Operation recognition system, operation recognition method, and program

The action recognition system uses a three-dimensional sensor to detect and notify specific movements with privacy protection, addressing the lack of privacy consideration in existing systems by using invisible light and reducing personally identifiable information.

JP2024158718AInactive Publication Date: 2024-11-08TAKAHATA PRECISION JAPAN
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2023074136
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-28
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 2024158718000001_ABST
    Figure 2024158718000001_ABST
Patent Text Reader

Abstract

To provide an operation recognition system that detects a state of a person and a specific operation while taking privacy protection into consideration.SOLUTION: An operation recognition system which recognizes an operation of a target, includes: storage means that stores specific operation data indicative of a specific operation including a series of predefined postures and operations of at least one body site of the target; detection means that continuously acquires point cloud data indicating a plurality of positions on a surface of the target and generating a three-dimensional coordinate information value of the target from the point cloud data; display means that continuously displays the operation of the target as the point cloud data having the three-dimensional coordinate information value generated by the detection means; reception means that receives designation of the specific operation from among a plurality of operations of the target; and notification means that notifies, when the operation of the target coincides with the designated specific operation, occurrence of the specific operation.SELECTED DRAWING: Figure 6
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an action recognition system, an action recognition method, and a program. [Background technology]

[0002] A known action recognition system includes an input receiving unit that plays and displays a first video of a person performing a specific action, and receives, while the first video is being played and displayed, an instruction input indicating a position related to the specific action on a frame of the first video, and a determination unit that calculates a similarity between the first video and the second video based on a comparison result of features between a second feature point group including one or more feature points included in the second video and a first feature point group including two or more feature points included in the first video, and determines whether the second video includes the specific action based on the calculated similarity, wherein, when calculating the similarity, the determination unit assigns a greater weight to the comparison result of features of the first feature point group that are closer to a position indicated by the instruction input. (Patent Document 1)

[0003] A nurse call system is also known that has a nurse call handset that is installed in a bed and allows a patient to call a nurse, and a nurse call parent unit that is installed in a nurse's station and responds to calls made by the nurse call handset, the nurse call system comprising a camera that images the patient in bed from above the bed, and a status determination unit that analyzes the image captured by the camera to detect changes in the patient's condition and output a first signal if a change in condition occurs, the nurse call parent unit has an alarm unit that receives the first signal and performs a first alarm operation, the status determination unit analyzes the image and if it detects a specified behavior of a person including at least one of the patient and the nurse, outputs a second signal different from the first signal, and the camera or the nurse call parent unit receives the second signal and performs a second alarm operation (Patent Document 2). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2022-77870 [Patent Document 2] JP 2023-51150 A Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention detects a person's state and specific motion behavior while taking into consideration privacy protection. [Means for solving the problem]

[0006] In order to solve the above problem, the action recognition system according to claim 1 comprises: A motion recognition system for performing motion recognition of a target, A storage means for storing specific motion data indicative of specific motions including a predefined series of postures and motions of at least one body part of the subject; a detection means for continuously acquiring point cloud data indicating a plurality of positions on a surface of the object, and generating three-dimensional coordinate information values ​​of the object from the point cloud data; a display means for continuously displaying the target's motion as point cloud data having the three-dimensional coordinate information values ​​generated by the detection means; A reception means for receiving a designation of the specific motion among the plurality of target motions; and a notification means for notifying the occurrence of the specific motion when the target motion coincides with the specified specific motion. It is characterized by:

[0007] The invention described in claim 2 is the action recognition system described in claim 1, the detection means projects invisible light from an array light source consisting of a plurality of light-emitting elements through a diffractive optical element, receives reflected light from the surface of the object, and acquires the point cloud data; It is characterized by:

[0008] The invention described in claim 3 is the action recognition system described in claim 1, The specific movement is a physical movement including an angle and a width of the movement of the body part of the target. It is characterized by:

[0009] The invention described in claim 4 is the action recognition system described in claim 1, When notifying that the specific action has occurred, the point cloud data acquired by the detection means is recorded. It is characterized by:

[0010] In order to solve the above problem, the action recognition method according to claim 5 comprises: A method for recognizing a target action, comprising: storing specific motion data indicative of specific motions including a predefined series of postures and motions of at least one body part of the subject; a detection step of continuously acquiring point cloud data indicating a plurality of positions on a surface of the object, and generating three-dimensional coordinate information values ​​of the object from the point cloud data; a display step of continuously displaying the target motion as point cloud data having the three-dimensional coordinate information values ​​generated in the detection step; a receiving step of receiving a designation of the specific motion among the plurality of target motions; and a notification step of notifying the occurrence of the specific action when the target action coincides with the specified specific action. It is characterized by:

[0011] In order to solve the above problem, the program according to claim 6 comprises: On the computer, storing specific motion data indicative of specific motions including a predefined series of postures and motions of at least one body part of the subject; a detection step of continuously acquiring point cloud data indicating a plurality of positions on a surface of the object, and generating three-dimensional coordinate information values ​​of the object from the point cloud data; a display step of continuously displaying the target motion as a moving image in the form of point cloud data having the three-dimensional coordinate information values ​​generated in the detection step; a receiving step of receiving a designation of the specific motion among the plurality of target motions; and a notification step of notifying the occurrence of the specific motion when the target motion coincides with the specified specific motion. It is characterized by: Effect of the Invention

[0012] According to the invention described in claim 1, a person's state and specific motion behavior can be detected while taking into consideration the protection of privacy.

[0013] According to the invention described in claim 2, the target's movements can be acquired as point cloud data using invisible and safe light.

[0014] According to the invention as recited in claim 3, a specific action of a target can be visualized.

[0015] According to the invention as recited in claim 4, the occurrence of a specific action can be recorded.

[0016] According to the invention as set forth in claims 5 and 6, a person's state and specific motion behavior can be detected while taking into consideration the protection of privacy. [Brief description of the drawings]

[0017] [Figure 1] 1 is a block diagram showing a functional configuration of an action recognition system according to an embodiment of the present invention. [Diagram 2] 11A to 11C are diagrams illustrating examples of motion patterns of specific motions in the present embodiment. [Diagram 3] FIG. 2 is a block diagram showing the functional configuration of a three-dimensional sensor. [Figure 4] FIG. 2A is a schematic diagram showing dot pattern irradiation of a three-dimensional sensor, and FIG. 2B is a diagram showing an example of the measurement range of the three-dimensional sensor. [Diagram 5]1 is a schematic diagram showing an example of the arrangement of a three-dimensional sensor provided in the action recognition system. [Figure 6] 11 is a flowchart showing the flow of a detection process for detecting a three-dimensional movement of a target in the movement recognition system. FIG. [Figure 7] FIG. 13 is a diagram conceptually illustrating a process of extracting point cloud data of only a patient from the acquired point cloud data. [Figure 8] FIG. 11 is a conceptual diagram illustrating an example of a process for removing noise from point cloud data. [Figure 9] FIG. 13 is a diagram for explaining an example of calculating three-dimensional coordinate information values ​​of a patient by trigonometry. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Next, specific examples of the embodiments of the present invention will be described with reference to the drawings, but the present invention is not limited to the following embodiments. In the following explanation using the drawings, it should be noted that the drawings are schematic and the ratios of the dimensions, etc. may differ from the actual ones, and in order to facilitate understanding, illustrations other than those of components necessary for the explanation have been omitted as appropriate.

[0019] (1) Overall configuration of the motion recognition system FIG. 1 is a block diagram showing the functional configuration of the action recognition system 1 according to this embodiment, FIG. 2 is a diagram showing an example of an action pattern of a specific action in this embodiment, FIG. 3 is a block diagram showing the functional configuration of the three-dimensional sensor 20, FIG. 4(a) is a schematic diagram showing the dot pattern irradiation of the three-dimensional sensor 20, and (b) is a diagram showing an example of the measurement range of the three-dimensional sensor 20. The overall configuration of the action recognition system 1 will be described below with reference to the drawings.

[0020] The motion recognition system 1 according to this embodiment is a system that selects a pattern of a specific motion of a target person, and displays an alert when the specific motion occurs while capturing an image of the person. As shown in FIG. 1, the system includes a specific movement data memory unit 10 that stores specific movement data indicating specific movements including a predetermined series of postures and movements of at least one body part of the target M, a three-dimensional sensor 20 as a detection means that continuously acquires point cloud data P indicating multiple positions on the surface of the target M and generates three-dimensional coordinate information values ​​of the target M from the point cloud data P, a display unit 30 as a display means that continuously displays the movements of the target M as point cloud data having three-dimensional coordinate information values ​​generated by the three-dimensional sensor 20, an input receiving unit 40 as a receiving means that accepts the designation of a specific movement among the multiple movements of the target M, a notification unit 50 as a notification means that notifies that a specific movement has occurred when a movement of the target M matches the designated specific movement, and a recording unit 60 that records the point cloud data P acquired by the three-dimensional sensor 20.

[0021] In the action recognition system 1, the processing of the specific action data storage unit 10, the display unit 30, the input receiving unit 40, the notification unit 50 and the recording unit 60 is realized by, for example, a general computer in which a processor consisting of a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory) executes a predetermined program. The three-dimensional sensor 20 can perform light emission control, light reception control, and communication control using a program processing device implemented as a Raspberry Pi (registered trademark), a single-board computer equipped with an ARM processor, or a small computer device, but is not limited to this.

[0022] (Specific action data storage unit) The specific motion data storage unit 10 stores, as motion pattern data, specific motions including a series of predefined postures and motions of body parts of the target M. Here, the specific motions include, but are not limited to, lying on the bed, sitting up from the bed, sitting on the bed, standing up from the bed, touching the arm, touching the neck, touching the shoulder, standing, and the like, as shown as motion pattern examples in Fig. 2.

[0023] (3D sensor) As shown in the block diagram of Figure 3, the three-dimensional sensor 20 comprises a projector 21 consisting of a light-emitting element that emits light, an image sensor module 22 consisting of an imaging element that receives light reflected from the surface of the object to be imaged, and a control unit 23 that controls the light emission of the projector 21, the light reception of the image sensor module 22, and the processing of the received light data.

[0024] The projector 21 is composed of a VCSEL (Vertical Cavity Surface Emitting LASER) 211, which is an array light source consisting of multiple light-emitting elements, and a transmissive diffractive optical element (DOE) 212 that controls the light distribution of the laser light above the VCSEL 211. The VCSEL 211 emits invisible near-infrared laser light with a wavelength of 940 nm, making it possible to capture images both during the day and at night. The diffractive optical element 212 converts the light emitted by the VCSEL 211 into a regular dot pattern of light distribution, and irradiates the target M with a plurality of beams of distance measuring light.

[0025] 4(a) shows an example in which light emitted from the projector 21 is converted by the diffractive optical element 212 into distance measurement light L1 to Ln having a spread angle θ1 so as to be distributed as a regular dot pattern to the target M. In this embodiment, the dot pattern is irradiated with 4000 to 5000 laser beams, and as an example, as shown in FIG. 4(b), the measurement range (R) is 285×285 mm to 1900×1900 mm with a measurement distance (L) of 300 mm to 2000 mm.

[0026] The image sensor module 22 uses a CMOS (Complementary Metal Oxide Semiconductor) image sensor as a photoelectric conversion element. The image sensor module 22 receives the reflected light of the invisible near-infrared laser light emitted from the projector 21 and reflected by the target M, and acquires it as point cloud data P.

[0027] In this embodiment, the control unit 23 is configured with a Raspberry Pi (registered trademark), which is a single-board computer equipped with an ARM processor. The control unit 23 controls the operations of the projector 21 and the image sensor module 22, and processes the point cloud data P captured by the image sensor module 22 to generate three-dimensional coordinate information values.

[0028] The 3D sensor 20 configured in this manner emits invisible laser light from the projector 21 toward the object M, receives the light reflected from the surface of the object M with the image sensor module 22, acquires point cloud data P, and detects the stereoscopic and three-dimensional movement of the object M.

[0029] (Display) The display unit 30 can be realized in various ways, but in this embodiment, it can be realized as a display of a computer in which the program of the action recognition system 1 is installed, and outputs various information. In this embodiment, the action of the target M detected by the three-dimensional sensor 20 is displayed in real time as point cloud data P having three-dimensional coordinate information values. The display unit 30 may also be configured as a touch panel display and serve as the input receiving unit 40.

[0030] The movements of the target M displayed on the display unit 30 are displayed as point cloud data P having three-dimensional coordinate information values, and therefore there is a lower risk of obtaining information that could identify an individual compared to camera images (RGB color images) taken with a webcam capable of capturing still and moving images, making the display more considerate of privacy protection.

[0031] (Input reception section) The input receiving unit 40 receives the designation of a specific action among a plurality of actions of the target M, and specifically, receives input information of a specific action pattern designated by, for example, a user of the action recognition system 1. The input operation of the input information may be performed through an input device of a computer constituting the action recognition system 1, and specifically, is realized by a touch panel display or the like. For example, when the computer constituting the action recognition system 1 has a touch panel display, the touch panel display functions as the display unit 30 and the input receiving unit 40. Note that the input receiving unit 40 is not limited to a touch panel display, and may be, for example, a keyboard, a mouse, or a mechanical switch. The input receiving unit 40 may also be a microphone. Alternatively, the input reception unit 40 may be a part of an independent device such as a remote controller, or may be a part of a mobile terminal (smartphone or tablet terminal) on which a dedicated application program is installed. In this case, the input reception unit 40 receives the input information sent from the mobile terminal via a network, thereby receiving the input information.

[0032] The specific motion patterns designated by the user are specific motion patterns pre-stored in the specific motion data storage unit 10, and examples include lying in bed, sitting up in bed, sitting on the bed, standing up from the bed, touching the arm, touching the neck, touching the shoulder, standing, etc. Furthermore, the specific movement patterns pre-stored in the specific movement data storage unit 10 can be added as movements that require particular attention in accordance with the situation of each individual target M, and the user can specify the added specific movement pattern via the input receiving unit 40.

[0033] (Notification Department) When the motion of the target M matches the designated specific motion, the notification unit 50 issues an alert to the effect that the specific motion has occurred. Here, when the movement of target M matches the specified specific movement, it means that the detected movement of target M is judged to have a certain degree of probability to be the movement specified by the user as the specific movement to be detected, and the movement prompts the user to check the situation. For example, it is determined whether or not a specific action such as sitting on the bed, standing up from the bed, touching the arm, touching the neck, touching the shoulder, standing, etc. may have occurred, and if it is determined that a specific action has occurred, the notification unit 50 notifies the user that a specific action has occurred.

[0034] The notification unit 50 may be configured, for example, with a speaker that notifies information by sound, a vibrator that notifies information by vibration, a lamp that notifies information by lighting or blinking, etc. Alternatively, the display unit 30 may function as the notification unit 50 by displaying information on a display. The notification unit 50 is not limited to the example shown here, and may be configured with other mechanisms capable of notifying information, or may be configured with a combination of multiple mechanisms. Furthermore, these notification units 50 may be provided independently of the computer constituting the action recognition system 1, and may be controlled by communication.

[0035] When the notification unit 50 notifies that a specific operation has occurred, it records the point cloud data P acquired by the three-dimensional sensor 20. The recording unit 60 that records the point cloud data P can be configured with a recording medium such as a semiconductor memory including a non-volatile memory such as a non-volatile RAM (NVRAM) or a hard disk drive (HDD). The recorded point cloud data can be shared between users by recording it as data in a format such as a comma separated value (CSV), JavaScript object notation (JSON), or extensible markup language (XML).

[0036] (2) Specific action detection process Fig. 5 is a schematic diagram showing an example of the arrangement of the three-dimensional sensor 20 provided in the action recognition system 1, Fig. 6 is a flowchart showing the flow of the detection process for detecting three-dimensional actions of the target M in the action recognition system 1, Fig. 7 is a diagram conceptually showing the process of extracting point cloud data P of only the patient from the acquired point cloud data P, and Fig. 8 is a conceptual diagram explaining an example of the process of removing noise from the point cloud data P. The detection process of a specific action in the action recognition system 1 according to this embodiment will be explained below with reference to the drawings.

[0037] In the motion recognition system 1 according to this embodiment, as shown in FIG. 5, the three-dimensional sensor 20 is installed above the bed 70 and is configured to capture images focusing on the condition and motion of the patient M using the bed 70.

[0038] First, in step S101, the three-dimensional sensor 20 is turned on, and the projector 21 irradiates the patient M with laser light (S101). The laser light is emitted as several thousand aligned dots at the same time. The laser light is emitted at regular intervals while acquiring point cloud data P of the patient M, and the laser light emitted as aligned dots toward the patient M is received by the image sensor module 22 and acquired in real time as point cloud data P (S102).

[0039] Next, point cloud data P showing the background other than the bed 70 and the patient M is removed from the point cloud data P acquired in step S102, and point cloud data P of only the bed 70 and the patient M is extracted (S103). Specifically, as shown in Fig. 7(a), from the point cloud data P stored in the recording unit 60, several tens of points are extracted in each of the X and Y directions, and the variance σ1 in the Z-axis direction perpendicular to the X and Y axes is calculated. If the calculated variance σ1 in the Z-axis direction is greater than a predetermined value, it is assumed that there is movement, that is, that patient M has been detected, and point cloud data P of patient M is extracted (see Fig. 7(b)). In addition, for bed 70, the area of ​​bed 70 is calculated from the size of bed 70 registered in advance, and point cloud data of bed 70 is extracted (S103).

[0040] In step S103, noise is removed from the point cloud data P from which the point cloud data P showing the background other than the bed 70 and the patient M has been removed, and the point cloud data P of the bed 70 and the patient M is extracted (S104). As shown in Fig. 8, the variance σ2 of the neighboring points of the point cloud data that are outside a virtual sphere with a radius of a predetermined threshold value centered on any one point Pn of the acquired point cloud data P is calculated, and if the variance σ2 is greater than a predetermined value, it is determined to be noise and removed from the point cloud data P. This process is repeatedly performed for each point of the point cloud data P to remove noise from the point cloud data P and extract the point cloud data P of the bed 70 and the patient (S104). In addition, noise may be detected by calculating a statistical outlier in which the average distance from any one point Pn of the acquired point cloud data P to the neighboring points is far from the average of the entire point cloud data, and the noise may be removed from the acquired point cloud data P as noise, or this process may be performed additionally.

[0041] Then, in step S105, noise is removed, and the three-dimensional posture of the patient M is calculated from the point cloud data P of only the area where the bed 70 and the patient M are present (S105). 9 shows an example of calculating the three-dimensional coordinate information value of the patient M by trigonometry. The distance D between an arbitrary point Pn of the point cloud data P in FIG. 9 and the three-dimensional sensor 20 is calculated by the following formula 1, where A is the distance between the projector 21 and the image sensor module 22, α1 is the angle between the distance measuring light L1 and the central axis c1 of the projector 21, and α2 is the angle between the central axis c2 of the image sensor module 22 and the reflected light R1 received by the image sensor module 22. D*tanα1+D*tanα2=A (Equation 1) This makes it possible to calculate the distance from the projector 21 to the patient M onto which the distance measuring light L1 is projected, that is, the three-dimensional coordinate information value of the patient M. For each point of the point cloud data P of the bed 60 and the patient M, the three-dimensional coordinate information value can be calculated from the above relational expressions.

[0042] Next, based on the specific movement data stored in the specific movement data storage unit 10, it is determined whether the condition and movement of the patient M generated by the three-dimensional sensor 20 are the specific movement specified by the user (step S106). Specifically, it is determined whether the patient M is in any of the following states: lying on the bed (supine or lateral position), sitting on the bed (sitting on the edge of the bed), touching his / her arm, standing up from the bed (getting out of bed), touching his / her arm, touching his / her neck, touching his / her shoulder, or standing. Whether the above-mentioned specific motion is present is determined by whether the difference between the stored specific motion data and the three-dimensional coordinate information value generated by the three-dimensional sensor 20 is smaller than a predetermined threshold value.

[0043] In step S106, when it is determined that a specific movement has occurred in the patient M being watched over (step S106; Yes), the notification unit 50 issues an alert to the effect that a specific movement has occurred (step S107). Specifically, the condition and movements of patient M are displayed in real time on the display as point cloud data P, and an indication that a specific movement has been designated is given on the display, a lamp or the like is turned on or blinked, a sound is emitted from a speaker, or some other such indication is given (S107).

[0044] Then, when the notification unit 50 notifies that a specific action has occurred, in step S108, the point cloud data P acquired by the three-dimensional sensor 20 is recorded (step S108). The recorded point cloud data P is recorded as data in a format such as CSV (Comma Separated Value), JSON (JavaScript Object Notation), or XML (Extensible Markup Language).

[0045] As described above, the action recognition system 1 of this embodiment includes a specific action data storage unit 10 that stores specific action data indicating specific actions including a predefined series of postures and actions of at least one body part of the target person, a 3D sensor 20 that continuously acquires point cloud data P indicating multiple positions on the surface of the target person and generates three-dimensional coordinate information values ​​of the person from the point cloud data P, a display unit 30 that continuously displays the actions of the target person as point cloud data P having the three-dimensional coordinate information values ​​generated by the 3D sensor 20, an input receiving unit 40 that receives designation of a specific action from among the multiple actions of the target person, an alarm unit 50 that notifies that a specific action has occurred when the action of the target person matches the designated specific action, and a recording unit 60.

[0046] According to this configuration, various three-dimensional movements of a person can be confirmed in real time by the point cloud data P having three-dimensional coordinate information values. In particular, each point of the point cloud data P has a three-dimensional coordinate information value recorded, so it is possible to recognize the movements of body parts that are difficult to understand because they are in close contact with the body. Furthermore, according to this configuration, the human movements displayed on the display unit 30 are displayed as point cloud data P having three-dimensional coordinate information values, so there is a lower risk of obtaining information that could identify an individual compared to camera images (RGB color images) using a Web camera, making the display more considerate of privacy protection.

[0047] In this embodiment, an example of detecting the condition and specific movements of a patient M using a bed has been described, but the movement recognition system 1 of this embodiment can be suitably installed in hospitals, nursing homes, elderly welfare facilities, residences, etc. depending on the type of subject whose privacy needs to be protected, and can recognize and analyze the condition and movements of people who need to be watched over. [Explanation of symbols]

[0048] 1. Motion Recognition System 10. Specific operation data storage unit 20...3D sensor 21...Projector, 211...VCSEL, 212...Diffractive optical element 22 Image sensor module 23 Processing section 30...Display section 40 Input reception section 50. Notification Department 60 Recording section

Claims

1. A motion recognition system for performing motion recognition of a target, A storage means for storing specific motion data indicative of specific motions including a predefined series of postures and motions of at least one body part of the subject; a detection means for continuously acquiring point cloud data indicating a plurality of positions on a surface of the object, and generating three-dimensional coordinate information values ​​of the object from the point cloud data; a display means for continuously displaying the target's motion as point cloud data having the three-dimensional coordinate information values ​​generated by the detection means; A reception means for receiving a designation of the specific motion among the plurality of target motions; and a notification means for notifying the occurrence of the specific motion when the target motion coincides with the specified specific motion.

1. A motion recognition system comprising:

2. the detection means projects invisible light from an array light source consisting of a plurality of light-emitting elements through a diffractive optical element, receives reflected light from the surface of the object, and acquires the point cloud data; The action recognition system according to claim 1 .

3. The specific movement is a physical movement including an angle and a width of the movement of the body part of the target. The action recognition system according to claim 1 .

4. When notifying that the specific action has occurred, the point cloud data acquired by the detection means is recorded. The action recognition system according to claim 1 .

5. A method for recognizing a target action, comprising: storing specific motion data indicative of specific motions including a predefined series of postures and motions of at least one body part of the subject; a detection step of continuously acquiring point cloud data indicating a plurality of positions on a surface of the object, and generating three-dimensional coordinate information values ​​of the object from the point cloud data; a display step of continuously displaying the target motion as point cloud data having the three-dimensional coordinate information values ​​generated in the detection step; a receiving step of receiving a designation of the specific motion among the plurality of target motions; and a notification step of notifying the occurrence of the specific action when the target action coincides with the specified specific action.

13. A motion recognition method comprising:

6. On the computer, storing specific motion data indicative of specific motions including a predefined series of postures and motions of at least one body part of the subject; a detection step of continuously acquiring point cloud data indicating a plurality of positions on a surface of the object, and generating three-dimensional coordinate information values ​​of the object from the point cloud data; a display step of continuously displaying the target motion as a moving image in the form of point cloud data having the three-dimensional coordinate information values ​​generated in the detection step; a receiving step of receiving a designation of the specific motion among the plurality of target motions; and a notification step of notifying the occurrence of the specific motion when the target motion coincides with the specified specific motion. A program characterized by:

Citation Information

Patent Citations

  • Operation recognition system, operation recognition method and operation recognition program

    JP2022077870A

  • Nurse call system and state determination system

    JP2023051150A