Sleep estimation system, sleep estimation method, and program

Abstract

The present disclosure addresses the problem of accurately estimating a sleep state without depending on a detection distance. A sleep estimation system (1) comprises a thermal image acquisition unit (201), a distance acquisition unit (202), a body movement analysis unit (203), and a sleep estimation unit (204). The thermal image acquisition unit (201) acquires a thermal image of a sleeper from a thermal image sensor (10). The distance acquisition unit (202) acquires a detection distance which is the distance from the thermal image sensor (10) to bedding of the sleeper. The body movement analysis unit (203) analyzes, on the basis of the thermal image, the body movement of the sleeper during sleep, to determine a body movement feature amount. The sleep estimation unit (204) estimates the sleep state of the sleeper from the body movement feature amount. The body movement analysis unit (203) corrects the body movement feature amount on the basis of the detection distance acquired by the distance acquisition unit (202). The sleep estimation unit (204) uses the corrected body movement feature amount to estimate the sleep state of the sleeper.

Description

Sleep estimation system, sleep estimation method, and program

[0001] The present disclosure generally relates to a sleep estimation system, a sleep estimation method, and a program, and more particularly to a sleep estimation system, a sleep estimation method, and a program that estimate the sleep state of a sleeper.

[0002] Patent Document 1 describes an air conditioner that determines the sleeping state of a user and controls air conditioning in accordance with the sleeping state.

[0003] The air conditioner in Patent Document 1 identifies a person's head, torso, limbs from a thermal pixel image, which is a temperature distribution detected by an infrared sensor, analyzes the magnitude and frequency of body movements of each identified part, as well as the surface temperature of each part, and predicts and judges the person's sleeping state based on the analysis results.

[0004] When using thermal images obtained from the detection results of an infrared sensor (image sensor), the detection results of human parts change when the distance (detection distance) between the infrared sensor and the bedding changes, which may result in inaccurate estimation of sleep state.

[0005] JP 2010-133692 A

[0006] The present disclosure has been made in consideration of the above-mentioned problems, and aims to provide a sleep estimation system, a sleep estimation method, and a program that can accurately estimate a sleep state without depending on the detection distance.

[0007] A sleep estimation system according to one aspect of the present disclosure includes a thermal image acquisition unit, a distance acquisition unit, a body movement analysis unit, and a sleep estimation unit. The thermal image acquisition unit acquires a thermal image of a sleeper from a thermal image sensor. The distance acquisition unit acquires a detected distance, which is the distance from the thermal image sensor to the sleeper's bedding. The body movement analysis unit analyzes the sleeper's body movement during sleep based on the thermal image to obtain a body movement feature. The sleep estimation unit estimates the sleep state of the sleeper from the body movement feature. The body movement analysis unit corrects the body movement feature based on the detected distance acquired by the distance acquisition unit. The sleep estimation unit estimates the sleep state of the sleeper using the corrected body movement feature.

[0008] A sleep estimation system according to one aspect of the present disclosure includes a thermal image acquisition unit, a distance acquisition unit, a body movement analysis unit, and a sleep estimation unit. The thermal image acquisition unit acquires a thermal image of a sleeper from a thermal image sensor. The distance acquisition unit acquires a detected distance, which is the distance from the thermal image sensor to the sleeper's bedding. The body movement analysis unit analyzes the sleeper's body movement during sleep based on the thermal image to obtain a body movement feature. The sleep estimation unit estimates the sleep state of the sleeper from the body movement feature. The sleep estimation unit counts a body movement density, which is the number of body movements of the sleeper per unit time, based on the body movement feature, and estimates the sleep state of the sleeper based on the counting result. When counting the body movement density, the sleep estimation unit corrects a reference value, which is a standard for determining that a body movement of the sleeper has occurred, based on the detected distance acquired by the distance acquisition unit. The sleep estimation unit counts the body movement density of the sleeper using the corrected reference value.

[0009] A sleep estimation method according to one aspect of the present disclosure includes a thermal image acquisition step, a distance acquisition step, a body movement analysis step, and a sleep estimation step. In the thermal image acquisition step, a thermal image of a sleeper is acquired from a thermal image sensor. In the distance acquisition step, a detected distance, which is the distance from the thermal image sensor to the sleeper's bedding, is acquired. The body movement analysis step unit analyzes the body movement of the sleeper during sleep based on time-series changes in each of multiple pixels of the thermal image to obtain body movement feature amounts. In the sleep estimation step, a sleep state of the sleeper is estimated from the body movement feature amounts. In the body movement analysis step, the body movement feature amounts are corrected based on the detected distance acquired in the distance acquisition step. In the sleep estimation step, the sleep state of the sleeper is estimated using the corrected body movement feature amounts.

[0010] A sleep estimation method according to one aspect of the present disclosure includes a thermal image acquisition step, a distance acquisition step, a body movement analysis step, and a sleep estimation step. In the thermal image acquisition step, a thermal image of a sleeper is acquired from a thermal image sensor. In the distance acquisition step, a detected distance, which is the distance from the thermal image sensor to the sleeper's bedding, is acquired. The body movement analysis step analyzes the sleeper's body movement during sleep based on time-series changes in each of multiple pixels in the thermal image to obtain a body movement feature. In the sleep estimation step, a sleep state of the sleeper is estimated from the body movement feature. In the sleep estimation step, a body movement density, which is the number of body movements per unit time, is counted, and the sleep state of the sleeper is estimated based on the counting result. When counting the body movement density, in the sleep estimation step, a reference value serving as a reference for determining that the sleeper's body movement has occurred is corrected based on the detected distance acquired in the distance acquisition step. In the sleep estimation step, the body movement density of the sleeper is counted using the corrected reference value.

[0011] A program according to one aspect of the present disclosure is a program for causing a computer system to execute any one of the sleep estimation methods described above.

[0012] FIG. 1 is a block diagram illustrating a configuration of a sleep estimation system according to a first embodiment of the present disclosure. FIG. 2 is a system diagram illustrating an example of use of the sleep estimation system. FIG. 3 is an explanatory diagram illustrating an example of installation of a thermal image sensor included in the sleep estimation system. FIG. 4 is a graph illustrating a relational expression used by the sleep estimation system to correct body movement features. FIG. 5 is a flowchart illustrating the operation of the sleep estimation system. FIG. 6 is a graph illustrating changes in body movement features when the detection distance is a reference distance. FIG. 7 is a graph illustrating changes in body movement features when the detection distance is longer than the reference distance. FIG. 8 is a graph illustrating changes in body movement features when the detection distance is shorter than the reference distance. FIG. 9 is an explanatory diagram illustrating angle adjustment of a thermal image sensor according to a first modification of the first embodiment. FIG. 10 is an explanatory diagram illustrating angle adjustment of a thermal image sensor according to a second modification of the first embodiment. FIG. 11 is a block diagram illustrating a configuration of a sleep estimation system according to a second embodiment of the present disclosure. FIG. 12 is a flowchart illustrating the operation of the sleep estimation system. FIG. 13 is a graph illustrating changes in body movement features and reference values ​​when the detection distance is the reference distance. 14 and 15 are graphs showing changes in body movement feature amounts and corrected reference values ​​when the detection distance is longer than the reference distance, respectively.

[0013] The embodiments and modifications described below are merely examples of the present disclosure, and the present disclosure is not limited to these embodiments and modifications. Various modifications other than these embodiments and modifications are possible depending on the design, etc., as long as they do not deviate from the technical concept of the present disclosure.

[0014] First Embodiment A sleep estimation system 1 according to a first embodiment will be described below with reference to FIGS.

[0015] (1) Overview As shown in FIG. 1 , the sleep estimation system 1 according to the first embodiment includes a thermal image acquisition unit 201, a distance acquisition unit 202, a body movement analysis unit 203, and a sleep estimation unit 204. The thermal image acquisition unit 201 acquires a thermal image of a sleeper u1 (see FIG. 2 ) from the thermal image sensor 10. The distance acquisition unit 202 acquires a detection distance, which is the distance from the thermal image sensor 10 to the bedding F1 (see FIG. 3 ) of the sleeper u1. The body movement analysis unit 203 analyzes the body movement of the sleeper u1 during sleep based on the thermal image to obtain a body movement feature amount. The sleep estimation unit 204 estimates the sleep state of the sleeper u1 from the body movement feature amount. The body movement analysis unit 203 corrects the body movement feature amount based on the detection distance acquired by the distance acquisition unit 202. The sleep estimation unit 204 estimates the sleep state of the sleeper u1 using the corrected body movement feature amount.

[0016] According to this configuration, the body movement feature amount is corrected according to the detection distance, so that the sleep state can be estimated with high accuracy without depending on the detection distance.

[0017] (2) Configuration (2.1) Sleep Estimation System The sleep estimation system 1 estimates the sleep state of a person (sleeper u1) sleeping in a space SP1 (see FIG. 2 ). The sleep estimation system 1 transmits the estimation result to an information terminal 30. Here, the information terminal 30 is, for example, a smartphone or a tablet terminal.

[0018] As shown in FIG. 1 , the sleep estimation system 1 includes a thermal image sensor 10 and a signal processing device 20 .

[0019] The thermal image sensor 10 receives infrared light emitted from a person. The thermal image sensor 10 outputs a thermal image based on the received infrared light. Specifically, the thermal image sensor 10 receives infrared light emitted from a sleeping person (sleeper u1) and outputs a thermal image based on the received infrared light to the signal processing device 20. More specifically, the thermal image sensor 10 continuously receives infrared light emitted from the sleeper u1 and outputs multiple continuous thermal images, i.e., a moving thermal image, to the signal processing device 20. The thermal image sensor 10 is installed, for example, on the ceiling surface (hereinafter referred to as the top surface) C1 (see FIG. 3) of the space SP1. Here, the vertical distance h1 from the thermal image sensor 10 to the bedding F1 (see FIG. 3) is defined as the detection distance. The region R1 shown in FIG. 3 is defined as the detection region of the thermal image sensor 10.

[0020] The signal processing device 20 analyzes the body movement of the sleeping person u1 based on the moving image of the thermal image, obtains a body movement feature amount, and corrects the obtained body movement feature amount. The signal processing device 20 estimates the sleep state of the sleeping person u1 based on the corrected body movement feature amount. As shown in FIG. 1 , the signal processing device 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

[0021] The signal processing device 20 includes, for example, a computer system having a processor and a memory. The processor executes a program stored in the memory, causing the computer system to function as the control unit 23. The program executed by the processor is pre-recorded in the memory of the computer system here, but may also be provided by being recorded on a recording medium such as a memory card, or via a telecommunications line such as the Internet.

[0022] The communication unit 21 has a communication interface for communicating with the information terminal 30. For example, the communication unit 21 is configured to be able to communicate with the information terminal 30 via wireless communication. Note that the communication unit 21 may also be configured to be able to communicate with the information terminal 30 via wired communication.

[0023] The storage unit 22 is configured by a device selected from a read-only memory (ROM), a random access memory (RAM), an electrically erasable programmable read-only memory (EEPROM), and the like.

[0024] The memory unit 22 stores information used to correct the body movement feature amount. The memory unit 22 stores, as information used to correct the body movement feature amount, a detection distance and a relational expression defining the relationship between the body movement feature amount and the detection distance. The relational expression is a function K1 (see FIG. 4 ) that expresses the relationship between the body movement feature amount and the detection distance. The function K1 expressing the relationship between the body movement feature amount and the detection distance expresses the relationship between the detection distance and the body movement feature amount normalized using the body movement feature amount (representative feature amount) obtained at the reference distance d1 as a reference, and passes through a reference point P0, which is a coordinate point formed by the reference distance d1 and the reference feature amount "1" (see FIG. 4 ). Here, the representative feature amount is the body movement feature amount obtained from a thermal image output by the thermal image sensor 10 in a situation where no sleeping person is present. The reference feature amount is the normalized representative feature amount. Furthermore, the function expressing the relationship between the body movement feature amount and the detection distance has an output value that is larger than the reference feature amount as the detection distance becomes shorter than the reference distance, and an output value that is smaller than the reference feature amount as the detection distance becomes longer than the reference distance. The relational expression (relational expression) stored in the storage unit 22 receives the detected distance as an input and outputs a normalized representative feature amount. Furthermore, the storage unit 22 stores the above-mentioned representative feature amount.

[0025] As shown in FIG. 1 , the control unit 23 includes a thermal image acquisition unit 201 , a distance acquisition unit 202 , a body movement analysis unit 203 , a sleep estimation unit 204 , and a transmission processing unit 205 .

[0026] The thermal image acquisition unit 201 acquires a thermal image of the sleeping person u1 from the thermal image sensor 10. The thermal image acquisition unit 201 acquires a thermal image (moving image) of the sleeping person u1 output from the thermal image sensor 10. That is, the thermal image acquisition unit 201 acquires a thermal image based on the detection result of the thermal image sensor 10.

[0027] The distance acquisition unit 202 acquires the detected distance, which is the distance from the thermal image sensor 10 to the bedding F1 of the sleeping person u1. Specifically, the distance acquisition unit 202 acquires the detected distance from the storage unit 22.

[0028] The body movement analysis unit 203 analyzes the body movement of the sleeper u1 while he / she is asleep based on the thermal image to determine a body movement feature amount. The body movement analysis unit 203 determines the body movement feature amount based on the thermal changes along a time series obtained from the moving image of the thermal image. The thermal image includes a plurality of pixels. The body movement analysis unit 203 determines the body movement feature amount based on the thermal changes along a time series for each of the plurality of pixels. More specifically, the body movement analysis unit 203 determines the body movement feature amount of the sleeper u1 based on the thermal changes along a time series for each predetermined period (e.g., every second).

[0029] Furthermore, the body movement analysis unit 203 corrects the body movement feature amount based on the detected distance acquired by the distance acquisition unit 202. That is, the body movement analysis unit 203 corrects the body movement feature amount of the sleeping person u1, which is calculated based on the thermal change along the time series, based on the detected distance acquired by the distance acquisition unit 202.

[0030] Specifically, the body movement analysis unit 203 corrects the body movement feature amount using the detection distance and a relational expression (function) stored in the storage unit 22. Here, the body movement analysis unit 203 corrects the body movement feature amount using the detection distance and a relational expression (function) stored in the storage unit 22. For example, the body movement analysis unit 203 calculates a normalized feature amount by normalizing the calculated body movement feature amount by dividing it by the representative feature amount described above. The body movement feature amount is corrected using the detection distance and the function stored in the storage unit 22. The body movement analysis unit 203 corrects the body movement feature amount by multiplying the body movement feature amount (normalized feature amount) by a correction value obtained by substituting the detection distance into the function and raising the value obtained to the power of −1. In other words, the body movement analysis unit 203 corrects the body movement feature amount by multiplying the body movement feature amount by the inverse of the value obtained by substituting the temperature into the linear function.

[0031] The sleep estimation unit 204 estimates the sleep state of the sleeper u1 using the body movement feature. That is, the sleep estimation unit 204 estimates the sleep state of the sleeper u1 using the corrected body movement feature (corrected normalized feature). For example, during estimation, the sleep estimation unit 204 uses the corrected body movement feature to calculate a body movement density, which represents the number of body movements occurring per predetermined time. Specifically, the sleep estimation unit 204 determines that a corrected body movement feature that is equal to or greater than a predetermined reference value per predetermined time period indicates that a body movement has occurred, and calculates the body movement density. More specifically, the sleep estimation unit 204 counts the body movement density by counting the corrected body movement feature (corrected normalized feature) that is equal to or greater than the predetermined reference value. The sleep estimation unit 204 estimates the sleep state of the sleeper u1 based on the body movement density per predetermined time period. The sleep estimation unit 204 counts the body movement density, which is the number of body movements per unit time, and estimates the sleep state of the sleeper u1 based on the counting result. Here, the reference value is a value that serves as a reference for determining that a body movement of a sleeping person has occurred.

[0032] The transmission processing unit 205 notifies the information terminal 30 of the estimation result of the sleep estimation unit 204, i.e., the sleep state of the sleeper u1 estimated by the sleep estimation unit 204. Specifically, the transmission processing unit 205 transmits the estimation result of the sleep estimation unit 204 via the communication unit 21.

[0033] (2.2) Information Terminal The information terminal 30 has, for example, a computer system having a processor and a memory. The processor executes a program stored in the memory, causing the computer system to realize the functions of the information terminal 30. The program executed by the processor is pre-recorded in the memory of the computer system in this example, but it may also be provided by being recorded on a recording medium such as a memory card, or via a telecommunications line such as the Internet.

[0034] The information terminal 30 is configured to be able to communicate with the sleep estimation system 1. Specifically, the information terminal 30 is configured to be able to communicate with the signal processing device 20.

[0035] The information terminal 30 acquires the estimation result of the signal processing device 20 from the signal processing device 20. Upon acquiring the estimation result, the information terminal 30 displays the estimation result on a display unit included in the information terminal 30. Here, the display unit is a thin display device such as a liquid crystal display or an organic electroluminescence (EL) display.

[0036] (3) Operation Here, the operation of the sleep estimation system 1 will be described with reference to the flowchart shown in FIG.

[0037] The thermal image acquisition unit 201 acquires a thermal image of the sleeping person u1 from the thermal image sensor 10 (step S1). The thermal image acquisition unit 201 acquires a thermal image (a moving image) based on the detection result of the thermal image sensor 10.

[0038] The distance acquisition unit 202 acquires the detected distance from the storage unit 22 (step S2).

[0039] The body movement analysis unit 203 performs a body movement analysis process (step S3).

[0040] The body movement analysis process will be described in detail below.

[0041] The body movement analysis unit 203 analyzes the body movement of the sleeper u1 during sleep based on the thermal image to acquire body movement feature amounts (step S31). More specifically, the body movement analysis unit 203 acquires the body movement feature amounts of the sleeper u1 based on time-series thermal changes every predetermined period (e.g., every second).

[0042] The body movement analysis unit 203 calculates a correction value (step S32) using the detected distance acquired in step S2 and the relational expression (function) stored in the storage unit 22. More specifically, the body movement analysis unit 203 determines the correction value as a value obtained by substituting the detected distance into the relational expression (function) stored in the storage unit 22 and raising the value obtained to the power of −1.

[0043] The body movement analysis unit 203 performs a correction process (step S33). The body movement analysis unit 203 performs correction on the body movement feature amounts. The body movement analysis unit 203 corrects the body movement feature amounts by multiplying the normalized feature amounts by a correction value. More specifically, the body movement analysis unit 203 corrects the multiple body movement feature amounts by multiplying the normalized feature amounts of each of the multiple body movement feature amounts obtained for each predetermined period by a correction value.

[0044] When the body movement analysis unit 203 finishes the body movement analysis process, the sleep estimation unit 204 performs a sleep estimation process (step S4). The sleep estimation unit 204 estimates the sleep state of the sleeper u1 using the body movement feature amount. That is, the sleep estimation unit 204 estimates the sleep state of the sleeper u1 using the corrected body movement feature amount.

[0045] The transmission processing unit 205 performs a notification process (step S5). The transmission processing unit 205 notifies the information terminal 30 of the estimation result of the sleep estimation unit 204.

[0046] (4) Comparison Fig. 6 shows an example of a graph G1 representing the change in uncorrected body movement feature amount over time when the detection distance is a reference distance d1. Fig. 7 shows an example of a graph G2 representing the change in uncorrected body movement feature amount over time when the detection distance is longer than the reference distance d1. Fig. 8 shows an example of a graph G3 representing the change in uncorrected body movement feature amount over time when the detection distance is shorter than the reference distance d1.

[0047] Comparing Fig. 6 with Fig. 7, the difference (amplitude) between the maximum point and the minimum point in graph G2 of the body movement feature amount shown in Fig. 7 is smaller than the amplitude in graph G1 shown in Fig. 6. Furthermore, comparing Fig. 6 with Fig. 8, the amplitude in graph G3 of the body movement feature amount shown in Fig. 8 is larger than the amplitude in graph G1 shown in Fig. 6. In other words, it can be said that the amplitude of the body movement feature amount depends on the detection distance.

[0048] Therefore, when detecting the body movement of the same person, it is not possible to accurately obtain body movement feature amounts depending on the detection distance. The reason for this is explained below.

[0049] In a sleep estimation system that does not correct body movement features (hereinafter referred to as a sleep estimation system of a comparative example), a body movement feature (uncorrected body movement feature) that is equal to or greater than a predetermined reference value a1 shown in Figures 6 to 8 is determined to be a body movement, and the body movement density is calculated.

[0050] For example, when the detection distance is long, the amplitude of the body movement feature amount becomes small. Therefore, compared to when the detection distance is used as the reference distance, the number of body movement feature amounts that are equal to or greater than the predetermined reference value a1 becomes smaller, and the number of times that it is determined that a body movement has occurred decreases. In other words, there is a possibility that a point where it should be determined that a body movement has occurred will be determined that no body movement has occurred.

[0051] Furthermore, when the detection distance is short, the amplitude of the body movement feature amount becomes large. Therefore, compared to when the detection distance is used as the reference distance, the number of body movement feature amounts that are equal to or greater than the predetermined reference value a1 increases, and the number of times that body movement is determined to have occurred also increases. In other words, there is a possibility that points where no body movement has occurred will be determined to have occurred.

[0052] Therefore, depending on the detection distance, it may not be possible to accurately obtain the body movement feature amount.

[0053] On the other hand, in this embodiment, the sleep estimation system 1 corrects the body movement feature using a function that represents the relationship between the body movement feature and the detection distance. Here, the output value of the function increases relative to the reference value as the detection distance decreases relative to the reference distance, and decreases relative to the reference value as the detection distance increases relative to the reference distance. The correction value is the reciprocal of the output value. Therefore, the sleep estimation system 1 can reduce the amplitude by performing a correction when the amplitude is large, and increase the amplitude by performing a correction when the amplitude is small. As a result, the corrected body movement feature can be made equivalent to the body movement feature obtained when the detection distance is the reference distance. Therefore, the sleep estimation system 1 can accurately estimate the sleep state without depending on the detection distance.

[0054] (5) Advantages As described above, the sleep estimation system 1 of embodiment 1 includes a thermal image acquisition unit 201, a distance acquisition unit 202, a body movement analysis unit 203, and a sleep estimation unit 204. The thermal image acquisition unit 201 acquires a thermal image of the sleeper u1 from the thermal image sensor 10. The distance acquisition unit 202 acquires a detection distance, which is the distance from the thermal image sensor 10 to the bedding F1 of the sleeper u1. The body movement analysis unit 203 analyzes the body movement of the sleeper u1 during sleep based on the thermal image to obtain body movement feature amounts. The sleep estimation unit 204 estimates the sleep state of the sleeper u1 from the body movement feature amounts. The body movement analysis unit 203 corrects the body movement feature amounts based on the detection distance acquired by the distance acquisition unit 202. The sleep estimation unit 204 estimates the sleep state of the sleeper u1 using the corrected body movement feature amounts.

[0055] According to this configuration, the body movement feature amount is corrected according to the detection distance, so that the sleep state can be estimated with high accuracy without depending on the detection distance.

[0056] (6) Modifications Modifications are listed below. The modifications described below can be applied in appropriate combination with the first embodiment.

[0057] (6.1) Modification 1 When the thermal image sensor 10 is provided on the top surface C1, it is preferable that the thermal image sensor 10 be provided in a portion of the top surface C1 that is close to the head of the sleeping person u1, as shown in Fig. 9. Furthermore, it is preferable that the inclination of the thermal image sensor 10 is adjusted so that the entire body of the sleeping person u1 is included in the detection area R10. Specifically, the light receiving surface of the thermal image sensor 10 that receives infrared light from the sleeping person is adjusted to form an angle θ (>0) with respect to the vertical direction so that the entire body of the sleeping person u1 is included in the detection area R10.

[0058] (6.2) Modification 2 The thermal image sensor 10 may be provided on a wall surface W1 as shown in FIG.

[0059] When the thermal image sensor 10 is mounted on the wall W1, the wall W1 is positioned on the opposite side of the sleeper u1's head from the sleeper's feet when the sleeper u1 is in a sleeping position. Furthermore, the inclination of the thermal image sensor 10 is adjusted so that the entire body of the sleeper u1 is included in the detection region R11. Specifically, the light receiving surface of the thermal image sensor 10 that receives infrared light from the sleeper is adjusted to form an angle θ (>0) with respect to the horizontal direction so that the entire body of the sleeper u1 is included in the detection region R10.

[0060] (6.3) Modification 3 The sleep estimation system 1 is configured to transmit the estimation result to the information terminal 30, but is not limited to this configuration.

[0061] If the sleep estimation system 1 includes a display unit, the sleep estimation system 1 may display the estimation result on the display unit of the sleep estimation system 1 .

[0062] (6.4) Modification 4 The sleep estimation system 1 may notify the information terminal 30 of the estimation result via a server using a network such as the Internet.

[0063] (6.5) Modification 5 Although the sleep inference system 1 is configured to include the thermal image sensor 10, the configuration is not limited to this. The thermal image sensor 10 is not an essential component of the sleep inference system 1. In other words, the sleep inference system 1 does not have to include the thermal image sensor 10. In short, it is sufficient for the sleep inference system 1 to include at least the signal processing device 20. In this case, the signal processing device 20 of the sleep inference system 1 acquires a thermal image from a thermal image sensor provided outside the sleep inference system 1.

[0064] (6.6) Modification 6 In the above embodiment, the body movement analysis unit 203 is configured to multiply the normalized feature amount by the correction value, but is not limited to this configuration.

[0065] The body movement analysis unit 203 may multiply the body movement feature amount before normalization by the correction value to calculate the corrected body movement feature amount.

[0066] (Embodiment 2) Here, a sleep estimation system 1A according to embodiment 2 will be described. The sleep estimation system 1A according to embodiment 2 differs from the sleep estimation system 1 according to embodiment 1 in that the sleep estimation system 1A according to embodiment 2 corrects the reference value used when counting the body movement density. The following description will focus on the differences. Note that components similar to those according to embodiment 1 are denoted by the same reference numerals, and their description will be omitted as appropriate.

[0067] (1) Overview As shown in FIG. 11 , the sleep estimation system 1A according to the second embodiment includes a thermal image acquisition unit 201, a distance acquisition unit 202, a body movement analysis unit 203A, and a sleep estimation unit 204A. The thermal image acquisition unit 201 acquires a thermal image of a sleeper u1 (see FIG. 2 ) from the thermal image sensor 10. The distance acquisition unit 202 acquires a detection distance, which is the distance from the thermal image sensor 10 to the bedding F1 (see FIG. 3 ) of the sleeper u1. The body movement analysis unit 203A analyzes the body movement of the sleeper u1 during sleep based on the thermal image to obtain body movement feature amounts. The sleep estimation unit 204A estimates the sleep state of the sleeper u1 from the body movement feature amounts. The sleep estimation unit 204A counts a body movement density, which is the number of body movements of the sleeper u1 per unit time, based on the body movement feature amounts, and estimates the sleep state of the sleeper u1 based on the counting result. When counting the body movement density, the sleep estimation unit 204A corrects a reference value, which is a reference for determining that body movement of the sleeper u1 has occurred, based on the detected distance acquired by the distance acquisition unit 202. The sleep estimation unit 204A counts the body movement density of the sleeper u1 using the corrected reference value.

[0068] According to this configuration, the reference value is corrected in accordance with the detection distance, so that the sleep state can be estimated with high accuracy without depending on the detection distance.

[0069] (2) Configuration (2.1) Sleep Estimation System The sleep estimation system 1A estimates the sleep state of a person (sleeper u1) sleeping in a space SP1 (see FIG. 2 ). The sleep estimation system 1A transmits the estimation result to the information terminal 30.

[0070] As shown in FIG. 11, the sleep estimation system 1A includes a thermal image sensor 10 and a signal processing device 20A.

[0071] The signal processing device 20A analyzes the body movement of the sleeper u1 based on the moving image of the thermal image to determine a body movement feature amount.The signal processing device 20A counts the body movement density, which is the number of body movements of the sleeper u1 per unit time, based on the determined body movement feature amount.When counting the body movement density, the sleep estimation unit 204A corrects a reference value, which is a standard for determining that a body movement of the sleeper u1 has occurred, according to the detection distance.The signal processing device 20A counts the body movement density of the sleeper u1 using the corrected reference value and estimates the sleep state of the sleeper u1 based on the counting result.

[0072] As shown in FIG. 11, the signal processing device 20A includes a communication unit 21, a storage unit 22A, and a control unit 23A.

[0073] The signal processing device 20A includes, for example, a computer system having a processor and a memory. The processor executes a program stored in the memory, causing the computer system to function as the control unit 23A. The program executed by the processor is pre-recorded in the memory of the computer system here, but may also be provided by being recorded on a recording medium such as a memory card, or via a telecommunications line such as the Internet.

[0074] The storage unit 22A is configured by a device selected from a ROM, a RAM, an EEPROM, or the like.

[0075] The memory unit 22A stores a reference value. Furthermore, the memory unit 22A stores information used to correct the reference value. The memory unit 22A stores, as information used to correct the reference value, a detection distance and a relational expression that defines the relationship between the detection distance and a correction coefficient used to correct the reference value. The relational expression is a function that expresses the relationship between the correction coefficient and the detection distance. The function that expresses the relationship between the correction coefficient and the detection distance passes through a reference point, which is a coordinate point formed by the reference distance d1 and the reference correction value "1." Furthermore, the function that expresses the relationship between the correction coefficient and the detection distance has an output value (correction coefficient) that is greater than the reference correction value as the detection distance becomes shorter than the reference distance, and an output value that is smaller than the reference correction value as the detection distance becomes longer than the reference distance.

[0076] As shown in FIG. 11, the control unit 23A includes a thermal image acquisition unit 201, a distance acquisition unit 202, a body movement analysis unit 203A, a sleep estimation unit 204A, and a transmission processing unit 205.

[0077] The body movement analysis unit 203A analyzes the body movement of the sleeper u1 while he / she is asleep based on the thermal image to determine a body movement feature amount. The body movement analysis unit 203A determines the body movement feature amount based on the thermal changes along a time series obtained from the moving image of the thermal image. The thermal image includes a plurality of pixels. The body movement analysis unit 203A determines the body movement feature amount based on the thermal changes along a time series for each of the plurality of pixels. More specifically, the body movement analysis unit 203A determines the body movement feature amount of the sleeper u1 based on the thermal changes along a time series for each predetermined period (e.g., one second). Furthermore, the body movement analysis unit 203A normalizes the determined body movement feature amount by dividing it by the representative feature amount described above to calculate a normalized feature amount.

[0078] As shown in FIG. 11 , the sleep estimation unit 204A includes a correction unit 211, a body movement density acquisition unit 212, and a sleep determination unit 213.

[0079] When counting the body movement density, the correction unit 211 corrects a reference value, which is a reference for determining that body movement of the sleeper u1 has occurred, based on the detected distance acquired by the distance acquisition unit 202. The correction unit 211 corrects the reference value using the detected distance and a relational expression that defines the relationship between a correction coefficient and the detected distance and is stored in the storage unit 22A. More specifically, the correction unit 211 corrects the reference value by multiplying the reference value by a value obtained by substituting the detected distance into a function that represents the relationship between the correction coefficient and the detected distance.

[0080] The body movement density acquisition unit 212 acquires the body movement density. The body movement density acquisition unit 212 counts the body movement density, which is the number of body movements per unit time. Specifically, the body movement density acquisition unit 212 counts the body movement density of the sleeper u1 using the corrected reference value. More specifically, the body movement density acquisition unit 212 counts the body movement density by counting the body movement feature amount (normalized feature amount) that is equal to or greater than the corrected reference value.

[0081] The sleep determining unit 213 determines the sleep state of the sleeper u1 based on the counting result, that is, the sleep determining unit 213 estimates the sleep state of the sleeper u1 based on the counting result.

[0082] (3) Operation Here, the operation of the sleep estimation system 1A will be described with reference to the flowchart shown in FIG.

[0083] The thermal image acquisition unit 201 acquires a thermal image of the sleeping person u1 from the thermal image sensor 10 (step S101). The thermal image acquisition unit 201 acquires a thermal image (a moving image) based on the detection result of the thermal image sensor 10.

[0084] The distance acquisition unit 202 acquires the detected distance from the storage unit 22 (step S102).

[0085] The body movement analysis unit 203A acquires the body movement feature amount of the sleeping person u1 (step S103). The body movement analysis unit 203A acquires the body movement feature amount of the sleeping person u1 based on the thermal change along the time series for each predetermined period (for example, every second).

[0086] The sleep estimation unit 204A performs a sleep estimation process (step S104).

[0087] The sleep estimation process will be described in detail below.

[0088] The correction unit 211 of the sleep estimation unit 204A calculates a correction value (step S111). Specifically, the correction unit 211 uses a function representing the relationship between a correction coefficient and the detected distance to calculate the correction value as a value obtained by substituting the detected distance into the function.

[0089] The correction unit 211 performs the correction process (step S112). Specifically, the correction unit 211 multiplies the reference value stored in the storage unit 22A by the calculated correction value to obtain the corrected reference value.

[0090] The body movement density acquiring section 212 of the sleep estimation section 204A acquires the body movement density (step S113). The body movement density acquiring section 212 counts the body movement density of the sleeper u1 per unit time using the corrected reference value.

[0091] The sleep determination unit 213 of the sleep estimation unit 204A performs a sleep determination process (step S114). The sleep determination unit 213 determines the sleep state of the sleeper u1 based on the counting result.

[0092] When the sleep estimation unit 204A finishes the sleep determination process, the transmission processing unit 205 performs a notification process (step S105). The transmission processing unit 205 notifies the information terminal 30 of the estimation result (determination result) of the sleep estimation unit 204A.

[0093] (4) Comparison Fig. 13 shows an example of a graph G11 that represents changes in body movement feature amounts determined by the body movement analysis unit 203A over time when the detection distance is a reference distance d1. Fig. 14 shows an example of a graph G21 that represents changes in body movement feature amounts determined by the body movement analysis unit 203A over time when the detection distance is longer than the reference distance d1. Fig. 15 shows an example of a graph G31 that represents changes in body movement feature amounts determined by the body movement analysis unit 203A over time when the detection distance is shorter than the reference distance d1.

[0094] Comparing Fig. 13 with Fig. 14, the amplitude of the body movement feature amount in graph G21 shown in Fig. 14 is smaller than the amplitude of the graph G11 shown in Fig. 13. Comparing Fig. 13 with Fig. 15, the amplitude of the body movement feature amount in graph G31 shown in Fig. 15 is larger than the amplitude of the graph G11 shown in Fig. 13. In other words, as described above, it can be said that the amplitude of the body movement feature amount depends on the detection distance.

[0095] In a sleep estimation system that does not correct body movement features (hereinafter referred to as a sleep estimation system of a comparative example), a body movement feature that is equal to or greater than a predetermined reference value a1 shown in Figure 13 is determined to be a body movement, and the body movement density is calculated.

[0096] Therefore, if the reference value a1 is used to calculate the body movement density in Fig. 14, there is a possibility that a point where it should be determined that a body movement has occurred will be determined as not having occurred. Also, if the reference value a1 is used to calculate the body movement density in Fig. 15, there is a possibility that a point where no body movement has occurred will be determined as having occurred.

[0097] Therefore, the sleep estimation system of the comparative example cannot accurately determine the body movement density depending on the detection distance.

[0098] On the other hand, in this embodiment, the sleep estimation system 1A corrects the reference correction value using a function that represents the relationship between the correction coefficient and the detection distance. Here, the function's output value (correction coefficient) increases relative to the reference correction value as the detection distance decreases relative to the reference distance, and decreases relative to the reference correction value as the detection distance increases relative to the reference distance. For example, if the detection distance is longer than the reference distance d1, the correction process changes the reference value from "a1" to "a2," which is smaller than "a1" (see FIG. 14). This allows points where body movement should be determined to have occurred to be more reliably determined to have occurred. Furthermore, if the detection distance is shorter than the reference distance d1, the correction process changes the reference value from "a1" to "a3," which is larger than "a1" (see FIG. 15). This reduces the likelihood of determining that a point where no body movement has occurred has occurred. Therefore, by correcting the reference value, the sleep estimation system 1A can make the count results of the body movement density equivalent to the count results of the body movement density obtained when the detection distance is the reference distance. Therefore, the sleep estimation system 1A can prevent a decrease in accuracy of estimation of a sleep state compared to the sleep estimation system of the comparative example.

[0099] (5) Advantages As described above, the sleep estimation system 1A of embodiment 2 includes a thermal image acquisition unit 201, a distance acquisition unit 202, a body movement analysis unit 203A, and a sleep estimation unit 204A. The thermal image acquisition unit 201 acquires a thermal image of the sleeper u1 from the thermal image sensor 10. The distance acquisition unit 202 acquires a detection distance, which is the distance from the thermal image sensor 10 to the bedding F1 of the sleeper u1. The body movement analysis unit 203A analyzes the body movement of the sleeper u1 during sleep based on the thermal image to obtain body movement feature amounts. The sleep estimation unit 204A estimates the sleep state of the sleeper u1 from the body movement feature amounts. The sleep estimation unit 204A counts the body movement density, which is the number of body movements of the sleeper u1 per unit time, based on the body movement feature amounts, and estimates the sleep state of the sleeper u1 based on the counting result. When counting the body movement density, the sleep estimation unit 204A corrects a reference value, which is a reference for determining that body movement of the sleeper u1 has occurred, based on the detected distance acquired by the distance acquisition unit 202. The sleep estimation unit 204A counts the body movement density of the sleeper u1 using the corrected reference value.

[0100] According to this configuration, the reference value is corrected in accordance with the detection distance, so that the sleep state can be estimated with high accuracy without depending on the detection distance.

[0101] (6) Modifications Modifications are listed below. The modifications described below can be applied in appropriate combination with the second embodiment.

[0102] (6.1) Modification 1 Modifications 1 and 2 described in the first embodiment can be applied to the sleep estimation system 1A of the second embodiment.

[0103] That is, the thermal image sensor 10 is provided on the ceiling surface C1 or the wall surface W1 (see FIGS. 9 and 10).

[0104] When the thermal image sensor 10 of the sleep estimation system 1A is installed on the top surface C1, the thermal image sensor 10 is installed in a part of the top surface C1 that is close to the head of the sleeper u1, and the inclination of the thermal image sensor 10 is adjusted so that the entire body of the sleeper u1 is included in the detection area R10 (see Figure 9).

[0105] When the thermal image sensor 10 of the sleep estimation system 1A is installed on a wall W1, the wall W1 is installed on the opposite side of the sleeper u1's head from the sleeper's feet when the sleeper u1 is in the sleeping position, and the inclination of the thermal image sensor 10 is adjusted so that the entire body of the sleeper u1 is included in the detection area R11 (see Figure 10).

[0106] (6.2) Modification 2 Modifications 3 to 6 described in the first embodiment can be applied to the sleep estimation system 1A of the second embodiment.

[0107] (Other Modifications) The above embodiment is merely one of various embodiments of the present disclosure. Various modifications can be made to the above embodiment depending on the design, etc., as long as the object of the present disclosure can be achieved. Furthermore, functions similar to those of the sleep estimation system 1 may be embodied in a sleep estimation method, a computer program, a non-transitory recording medium on which a program is recorded, or the like. The sleep estimation method of the sleep estimation system 1 according to one aspect includes a thermal image acquisition step, a distance acquisition step, a body movement analysis step, and a sleep estimation step. In the thermal image acquisition step, a thermal image of the sleeper u1 is acquired from the thermal image sensor 10. In the distance acquisition step, a detection distance, which is the distance from the thermal image sensor 10 to the bedding F1 of the sleeper u1, is acquired. In the body movement analysis step, the body movement of the sleeper u1 during sleep is analyzed based on time-series changes in each of multiple pixels in the thermal image to obtain body movement feature values. In the sleep estimation step, the sleep state of the sleeper u1 is estimated from the body movement feature values. In the body movement analysis step, the body movement feature values ​​are corrected based on the detection distance acquired in the distance acquisition step. In the sleep estimation step, the sleep state of the sleeper u1 is estimated using the corrected body movement feature amount. A program according to one aspect is a program for causing a computer system to function as the sleep estimation system 1 or the sleep estimation method of the sleep estimation system 1 described above.

[0108] Furthermore, a sleep estimation method of the sleep estimation system 1A according to one aspect includes a thermal image acquisition step, a distance acquisition step, a body movement analysis step, and a sleep estimation step. In the thermal image acquisition step, a thermal image of the sleeper u1 is acquired from the thermal image sensor 10. In the distance acquisition step, a detected distance, which is the distance from the thermal image sensor 10 to the bedding F1 of the sleeper u1, is acquired. In the body movement analysis step, the body movement of the sleeper u1 during sleep is analyzed based on time-series changes in each of multiple pixels in the thermal image to determine a body movement feature. In the sleep estimation step, the sleep state of the sleeper u1 is estimated from the body movement feature. In the sleep estimation step, a body movement density, which is the number of body movements per unit time, is counted, and the sleep state of the sleeper u1 is estimated based on the counting result. In the sleep estimation step, when counting the body movement density, a reference value serving as a reference for determining that the sleeper u1 has made a body movement is corrected based on the detected distance acquired in the distance acquisition step. In the sleep estimation step, the body movement density of the sleeper u1 is counted using the corrected reference value. A program according to one aspect is a program for causing a computer system to function as the sleep estimation system 1A or the sleep estimation method of the sleep estimation system 1A.

[0109] The sleep estimation system 1, 1A or the sleep estimation method of the sleep estimation system 1, 1A according to the present disclosure includes a computer system. The computer system has a processor and memory as hardware. The processor executes a program stored in the memory of the computer system to realize the function of the sleep estimation system 1, 1A or the sleep estimation method of the sleep estimation system 1, 1A according to the present disclosure. The program may be pre-stored in the memory of the computer system or may be provided via a telecommunications line. The program may also be provided by being recorded on a non-transitory recording medium readable by the computer system, such as a memory card, an optical disk, or a hard disk drive. The processor of the computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large-scale integrated circuit (LSI). The integrated circuits, such as ICs and LSIs, are referred to by different names depending on the degree of integration, and include integrated circuits called system LSIs, very large-scale integration (VLSIs), or ultra-large-scale integration (ULSIs). Furthermore, a field-programmable gate array (FPGA) that is programmed after the LSI is manufactured, or a logic device that allows the reconfiguration of the connections within the LSI or the reconfiguration of the circuit partitions within the LSI, can also be employed as a processor. Multiple electronic circuits may be integrated into a single chip or distributed across multiple chips. Multiple chips may be integrated into a single device or distributed across multiple devices.

[0110] Furthermore, it is not essential for the sleep estimation systems 1 and 1A that multiple functions are integrated into a single housing, and the components of the sleep estimation systems 1 and 1A may be distributed across multiple housings. Furthermore, at least some of the functions of the sleep estimation systems 1 and 1A may be realized by the cloud (cloud computing) or the like.

[0111] (Summary) As described above, the sleep estimation system (1) of the first aspect includes a thermal image acquisition unit (201), a distance acquisition unit (202), a body movement analysis unit (203), and a sleep estimation unit (204). The thermal image acquisition unit (201) acquires a thermal image of a sleeper (u1) from a thermal image sensor (10). The distance acquisition unit (202) acquires a detection distance, which is the distance from the thermal image sensor (10) to the bedding (F1) of the sleeper (u1). The body movement analysis unit (203) analyzes the body movement of the sleeper (u1) during sleep based on the thermal image to obtain a body movement feature amount. The sleep estimation unit (204) estimates the sleep state of the sleeper (u1) from the body movement feature amount. The body movement analysis unit (203) corrects the body movement feature amount based on the detection distance acquired by the distance acquisition unit (202). A sleep estimation unit (204) estimates the sleep state of the sleeper (u1) using the corrected body movement feature amount.

[0112] According to this aspect, the body movement feature amount is corrected according to the detection distance, so that the sleep state can be estimated with high accuracy without depending on the detection distance.

[0113] In the sleep estimation system (1) of the second aspect, in the first aspect, the body movement analysis unit (203) corrects the body movement feature amount using the detection distance and a relational expression that defines the relationship between the body movement feature amount and the detection distance.

[0114] According to this aspect, the body movement feature amount is corrected using the detection distance and a relational expression that defines the relationship between the body movement feature amount and the detection distance, so that the body movement feature amount can be calculated with high accuracy, and as a result, the sleep state can be estimated with high accuracy without depending on the detection distance.

[0115] In the sleep estimation system (1) of the third aspect, in the second aspect, the relational expression is a function expressing the relationship between the body movement feature amount and the detection distance, and the body movement analysis unit (203) corrects the body movement feature amount by multiplying the body movement feature amount by a correction value obtained by substituting the detection distance into the function and raising the value obtained to the power of −1.

[0116] According to this embodiment, the body movement feature amount can be calculated with high accuracy, and as a result, the sleep state can be estimated with high accuracy without depending on the detection distance.

[0117] A sleep estimation system (1A) according to a fourth aspect includes a thermal image acquisition unit (201), a distance acquisition unit (202), a body movement analysis unit (203A), and a sleep estimation unit (204A). The thermal image acquisition unit (201) acquires a thermal image of a sleeper (u1) from a thermal image sensor (10). The distance acquisition unit (202) acquires a detection distance, which is the distance from the thermal image sensor (10) to the bedding (F1) of the sleeper (u1). The body movement analysis unit (203A) analyzes the body movement of the sleeper (u1) during sleep based on the thermal image to determine body movement feature amounts. The sleep estimation unit (204A) estimates the sleep state of the sleeper (u1) from the body movement feature amounts. The sleep estimation unit (204A) counts the body movement density, which is the number of body movements of the sleeper (u1) per unit time, based on the body movement feature amount, and estimates the sleep state of the sleeper (u1) based on the counting result. When counting the body movement density, the sleep estimation unit (204A) corrects a reference value, which is a reference for determining that a body movement of the sleeper (u1) has occurred, based on the detected distance acquired by the distance acquisition unit (202). The sleep estimation unit (204A) counts the body movement density of the sleeper (u1) using the corrected reference value.

[0118] According to this embodiment, the reference value is corrected in accordance with the detection distance, so that the sleep state can be estimated with high accuracy without depending on the detection distance.

[0119] In the sleep estimation system (1A) of the fifth aspect, in the fourth aspect, the sleep estimation unit (204A) corrects the reference value using a relational equation that defines the relationship between the detection distance and a correction coefficient used to correct the reference value, and the detection distance.

[0120] According to this aspect, the body movement feature is corrected using the detection distance and a relational expression that defines the relationship between the correction coefficient and the detection distance, so that the body movement feature can be calculated with high accuracy, and as a result, the sleep state can be estimated with high accuracy without depending on the detection distance.

[0121] In the sleep estimation system (1A) of the sixth aspect, in the fifth aspect, the relational expression is a function expressing the relationship between a correction coefficient and a detection distance, and the sleep estimation unit (204A) corrects the reference value by multiplying the reference value by a value obtained by substituting the detection distance into the function as a correction value.

[0122] According to this embodiment, the body movement feature amount can be calculated with high accuracy, and as a result, the sleep state can be estimated with high accuracy without depending on the detection distance.

[0123] The sleep estimation system (1, 1A) of a seventh aspect is any one of the first to sixth aspects, further including a thermal image sensor (10). The thermal image sensor (10) is provided on a ceiling surface (C1) or a wall surface (W1) of a space (SP1) where a sleeper (u1) sleeps.

[0124] According to this aspect, a thermal image can be acquired from the thermal image sensor (10).

[0125] In the sleep estimation system (1, 1A) of the eighth aspect, when the thermal image sensor (10) is provided on the top surface (C1) in the seventh aspect, the thermal image sensor (10) is provided in a part of the top surface (C1) close to the head of the sleeping person (u1), and the inclination is adjusted so that the entire body of the sleeping person (u1) is included in the detection area (R10).

[0126] According to this embodiment, the entire body of the sleeping person (u1) can be reliably included in the thermal image, and as a result, the body movement feature amount can be calculated with high accuracy.

[0127] In the sleep estimation system (1, 1A) of the ninth aspect, when the thermal image sensor (10) is provided on the wall surface (W1) in the seventh aspect, the thermal image sensor (10) is provided on the wall surface (W1) located on the opposite side of the sleeper (u1)'s head from the sleeper's feet when the sleeper (u1) is in the sleeping position. The inclination of the thermal image sensor (10) is adjusted so that the entire body of the sleeper (u1) is included in the detection area (R11).

[0128] According to this embodiment, the entire body of the sleeping person (u1) can be reliably included in the thermal image, and as a result, the body movement feature amount can be calculated with high accuracy.

[0129] A tenth aspect of the sleep estimation method includes a thermal image acquisition step, a distance acquisition step, a body movement analysis step, and a sleep estimation step. In the thermal image acquisition step, a thermal image of a sleeper (u1) is acquired from a thermal image sensor (10). In the distance acquisition step, a detected distance, which is the distance from the thermal image sensor (10) to the bedding (F1) of the sleeper (u1), is acquired. In the body movement analysis step, body movement of the sleeper (u1) during sleep is analyzed based on time-series changes in each of multiple pixels of the thermal image to determine body movement feature amounts. In the sleep estimation step, the sleep state of the sleeper (u1) is estimated from the body movement feature amounts. In the body movement analysis step, the body movement feature amounts are corrected based on the detected distance acquired in the distance acquisition step. In the sleep estimation step, the sleep state of the sleeper (u1) is estimated using the corrected body movement feature amounts.

[0130] According to this embodiment, the sleep state can be estimated with high accuracy without depending on the detection distance.

[0131] The sleep estimation method of the eleventh aspect includes a thermal image acquisition step, a distance acquisition step, a body movement analysis step, and a sleep estimation step. In the thermal image acquisition step, a thermal image of a sleeper (u1) is acquired from a thermal image sensor (10). In the distance acquisition step, a detected distance, which is the distance from the thermal image sensor (10) to the bedding (F1) of the sleeper (u1), is acquired. In the body movement analysis step, the body movement of the sleeper (u1) during sleep is analyzed based on time-series changes in each of multiple pixels in the thermal image to determine a body movement feature. In the sleep estimation step, the sleep state of the sleeper (u1) is estimated from the body movement feature. In the sleep estimation step, a body movement density, which is the number of body movements per unit time, is counted, and the sleep state of the sleeper (u1) is estimated based on the counting result. In the sleep estimation step, when counting the body movement density, a reference value serving as a reference for determining that a body movement of the sleeper (u1) has occurred is corrected based on the detected distance acquired in the distance acquisition step. In the sleep estimation step, the corrected reference value is used to count the body movement density of the sleeper (u1).

[0132] According to this embodiment, the sleep state can be estimated with high accuracy without depending on the detection distance.

[0133] A program according to a twelfth aspect is a program for causing a computer system to execute the sleep estimation method according to the tenth or eleventh aspect.

[0134] According to this embodiment, the sleep state can be estimated with high accuracy without depending on the detection distance.

[0135] 1, 1A Sleep estimation system 10 Thermal image sensor 201 Thermal image acquisition unit 202 Distance acquisition unit 203, 203A Body movement analysis unit 204, 204A Sleep estimation unit C1 Top surface F1 Bedding R10 Detection area R11 Detection area SP1 Space u1 Sleeper W1 Wall surface

Claims

1. A sleep estimation system comprising: a thermal image acquisition unit that acquires a thermal image of a sleeping person from a thermal image sensor; a distance acquisition unit that acquires a detected distance, which is the distance from the thermal image sensor to the sleeping person's bedding; a body movement analysis unit that analyzes the body movements of the sleeping person during sleep based on the thermal image to determine body movement features; and a sleep estimation unit that estimates the sleeping state of the sleeping person from the body movement features, wherein the body movement analysis unit corrects the body movement features based on the detected distance acquired by the distance acquisition unit, and the sleep estimation unit estimates the sleeping state of the sleeping person using the corrected body movement features.

2. The sleep estimation system according to claim 1, wherein the body movement analysis unit corrects the body movement feature amount using the detection distance and a relational expression that defines the relationship between the body movement feature amount and the detection distance.

3. The sleep estimation system of claim 2, wherein the relational expression is a function expressing the relationship between the body movement feature amount and the detection distance, and the body movement analysis unit corrects the body movement feature amount by multiplying the body movement feature amount by a correction value obtained by substituting the detection distance into the function and raising the value to the power of -1.

4. A sleep estimation system comprising: a thermal image acquisition unit that acquires a thermal image of a sleeper from a thermal image sensor; a distance acquisition unit that acquires a detected distance, which is the distance from the thermal image sensor to the sleeper's bedding; a body movement analysis unit that analyzes the body movements of the sleeper during sleep based on the thermal image to determine body movement features; and a sleep estimation unit that estimates the sleep state of the sleeper from the body movement features, wherein the sleep estimation unit counts a body movement density, which is the number of body movements of the sleeper per unit time, based on the body movement features, and estimates the sleep state of the sleeper based on the counting result, and when counting the body movement density, the sleep estimation unit corrects a reference value that serves as a standard for determining that body movement of the sleeper has occurred, based on the detected distance acquired by the distance acquisition unit, and the sleep estimation unit counts the body movement density of the sleeper using the corrected reference value.

5. The sleep estimation system according to claim 4, wherein the sleep estimation unit corrects the reference value using a relational expression that defines the relationship between the detection distance and a correction coefficient used to correct the reference value, and the detection distance.

6. The sleep estimation system of claim 5, wherein the relational expression is a function expressing the relationship between the correction coefficient and the detection distance, and the sleep estimation unit corrects the reference value by multiplying the reference value by a value obtained by substituting the detection distance into the function as a correction value.

7. The sleep estimation system according to any one of claims 1 to 6, further comprising the thermal image sensor, wherein the thermal image sensor is provided on a ceiling or wall of the space in which the sleeper sleeps.

8. A sleep estimation system as described in claim 7, wherein when the thermal image sensor is installed on the top surface, the thermal image sensor is installed in a part of the top surface close to the sleeper's head, and is tilted so that the sleeper's entire body is included in the detection area.

9. A sleep estimation system as described in claim 7, wherein when the thermal image sensor is installed on the wall surface, the thermal image sensor is installed on the wall surface located on the opposite side of the sleeper's head from the sleeper's feet when the sleeper is in the sleeping position, and is tilted and adjusted so that the sleeper's entire body is included in the detection area.

10. A sleep estimation method comprising: a thermal image acquisition step of acquiring a thermal image of a sleeping person from a thermal image sensor; a distance acquisition step of acquiring a detected distance, which is the distance from the thermal image sensor to the bedding of the sleeping person; a body movement analysis step of analyzing the body movement of the sleeping person during sleep based on time-series changes in each of a plurality of pixels of the thermal image to obtain body movement features; and a sleep estimation step of estimating the sleeping state of the sleeping person from the body movement features, wherein in the body movement analysis step, the body movement features are corrected based on the detected distance acquired in the distance acquisition step, and in the sleep estimation step, the corrected body movement features are used to estimate the sleeping state of the sleeping person.

11. A sleep estimation method comprising: a thermal image acquisition step of acquiring a thermal image of a sleeping person from a thermal image sensor; a distance acquisition step of acquiring a detected distance, which is the distance from the thermal image sensor to the bedding of the sleeping person; a body movement analysis step of analyzing the body movement of the sleeping person during sleep based on time-series changes in each of a plurality of pixels of the thermal image to obtain body movement features; and a sleep estimation step of estimating the sleep state of the sleeping person from the body movement features, wherein the sleep estimation step counts a body movement density, which is the number of body movements per unit time, and estimates the sleep state of the sleeping person based on the counting result, and when counting the body movement density, the sleep estimation step corrects a reference value, which is a standard for determining that body movement of the sleeping person has occurred, based on the detected distance acquired in the distance acquisition step, and the sleep estimation step counts the body movement density of the sleeping person using the corrected reference value.

12. A program for causing a computer system to execute the sleep estimation method according to claim 10 or 11.

Images