Information processing device, information processing method, and information processing program

Abstract

A 3D body model is estimated taking into account the specified body parts. [Solution] The information processing device according to the present application has a receiving unit, an estimation unit, and a providing unit. The receiving unit receives a designation of a position corresponding to a predetermined part on a screen that schematically shows the user's body. The estimation unit estimates a position on a 3D body model of the user that corresponds to the position designated on the screen. The providing unit provides information about the 3D body model, with the estimated position on the 3D body model being the position corresponding to the predetermined part.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known techniques for estimating a 3D body model of a person, etc. For example, there is known a technique for estimating a 3D body model in a state when the body shape is changed, such as a pose, using a skeletal-muscle model. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-024742 [Patent Document 2] Patent No. 4977742 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques have not been able to estimate a 3D body model that takes into account specific body parts.

[0005] The present application has been made in view of the above, and aims to estimate a 3D body model that takes into account predetermined parts. [Means for solving the problem]

[0006] The information processing device of the present application is characterized by having a reception unit that receives a specification of a position corresponding to a predetermined part on a screen that schematically shows a user's body, an estimation unit that estimates a position in a 3D body model of the user that corresponds to the specified position on the screen, and a provision unit that provides information about the 3D body model, with the estimated position in the 3D body model being the position corresponding to the predetermined part. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to obtain an effect of estimating a 3D body model that takes into account a predetermined part. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is an explanatory diagram for explaining the overall information processing according to the embodiment. [Figure 3] FIG. 3 is an explanatory diagram for explaining the estimation process of a 3D body model in a changed pose state. [Figure 4] FIG. 4 is an explanatory diagram (1) for explaining an example of a method for adding a virtual marker according to the embodiment. [Figure 5] FIG. 5 is an explanatory diagram (2) for explaining an example of a method for adding a virtual marker according to the embodiment. [Figure 6] FIG. 6 is an explanatory diagram for explaining the pose change process. [Figure 7] FIG. 7 is an explanatory diagram for explaining the change process according to the first method. [Figure 8] FIG. 8 is an explanatory diagram for explaining the change process according to the second method. [Figure 9] FIG. 9 is a diagram illustrating an example of the configuration of a user terminal according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of a user information storage unit according to the embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of a learning model storage unit according to the embodiment. [Figure 13] FIG. 13 is a flowchart (1) showing an example of information processing according to the embodiment. [Figure 14] FIG. 14 is a flowchart (2) illustrating an example of information processing according to the embodiment. [Figure 15] FIG. 15 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] (Embodiment) [1. Information Processing System Configuration] An information processing system 1 shown in Fig. 1 will be described. As shown in Fig. 1, the information processing system 1 includes a user terminal 10 and an information processing device 100. The user terminal 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication. Fig. 1 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment.

[0011] The user terminal 10 is an information processing device used by a user for whom a 3D body model is to be estimated. The user desires an accurate estimation of a 3D body model that takes into account the size when the body shape is changed, such as a pose. By accurately estimating a 3D body model that takes into account the size when the body shape is changed, it becomes possible to, for example, create clothing (such as custom-made clothing) that fits the size of the changed body shape.

[0012] The user terminal 10 may be any device that can implement the processes in the embodiment. The user terminal 10 may also be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. Figure 2 shows a case where the user terminal 10 is a smartphone.

[0013] The user terminal 10 is, for example, a smart device such as a smartphone or tablet, and is a portable terminal device capable of communicating with any server device via a wireless communication network such as 4G to 5G (Generations) or LTE (Long Term Evolution). The user terminal 10 may have a screen such as a liquid crystal display with a touch panel function, and may accept various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by a user's finger or stylus. In FIG. 2, the user terminal 10 is used by a user U1.

[0014] The information processing device 100 is an information processing device intended to estimate a 3D body model that takes into account an appropriate size when the body shape is changed. In the following embodiment, the information processing device 100 provides information on an accurate 3D body model that takes into account an appropriate size when, for example, the pose is changed. The information processing device 100 is realized, for example, by a server device or a cloud system that proposes clothing that fits the user's 3D body model.

[0015] The pose before the change and the pose after the change will be referred to as the "specific pose" and the "changed pose", respectively, as appropriate. In the following embodiments, the normal posture with both hands down will be described as the "specific pose", and the state with both hands spread horizontally will be described as the "changed pose". Furthermore, in the following embodiments, "estimation" will be described as being interchangeable with "generation", "measurement" or "measurement", "update" or "correction", etc. as appropriate. Furthermore, "change" will be described as being interchangeable with "transformation", etc. as appropriate.

[0016] [2. An example of information processing] The information processing device 100 performs two main processes. The first is a 3D body model estimation process, and the second is a pose change process (i.e., a changed pose estimation process). By combining these two processes, the information processing device 100 provides information on an accurate 3D body model that takes into account an appropriate size, for example, when changing a pose from a specific pose to a changed pose.

[0017] In the following embodiments, a process that combines the two processes will be described first, followed by a detailed description of each process. Note that in the following embodiments, the term "pose" is not limited to concepts based on changes in joint angles and positional relationships, but may also include concepts based on muscle movements such as the amount of force applied or the amount of twisting. Also, in the following embodiments, the predetermined part is not limited to joint parts such as elbows and knees, but may be any part of the body as long as it is a physical characteristic part.

[0018] Fig. 2 is an explanatory diagram for explaining the overall information processing according to the embodiment. Information processing that integrates two processes will be explained using Fig. 2. First, the first process will be explained. First, a position corresponding to a predetermined part is specified on the screen (step S11).

[0019] The information processing device 100 displays a schematic representation of the body of the user U1 on the screen and accepts the designation of a position on the screen that corresponds to a predetermined body part (step S101). For example, the information processing device 100 uses a virtual marker to designate the position. The virtual marker includes, for example, text indicating the predetermined body part. For example, the virtual marker is added by the user U1 performing an operation on the screen (for example, tapping or clicking). The virtual marker may also be added to the extension of the body, for example. For example, the virtual marker may be added to the extension of the body by tracing the body of the user U1.

[0020] The information processing device 100 accepts the designation of the position to which the virtual marker is attached (hereinafter referred to as the "marker position" where appropriate) as a position corresponding to a predetermined body part. For example, this is effective when the predetermined body part is hidden by clothing or the like and cannot be seen. To give a specific example, the information processing device 100 instructs the user U1 to "tap your navel," and when the user U1 taps on the screen, saying "roughly around here," a virtual marker is attached to the tapped position. The information processing device 100 then accepts the designation of this marker position as the position of the "navel" of the user U1.

[0021] The virtual markers assigned to the photographed user in this manner follow the movements of the photographed user. In other words, once assigned, the virtual markers follow the marker positions even if the user U1 changes his or her pose. For example, the information processing device 100 can make the virtual markers follow the movements of the user by using known tracking techniques such as known skeletal detection techniques and image processing. In this way, the information processing device 100 can assign virtual markers to the user instead of markers that have previously been directly attached to the user's body or clothing.

[0022] Furthermore, the virtual markers do not simply correspond to virtual markers, but also indicate attributes of the user's physical positions, such as "elbow," "wrist," or "navel." For example, the information processing device 100 instructs the user U1 to "tap your navel," thereby accepting the user's designation of a physical position to be assigned the attribute "navel." By linking the attribute "navel" to the designated position, the information processing device 100 can identify which position on the photographed user's body has the attribute "navel." As will be clear from the description below, the information processing device 100 can use the identified attribute "navel" to identify which position on the 3D model corresponding to the user has the attribute "navel."

[0023] The information processing device 100 estimates the corresponding position of the 3D body model that corresponds to the marker position (step S102). For example, the information processing device 100 estimates the position of the 3D body model that corresponds to the marker position. Then, the information processing device 100 sets the estimated position to a predetermined part. As a result, for example, if the predetermined part is the "navel," the position of the "navel" on the 3D body model is identified.

[0024] This 3D body model may be a general-purpose 3D body model, or may be a 3D body model set up for user U1 (for example, a 3D body model that schematically shows the body of user U1).

[0025] In this way, the information processing device 100 estimates (or may update or correct) a 3D body model that takes into account the predetermined body part (step S103). For example, if the predetermined body part is the "navel," the information processing device 100 estimates a 3D body model based on the estimated position of the "navel." In this way, the information processing device 100 estimates a 3D body model from the 2D on the screen.

[0026] For example, the information processing device 100 may receive a request to specify the position of the "navel" as a virtual marker. In this case, the information processing device 100 identifies another position (hereinafter, sometimes referred to as an "estimated position") that can be detected using skeletal detection technology or the like. Here, the attribute of the estimated position is also known in the 3D body model, and corresponds to, for example, a joint in the skeleton. The information processing device 100 then estimates the positional and distance relationships between the estimated position identified in the captured image and the position of the "navel," and estimates the position of the "navel" in the 3D body model from the estimated positional and distance relationships and the estimated position in the 3D body model. Note that the information processing device 100 may simultaneously modify the 3D model itself (for example, shoulder width or the length from the shoulder to the elbow) based on the positional and distance relationships between the estimated positions.

[0027] When multiple virtual markers are set, the information processing device 100 may modify the 3D body model based on the positional and distance relationships between the virtual markers, identify positions in the 3D body model corresponding to the virtual markers, and identify attributes of those positions. For example, when the information processing device 100 receives designation of virtual markers for the "shoulder," "elbow," and "navel," it identifies the positional and distance relationships of the multiple virtual markers using image analysis technology and modifies the user's 3D body model so that the identified positional and distance relationships are established. Then, the information processing device 100 estimates positions corresponding to the virtual markers in the 3D body model and assigns attributes corresponding to the virtual markers to the estimated positions.

[0028] In this way, the 3D body model is estimated by updating (correcting) it according to the body (physical features, etc.) of user U1. This makes it possible to use, for example, the 3D body model of user U1. This completes the first process. Next, the second process will be explained.

[0029] The information processing device 100 acquires an image of the user U1 (step S104). For example, the information processing device 100 acquires an image of the user U1 in a particular pose.

[0030] The information processing device 100 receives a designation of an altered pose from the user U1. Upon receiving the designation of the altered pose, the information processing device 100 estimates a 2D body model of the user U1 in the state of the designated altered pose (step S105). Note that the altered pose may be predetermined for each product (e.g., clothing).

[0031] In this case, for example, when an image is input, the information processing device 100 estimates the 2D body model of user U1 using a machine learning model (hereinafter referred to as the "learning model" as appropriate) that has been trained to output information about the 2D body model in a specified changed pose.

[0032] The information processing device 100 estimates a 3D body model of the user U1 in the changed pose based on the 3D body model that is the first processing result (step S106). Then, the information processing device 100 provides the estimation result (step S107).

[0033] In this case, for example, when the information processing device 100 inputs a 2D body model of user U1, it estimates the 3D body model of user U1 in a changed pose using a learning model that has been trained to output information about the 3D body model of user U1.

[0034] In this way, based on the 3D body model resulting from the first process, a 3D body model in the same pose is estimated from the 2D body model of user U1 in a modified pose. This makes it possible to use, for example, the 3D body model of user U1 in a modified pose. This completes the second process. Next, the details of each process will be explained.

[0035] (First process: Details of the 3D body model estimation process) Generally, physical markers are attached directly to a body model to change the pose of the body model, clarify the measurement position of the body model, etc. However, for example, in an environment with a lot of light, the image of the physical markers may become poor and the marker position may not be recognized. For this reason, for example, when attaching markers to multiple locations, it may be necessary to change the type of physical marker or prepare markers that suit the environment.

[0036] Therefore, in the following embodiment, virtual markers are added to the characteristic parts of a specific pose displayed on the terminal. This is expected to improve the estimation accuracy of the corresponding 3D body model. Furthermore, by manipulating the virtual markers, it becomes possible to estimate the 3D body model in a changed pose.

[0037] Fig. 3 is an explanatory diagram for explaining the estimation process of a 3D body model in a changed pose. In Fig. 3, a user U1 in a specific pose is shown on the screen of the user terminal 10. Virtual markers (markers M1 and M2) are also attached to the wrists of the user U1.

[0038] Furthermore, arrows P1 and P2 on the screen indicate the direction of operation for markers M1 and M2. For example, when arrow P1 is operated in the upper left direction, marker M1 moves in the upper left direction in response to the operation. In FIG. 3, the pose changes from a normal posture with hands down to a position with hands outstretched. In FIG. 3, the operation is performed by photographer F1 (not shown) who is photographing user U1.

[0039] The information processing device 100 acquires information within the screen. For example, the information processing device 100 acquires information of the user U1 included within the screen.

[0040] The information processing device 100 receives a designation of a changed pose from the photographer F1 by the photographer F1 adding virtual markers (markers M1 and M2) on the screen and performing an operation.

[0041] 3, the information processing device 100 receives a specification of a changed pose to a state in which both arms are spread horizontally by having the photographer F1 operate the wrists of the user U1 on the screen to add virtual markers (markers M1 and M2), and then operate marker M1 in an upper left direction and simultaneously operate marker M2 in an upper right direction. Note that the pose may be changed in response to an operation on the virtual markers, or the virtual markers may follow the movement of the user U1's body (i.e., in response to an operation on the body), or the virtual markers may follow the movement of the user U1.

[0042] The information processing device 100 estimates a 3D body model in a changed pose state by the second process described below. For example, the information processing device 100 estimates a 3D body model that takes into account the wrist region to which virtual markers (markers M1 and M2) are attached. In this case, for example, the information processing device 100 estimates the corresponding position of the wrist region of the 3D body model from the marker positions of markers M1 and M2, thereby estimating a 3D body model that takes into account the wrist region.

[0043] Although FIG. 3 illustrates an example in which a virtual marker is attached to the wrist, a virtual marker may also be attached to a part that cannot be determined visually. For example, a virtual marker may be attached to a part that is hidden by clothing. For example, a virtual marker may be attached to the "navel." By attaching a virtual marker to the "navel," which cannot be determined visually, and estimating a 3D body model that takes the "navel" into consideration, it becomes possible to accurately estimate the waist part of the 3D body model.

[0044] As a further modification, the assignment of virtual markers is not limited to cases where it is based on appearance judgment, but may also be applied to areas where estimation accuracy is low. For example, virtual markers may be assigned to areas where clothing is loose (areas where sagging occurs). For example, virtual markers may be assigned to the "crotch" or "armpit" areas. By assigning virtual markers to such "crotch" or "armpit" areas where estimation accuracy is low and estimating a 3D body model that takes the "crotch" or "armpit" areas into consideration, accurate estimation of the "crotch" or "armpit" areas of the 3D body model becomes possible.

[0045] Here, a method for adding a virtual marker according to the embodiment will be described. Three methods for adding a virtual marker will be described below as examples, but these are merely examples and are not particularly limited.

[0046] The first type of imprinting is when an instruction point for aligning a predetermined part is clearly indicated on the screen. Fig. 4 is an explanatory diagram (1) for explaining an example of a method for imprinting a virtual marker according to an embodiment.

[0047] 4, a virtual marker is displayed in the center of the screen of the user terminal 10. Simultaneously with the display of the virtual marker, an audio guide is played saying, "Please place your navel on the red mark."

[0048] Here, the user U1 may move relative to the virtual marker displayed on the screen to align it with the position corresponding to the specified part, or the photographer F1 may move the user terminal 10 to align it with the position corresponding to the specified part.

[0049] In either case, a virtual marker is added to a part that is aligned with the virtual marker in the center of the screen. The information processing device 100 then accepts the position where the virtual marker is added as a position corresponding to the predetermined part. In FIG. 4, since the voice guide instructs "navel," the position is accepted as a position corresponding to the "navel" part.

[0050] The second type of annotation is when clothing is used that allows for the estimation of a 3D body model when worn. Such clothing contains map information indicating the location for the estimation of the 3D body model. Therefore, by attaching virtual markers to the clothing, it becomes possible to associate specific body parts with the marker positions.

[0051] 5 is an explanatory diagram (2) for explaining an example of a method for adding a virtual marker according to an embodiment. In FIG. 5, clothing Z1 is used as an example of clothing for which such a 3D body model can be estimated.

[0052] In Fig. 5, as soon as the clothing Z1 is put on, a voice guide saying "Please align your navel with the red mark" is played, as in Fig. 4. The positioning of the virtual marker may be performed by the user U1 or by the photographer F1.

[0053] When the virtual marker is aligned, the information processing device 100 associates the marker position with a predetermined body part and stores the association between the marker position and the predetermined body part. In Fig. 5, the voice guide indicates "navel," so the marker position is associated with the body part of "navel" and is stored.

[0054] By storing the marker position and the "navel" area in association with each other, the information processing device 100 can estimate the "navel" area based on the map information of the clothing Z1 the next time the user U1 wears the clothing Z1, without having to specify it by adding a virtual marker.

[0055] A second variation of annotation is the use of annotations such as stickers that enable 3D body model estimation. Here, the stickers refer to annotations that are different from the conventional physical markers described above. Such annotations include, for example, map information indicating location, and using multiple annotations makes it possible to estimate a 3D body model. For example, by attaching such annotations to clothing, it becomes possible to estimate a 3D body model not only for the special clothing that allows 3D body model estimation as described above, but also for ordinary clothing worn daily.

[0056] The third type of assignment is when the person who assigns the virtual marker (for example, the user U1, the photographer F1, or the recipient of information about the 3D body model) has specialized knowledge about a specific part.

[0057] If the designator has specialized knowledge about a predetermined region, the designation by the designator is assumed to be accurate. When the designator has specialized knowledge about such a predetermined region, the information processing device 100 accepts the designation of a position corresponding to the predetermined region. In other words, the information processing device 100 accepts the designation of a position to which a virtual marker has been added by a designator with specialized knowledge about a predetermined region as a position corresponding to the predetermined region. For example, a designator with specialized knowledge about bone positions may add a virtual marker to the position of a specific bone.

[0058] (Second process: Details of pose change process) In estimating 3D body models, the poses that can be estimated are limited to specific poses such as normal postures, since the entire body needs to be accurately estimated. Furthermore, there is a need for further improvement in the estimation accuracy of specific body parts. Furthermore, when a pose change is required, for example, manual estimation is sometimes required.

[0059] An example of a change pose is a pose while riding a motorcycle. When riding a motorcycle, the lengths of the front and back of the upper body are different from those in a specific pose, so when clothing (such as a jacket) is created to match the specific pose, the length of the clothing may not fit the body. Also, it can be difficult to accurately select materials with different stretch rates for each part of clothing (such as a motorcycle suit) and to select the material area. Therefore, when clothing needs to be created to match a change pose, it is necessary to re-estimate the user's change pose.

[0060] Therefore, in the following embodiment, a 3D body model in a modified pose is estimated from a specific pose. This makes it possible to estimate the size of a desired part in a modified pose without needing data on multiple poses. Note that the following embodiment is not limited to creating clothing that fits a user, but can also be applied to training such as gym, Pilates, and yoga. For example, by estimating the external length of the body and comparing it with the previous estimate, it is possible to determine the effectiveness of training.

[0061] 6 is an explanatory diagram for explaining the pose change process. In the second process, the information processing device 100 associates the specific pose with the changed pose, and estimates the changed pose from the input specific pose.

[0062] The information processing device 100 estimates a 3D body model of the user U1 in a changed pose from a body model (2D body model or 3D body model) of the user U1 in a specific pose.

[0063] In this case, the 3D body model may be estimated using one learning model, or a plurality of learning models may be combined to estimate the 3D body model.

[0064] When making an estimation using one learning model, the information processing device 100 inputs a body model of the subject in a specific pose (the input information may be an image), and estimates the body model of user U1 in an altered pose using the learning model that has been trained to output information about the body model of the subject in an altered pose.

[0065] Here, we will explain the case where estimation is performed by combining multiple learning models. When estimation is performed by combining multiple learning models, two methods are assumed: a method of estimating a 2D body model in a changed pose state from a 2D body model in a specific pose state, and estimating a 3D body model in the changed pose state from the 2D body model in the changed pose state (hereinafter referred to as "first method" where appropriate), and a method of estimating a 3D body model in a specific pose state from the 2D body model in a specific pose state, and estimating a 3D body model in a changed pose state from the 3D body model in the specific pose state (hereinafter referred to as "second method" where appropriate).

[0066] FIG. 7 is an explanatory diagram illustrating the change process according to the first method. In the first method, the information processing device 100 receives a 2D body model of a subject in a specific pose (the input information may be an image), and estimates a 2D body model of the user U1 in the changed pose using a learning model that has been trained to output information about the 2D body model of the subject in the changed pose. In this case, the information processing device 100 may use an image generation AI to estimate the 2D body model of the user U1 in the changed pose. For example, even if the abdomen is not visible in the changed pose, the information processing device 100 may use the image generation AI to estimate a 2D body model in a state in which the abdomen is visible. Furthermore, the information processing device 100 may also estimate a 3D body model of the user U1 in the specific pose in a background process. This allows for comparison with the 3D body model in the changed pose by calculating the amount of change from the 3D body model in the changed pose, as described below.

[0067] The information processing device 100 then inputs a 2D body model of the subject and estimates a 3D body model of user U1 using a learning model that has been trained to output information about a 3D body model of the subject in the same pose. The information processing device 100 inputs the 2D body model of user U1 in a changed pose and estimates a 3D body model of user U1 in the changed pose. Note that the information processing device 100 may estimate the 3D body model of user U1 based on a predetermined rule base, or may estimate the 3D body model of user U1 based on a general conventional method from the image contours. The information processing device 100 may also estimate the 3D body model of user U1 by separating the clothing portion from the non-clothing portion. This allows the information processing device 100 to accurately estimate the 3D body model of user U1 in a changed pose.

[0068] At this time, the information processing device 100 may estimate the 3D body model of the user U1 in the changed pose state by updating the 3D body model in the general changed pose state. For example, the information processing device 100 may estimate the 3D body model of the user U1 in the changed pose state using a learning model that has been trained to output information about the 3D body model of the subject in the changed pose state by updating the 3D body model in the general changed pose state.

[0069] FIG. 8 is an explanatory diagram illustrating the change process according to the second method. In the second method, the information processing device 100 receives a 2D body model of a subject (the input information may be an image), and estimates a 3D body model of the user U1 using a learning model that has been trained to output information about a 3D body model of the subject in the same pose. The information processing device 100 receives a 2D body model of the user U1 in a specific pose and estimates a 3D body model of the user U1 in the specific pose. In this case, the information processing device 100 may estimate the 3D body model of the user U1 based on a predetermined rule base, or may estimate the 3D body model of the user U1 based on a general conventional method from the contours of the image.

[0070] In this case, the information processing device 100 may estimate the 3D body model of the user U1 in a specific pose state by updating the 3D body model in a general-purpose specific pose state. For example, the information processing device 100 may estimate the 3D body model of the user U1 in a specific pose state by using a learning model that has been trained to output information about the 3D body model of the subject in a specific pose state by updating the 3D body model in a general-purpose specific pose state.

[0071] When the information processing device 100 receives a 3D body model of the subject in a specific pose, it estimates the 3D body model of the user U1 in the changed pose using a learning model that has been trained to output information about the 3D body model of the subject in the changed pose. Note that at this time, the information processing device 100 may estimate the 3D body model of the user U1 in the changed pose using a learning model that has been additionally trained with skeletal muscle information of the user U1 (including, for example, information such as the starting point of movement).

[0072] [3. User terminal configuration] Next, the configuration of the user terminal 10 according to the embodiment will be described with reference to Fig. 9. Fig. 9 is a diagram showing an example of the configuration of the user terminal 10 according to the embodiment. As shown in Fig. 9, the user terminal 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14. Note that in the case where the user who is taking a picture of the user whose 3D body model is to be estimated is operating the terminal, the user may be substituted with the photographer and the user terminal with the photographer terminal, etc., as appropriate.

[0073] (Communications Department 11) The communication unit 11 is realized by, for example, a network interface card (NIC), etc. The communication unit 11 is connected to a predetermined network N by wire or wirelessly, and transmits and receives information to and from the information processing device 100, etc., via the predetermined network N.

[0074] (Input section 12) The input unit 12 accepts various operations from the user. For example, the input unit 12 may accept various operations from the user via a display screen using a touch panel function. Alternatively, the input unit 12 may accept various operations from buttons provided on the user terminal 10 or a keyboard or mouse connected to the user terminal 10.

[0075] (Output section 13) The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays information provided from the information processing device 100.

[0076] (Control unit 14) The control unit 14 is, for example, a controller, and is realized by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the user terminal 10 using RAM (Random Access Memory) as a work area. For example, these various programs include application programs installed in the user terminal 10. For example, these various programs include an application program that assigns virtual markers in accordance with user operations. The control unit 14 is also realized by an integrated circuit, such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0077] As shown in FIG. 9, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0078] (Receiving unit 141) The receiving unit 141 receives various information from another information processing device such as the information processing device 100. For example, the receiving unit 141 receives information about a body model of a user estimated by another information processing device such as the information processing device 100. Furthermore, for example, the receiving unit 141 receives information about a body model in which a position estimated by another information processing device such as the information processing device 100 is set as a predetermined part. For example, the receiving unit 141 receives information based on the positional relationship between a predetermined part and another part.

[0079] (Transmitter 142) The transmitting unit 142 transmits various information to other information processing devices such as the information processing device 100. For example, the transmitting unit 142 transmits user operation information. For example, the transmitting unit 142 transmits virtual marker assignment information based on the user's operation. Furthermore, for example, the transmitting unit 142 transmits designation information for a changed pose based on the user's operation.

[0080] 4. Configuration of Information Processing Device Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 10, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing device 100 may also include an input unit (e.g., a keyboard or a mouse) that accepts various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display) that displays various information.

[0081] (Communication unit 110) The communication unit 110 is realized by, for example, a NIC etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the user terminal 10 etc. via the network N.

[0082] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 10 , the storage unit 120 includes a user information storage unit 121 and a learning model storage unit 122.

[0083] The user information storage unit 121 stores user information. For example, the user information storage unit 121 stores information related to a body model of a user. For example, the user information storage unit 121 stores information indicating the physical characteristics of a user. For example, the user information storage unit 121 stores position information of the user's physical characteristic parts. For example, the user information storage unit 121 stores information indicating the association with map information of clothing that can be used to estimate a 3D body model. Here, FIG. 10 shows an example of the user information storage unit 121 according to the embodiment. As shown in FIG. 11, the user information storage unit 121 has items such as "user ID" and "user information."

[0084] "User ID" indicates identification information for identifying a user. "User information" indicates user information. In the example shown in FIG. 11, conceptual information such as "User information #1" and "User information #2" is stored in "User information," but in reality, coordinate information indicating the location of the user's characteristic body parts on the user's body model is stored.

[0085] The learning model storage unit 122 stores learning models. For example, the learning model storage unit 122 stores learning models that estimate various body models. FIG. 12 shows an example of the learning model storage unit 122 according to the embodiment. As shown in FIG. 12, the learning model storage unit 122 has items such as "learning model ID" and "learning model."

[0086] "Learning model ID" indicates identification information for identifying a learning model. "Learning model" indicates a learning model. In the example shown in Figure 12, conceptual information such as "Learning model #1" and "Learning model #2" is stored in "Learning model", but in reality, information on various parameters that make up the learning model is stored.

[0087] (control unit 130) The control unit 130 is a controller, and is realized by, for example, a CPU or an MPU executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also realized by, for example, an integrated circuit such as an ASIC or an FPGA.

[0088] 10, the control unit 130 has an acquisition unit 131, a reception unit 132, a first estimation unit 133, a second estimation unit 134, and a provision unit 135, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 10, and may be any other configuration as long as it performs the information processing described below.

[0089] (Acquisition part 131) The acquisition unit 131 acquires various pieces of information from an external information processing device. The acquisition unit 131 acquires various pieces of information from other information processing devices such as the user terminal 10.

[0090] The acquiring unit 131 acquires various pieces of information from the storage unit 120. The acquiring unit 131 also stores the acquired various pieces of information in the storage unit 120.

[0091] The acquisition unit 131 acquires, for example, operation information of a user. For example, the acquisition unit 131 acquires information on the assignment of a virtual marker based on the operation of the user. For example, the acquisition unit 131 acquires position information designated on a screen that schematically shows the user's body. For example, the acquisition unit 131 acquires position information designated as a position corresponding to a predetermined part on the screen that schematically shows the user's body.

[0092] The acquisition unit 131 also acquires, for example, information about a body model of the user in a predetermined pose, and an image of the user in a predetermined pose.

[0093] (Reception Department 132) The receiving unit 132 receives, for example, a designation of a position corresponding to a predetermined body part. For example, the receiving unit 132 receives a designation of a position corresponding to a predetermined body part on a screen that schematically shows the user's body. For example, the receiving unit 132 receives a designation of a position corresponding to a predetermined body part on content that schematically shows the user's body.

[0094] Furthermore, the receiving unit 132 receives, for example, a designation of a position to which a virtual marker is assigned on content that schematically shows the user's body as a position corresponding to a predetermined body part. For example, the receiving unit 132 receives, for example, a designation of a position to which a virtual marker is assigned on a 3D body model that schematically shows the user's body as a position corresponding to a predetermined body part. For example, the receiving unit 132 receives, for example, a designation of a position to which a virtual marker is assigned on a captured image that schematically shows the user's body as a position corresponding to a predetermined body part.

[0095] The receiving unit 132 also accepts, for example, a designation of a position where a virtual marker is assigned by a user on the screen aligning the position with a virtual marker displayed on a screen that schematically depicts the user's body, as a position corresponding to a predetermined body part. The receiving unit 132 also accepts, for example, a designation of a position where a virtual marker is assigned by a photographer who is photographing the user on the screen aligning the position with a virtual marker displayed on a screen that schematically depicts the user's body, as a position corresponding to a predetermined body part.

[0096] Furthermore, the receiving unit 132 receives a designation by a designator when the designator who designates a position corresponding to a predetermined body part has specialized knowledge about the predetermined body part. For example, the receiving unit 132 receives a designation by a designator when the designator, who is a recipient of information provided by the providing unit 135 described below, has specialized knowledge about the predetermined body part.

[0097] Furthermore, the receiving unit 132 receives, for example, a designation of a position corresponding to a predetermined part where the estimation accuracy of the position of the 3D body model decreases due to wearing clothing.

[0098] (1st estimation part 133) The first estimation unit 133 estimates, for example, a position designated as a position corresponding to a predetermined part. For example, the first estimation unit 133 estimates a position of the user's body model that corresponds to a position designated as a position corresponding to a predetermined part on a screen that schematically shows the user's body. For example, the first estimation unit 133 estimates a position of the user's body model that corresponds to a position designated as a position corresponding to a predetermined part on a screen that schematically shows the user's body.

[0099] Furthermore, the first estimation unit 133 estimates the position corresponding to the predetermined part when the clothes are worn, for example, based on the association with map information of the clothes that can be pre-set for estimating a 3D body model when worn. For example, the first estimation unit 133 estimates the position corresponding to the predetermined part when the clothes are worn, based on the relationship between map information of the clothes that can be pre-set for estimating a 3D body model when worn, and a position specified as the position corresponding to the predetermined part on a screen that schematically shows the user's body.

[0100] Furthermore, the first estimation unit 133 estimates a position corresponding to a predetermined part when the clothes are worn, for example, based on association with map information of the clothes based on annotations attached to the clothes for estimating a body model. For example, the first estimation unit 133 estimates a position corresponding to a predetermined part when the clothes are worn, based on a relationship between map information of the clothes based on annotations attached to the clothes for estimating a body model and a position designated as a position corresponding to the predetermined part on a screen that schematically shows the user's body.

[0101] (Second estimation section 134) The second estimation unit 134 estimates, for example, a body model of the user in a second pose different from the first pose. For example, the second estimation unit 134 estimates a body model including at least information indicating the user's physical characteristics (for example, it may be numerical information indicating coordinates, size, position, or length of the body's external dimension).

[0102] In addition, the second estimation unit 134 estimates the 3D body model of the user in the second pose state using a learning model that has been trained to output information about the 3D body model of the subject in the second pose state when information about the 2D body model of the subject in the first pose state is input, for example.

[0103] Furthermore, the second estimation unit 134 estimates the 2D body model of the user in the second pose state using a learning model that has been trained to output information about the 2D body model of the subject in the second pose state when information about the 2D body model of the subject in the first pose state is input. Note that at this time, in a background process, the second estimation unit 134 may estimate the 3D body model of the user in the first pose state using a learning model that has been trained to output information about the 3D body model of the subject in the first pose state when information about the 2D body model of the subject in the first pose state is input, and after estimating the 3D body model in the second pose state described below, calculate the amount of change and perform a comparison.

[0104] In addition, the second estimation unit 134 estimates the 3D body model of the user in a second pose using a learning model that has been trained to output information about the 3D body model of the subject in the same pose when a 2D body model of the subject is input.

[0105] In addition, the second estimation unit 134 estimates the 3D body model of the user in a first pose using a learning model that has been trained to input information about the subject's 2D body model and output information about the subject's 3D body model in the same pose.

[0106] In addition, the second estimation unit 134 estimates the 3D body model of the user in the second pose state, for example, using a learning model that has been trained to output information about the 3D body model of the subject in the second pose state when the 3D body model of the subject is input.

[0107] Furthermore, the second estimation unit 134 estimates a 3D body model of the user in a second pose from a 3D body model of the user in a first pose, for example, using a learning model that has additionally learned skeletal muscle information. For example, the second estimation unit 134 performs estimation using a learning model that has additionally learned skeletal muscle information including information such as the starting point of movement identified based on the skeletal muscle model. The skeletal muscle model may be a general-purpose learning model or a learning model tailored to each user.

[0108] In addition, the second estimation unit 134 estimates the user's 3D body model using a learning model that has been trained to output information about the subject's 3D body model by updating a pre-set general-purpose 3D body model when information about the subject's 2D body model is input, for example.

[0109] (Provider 135) The providing unit 135 provides, for example, information related to a body model. For example, the providing unit 135 provides information related to the body model by regarding the position estimated by the first estimating unit 133 as a position corresponding to a predetermined part. Furthermore, for example, the providing unit 135 provides information related to the body model estimated by the second estimating unit 134. Furthermore, for example, the providing unit 135 provides information based on the positional relationship between the predetermined part and other parts in order to clarify the position corresponding to the predetermined part.

[0110] [5. Information Processing Flow] Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to Fig. 13 and Fig. 14. Fig. 13 and Fig. 14 are flowcharts (1) and (2) showing the procedure of information processing by the information processing system 1 according to the embodiment.

[0111] 13, the information processing device 100 receives a designation of a position corresponding to a predetermined part on the screen using a virtual marker (step S201). The information processing device 100 estimates a position on the user's 3D body model that corresponds to the position designated on the screen (step S202). The information processing device 100 provides information on the 3D body model, with the estimated position on the user's 3D body model being the position corresponding to the predetermined part (step S203).

[0112] 14, the information processing device 100 acquires information about a 2D body model of a user in a first pose (step S301). The information processing device 100 estimates a 2D body model or a 3D body model of the user in a second pose using the learning model (step S302). The information processing device 100 provides information about the estimated body model (step S303).

[0113] [6. Effects] As described above, the information processing device 100 according to the embodiment includes the receiving unit 132, the first estimating unit 133, and the providing unit 135. The receiving unit 132 receives a designation of a position corresponding to a predetermined part on a screen that schematically shows the user's body. The first estimating unit 133 estimates a position on the user's 3D body model that corresponds to the position designated on the screen. The providing unit 135 provides information related to the 3D body model, with the estimated position on the 3D body model being the position corresponding to the predetermined part.

[0114] This allows the information processing apparatus 100 according to the embodiment to estimate a more accurate 3D body model that takes into account, for example, predetermined parts.

[0115] Furthermore, the accepting unit 132 accepts a designation on content that schematically shows the user's body.

[0116] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, taking into account a predetermined part designated in the content.

[0117] Furthermore, the accepting unit 132 accepts a designation of a position to which a virtual marker is attached on content that schematically shows the user's body as a position corresponding to a predetermined body part.

[0118] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, taking into consideration a predetermined part designated using a virtual marker.

[0119] Furthermore, the receiving unit 132 receives a designation of a position, to which a virtual marker is assigned, in a 3D body model that schematically shows the user's body as a position corresponding to a predetermined part.

[0120] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, by taking into consideration a predetermined part of the 3D body model that is designated using a virtual marker.

[0121] Furthermore, the accepting unit 132 accepts a designation of a position to which a virtual marker is attached on a captured image that schematically shows the user's body as a position corresponding to a predetermined part.

[0122] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, by taking into consideration a predetermined part designated on a captured image using a virtual marker.

[0123] Furthermore, the accepting unit 132 accepts a position on the screen to which a virtual marker is added by the user aligning the position with the virtual marker displayed on the screen as a position corresponding to a predetermined body part.

[0124] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, taking into consideration a predetermined part designated by the user through positioning.

[0125] In addition, the reception unit 132 receives a designation of a position where a virtual marker is added by a photographer photographing the user on the screen aligning the position with the virtual marker displayed on the screen as a position corresponding to a specified body part.

[0126] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, taking into consideration a predetermined part designated by the photographer through positioning.

[0127] Furthermore, the accepting unit 132 accepts a designation by a designator when the designator has specialized knowledge about a predetermined part.

[0128] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, taking into consideration the predetermined parts designated by a designator with specialized knowledge.

[0129] Furthermore, the receiving unit 132 receives a designation by a designator who is a recipient of information provided by the providing unit 135.

[0130] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model, for example, taking into consideration the predetermined body part designated by the designator who is the recipient of the information.

[0131] In addition, the first estimation unit 133 estimates the position when the clothing is worn based on the pre-set clothing map information for the clothing that allows a 3D body model to be estimated when worn, and the pre-associated relationship between the clothing map information and the position specified on the screen.

[0132] As a result, the information processing device 100 according to the embodiment can estimate an accurate 3D body model that takes into account predetermined parts, for example, based on map information of special clothing, without having to specify the predetermined parts every time.

[0133] In addition, the first estimation unit 133 estimates the position when the clothing is worn based on the pre-associated relationship between the clothing's map information, which is based on annotations attached to the clothing for estimating the 3D body model, and the position specified on the screen.

[0134] As a result, the information processing device 100 according to the embodiment can estimate an accurate 3D body model that takes into account specific parts, for example, based on map information of clothing based on attachments, without having to specify the specific parts each time.

[0135] The receiving unit 132 also receives designations corresponding to predetermined parts where the estimation accuracy of the position of the 3D body model decreases due to the wearing of clothing.

[0136] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model that takes into account, for example, certain parts where estimation accuracy is low.

[0137] Furthermore, the first estimation unit 133 estimates a position corresponding to the specified position in the 3D body model corresponding to the user's body.

[0138] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model by, for example, estimating a position of the 3D body model that corresponds to a specified predetermined part.

[0139] Furthermore, the providing unit 135 provides information based on the positional relationship between the predetermined part and other parts in order to clarify the position corresponding to the predetermined part.

[0140] As a result, the information processing apparatus 100 according to the embodiment can, for example, allow the information providing destination to accurately ascertain the position corresponding to the predetermined part.

[0141] As described above, the information processing device 100 according to the embodiment includes the acquisition unit 131, the second estimation unit 134, and the provision unit 135. The acquisition unit 131 acquires an image of the user in a first pose. The second estimation unit 134 estimates a body model of the user in a second pose that is different from the first pose, based on the image acquired by the acquisition unit 131. The provision unit 135 provides information about the body model estimated by the second estimation unit 134.

[0142] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model that takes into account, for example, the size of the state when the body shape is changed.

[0143] Furthermore, the second estimation unit 134 estimates a body model that includes at least information indicating the physical characteristics of the user.

[0144] This allows the information processing apparatus 100 according to the embodiment to estimate a more accurate 3D body model that includes at least information indicating the physical characteristics of the user, for example.

[0145] Furthermore, the second estimating unit 134 estimates a body model that includes at least numerical information indicating the physical characteristics of the user.

[0146] As a result, the information processing apparatus 100 according to the embodiment can estimate a more accurate 3D body model that includes at least numerical information indicating the physical characteristics of the user, for example.

[0147] Furthermore, when an image of the subject is input, the second estimation unit 134 estimates the body model using a learning model that has been trained to output information about the body model of the subject in a second pose.

[0148] As a result, the information processing apparatus 100 according to the embodiment can estimate an accurate body model by using, for example, a predetermined learning model.

[0149] In addition, when the second estimation unit 134 receives an image of the subject, it estimates a 2D body model of the user as a body model using a learning model that has been trained to output information about the 2D body model of the subject in a second pose.

[0150] As a result, the information processing apparatus 100 according to the embodiment can estimate an accurate 2D body model in the second pose by using, for example, a predetermined learning model.

[0151] In addition, when the second estimation unit 134 receives a 2D body model of the subject, it estimates the user's 3D body model using a learning model that has been trained to output information about the subject's 3D body model in the same pose as the 2D body model.

[0152] As a result, the information processing apparatus 100 according to the embodiment can estimate an accurate 3D body model by using, for example, a predetermined learning model.

[0153] Furthermore, when an image of the subject is input, the second estimation unit 134 estimates the 3D body model of the user using a learning model that has been trained to output information about the 3D body model of the subject in the same pose as the image.

[0154] As a result, the information processing apparatus 100 according to the embodiment can estimate an accurate 3D body model by using, for example, a predetermined learning model.

[0155] In addition, when the second estimation unit 134 receives the 3D body model of the subject, it estimates the 3D body model of the user as a body model using a learning model that has been trained to output information about the 3D body model of the subject in a second pose.

[0156] As a result, the information processing apparatus 100 according to the embodiment can estimate an accurate 3D body model in the second pose by using, for example, a predetermined learning model.

[0157] The second estimation unit 134 also performs estimation using a learning model that has learned the skeletal muscle information of the user.

[0158] As a result, the information processing apparatus 100 according to the embodiment can estimate an accurate 3D body model that takes into account, for example, the musculoskeletal information of the user.

[0159] In addition, when the second estimation unit 134 receives an image of the subject, it estimates the user's 3D body model using a learning model that has been trained to output information about the subject's 3D body model by updating a pre-set general-purpose 3D body model based on the image.

[0160] As a result, the information processing apparatus 100 according to the embodiment can more quickly estimate an accurate 3D body model by, for example, updating a general-purpose 3D body model.

[0161] [7. Hardware Configuration] Furthermore, the information processing device 100 (or the user terminal 10 and the information processing device 100) according to the above-described embodiment is realized, for example, by a computer 1000 configured as shown in FIG. 15. FIG. 15 is a hardware configuration diagram showing an example of a computer that realizes the functions of the user terminal 10 and the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0162] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0163] The HDD 1400 stores programs executed by the CPU 1100, data used by these programs, etc. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0164] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0165] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0166] For example, when the computer 1000 functions as the user terminal 10 and the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control units 14 and 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0167] [8. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0168] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0169] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0170] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0171] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0172] 1. Information Processing Systems 10 User terminal 11 Communications Department 12 Input section 13 Output section 14 Control Unit 100 Information processing device 110 Communications Department 120 Storage section 121 User information storage unit 122 Learning model memory unit 130 Control Unit 131 Acquisition Department 132 Reception Department 133 1st estimation part 134 Second estimation part 135 Provision Department 141 Receiving unit 142 Transmitter N Network

Claims

1. a receiving unit that receives designation of a position corresponding to a predetermined part to which a predetermined attribute is assigned on a screen that schematically shows the user's body; an estimation unit that estimates a position of the 3D body model of the user that corresponds to the specified position on the screen; a providing unit that associates the predetermined attribute with the estimated position of the 3D body model and provides information about the 3D body model as a position corresponding to the predetermined part; An information processing device comprising:

2. The estimation unit Clothing for estimating a 3D body model, the position of which is estimated when the clothing is worn based on a pre-associated relationship between map information of the clothing that is pre-set for the clothing and the specified position on the screen.

2. The information processing apparatus according to claim 1, wherein:

3. The reception unit The designation is accepted on content that schematically shows the user's body.

3. The information processing apparatus according to claim 2, wherein:

4. The reception unit and accepting the designation of a position to which a virtual marker is assigned on content that schematically shows the user's body as a position corresponding to the predetermined part.

4. The information processing apparatus according to claim 3,

5. The reception unit A position to which a virtual marker is assigned in a 3D body model that schematically shows the body of the user is accepted as the position corresponding to the predetermined part.

5. The information processing apparatus according to claim 4,

6. The reception unit and accepting the designation of a position to which a virtual marker is assigned as a position corresponding to the predetermined part on a photographed image that schematically shows the body of the user.

5. The information processing apparatus according to claim 4,

7. The reception unit The user aligns the position on the screen with the virtual marker displayed on the screen, and the position to which the virtual marker is assigned is accepted as the position corresponding to the predetermined part.

4. The information processing apparatus according to claim 3,

8. The reception unit A photographer photographing the user on the screen aligns the position of the virtual marker displayed on the screen with the virtual marker, and the position where the virtual marker is assigned is accepted as the position corresponding to the predetermined body part.

4. The information processing apparatus according to claim 3,

9. The reception unit If the person making the designation has specialized knowledge about the predetermined part, the designation by the person is accepted.

2. The information processing apparatus according to claim 1, wherein:

10. The reception unit and accepting the designation by the designator who is the recipient of the information provided by the providing unit.

10. The information processing apparatus according to claim 9,

11. The estimation unit The position is estimated when the clothing is worn based on a pre-associated relationship between map information of the clothing based on annotations attached to the clothing for estimating a 3D body model and the specified position on the screen.

2. The information processing apparatus according to claim 1, wherein:

12. The reception unit The designation corresponding to the predetermined part where the estimation accuracy of the position estimation of the 3D body model decreases due to wearing of the clothing is accepted.

12. The information processing device according to claim 2 or 11.

13. The estimation unit A position corresponding to the specified position is estimated in a 3D body model corresponding to the user's body.

2. The information processing apparatus according to claim 1, wherein:

14. The providing unit To clarify the position corresponding to the predetermined part, information based on the positional relationship between the predetermined part and other parts is provided.

2. The information processing apparatus according to claim 1, wherein:

15. 1. A computer-implemented information processing method, comprising: a receiving step of receiving, on a screen that schematically shows the user's body, a designation of a position corresponding to a predetermined part to which a predetermined attribute has been assigned; an estimation step of estimating a position of the 3D body model of the user that corresponds to the specified position on the screen; a providing step of associating the predetermined attribute with the estimated position of the 3D body model and providing information about the 3D body model as a position corresponding to the predetermined part; An information processing method comprising:

16. a receiving step of receiving, on a screen that schematically shows the user's body, a designation of a position corresponding to a predetermined body part to which a predetermined attribute has been assigned; an estimation step of estimating a position of the 3D body model of the user that corresponds to the specified position on the screen; a provision step of associating the predetermined attribute with the estimated position of the 3D body model and providing information about the 3D body model as a position corresponding to the predetermined part; An information processing program characterized by causing a computer to execute the above.

Images