JP6008911B2 - Motion recognition device, motion recognition method, and program - Google Patents

Description

  The present invention relates to a motion recognition device, a motion recognition method, and a program.

  In recent years, for example, in the field of information processing devices such as PCs, user gestures and hand gestures (hereinafter referred to as “gestures”) are photographed by a camera provided on the device side, and specific gestures are recognized based on the photographed images. When this is done, a gesture recognition technique that realizes a function corresponding to a recognized gesture in advance is widely known.

  With respect to the gesture recognition technology described above, for example, in Patent Document 1, in an application such as a game that uses a user's motion as an input interface, an event corresponding to the facial motion detected by the motion detection unit is searched from the table. A user interface program for executing an event is disclosed. Also, in this document, when the user touches the “?” Object displayed on the mirror image screen of the user displayed on the screen, the contact is judged and the “Usage Guide” text appears on the screen. It is described that it is displayed.

JP 2008-155942 A

  By the way, in the case of a technique in which a user's face motion is photographed by a camera provided on the apparatus side and a predetermined function is realized as in Patent Document 1, in order for the face motion to be recognized, the user must Must always face the device. In addition, such a technique forces the user to always have his face facing the apparatus side in order to realize a predetermined function. Also, in the first place, realizing a predetermined function using only the movement of the face for the operation is unnatural in view of the whole human movement, no matter how much the movement of the face conforms to the natural movement. I must say.

  The present invention has been made in view of such circumstances, and an object of the present invention is to provide an operation recognition device that realizes a desired function by a more natural operation that is not compelled by a user.

  In order to solve the above-described problems, the motion recognition apparatus of the present invention includes a photographing unit that photographs a space in which one or more still objects are arranged, a detecting unit that detects at least a part of the user's body in the space, and a photographing unit. 3D modeling means for generating 3D model data of the space based on the photographed image taken by the means, and part data comprising three-dimensional coordinate data for specifying the position of at least a part of the user's body from the detection result by the detection means In a surrounding space including at least a space around a space occupied by at least one still-life model among one or more still-life models included in the 3D model data of the space generated by the part data acquisition means to be acquired and the 3D modeling means Determination means for determining whether or not the part data acquired by the part data acquisition means is included; and , When it is determined to contain a site data enclosed space, characterized in that it comprises a function executing unit that executes a predetermined function, a.

  According to the present invention, it is possible to realize a desired function by a more natural operation that does not force the user.

It is operation | movement explanatory schematic using the personal computer as an example of the operation | movement recognition apparatus in embodiment of this invention. It is a figure which shows the hardware structural example of the operation | movement recognition apparatus in embodiment of this invention. It is a functional block diagram of the action recognition device in the embodiment of the present invention. It is a schematic diagram explaining the 3D modeling process in the action recognition process in the embodiment of the present invention. It is a schematic diagram explaining the proximity determination process in the action recognition process in the embodiment of the present invention. It is a schematic diagram which shows the operation example of the movement recognition process in embodiment of this invention. It is a schematic diagram which shows the operation example of the movement recognition process in embodiment of this invention. It is a schematic diagram which shows the operation example of the movement recognition process in embodiment of this invention. It is a flowchart which shows an example of the operation | movement recognition process sequence in embodiment of this invention.

  An operation recognition apparatus according to an embodiment of the present invention will be described below with reference to the drawings. In addition, in each figure, the same code | symbol is attached | subjected to the part which is the same or it corresponds, The duplication description is simplified thru | or abbreviate | omitted suitably. In the following description, an integrated personal computer (hereinafter referred to as “PC”) is used as an example in describing the motion recognition apparatus according to the present embodiment. However, the present invention is not limited to this. PC, notebook PC, multi-function mobile phone (smartphone), PDA (Personal Digital Assistant), mobile terminal such as mobile phone, television (TV) with information processing function, or information processing For example, the motion recognition apparatus of the present embodiment may be applied to a household appliance such as a refrigerator or a washing machine having a function, or a private car.

  The motion recognition apparatus according to the present embodiment recognizes a predetermined motion using at least a part of the user's body. In the present embodiment, the motion recognition using the user's fingers will be described below as an example. Shall. The motion recognized by the motion recognition device may be any motion that uses at least a part of the body, and is not limited to fingers and recognizes and recognizes any motion using arms, legs, face, or the whole body. Alternatively, a predetermined function corresponding to each operation content may be realized. The operation is not limited to the state in which the user's finger or the like is moving, but will be described below as including the state of the finger or the like at the moment of shooting the moving finger or the like.

  An outline of an operation using an integrated PC (hereinafter simply referred to as “PC”) 1 which is an example of an operation recognition apparatus in the present embodiment will be described with reference to FIG. The PC 1 includes, for example, a camera 11 that captures an indoor space in which one or more still life such as furniture is arranged, an IR (Infrared) camera 12, and a display 13. In addition, although not shown in figure, PC1 may be provided with input devices, such as a keyboard, a touchpad, or a touch panel, for example. In the indoor space S shown in FIG. 1, a desk 2, a standlight 3, and a sofa 4 are exemplarily disposed, and a hand M that is a part of the user's body is schematically illustrated. In the present embodiment, the IR camera 12 or the like detects an operation such as a touch on a still object such as the desk 2 disposed in the indoor space S.

  For example, the camera 11 is an imaging unit that captures an indoor space S as indicated by a broken line in FIG. 1 and takes the captured image into the PC 1. The camera 11 is preferably provided with a wide-angle lens from the viewpoint of photographing furniture and the like represented by the desk 2 arranged in the indoor space as much as possible. However, depending on the position of the furniture etc. arranged in the indoor space, for example, when the furniture etc. is arranged near the center of the room, it is not always necessary to use a wide-angle lens, depending on the arrangement situation of the furniture etc. In addition, lenses having different angles of view may be used. In other words, in the present embodiment, when the user's movement through the still life such as the desk 2 is detected by the IR camera 12, it is only necessary to be able to shoot an indoor space in which a still life that the user may touch is arranged. is there. In the present embodiment, the camera 11 is provided above the display 13. However, the present invention is not limited to this, and if a certain range of space such as the indoor space S can be photographed, the installation position with respect to the apparatus is determined. It doesn't matter. On the other hand, for example, a predetermined space may be photographed by fixing the camera installation position and changing the direction of the camera using a movable means (not shown).

  The IR camera 12 is detection means for detecting a hand M that is a part of the user's body. It goes without saying that the range indicated by the alternate long and short dash line schematically shows the detection area and is not limited to this range. In this embodiment, an IR camera that uses infrared rays to acquire a thermal image of an object is used as detection means. However, the present invention is not limited to this, and at least a part of the user's body is three-dimensionally detected. For example, a stereo camera system using a plurality of cameras or a system that obtains a distance image by measuring the return time after irradiating an object with infrared rays can be used. May be. As with the camera 11, the IR camera 12 may be installed at any position with respect to the apparatus.

  The display 13 is display means for displaying images and videos. In the present embodiment, since the PC 1 is used as an example of the motion recognition device, the display 13 is provided. However, the display is not an essential configuration in the present invention. However, when the processing content to be executed is confirmed by information such as an image as a result of the operation by the user, it goes without saying that the information needs to be displayed on a display means such as a display. For example, when the present invention is applied to home appliances such as a refrigerator and a washing machine, the state in which the functions of these home appliances are executed as a result of user operation is recognized through the five senses other than human vision. This is an example of the case where a display is not necessary.

  In the present embodiment, for example, whether or not the hand M touches the desk 2 in the indoor space S photographed by the camera 11 and the coordinate data of the indoor space S acquired based on the photographed image of the indoor space S photographed. A description will be given below of determination using the detection result of the hand M by the IR camera 12.

  Next, the hardware configuration of the motion recognition apparatus in the present embodiment will be described with reference to FIG. The motion recognition apparatus in the present embodiment includes, for example, a control unit 21, a RAM (Random Access Memory) 22, a ROM (Read Only Memory) 23, an HDD (Hard Disk Drive) 24, a photographing unit 25, and a detection unit. 26 and a display unit 27.

  The control unit 21 is, for example, a CPU (Central Processing Unit) that performs 3D modeling processing, position coordinate data acquisition processing, determination processing, function execution processing, and the like, which will be described later, in addition to the overall control of the motion recognition apparatus. Further, the control unit 21 controls each device described above in order to execute a predetermined function corresponding to the recognized operation in the present embodiment.

  For example, the RAM 22 may be used as a work area for the control unit 21 and as a temporary storage area for various data. The ROM 23 only needs to store various data necessary for control in addition to a control program such as BIOS (Basic Input Output System) executed by the control unit 21.

  The HDD 24 has a large capacity for storing, for example, 3D model data modeled by causing the control unit 21 to execute a predetermined 3D modeling program based on a captured image of the indoor space S captured using the capturing unit 25. It is a storage device. In the present embodiment, for example, the HDD 24 is built in the PC 1, but the HDD 24 may be externally attached.

  The imaging unit 25 is an imaging unit that images the indoor space S, such as the camera 11 described above. The imaging unit 25 may be, for example, a digital camera that includes a charge coupled device (CCD), a complementary metal-oxide semiconductor (CMOS), or the like as an image sensor that converts light into an electrical signal. Note that the resolution of the image sensor does not need to be particularly high as long as furniture and the like arranged in the space can be suitably recognized from the captured image of the indoor space S. However, for example, when the user's hand M is brought into contact with a specific part of the furniture such as the desk 2 as shown in FIG. 1 to realize a function corresponding to the specific part, the specific part It is preferable that a high-quality photographed image can be taken so that it can be distinguished from other parts.

  The detection unit 26 is a detection unit such as the above-described IR camera 12 that detects an operation performed by a part of the user's body, such as the hand M, as the user's operation. As described above, as the detection means, not only the IR camera but also a stereo camera system or the like may be used, and for example, the hand M may be recognized three-dimensionally.

  The display unit 27 is a display device such as a liquid crystal display or an organic EL display that displays various images. As described above, a display device such as a liquid crystal display is not indispensable for the present invention. However, when the PC 1 is used as an apparatus to which the present invention is applied as in the present embodiment, a display device such as a liquid crystal display is used. A predetermined display image may be displayed using.

  Next, functional blocks of the motion recognition apparatus in the present embodiment will be described with reference to FIG. The motion recognition apparatus in the present embodiment includes, as function blocks, an imaging unit 25, a detection unit 26, a 3D modeling unit 31, a part data acquisition unit 32, a determination unit 33, and a function execution unit 34. Has been. Since the imaging unit 25 and the detection unit 26 have been described above, description thereof is omitted here.

  The 3D modeling unit 31 is a 3D modeling unit that generates 3D model data of a space such as the indoor space S based on the captured image captured by the capturing unit 25. As the 3D model data to be generated, for example, in the indoor space S in FIG. 1, it is preferable to specify the positions of the desk 2, the standlight 3, and the sofa 4 in the indoor space S using coordinate data. In addition, about the production | generation of 3D model data, you may carry out using the existing technique.

  Further, the 3D modeling unit 31 assigns an identifier for identifying one or more still objects in the captured image based on at least a difference in color information of one or more still objects included in the captured image for each of the 3D model data of the one or more still objects. To do. For example, since the desk 2 and the standlight 3 in FIG. 1 are only acquired as the respective coordinate data by the 3D modeling unit 31, it is difficult to identify the desk 2 and the standlight 3 only by the data. . Therefore, for example, an identifier for identifying the desk 2 and the standlight 3 is given based on the difference in the color information of the still life. As for the correspondence between the assigned identifier and the desk 2 or the like, for example, table data that prescribes the correspondence may be stored in the HDD 24 or the like shown in FIG. Note that the desk 2 or the like is identified by specifying the approximate shape of the desk 2 or the like by specifying several coordinate data points acquired based on the photographed image together with the color information or instead of the color information, for example. It is good as well.

  The part data acquisition unit 32 is part data acquisition means for acquiring part data consisting of three-dimensional coordinate data that specifies the position of at least a part of the user's body from the detection result of the detection unit 26. For example, the part data acquisition unit 32 detects the user's hand M using the IR camera 12, visualizes the detected thermal energy, and uses the relative difference for each visualized thermal energy data. Then, three-dimensional coordinate data such as a part of the hand M, for example, the fingertip of the index finger is acquired.

  The determination unit 33 includes a part in an enclosed space including at least a space around a space occupied by at least one still-life model among one or more still-life models included in the 3D model data of the space generated by the 3D modeling unit 31. It is determined whether or not the part data acquired by the data acquisition unit 32 is included. Details of this processing will be described later with reference to FIG.

  The function execution unit 34 is a function execution unit that executes a predetermined function when the determination unit 33 determines that the part data is included in the enclosed space. Details of this process will be described later with reference to FIGS.

  Next, 3D modeling processing in the present embodiment will be described with reference to FIG. First, the photographing unit 25 photographs the indoor space S together with the desk 2, the standlight 3, and the sofa 4 as shown in FIG. The 3D modeling unit 31 performs 3D modeling processing based on the captured image data of the captured indoor space S.

  The 3D modeling unit 31 performs a division process on the 3D modeled indoor space S as each part constituting the indoor space S based on the difference in color information included in the captured image data. For example, an area including the desk 2 as shown in FIG. 4B, an area including the standlight 3 as shown in FIG. 4C, and an area including the sofa 4 as shown in FIG. 4D. As shown in FIG. 4 (e), the image is divided into regions each containing the article 50 placed on the desk 2.

  The 3D modeling unit 31 includes, for each of the divided areas, an area including the desk 2, an area including the standlight 3, an area including the sofa 4, and the article 50. An identifier for identifying the region is assigned to the 3D model data of each divided region.

  Next, the action recognition process in this embodiment is demonstrated with reference to FIG. 5 with the process by the determination part 33. FIG. Here, an example of a process for determining whether or not a part of the user's hand M or the fingertip of the index finger has approached the desk 2 shown in FIG. 1 will be described.

  First, it is assumed that 3D model data of a region including the desk 2 surrounded by the coordinates A to H is obtained by the 3D modeling unit 31 as the 3D model data of the desk 2. In practice, as shown in FIG. 4, the 3D modeling unit 31 divides the 3D model data of the indoor space S as an area including the desk 2, so that the corner of the desk 2 is not necessarily shown in FIG. The coordinates A to H do not correspond to the eight points, but here, for convenience of explanation, it is assumed that the coordinates A to the coordinates H correspond to the eight corners of the desk 2.

  Here, a three-dimensional coordinate space with the coordinate A as the origin is defined. The horizontal axis in the specified three-dimensional coordinate space is the X axis, the vertical axis is the Y axis, the depth axis is the Z axis, and a positive value is taken to the right of the origin on the X axis. A negative value is assumed on the left side. It is assumed that a positive value is taken above the origin on the Y axis and a negative value is taken below the origin. Further, assume that a positive value is taken on the back side from the origin on the Z axis, and a negative value is taken on the near side from the origin. For example, the coordinate A is [0, 0, 0], the coordinate B is [x, 0, 0], the coordinate C is [0, 0, z], and the coordinate D is [x, 0]. , 0]. The coordinate E is [0, -y, 0], the coordinate F is [x, -y, 0], the coordinate G is [0, -y, z], and the coordinate H is [x, −y, z].

  Further, the determination unit 33 sets a determination region for determining whether or not the hand M has approached the desk 2. For example, a surrounding space surrounded by a rectangular parallelepiped composed of coordinates A ′ to H ′ is set as a coordinate position moved in the X axis, Y axis, and Z axis directions by a numerical value ± α from each of the coordinates A to H. . In addition, although the numerical value (alpha) is an example and the same numerical value is moved to all the coordinates AH here, it is not limited to this, You may move a different numerical value, respectively.

  For example, the coordinate A ′ is [−α, α, −α], the coordinate B ′ is [x + α, α, −α], the coordinate C ′ is [−α, α, z + α], and the coordinate D It is assumed that “x” is [x + α, α, z + α]. The coordinate E ′ is [−α, −y−α, −α], the coordinate F ′ is [x + α, −y−α, −α], and the coordinate G ′ is [−α, −y−. α, z + α], and the coordinate H ′ is [x + α, −y−α, z + α].

  Then, the determination unit 33 sets the determination region as a space region between the coordinates A to H and the coordinates A ′ to H ′. The spatial area that is the determination area is represented by [A ′ to H ′] − [A to H] as illustrated in a simplified manner. The determination unit 33 acquires, for example, coordinates M1 [xi, yi, zi] of [A ′ to H ′] − [A to H] as the region data of the fingertip of the index finger in the hand M by the region data acquisition unit 32. When it is included in the determination area, it is determined that the fingertip of the index finger in the hand M is close to the desk 2. When this is expressed by a simple formula, “[A′˜H ′] − [A˜H] ≧ M” as shown in the figure. Needless to say, the smaller the determination area, the higher the recognition sensitivity. In addition, here, the rectangular parallelepiped that defines the enclosed space is defined based on eight coordinates, but is an example. For example, two arbitrary three-dimensional coordinates around a furniture such as a desk 2 are set, A rectangular parallelepiped composed of six surfaces is defined by defining three planes each having two sides that are extended by a predetermined distance in the two axis directions of the X axis direction, the Y axis direction, or the Z axis direction from each of the two three-dimensional coordinates. It may be specified.

  Here, for example, the enclosed space is a rectangular parallelepiped because the enclosed space is set based on a coordinate space consisting of 8 points from coordinates A to H as 3D model data of the desk 2, for example. It is not limited, The determination area as enclosed space may change according to solid shapes, such as furniture arranged in space. That is, for example, the determination region may be a three-dimensional shape such as a cube, a sphere, a cylinder, a cone, a triangular pyramid, a parallelepiped, a pentagonal column, or a hexagonal column.

  Next, a function execution process will be described with reference to FIGS. 6 to 8 together with a specific example of a function executed by the function execution unit 34 when the determination unit 33 determines that the hand M is included in the determination region. . Here, it is described that the hand M is included in the determination area, for example, if the hand M touches the desk 2 in the determination area of the desk 2.

  As shown in FIG. 6, when the hand M is included in the determination area of the standlight 3, that is, when the hand M touches the standlight 3, for example, the function of turning on the power of the PC 1 shown in FIG. Is executed by the function execution unit 34. As the function execution processing, for example, a table is set in which identifiers associated with the 3D model data of each divided area are associated with the respective functions. When it is determined that M is included in each determination region, a predetermined function corresponding to the identifier associated with the 3D model data of each determination region may be executed.

  Note that, when the hand M is included in the determination region of the standlight 3, the determination unit 33 is based on two or more region data acquired by the region data acquisition unit 32 and time information associated with the region data. Thus, the movement amount of at least a part of the user's body in the enclosed space may be determined. Then, the function execution unit 34 may adjust the performance state of the predetermined function according to the movement amount determined by the determination unit 33.

  In FIG. 6, for example, when the umbrella of the standlight 3 is touched, the detection unit 26 detects the movement of moving the hand M so as to slide on the surface of the umbrella in a certain direction. At this time, the part data acquisition unit 32 acquires part data as the movement start point of the hand M, part data as the movement end point of the hand M, clock information associated with the part data, and the like. . And the determination part 33 determines the moving amount | distance of the hand M based on those acquisition data. The function execution unit 34 adjusts, for example, the brightness of the standlight 3 as a predetermined function display state according to the amount of movement of the hand M. In other words, the “state of exhibiting the predetermined function” here refers to a light / dark state as a state in which the function of adjusting brightness is exhibited as in the above example. In addition, this example is an example and is not limited to this.

  Further, as shown in FIG. 7, when the hand M is included in the determination area of the desk 2 and close to a predetermined position of the desk 2, that is, when the hand M touches the predetermined position of the desk 2, The execution unit 34 may execute a function corresponding to each position. For example, when the hand M touches 2c on the desk 2, the function execution unit 34 may execute a function of starting the TV application in the PC 1. Further, when the hand M touches 2rf on the desk 2, the function execution unit 34 may execute a function of causing the N station to select a channel in the PC1. Further, when the hand M touches 2lr on the desk 2, the function execution unit 34 may execute a function of causing the W station to select a channel in the PC 1.

  Furthermore, as shown in FIG. 8, when the hand M is included in the determination region of the sofa 4 and, for example, close to both armrests of the sofa 4, that is, when the hand M touches the armrest of the sofa 4, In the PC 1, the volume adjustment function may be executed by the function execution unit 34. For example, when the hand M touches 4r, the volume may be adjusted to high, and when the hand M touches 4l, the volume may be adjusted to low.

  The determination unit 33 determines the movement speed of at least a part of the user's body based on the movement amount and the time information, and the function execution unit 34 determines according to the determined movement speed. It is good also as changing the adjustment level of a display state according to the intensity | strength at least one part adjoins to a still life. Here, the “adjusted state adjustment level” means, for example, FIG. 8, the volume adjustment level in a state where the volume adjustment is being performed. More specifically, if the strength with which the hand M touches the armrest 4l or 4r is strong, the degree of volume change may be increased, and if the strength with which the hand M touches the armrest is weak, the degree of volume change. Should be reduced. For example, if you touch the armrest strongly, you can increase or decrease the volume quickly. Good.

  Next, the operation recognition processing procedure in this embodiment will be described with reference to FIG. First, the 3D modeling unit 31 converts the indoor space S into a 3D model based on the captured image of the indoor space S photographed by the photographing unit 25 (step S1).

  Next, when the hand M is detected by the detection unit 26 in the indoor space S (step S2, YES), the part data acquisition unit 32 acquires coordinate data that is part data of the hand M (step S3). On the other hand, when the hand M is not detected by the detection unit 26 in the indoor space S (step S2, NO), the detection unit 26 continues to detect the hand M (step S2).

  Thereafter, when the determination unit 33 determines that the hand M has touched furniture such as the desk 2 in the 3D modeled indoor space S (step S4, YES), the function execution unit 34 determines that the touched desk 2 is touched. A function corresponding to the above is executed (step S5). On the other hand, when the touch determination is not made by the determination unit 33 (step S4, NO), the process ends.

  Each of the above-described embodiments is a preferred embodiment of the present invention, and various modifications can be made without departing from the scope of the present invention. For example, each process in the above-described motion recognition apparatus of the present embodiment can be executed using hardware, software, or a combined configuration of both.

  When executing processing using software, a program in which a processing sequence is recorded can be installed and executed in a storage unit such as a memory in a computer incorporated in dedicated hardware. . Alternatively, the program can be installed and executed on a general-purpose computer capable of executing various processes.

  Further, in the case of a technique for executing a predetermined function based on a photographed gesture as in Patent Document 1, for example, when a predetermined function is not executed by a gesture, the user is caused by a gesture recognition defect. I don't know if it is due to something else or something else. On the other hand, by making it recognize as a contact operation to a still life as in this embodiment, for example, if the contact operation is recognized, the user can surely make a gesture by tactile sensation through the contact operation to the still life. You can feel that you have gone.

1 PC
2 desks 3 standlights 4 sofa 11 camera 12 IR camera 13 display 21 control unit 22 RAM
23 ROM
24 HDD
25 imaging unit 26 detection unit 27 display unit 31 3D modeling unit 32 part data acquisition unit 33 determination unit 34 function execution unit

Claims (6)

Photographing means for photographing a space in which one or more still lifes are arranged;
Detecting means for detecting at least part of the user's body in the space;
3D modeling means for generating 3D model data of the space based on a photographed image photographed by the photographing means;
Part data acquisition means for acquiring part data consisting of three-dimensional coordinate data specifying the position of at least a part of the user's body from the detection result by the detection means;
Obtaining the part data in a surrounding space including at least a space around a space occupied by at least one of the one or more still life models included in the 3D model data of the space generated by the 3D modeling means Determining means for determining whether or not the part data acquired by the means is included;
A function execution unit that executes a predetermined function when the determination unit determines that the part data is included in the enclosed space;
A motion recognition apparatus comprising:   The 3D modeling means assigns an identifier for identifying one or more still objects in the captured image based on at least a difference in color information of the one or more still objects included in the captured image for each of the 3D model data of the one or more still objects. The motion recognition apparatus according to claim 1, further comprising: The determination means is based on two or more part data acquired by the part data acquisition means and time information associated with the part data, and a movement amount of at least a part of the user's body in the enclosed space Determine
The motion recognition apparatus according to claim 1, wherein the function execution unit adjusts a state of performing a predetermined function according to the determined movement amount. The determination means determines a movement speed of at least a part of the user's body based on the movement amount and the time information,
The function execution means changes the adjustment level of the display state according to the strength with which at least a part of the user's body approaches the still life, which is determined according to the determined moving speed. The motion recognition apparatus according to claim 3. Photographing a space in which one or more still lifes are arranged;
Detecting at least a portion of a user's body in the space;
Generating 3D model data of the space based on the captured image and storing it in a storage unit;
Acquiring part data consisting of three-dimensional coordinate data specifying the position of at least a part of the user's body from the detection result, and storing it in the storage unit;
Stored in the storage unit in an enclosed space including at least a space surrounding a space occupied by at least one still-life model of the one or more still-life models included in the 3D model data of the space stored in the storage unit Determining whether the included site data is included;
A step of executing a predetermined function when it is determined that the part data is included in the enclosed space;
A motion recognition method comprising: A process of photographing a space in which one or more still lifes are arranged;
Detecting at least part of the user's body in the space;
Processing for generating 3D model data of the space based on the captured image and storing it in a storage unit;
A process of acquiring part data consisting of three-dimensional coordinate data for specifying the position of at least a part of the user's body from the detection result and storing it in the storage unit;
Stored in the storage unit in an enclosed space including at least a space surrounding a space occupied by at least one still-life model of the one or more still-life models included in the 3D model data of the space stored in the storage unit A process for determining whether or not included part data is included,
A process of executing a predetermined function when it is determined that the part data is included in the enclosed space;
A program that causes a computer to execute.

Images