Pose estimation system, pose estimation method, and program

Abstract

This invention provides a posture estimation system that can improve the accuracy of estimating the posture of a living organism by using atmospheric pressure. [Solution] A posture estimation system is provided, comprising a pressure measuring unit that measures atmospheric pressure using at least one wearable sensor attached to a living body, and an estimation unit that estimates the posture of the living body using the measured atmospheric pressure. The postures are standing, sitting, and lying down. The posture estimation system estimates the posture of the living body by storing the pressure difference for each posture in advance.

Description

[Technical Field]

[0001] The present disclosure relates to a posture estimation system, a posture estimation method, and a program. [Background Art]

[0002] Patent Document 1 describes an operating state monitoring system capable of publicly managing measurement results in accordance with the mounting direction of a sensor. [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Unexamined Patent Publication No. 2022-34450 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] However, Patent Document 1 does not disclose that the sensor measures atmospheric pressure. Therefore, an object of the present disclosure is to provide a posture estimation system with improved accuracy for estimating the posture of a living body by measuring atmospheric pressure. [Means for Solving the Problem]

[0005] The posture estimation system of the present disclosure includes: an atmospheric pressure measurement unit that measures the atmospheric pressure by using at least one wearable sensor attached to a living body that measures three-axis acceleration and atmospheric pressure; and an estimation unit that estimates the posture of the living body using the measured atmospheric pressure.

[0006] The above configuration provides a posture estimation system capable of improving the accuracy of estimating the posture of a living body using atmospheric pressure.

[0007] The posture estimation system of the present disclosure is characterized in that: the posture includes a human standing position, sitting position, and lying position.

[0008] The above configuration is an example of an estimation approach.

[0009] The attitude estimation system disclosed herein is The method is characterized by estimating the posture of the living organism by pre-memorizing the pressure difference for each posture.

[0010] The above configuration is an example of a method for estimating the posture of a living organism.

[0011] The attitude estimation system disclosed herein is The method is characterized by classifying the measured atmospheric pressure into patterns and estimating the posture of the living organism.

[0012] The above configuration is an example of a method for estimating the posture of a living organism.

[0013] The pattern classification described herein is characterized by being performed using machine learning.

[0014] The above configuration demonstrates that the posture estimation system of this disclosure uses AI (Artificial Intelligence).

[0015] The pattern classification described herein is characterized by being performed by an algorithm.

[0016] The above configuration demonstrates that the attitude estimation system of this disclosure can also be performed using algorithmic analysis.

[0017] The attitude estimation system disclosed herein is There are multiple wearable sensors, The system is characterized by estimating the posture of the living organism by combining the 3-axis acceleration, 3-axis angular velocity, and the angle between sensors of each wearable sensor.

[0018] The above configuration can improve the accuracy of posture estimation.

[0019] The attitude estimation system disclosed herein is The posture of the living body is estimated based on the magnitude relationship of the measured air pressure difference, which is characterized by the above.

[0020] The above configuration is an example of a method for estimating the posture of a living body.

[0021] The posture estimation method of the present disclosure is: measuring the atmospheric pressure using at least one wearable sensor attached to the living body for measuring atmospheric pressure, a posture estimation method that estimates the posture of the living body using the measured atmospheric pressure.

[0022] With the above configuration, a posture estimation method capable of improving the accuracy of estimating the posture of a living body using atmospheric pressure is provided.

[0023] The program of the present disclosure is: measuring the atmospheric pressure using at least one wearable sensor attached to the living body for measuring atmospheric pressure, a program that causes an information processing apparatus to execute estimating the posture of the living body using the measured atmospheric pressure.

[0024] With the above configuration, a program capable of improving the accuracy of estimating the posture of a living body using atmospheric pressure is provided. Effects of the Invention

[0025] According to the present disclosure, a posture estimation system capable of improving the accuracy of estimating the posture of a living body using atmospheric pressure is provided. Brief Description of Drawings

[0026] [Figure 1] It is a block diagram showing the configuration of the posture estimation system according to an embodiment. [Figure 2] It is a flowchart of the posture estimation method according to an embodiment. [Figure 3] It is a diagram showing the measurement results obtained using a sensor of the posture estimation system according to an embodiment. [Figure 4] This figure shows an example of sensor mounting for the attitude estimation system according to the embodiment. [Figure 5] This figure shows a first example of how a sensor in the posture estimation system according to the embodiment measures the pressure difference. [Figure 6] This figure shows a second example of how the pressure difference is measured by a sensor of the posture estimation system according to the embodiment. [Figure 7] This figure shows a third example of how to measure the pressure difference using a sensor of the posture estimation system according to the embodiment. [Figure 8] This figure shows a fourth example of how to measure the pressure difference using a sensor of the posture estimation system according to the embodiment. [Figure 9] This figure shows an example of the results obtained by measuring the pressure difference using the attitude estimation system according to the embodiment. [Figure 10] This figure shows an example of a presumed posture according to the embodiment. [Figure 11] This is a diagram showing the configuration of the information processing device according to the embodiment. [Modes for carrying out the invention]

[0027] Embodiment Embodiments of the present invention will be described below with reference to the drawings. However, the invention claimed is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential for solving the problem. For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary.

[0028] (Description of the posture estimation system according to the embodiment) Figure 1 is a block diagram showing the configuration of the attitude estimation system according to the embodiment. Figure 3 is a diagram showing the results measured using the sensor of the attitude estimation system according to the embodiment. Figure 4 is a diagram showing an example of mounting the sensor of the attitude estimation system according to the embodiment. Figure 5 is a diagram showing a first mounting example in which the pressure difference is measured using the sensor of the attitude estimation system according to the embodiment. Figure 6 is a diagram showing a second mounting example in which the pressure difference is measured using the sensor of the attitude estimation system according to the embodiment. Figure 7 is a diagram showing a third mounting example in which the pressure difference is measured using the sensor of the attitude estimation system according to the embodiment. Figure 8 is a diagram showing a fourth mounting example in which the pressure difference is measured using the sensor of the attitude estimation system according to the embodiment. Figure 9 is a diagram showing an example of the results of measuring the pressure difference with the attitude estimation system according to the embodiment. Figure 10 shows an example of an estimated posture according to the embodiment. The posture estimation system according to the embodiment will be described with reference to Figures 1 and 3 through 10.

[0029] As shown in Figure 1, the attitude estimation system 100 according to this embodiment includes a pressure measurement unit 101 and an estimation unit 102.

[0030] The pressure measuring unit 101 measures atmospheric pressure using at least one wearable sensor attached to a living body that measures 3-axis acceleration, 3-axis angular velocity, and atmospheric pressure. The 3 axes refer to the X, Y, and Z axes of a three-dimensional coordinate system. The wearable sensor is attached to a living body, especially a person, by wrapping a band around the upper arm, forearm, upper leg, lower leg, back, abdomen, head, etc. If multiple wearable sensors are attached, their relative angles can also be measured.

[0031] As shown in Figure 3, wearable sensors can observe a person's gait. Because they can measure with considerable detail, they can be used in the rehabilitation of people with disabilities. If exercise intensity can be monitored 24 hours a day during rehabilitation, it can further motivate patients to engage in rehabilitation.

[0032] As shown in Figure 4, it is not necessary to attach wearable sensors to all selected locations. You can choose to attach multiple wearable sensors. For example, in the case of rehabilitation of the right leg, it is possible to attach sensors to the upper right thigh and the lower right leg for detailed measurements.

[0033] As shown in Figure 5, the pressure difference may be the pressure difference between multiple wearable sensors. In this case, the multiple wearable sensors can be attached at different heights to create a pressure difference, for example, between the lower leg and upper arm, the back and lower leg, the upper leg and upper arm, or the upper leg and back.

[0034] As shown in Figure 6, the pressure difference may be the difference in pressure between the mobile terminal 601, particularly a smartphone, and the wearable sensor. In this case, only one wearable sensor is needed. Alternatively, an external terminal that determines the reference position may be used instead of the mobile terminal 601.

[0035] The estimation unit 102 uses the measured atmospheric pressure to estimate the posture of the living organism.

[0036] As shown in Figure 10, pressure differences occur at the ankles and back when a person is standing, sitting, or lying down. Figure 11 shows the measured pressure differences. Areas with large pressure differences can be defined as standing, areas in between as sitting, and areas with small pressure differences as lying down. When walking, the standing position can be determined. Furthermore, when walking, this can be determined using acceleration sensors and angular velocity sensors.

[0037] In this way, by pre-memorizing the pressure differences for each posture, it is possible to estimate the posture of a living organism. In particular, by memorizing at least two pressure differences, the remaining posture can also be determined.

[0038] In addition, the system can perform pattern classification and posture determination based on various pieces of information. Pattern classification can be done by training the system with supervised data to learn the correct answers and then performing the determination. Alternatively, pattern classification can also be performed using machine learning through unsupervised learning.

[0039] Alternatively, pattern classification is performed using an algorithm. The average value over a certain period is divided into three parts, and posture is judged. In the case of continuity, the moment when the atmospheric pressure changes significantly is judged as a change in posture and is not included in the calculation of the average value. In the case of gradual changes, the average value is calculated when the average value crosses a certain threshold. If the change is gradual and it is unclear whether it is standing or sitting, the determination is made using a moving average. In that case, the posture is judged over a shorter period and more precisely.

[0040] Additionally, the initial pressure difference can be calibrated as a specific posture. Since the posture is divided into three stages, a higher pressure difference indicates an upright position, and a lower pressure difference indicates a supine position. In this way, posture can be estimated based on the relative magnitudes of the measured pressure differences.

[0041] As shown in Figures 7 and 8, wearable sensors other than those measuring pressure differences may be attached. As shown in Figure 9, the pressure difference changes significantly when posture changes. Therefore, there is a possibility of misdetection of posture. To address this, the accuracy of posture estimation can be improved by estimating the posture of the living organism by combining the 3-axis acceleration, 3-axis angular velocity, and the angle between sensors of each of the multiple wearable sensors.

[0042] With the above configuration, a posture estimation system can be provided that can improve the accuracy of estimating the posture of a living organism using atmospheric pressure.

[0043] (Description of the posture estimation method according to the embodiment) Figure 2 is a flowchart of the posture estimation method according to the embodiment. Figure 10 is a block diagram showing the configuration of the information processing device according to the embodiment. The posture estimation method according to the embodiment will be explained with reference to Figures 2 and 10.

[0044] First, the atmospheric pressure is measured (step S201). The pressure difference is measured using at least one wearable sensor attached to the body that measures 3-axis acceleration, 3-axis angular velocity, and atmospheric pressure. Multiple wearable sensors are used to measure the pressure difference. Alternatively, the atmospheric pressure is measured using a wearable sensor and a mobile terminal 601. Next, the posture is estimated (step 202). The posture of the body is estimated using the measured pressure difference.

[0045] The above configuration provides a posture estimation method that can improve the accuracy of estimating the posture of a living organism using atmospheric pressure.

[0046] The above method can be implemented by having an information processing device perform the processing. As shown in Figure 11, the information processing device 1100 includes a processor 1101 that executes a program and performs processing, and a memory 1102 that stores the program. The information processing device 1100 may be a single device or multiple devices. The information processing device 1100 may also be a cloud server that distributes and processes some or all of its functions.

[0047] Some or all of the processing in the information processing device 1100 can be implemented as a computer program. Such a program can be stored using various types of non-temporary computer-readable media and supplied to a computer. Non-temporary computer-readable media include various types of tangible recording media. Examples of non-temporary computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). Alternatively, the program may be supplied to the computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. Temporary computer-readable media can be supplied to the computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0048] It should be noted that the present invention is not limited to the embodiments described above, and can be modified as appropriate without departing from the spirit of the invention. [Explanation of Symbols]

[0049] 100 Attitude estimation system, 101 Barometric pressure measurement unit, 102 Estimation unit, 601 Mobile terminal, 1100 Information processing unit, 1101 Processor, 1102 Memory

Claims

1. A pressure measuring unit that measures the pressure using at least one wearable sensor attached to a living body to measure the pressure, A posture estimation system comprising: an estimation unit that estimates the posture of the living organism using the measured atmospheric pressure.

2. The posture estimation system according to claim 1, wherein the aforementioned posture is a person standing, sitting, or lying down.

3. The posture estimation system according to claim 1, which estimates the posture of the living organism by storing the pressure difference for each posture in advance.

4. The posture estimation system according to claim 1, which classifies the measured atmospheric pressure into patterns and estimates the posture of the living organism.

5. The posture estimation system according to claim 4, wherein the pattern classification is performed by machine learning.

6. The posture estimation system according to claim 4, wherein the pattern classification is performed by an algorithm.

7. There are multiple wearable sensors, The posture estimation system according to claim 1, which estimates the posture of the living organism by combining the three-axis acceleration, three-axis angular velocity, and angle between sensors of each wearable sensor.

8. The posture estimation system according to claim 1, which estimates the posture of the living organism based on the relative magnitudes of the measured pressure differences.

9. The atmospheric pressure is measured using at least one wearable sensor attached to a living body that measures atmospheric pressure, A posture estimation method for estimating the posture of a living organism using the measured atmospheric pressure.

10. The atmospheric pressure is measured using at least one wearable sensor attached to a living body that measures atmospheric pressure, A program that causes an information processing device to estimate the posture of the living organism using the measured atmospheric pressure.

Images