a concentration state. The concentration state determination unit 25a is realized by, for example, a processor, a storage device, and a program stored in the storage device. When the facial direction of the target person 101 detected by the detection unit 27 does not change for a first time period, the concentration state determination unit 25a determines that the target person 101 is in a concentration state in the received image.

[0132] The focus measurement device 100a in this embodiment does not require the execution of a task or the like in storing habit information in the memory unit 21, and only needs to acquire the posture of the subject 101 from an image in which the subject 101 is captured.

[0133] Specifically, the detection unit 27 receives an image of the subject 101 from the acquisition unit 11 as shown in Fig. 12. The detection unit 27 detects the facial direction of the subject 101 in the acquired image (S301). Here, the reception of the image and the detection of the facial direction of the subject 101 by the detection unit 27 are performed continuously in time series. That is, the detection unit 27 generates data indicating a change over time in the facial direction of the subject 101.

[0134] In the concentration state determination section 25a, using the generated data indicating the change over time in the facial direction, it is determined whether the facial direction of the subject 101 has not changed for a first time or more, that is, whether the facial direction is constant for a first time or more (S302). The first time is, for example, an average time during which the subject 101 remains in a state of concentration. The first time may also be, for example, the shortest time during which the subject 101 remains in a state of concentration. The first time may also be, for example, an average time during which a standard state of concentration continues.

[0135] When the concentration state determination unit 25a determines that the facial direction of the subject 101 has not changed for the first time or more, that is, that the facial direction has been constant for the first time or more (Yes in S302), the body parts recognition unit 13 calculates the target positional relationship in the acquired image (S303). Furthermore, the habit information including the information indicating the calculated target positional relationship is stored in the storage unit 21 (S304).

[0136] On the other hand, if the concentration state determination unit 25a determines that the facial direction of the subject 101 has changed in a time shorter than the first time, that is, that the facial direction has changed before the first time has elapsed (No in S302), the concentration measurement device 100a terminates the processing.

[0137] Through the above processing, the memory unit 21 stores habit information including information indicating the object positional relationship calculated in an image acquired when the subject 101's facial direction was constant for at least the first hour and the subject 101 was in a state of concentration.

[0138] Therefore, the concentration measurement device 100a in this modification can use the habits of the subject 101 to measure the concentration level of the subject 101 based on a determination of whether the subject 101 is in a state of concentration, and can therefore be applied to a wide range of uses. Furthermore, the concentration measurement device 100a can reduce individual differences in movements during concentration and measure the concentration level of the subject 101 with high accuracy.

[0139] As described above, one aspect of the concentration measurement device 100a in this embodiment further includes a detection unit that detects the facial direction of the subject, and a concentration state determination unit that determines that the subject is in a concentration state when the facial direction of the subject does not change for a first hour or more, and the habit information stored in the memory unit includes information indicating the subject positional relationship calculated by the body parts recognition unit in the image acquired by the acquisition unit when the concentration state determination unit determines that the subject is in a concentration state.

[0140] According to this, an image is acquired of the subject 101 who is determined to be in a state of concentration, with the face direction not changing for a first time or more, based on the determination based on the time until the face direction of the subject 101 changes. The subject 101 in the image is in a state of concentration, and it is presumed that the subject 101 is performing an action that can be taken when in a state of concentration. Therefore, the positional relationship of two or more parts of the body of the subject 101 in the image is considered to define the habit of the subject 101. The positional relationship of two or more parts of the body due to the habit of the subject 101 can be stored in advance in the storage unit 21, and the concentration state of the subject 101 can be determined using this. Therefore, the concentration measurement device 100a can measure the concentration level of the subject 101 with higher accuracy based on the habit of the subject 101 himself.

[0141] Furthermore, for example, the first time period may be an average time period during which the facial orientation of the subject does not change.

[0142] According to this, it is possible to determine whether the subject 101 is in a state of concentration based on the time it takes for the subject 101's facial direction to change. If the time it takes for the subject 101's facial direction to change is longer than the average time, it is determined that the subject 101 in the image is in a state of concentration, and the concentration state of the subject 101 can be determined using the positional relationship of two or more parts of the subject 101's body. Therefore, the concentration measurement device 100a can measure the concentration level of the subject 101 with high accuracy based on the subject 101's own habits.

[0143] (Other embodiments) Although the concentration measurement device, the concentration measurement method, and the program according to the present disclosure have been described above based on the above-mentioned embodiments, the present disclosure is not limited to the above-mentioned embodiments. For example, the present disclosure also includes forms obtained by applying various modifications to the embodiments that a person skilled in the art can think of, and forms realized by arbitrarily combining the components and functions of the embodiments within the scope of the present disclosure.

[0144] In the above embodiment and the like, an example has been described in which the subject's track record of the task performed and the subject's facial orientation are used to calculate the subject's habit when the subject is in a state of concentration as the subject positional relationship, but as long as the subject positional relationship can be calculated, there is no particular restriction on the subject's behavior. For example, the subject may be engaged in an activity such as sports.

[0145] In the above embodiment, the image of the subject captured at one point in time is used to determine whether the subject is in a state of concentration, but the image may be a moving image, for example. The concentration measurement device may use positional changes in two or more parts of the body caused by the subject's habit of concentrating and determine whether the positional changes in two or more parts of the body of the subject in the moving image match with those of the subject.

[0146] Also, for example, the subject's concentration habit may be defined by more complicated criteria. For example, the subject's concentration habit of "nail biting" may be defined based on whether or not the following three conditions are all satisfied: "the subject's hands and mouth are within a specific distance," "the subject's cheek muscles are moving," and "the subject's fingers are extended."

[0147] Also, for example, while it has been explained that the positional relationship between two or more parts of the body is determined by distance, it does not have to be determined only by distance and may be determined without using distance. For example, the subject's habit of "touching the upper lip" when concentrating may be determined based on two conditions that the subject's "hands and mouth are within a specific distance" and that the "mouth is lower than the hands". Also, for example, the subject's habit of "touching the head" when concentrating may be determined based on one condition that the "hands are higher than the forehead".

[0148] For example, the present disclosure can be realized not only as a concentration measurement device, but also as a program including, as steps, processes performed by each component of the concentration measurement device, and a computer-readable recording medium on which the program is recorded. The program may be pre-recorded on the recording medium, or may be supplied to the recording medium via a wide area communication network including the Internet.

[0149] In other words, the above-mentioned comprehensive or specific aspects may be realized by a system, an apparatus, an integrated circuit, a computer program, or a computer-readable recording medium, or may be realized by any combination of a system, an apparatus, an integrated circuit, a computer program, and a recording medium. [Industrial Applicability]

[0150] The concentration measurement device disclosed herein is installed in buildings such as homes, offices, and cram schools, or in moving bodies such as automobiles, and is used for purposes such as measuring a subject's concentration with high accuracy. [Explanation of symbols]

[0151] 11 Acquisition Department 13 Body parts recognition unit 15 Concentration Habit Determination Department 17 Concentration calculation part 21 Memory section 23 Task Results Acquisition Department 25, 25a Concentration state determination unit 27 Detection unit 100, 100a Concentration measuring device 101 Target 101a Part of face (chin) 101b hand 201 Input section 202 Output section

Claims

1. An acquisition unit that acquires an image of a subject; a body part recognition unit that recognizes a position of each of two or more parts of the subject's body in the image acquired by the acquisition unit, and calculates a shortest distance between the recognized two or more parts of the subject's body in coordinates on the image; a concentration habit determination unit that determines whether the subject is in a state of concentration based on the shortest distance calculated by the body part recognition unit and the shortest distance in a habit that a person may have when in a state of concentration, the habit being defined by a positional relationship of two or more parts of the person's body; a concentration degree calculation unit that calculates a concentration degree of the subject using a result of the determination by the concentration habit determination unit; A storage unit in which habit information regarding a positional relationship between two or more parts of a person's body that defines the habit is stored in advance; A task performance acquisition unit that acquires performance of a task performed by the subject; a concentration state determination unit that determines whether the subject is in a concentration state based on the performance of the task, The concentration habit determination unit determines whether the subject is in a concentration state based on the shortest distance and the habit information stored in the storage unit, The acquisition unit acquires an interruption image capturing an image of the subject who has interrupted performance of the task for a second period or more, The habit information stored in the storage unit includes information indicating the shortest distance calculated in the interrupted image when it is determined that the subject is in a concentration state during the interruption of the task based on the performance of the task of the subject who resumed the task after interrupting the performance of the task. Concentration measuring device.

2. The acquisition unit acquires a moving image including a plurality of the images, the body part recognition unit calculates a shortest distance from a positional relationship of two or more parts of the subject's body in each of the plurality of images of the video; the concentration habit determination unit determines whether the subject is in a concentration state based on a change in the shortest distance between two or more parts of the subject's body in the moving image and a change in the shortest distance between two or more parts of the body due to the subject's concentration habit. The concentration measurement device according to claim 1 .

3. The habit information stored in the storage unit includes information indicating a positional relationship between two or more parts of a person's body, which defines a standard habit obtained by statistically processing the habits of a plurality of people. The concentration measurement device according to claim 1 .

4. The habit information stored in the storage unit indicates a positional relationship between two or more parts of the person's body in at least one of the standard habit actions, which are a motion of the person touching a part of the face with a hand, a motion of stroking the neck with a hand, a motion of putting both hands together, a motion of touching the hair with a hand, and a motion of folding both arms. The concentration measurement device according to claim 3 .

5. Further, a task performance acquisition unit that acquires performance of a task performed by the subject person; a concentration state determination unit that determines whether the subject is in a concentration state based on the performance of the task, The acquisition unit acquires, as the image, an implementation image in which the subject is performing a task, The habit information stored in the storage unit includes information indicating the shortest distance calculated in the implementation image acquired when the concentration state determination unit determines that the subject is in a concentration state. The concentration measurement device according to claim 1 .

6. The task performance acquisition unit acquires a progress speed of the task performed by the subject as the performance of the task, The concentration state determination unit determines that the subject is in a concentration state when a progress speed of the task is greater than a predetermined speed. The concentration measurement device according to claim 5 .

7. The predetermined speed is an average speed of progress of the subject in the task. The concentration measurement device according to claim 6.

8. the task performance acquisition unit acquires a score of the task performed by the subject as the performance of the task; The concentration state determination unit determines that the subject is in a concentration state when the score of the task is higher than a predetermined value. The concentration measurement device according to claim 5 .

9. The predetermined value is an average score of one or more of the tasks performed by the subject. The concentration measurement device according to claim 8.

10. Further, a detection unit that detects a facial direction of the subject; and a concentration state determination unit that determines that the subject is in a concentration state when the facial orientation of the subject does not change for a first time or more, The habit information stored in the storage unit includes information indicating the shortest distance calculated by the body part recognition unit in the image acquired by the acquisition unit when the concentration state determination unit determines that the subject is in a concentration state. The concentration measurement device according to claim 1 .

11. The first time period is an average time period during which the facial orientation of the subject does not change. The concentration measurement device according to claim 10.

12. The task performance acquisition unit acquires a progress speed of the task performed by the subject as the performance of the task, The concentration state determination unit determines that the subject is in a concentration state during the interruption of the task when a progress speed of the task is greater than a predetermined speed. The concentration measurement device according to claim 1 .

13. The predetermined speed is an average speed of progress of the subject in the task. The concentration measurement device according to claim 12.

14. The task performance acquisition unit acquires a performance of the task performed by the subject as the performance of the task, The concentration state determination unit determines that the subject is in a concentration state during the interruption of the task when the performance of the task is higher than a predetermined value. The concentration measurement device according to claim 1 .

15. The predetermined value is an average of performance in one or more tasks previously performed by the subject. The concentration measurement device according to claim 14.

Images