JP2014180519A - Information processing apparatus, information processing method and program - Google Patents

Abstract

To improve the accuracy of posture search.
An information processing apparatus includes an actual posture information acquisition unit, a bone length acquisition unit, and a database generation unit. The actual posture information acquisition unit 52 acquires user's actual posture information. The bone length acquisition unit 51 acquires a bone length indicating the length of the user's bone. The database generation unit 53 queries the acceleration output from the acceleration sensor attached to the user based on the posture information acquired by the actual posture information acquisition unit 52 and the bone length acquired by the bone length acquisition unit 51. As shown, a posture database 71 for generating user posture information is generated.
[Selection] Figure 3

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program.

  In recent years, a motion capture technique for acquiring an action of a real person has been actively put into practical use. In the field of video creation using computer graphics (Computer Graphics: hereinafter referred to as “CG”), motion capture converts three-dimensional information obtained by photographing a person's movement into digital data, A technology that gives various operations to a computer and analyzes user operations.

  For example, a technique is known in which a plurality of inertial sensors such as an acceleration sensor are fixed to a person's body to perform motion capture, and a database is referred to using acceleration data obtained from the plurality of inertial sensors as a query (for example, Patent Document 1). In these databases, as data about a predetermined person, for example, a user, data on the body motion and acceleration data on the body motion are stored. Therefore, when user acceleration data is input as a query to the database, the posture motion (body motion) corresponding to the input acceleration data is referred to from the database.

Japanese Patent No. 4679967

  However, since the acceleration data of the conventional database including Patent Document 1 depends on the size of the body, when the user's posture search is performed, the accuracy is not necessarily high, and an improvement in the accuracy is desired. .

  The present invention has been made in view of such a situation, and an object thereof is to improve the accuracy of posture search.

In order to achieve the above object, an information processing apparatus of one embodiment of the present invention provides:
Actual posture information acquisition means for acquiring the user's actual posture information;
Bone length acquisition means for acquiring a bone length indicating the bone length of the user;
Based on the posture information acquired by the actual posture information acquisition unit and the bone length acquired by the bone length acquisition unit, the acceleration output from the acceleration sensor attached to the user as a query, Database generating means for generating a database for outputting user posture information;
It is characterized by providing.

  According to the present invention, it is possible to improve the accuracy of posture search.

It is a block diagram which shows the hardware constitutions of the information processing apparatus which concerns on embodiment of this invention. It is a figure which shows the outline of the external appearance of the user used as the object of motion capture to which 5 sensors were stuck. It is a functional block diagram which shows the functional structure for performing a database production | generation process, a conversion function production | generation process, and an attitude | position estimation process among the functional structures of the information processing apparatus of FIG. 4 is a flowchart for explaining a flow of database generation processing executed by an information processing apparatus having the functional configuration of FIG. 3. 4 is a flowchart for explaining a flow of conversion function generation processing executed by an information processing apparatus having the functional configuration of FIG. 3. 4 is a flowchart illustrating a flow of posture estimation processing executed by an information processing apparatus having the functional configuration of FIG. 3.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing a hardware configuration of an information processing apparatus according to an embodiment of the present invention.
The information processing apparatus 1 is configured as a server, for example, and is used for a motion capture technique for acquiring a user's operation.

  The information processing apparatus 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, a sensor unit 16, and an input unit. 17, an output unit 18, a storage unit 19, a communication unit 20, and a drive 21.

  The CPU 11 executes various processes according to a program recorded in the ROM 12 or a program loaded from the storage unit 19 to the RAM 13.

  The RAM 13 appropriately stores data necessary for the CPU 11 to execute various processes.

  The CPU 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output interface 15 is also connected to the bus 14. A sensor unit 16, an input unit 17, an output unit 18, a storage unit 19, a communication unit 20, and a drive 21 are connected to the input / output interface 15.

The sensor unit 16 includes a plurality of sensors that measure the movement of the user's body with a predetermined physical quantity.
In the present embodiment, the sensor unit 16 includes a plurality of triaxial acceleration sensors.
The triaxial acceleration sensor detects a triaxial acceleration component by a piezoresistive type or capacitance type detection mechanism, and outputs acceleration data for each triaxial component representing the detection result. A plurality of these three-axis acceleration sensors are attached in a predetermined direction to a user who is an object of motion capture.

Here, with reference to FIG. 2, a three-axis acceleration sensor attached to a user who is a target of motion capture will be described. Hereinafter, unless otherwise specified, the sensor means a triaxial acceleration sensor.
FIG. 2 is a diagram showing an outline of the appearance of a user who is a target of motion capture, with five sensors attached.
In the example of FIG. 2, five sensors 16-1 to 16-5 constituting the sensor unit 16 (FIG. 1) are attached to each part of the body of the user 100.
Specifically, as shown in FIG. 2A, the sensor 16-1 is at the tip of the left hand of the user 100, the sensor 16-2 is at the tip of the right hand of the user 100, and the sensor 16-3 is at the left foot of the user 100. The sensor 16-4 is attached to the tip of the right leg of the user 100, and the sensor 16-5 is attached to the trunk of the user 100, respectively.
As shown in FIG. 2 (1), at the start of motion capture, the user 100 faces the front side surface of FIG. 2 (1) (hereinafter, this surface is referred to as “front”).
After the start of motion capture, for example, as shown in FIG. 2B, the sensor 16-2 attached to the left hand of the user 100 (the right hand when viewed from the front) slightly moves downward toward the front. Then, the information processing apparatus 1 detects that the left hand has moved downward as an operation of the user 100.
Similarly, after the start of motion capture, for example, as shown in FIG. 2 (3), the sensor 16-1 attached to the left hand of the user 100 and the right hand (left hand when viewed from the front) are attached. When the sensor unit 16-2 moves slightly downward, the information processing apparatus 1 detects that the left hand and the right hand have moved downward as the operation of the user 100. Furthermore, for example, as shown in FIG. 2 (3), when the sensor unit 16-3 attached to the left foot (the right foot toward the front) of the user 100 moves slightly upward, the information processing apparatus 1 As an operation of the user 100, it is detected that the left foot has moved upward.

Returning to FIG. 1, the input unit 17 is configured with various buttons and the like, and inputs various information according to a user's instruction operation.
The output unit 18 includes a display, a speaker, and the like, and outputs images and sounds.

The storage unit 19 is configured by a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various programs such as application programs in addition to various image data.
The communication unit 20 controls communication performed with other devices (not shown) via a network including the Internet.

  A removable medium 31 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately attached to the drive 21. The program read from the removable medium 31 by the drive 21 is installed in the storage unit 19 as necessary. The removable medium 31 can also store various data such as image data stored in the storage unit 19 in the same manner as the storage unit 19.

FIG. 3 is a functional block diagram showing a functional configuration for executing database generation processing, conversion function generation processing, and posture estimation processing, among the functional configurations of the information processing apparatus 1.
The database generation process is one of the pre-processes of motion capture, and refers to a series of processes from acquiring bone length together with a plurality of posture information and generating a posture database using them. The bone length is the length of a bone constituting the skeleton of the person, and indicates the length between the joints constituting the person that is the target of motion capture. The bone length is acquired for each person to be motion-captured because there is an individual difference among individuals.
The conversion function generation process is one of the pre-processing of motion capture, and since an error is included in the acceleration output from the sensor unit 16, a conversion function φ that outputs the acceleration from which the error is removed. A series of processes from generation to storage.
Posture estimation processing is obtained by acquiring acceleration output from sensors (sensors 16-1 to 16-5 in the example of FIG. 2) attached to each part of the user's body that is the target of motion capture. Until the user's posture information is acquired by correcting (converting) the acceleration with the conversion function φ, referring to the posture database using the corrected acceleration as a query, and estimating the current posture of the user based on the posture information A series of processes.

In the CPU 11, when the execution of the database generation process, the conversion function generation process, or the posture estimation process is controlled, the preprocessing unit 41 and the actual operation unit 42 function.
In the pre-processing unit 41, when the execution of the database generation process or the conversion function generation process is mainly controlled, the bone length acquisition unit 51, the actual posture information acquisition unit 52, the database generation unit 53, and the conversion function generation unit 54 And it works.
In the actual operation unit 42, when execution of posture estimation processing is mainly controlled, an acceleration acquisition unit 61, an acceleration correction unit 62, a posture information acquisition unit 63, and a posture estimation unit 64 function.
In addition, a posture database 71 is stored in one area of the storage unit 19, and a conversion function storage unit 72 is provided in another area of the storage unit 19.

The bone length acquisition unit 51 acquires the bone length B ^length ^ of the user who is the target of motion capture in the posture estimation processing when executing the pre-processing database generation processing.
The bone length B ^length ^ acquired by the bone length acquisition unit 51 employs input information based on the user's operation on the input unit 17 in the present embodiment, but is not particularly limited thereto. For example, the bone length acquisition unit 51 acquires various types of information related to the user, specifically, for example, acquires information on a combination of at least one of race, gender, height, age, weight, and the like. The bone length B ^length ^ may be acquired by performing a predetermined calculation based on the calculation.

The actual posture information acquisition unit 52 acquires the posture information of all actual movements of the user with the index t (time t) in time series order when executing the pre-processing database generation processing.
As the name implies, the posture information may be information indicating the instantaneous posture of the person (here, the user) that is the target of motion capture, but in this embodiment, each of the users at time t as an index The joint angle θt ^ is adopted. The joint angle θ ^ is an angle between two bones that expands around each joint of a person. Hereinafter, the joint angle θ is also referred to as “posture θ” as appropriate.

The database generation unit 53 performs motion capture based on the series of time-series postures θ (index) ^ acquired by the actual posture information acquisition unit 52 and the bone length B ^length ^ acquired by the bone length acquisition unit 51. A posture database 71 is generated for a person (here, a user) that is the target of the above.

Specifically, for example, the following equations (1) and (2) are used in generating the posture database.
B ^position ^ = Function (θ ^, B ^length ^) (1)
B ^acc ^ = (d / dt) (d / dt) B ^position ^ + (− G) (2)
In the equation (1), the joint position B ^position ^ is a value in which the positions of all joints are represented by vectors. The joint position B ^position ^ is calculated as an output of a function Function having the posture θ ^ and the bone length (length between joints) B ^length ^ as arguments. The bone length B ^length ^ is a value represented by a vector.
In equation (2), B ^acc ^ is a value representing the acceleration of each joint as a vector, and the second-order time differentiation is applied to the joint position B ^position ^ calculated according to equation (1). Thereafter, the gravity acceleration G is added as the influence of gravity to calculate. The gravitational acceleration G is a factor that mainly affects only the gravitational direction (vertical direction).

The database generation unit 53 includes a bone length B ^length ^ acquired by the bone length acquisition unit 51 and a series of sequences acquired by the actual posture information acquisition unit 52 as basic information of a user who is a target of motion capture in the posture estimation process. A series of joint positions B ^position ^ respectively corresponding to a series of time series attitudes θ (index) are obtained by substituting and calculating time series attitudes θ (index) ^ in the equation (1). Then, the database generation unit 53 assigns the series of joint positions B ^position ^ to the equation (2) and calculates the series of accelerations B ^acc (respectively corresponding to the series of time series postures θ (index). index) ^.
That is, the bone length B ^length ^ and a series of time-series joint angles θ (index) ^ are input as basic information of the user, and the calculation of the formulas (1) and (2) is performed. A series of accelerations B ^acc (index) ^ respectively corresponding to the time-series postures θ (index) ^ are generated.

Then, the database generation unit 53 structures the data so that an (approximate) k nearest neighbor search can be performed on the series of accelerations B ^acc (index) ^.
That is, when the database generation unit 53 inputs the acceleration output from the sensor unit 16 (more precisely, the acceleration converted by the conversion function described later in the present embodiment) as a query, a series of acceleration B ^acc (index) ) ^ (Approximate) k nearest neighbor search, and a database capable of outputting acceleration information B ^acc (index) ^ near the query and corresponding attitude θ ^ (index) is the attitude database 71. And stored in the storage unit 19.

Heretofore, the bone length acquisition unit 51, the actual posture information acquisition unit 52, and the database generation unit 53 that function when the database generation process is executed as one of the pre-processing have been described.
Next, the conversion function generation unit 54 that functions when the conversion function generation process is executed as another pre-process will be described.

  The conversion function generation unit 54 generates a conversion function φ (G) for converting (correcting) the acceleration G output from the sensor unit 16 into an ideal acceleration G ′.

Hereinafter, an example of a method for generating the conversion function φ will be described.
A user who is a target of motion capture in the posture estimation process enters a stationary state at the reference posture at an arbitrary timing before the posture estimation process is executed.
Here, the reference posture refers to a posture in which the axes of sensors (sensors 16-1 to 16-5 in the example of FIG. 2) attached to the user's limbs are parallel to the gravity axis. For example, a state where the user continuously takes a posture in which the axes of the bones of the limbs are parallel to the direction of gravity corresponds to a stationary state in the reference posture.
Sensors (sensors 16-1 to 16-5 in the example of FIG. 2) are attached to the user's limbs that are stationary in the reference posture, and the vector value output from the sensor in this state is the acceleration G. .
In addition, when the skeleton data used in the posture database 71 is a vector value output from a sensor virtually attached to the limb when stationary in a reference posture, the ideal acceleration G ′ And
The conversion function generation unit 54 obtains a conversion function φ () that satisfies the following expression (3). In this embodiment, a quaternion is used as the conversion function φ ().
G ′ = φ (G) (3)
If this conversion function φ () is used during the execution of the posture estimation process described later, the actual output data from the sensor is converted to a value closer to the posture database 71, which makes it possible to accurately estimate the posture. .

Furthermore, a specific example of a method for generating the conversion function φ will be described below.
Here, as shown in FIG. 2, it is assumed that the Y-axis of the sensor is set to be substantially parallel to the vertical direction, and the X-axis and the Z-axis are set to be substantially parallel to the horizontal direction. At this time, ideally, only the output of the Y axis parallel to the gravity direction (vertical direction) of the sensor is “1G”, and the outputs of the X axis and the Y axis are “0”.
That is, the ideal acceleration G ′ = (x, y, z) = (0, 1G, 0). However, since the sensor is actually set to be inclined with respect to the user's bone, ideal acceleration G ′ = (Δx, y, Δz).
The conversion function generator 54 obtains a conversion function φ () that satisfies G ′ = φ (G). In this embodiment, a quaternion is used as the conversion function φ (). This quaternion is represented by an angle axis expression of the rotation axis R = (− Δx, 0, Δz) and the rotation angle θ = atan (√ (Δx ² + Δz ² ) / y).
The conversion function generation unit 55 stores the conversion function φ () generated in this way in the conversion function storage unit 72.

The preprocessing unit 41 that functions during the preprocessing, specifically, the bone length acquisition unit 51, the actual posture information acquisition unit 52, the database generation unit 53, and the conversion function generation unit 54 has been described.
Next, the actual operation unit 42 that functions in the posture estimation process in which motion capture is performed, specifically, the acceleration acquisition unit 61, the acceleration correction unit 62, the posture information acquisition unit 63, and the posture estimation unit 64 will be described. .

  The acceleration acquisition unit 61 acquires the acceleration A output from a sensor (sensors 16-1 to 16-5 in the example of FIG. 2) attached to a user who is a target of motion capture.

The acceleration correction unit 62 corrects the acceleration A acquired by the acceleration acquisition unit 61 using the conversion function φ stored in the conversion function storage unit 72.
Specifically, the acceleration correction unit 62 uses the acceleration A acquired by the acceleration acquisition unit 61 as an input parameter for the conversion function φ stored in the conversion function storage unit 72 to perform calculation, thereby performing post-conversion The acceleration A ′ = (φ) (after correction) is acquired.
Further, the acceleration correction unit 62 performs filtering on the converted acceleration A ′ to obtain the converted acceleration A ″ = Filter (A ′) from which noise has been removed. Here, Filter () indicates a low-pass filter.

The posture information acquisition unit 63 refers to the posture database 71 using the converted acceleration A ″ acquired by the acceleration correction unit 62 as a query.
That is, the posture information acquisition unit 63 performs a k nearest neighbor search on the converted acceleration A ″ based on the posture database 71, and postures θ1 to θ1 corresponding to the nearest neighbors of the acceleration data At in the posture database 71. Obtain θk.

  The posture estimation unit 64 estimates the current posture and action recognition of the user based on the postures θ1 to θk acquired by the posture information acquisition unit 63.

Next, a database generation process executed by the information processing apparatus 1 having the functional configuration shown in FIG. 3 will be described with reference to FIG.
FIG. 4 is a flowchart for explaining the flow of database generation processing executed by the information processing apparatus 1 having the functional configuration of FIG.

  The database generation process is started at an arbitrary timing before the motion capture (posture estimation process) is executed, and the following series of processes is executed.

In step S11, the bone length acquisition unit 51 acquires the user's bone length B ^length ^.

  In step S12, the actual posture information acquisition unit 52 acquires a series of time-series postures θ ^ of the user.

In step S13, the database generation unit 53 assigns the user's bone length B ^length ^ and the continuous time series attitude θ ^ to the above-described equation (1) and calculates, thereby calculating a series of time series attitudes θ. A series of joint positions B ^position ^ corresponding to (index) is calculated.

In step S <b ^> 14, the database generation unit 53 assigns a series of joint positions B ^position ^ to the above-described equation (2) and performs a calculation, whereby a series of accelerations respectively corresponding to a series of time series posture θ (index). B ^acc (index) ^ is calculated.

In step S ^< b ^> 15, the database generation unit 53 generates a posture database 71 using a series of accelerations B ^acc (index) ^.
When the posture database 71 is stored in the storage unit 19, the database generation process ends.

Next, a conversion function generation process executed by the information processing apparatus 1 having the functional configuration shown in FIG. 3 will be described with reference to FIG.
FIG. 5 is a flowchart for explaining the flow of conversion function generation processing executed by the information processing apparatus 1 having the functional configuration of FIG.

  The conversion function generation process is started at an arbitrary timing before the motion capture (posture estimation process) is executed, and the following series of processes is executed.

  In step S31, the conversion function generating unit 54 acquires the acceleration G in the user's reference posture, that is, the acceleration G output from the sensor.

In step S <b> 32, the conversion function generation unit 54 generates a conversion function φ () that satisfies G ′ = φ (G) in an ideal reference posture based on the acceleration G.
When the conversion function () is stored in the storage unit 19, the conversion function generation process ends.

Next, with reference to FIG. 6, the posture estimation process executed by the information processing apparatus 1 having the functional configuration shown in FIG. 3 will be described.
FIG. 6 is a flowchart illustrating the flow of posture estimation processing executed by the information processing apparatus 1 having the functional configuration of FIG.

  In the posture estimation process, a predetermined operation on the input unit 17 is performed in a state where sensors (sensors 16-1 to 16-5 in the example of FIG. 2) are attached to each part of the body of the user to be a target of motion capture. The process is started when triggered by the above, and the following series of processes is executed.

  In step S51, the acceleration acquisition unit 61 acquires the acceleration A from a sensor attached to the user.

  In step S52, the acceleration correction unit 62 acquires the converted acceleration A ′ = φ (A) by substituting the acceleration data A acquired in the process of step S31 into the conversion function φ () and performing the calculation. .

  In step S53, the acceleration correction unit 62 performs a filtering process on the converted acceleration A ′ acquired in the process of step S52, thereby removing the converted acceleration A ″ = Filter (A ') Get.

  In step S54, the posture information acquisition unit 63 refers to the posture database 71 using the acceleration A ″ acquired in the process of step S53 as a query.

  In step S 55, the posture information acquisition unit 63 performs a k nearest neighbor search on the converted acceleration A ″ based on the posture database 71, and the posture θ 1 corresponding to the posture and the nearest neighbor of the acceleration At in the database 71. Obtain ~ θk.

  In step S56, the posture estimation unit 64 estimates the current posture based on the postures θ1 to θk acquired in the process of step S55. When this process ends, the posture estimation process ends.

As described above, the information processing apparatus 1 of this embodiment includes the actual posture information acquisition unit 52, the bone length acquisition unit 51, and the database generation unit 53.
The actual posture information acquisition unit 52 acquires user's actual posture information.
The bone length acquisition unit 51 acquires the user's bone length.
The database generation unit 53 generates a posture database 71 based on the posture information acquired by the actual posture information acquisition unit 52 and the bone length information acquired by the bone length acquisition unit 51.
Thus, since the user's bone length is input when generating the posture database 71, the acceleration data in the posture database 71 is adapted to the user. As a result, a posture similar to an actual posture can be accurately estimated based on the posture database 71 regardless of the skeleton difference in which there are individual differences between individuals, and as a result, the accuracy of posture search can be improved.
More specifically, since the size of the skeleton varies among individuals, the length of bones constituting the skeleton, that is, the bone length, is different for each person.
In this regard, the acceleration data in the database including the body posture information depends on the size of the user's body. In conventional databases, the bone length of the user is often different from the bone length in the database used as a reference for generating acceleration data. In such a case, it is difficult to obtain a similar posture motion. Therefore, the accuracy of posture search is lowered.
On the other hand, in the information processing apparatus 1 according to the present embodiment, the posture database 71 is generated in consideration of the user's bone length, so that the user's bone length and the bone length in the posture database 71 are slid. As a result, the accuracy of posture search can be improved.

In addition, the information processing apparatus 1 according to the present embodiment further includes a conversion function generation unit 54.
The conversion function generation unit 54 generates a conversion function φ () for converting the output value of the sensor based on the acceleration output from the sensor attached to the user who takes the reference posture and the ideal acceleration. can do.
Here, the waveform of the acceleration data changes depending on the mounting direction of the sensor to the user. For this reason, there are many cases in which there is a difference between the orientation of the sensor virtually attached to the interior of the conventional database and the orientation of the sensor actually attached to the user. In this case, an error occurs between the acceleration in the conventional database and the actual acceleration output from the sensor. As a result, it becomes difficult to obtain a highly accurate posture action similar to an actual posture based on a conventional database, and the accuracy of posture search is lowered.
As a countermeasure, it is possible to accurately mount the sensor in a predetermined direction. However, it is practically difficult to accurately mount the sensor. The bones of the human skeleton model are treated as straight lines, but the actual human body is rounded, and it is practically difficult to fix a large number of sensors along the bones. Therefore, it is not realistic to take this measure.
On the other hand, in the information processing apparatus 1 of the present embodiment, the output value of the sensor is converted based on the acceleration output from the sensor attached to the user who takes the reference posture and the ideal acceleration. A conversion function φ () can be used. Thereby, the error which arises with the attachment of the acceleration sensor to the user can be reduced. In other words, the acceleration in the posture database 71 and the actual acceleration output from the sensor are matched, and the accuracy of posture search can be improved regardless of the direction in which the sensor is attached to the user.

In addition, the information processing apparatus 1 according to the present embodiment further includes an acceleration correction unit 62 and an attitude information acquisition unit 63.
The acceleration correction unit 62 corrects the acceleration output from the sensor attached to the user using the conversion function φ ().
The posture information acquisition unit 63 acquires the posture information of the user by referring to the posture database 71 using the corrected acceleration as a query.
This makes it possible to easily realize a posture search with improved accuracy.

In addition, the acceleration correction unit of the information processing apparatus 1 according to the present embodiment further corrects the acceleration corrected using the conversion function by performing a filter process.
That is, the acceleration data actually output from the sensor includes noise, and conventionally, the acceleration data waveform in the database is often different from the waveform, and the accuracy of posture search has deteriorated.
On the other hand, in the present embodiment, noise is removed by performing the filtering process, and thus the corrected acceleration after noise removal approaches the acceleration waveform in the database. The accuracy can be improved.

In addition, the bone length acquisition unit 51 of the information processing apparatus 1 according to the present embodiment obtains information on a combination of at least one of the race, sex, height, age, and weight of the user, and uses the information. The bone length is obtained by performing the above operation.
Thereby, a bone length appropriate for at least one combination of race, gender, height, age, and weight is acquired, and the posture database 71 is generated. Therefore, when a person corresponding to at least one of race, gender, height, age, and weight is a target of motion capture, a posture similar to an actual posture is accurately estimated based on the posture database 71. Is done. That is, the accuracy of posture search can be improved.

  In addition, this invention is not limited to the above-mentioned embodiment, The deformation | transformation in the range which can achieve the objective of this invention, improvement, etc. are included in this invention.

  In the above-described embodiment, the sensor 16-1 is at the tip of the left hand of the user 100, the sensor 16-2 is at the tip of the right hand of the user 100, the sensor 16-3 is at the tip of the left foot of the user 100, and the sensor 16-4 is The sensor 16-5 is attached to the tip of the right foot of the user 100 on the trunk of the user 100, but is not limited thereto. That is, the number of sensors and the sticking location are not particularly limited.

  In the above-described embodiment, the motion capture is described as an example, but it can also be used for other purposes such as tracking of a moving object.

In the above-described embodiment, the information processing apparatus 1 to which the present invention is applied has been described using a personal computer as an example, but is not particularly limited thereto.
For example, the present invention can be applied to general electronic devices having an information processing function. Specifically, for example, the present invention can be applied to a notebook personal computer, a digital camera, a television receiver, a video camera, a portable navigation device, a mobile phone, a smartphone, a portable game machine, and the like.

The series of processes described above can be executed by hardware or can be executed by software.
In other words, the functional configuration of FIG. 3 is merely an example, and is not particularly limited. That is, it is sufficient that the information processing apparatus 1 has a function capable of executing the above-described series of processing as a whole, and what functional block is used to realize this function is not particularly limited to the example of FIG. .
In addition, one functional block may be constituted by hardware alone, software alone, or a combination thereof.

When a series of processing is executed by software, a program constituting the software is installed on a computer or the like from a network or a recording medium.
The computer may be a computer incorporated in dedicated hardware. The computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose personal computer.

  The recording medium including such a program is not only constituted by the removable medium 31 of FIG. 1 distributed separately from the apparatus main body in order to provide the program to the user, but also in a state of being incorporated in the apparatus main body in advance. It is comprised with the recording medium etc. which are provided in this. The removable medium 31 is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, a magneto-optical disk, or the like. The optical disk is composed of, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versatile Disk), or the like. The magneto-optical disk is configured by an MD (Mini-Disk) or the like. In addition, the recording medium provided to the user in a state of being preliminarily incorporated in the apparatus main body includes, for example, the ROM 12 in FIG. 1 in which a program is recorded, the hard disk included in the storage unit 19 in FIG.

  In the present specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in time series along the order, but is not necessarily performed in time series, either in parallel or individually. The process to be executed is also included.

  As mentioned above, although several embodiment of this invention was described, these embodiment is only an illustration and does not limit the technical scope of this invention. The present invention can take other various embodiments, and various modifications such as omission and replacement can be made without departing from the gist of the present invention. These embodiments and modifications thereof are included in the scope and gist of the invention described in this specification and the like, and are included in the invention described in the claims and the equivalents thereof.

The invention described in the scope of claims at the beginning of the filing of the present application will be appended.
[Appendix 1]
Actual posture information acquisition means for acquiring the user's actual posture information;
Bone length acquisition means for acquiring a bone length indicating the bone length of the user;
Based on the posture information acquired by the actual posture information acquisition unit and the bone length acquired by the bone length acquisition unit, the acceleration output from the acceleration sensor attached to the user as a query, Database generating means for generating a database for outputting user posture information;
An information processing apparatus comprising:
[Appendix 2]
A conversion function generating means for generating a conversion function for converting an output value of the acceleration sensor based on an acceleration output from the acceleration sensor attached to the user taking a reference posture and an ideal acceleration;
The information processing apparatus according to appendix 1, further comprising:
[Appendix 3]
Acceleration correction means for correcting the acceleration output from the acceleration sensor attached to the user using the conversion function generated by the conversion function generation means;
Attitude information acquisition means for acquiring attitude information of the user by referring to the database generated by the database generation means using the acceleration corrected by the acceleration correction means as a query;
The information processing apparatus according to appendix 2, further comprising:
[Appendix 4]
The acceleration correction means further corrects the acceleration corrected using the conversion function by performing a filtering process.
The information processing apparatus according to supplementary note 3, wherein
[Appendix 5]
The bone length acquisition means obtains information on a combination of at least one of race, gender, height, age, and weight for the user, and executes a predetermined calculation using the information to obtain the bone The information processing apparatus according to any one of supplementary notes 1 to 4, wherein a length is acquired.
[Appendix 6]
An information processing method executed by an information processing apparatus,
An actual posture information acquisition step for acquiring user's actual posture information;
A bone length acquisition step of acquiring a bone length indicating the length of the bone of the user;
Based on the posture information acquired in the actual posture information acquisition step and the bone length acquired in the bone length acquisition step, the acceleration output from the acceleration sensor attached to the user as a query, A database generation step of generating a database for outputting user posture information, and an information processing method comprising:
[Appendix 7]
Computer
Real posture information acquisition means for acquiring user's actual posture information;
Bone length acquisition means for acquiring a bone length indicating the bone length of the user;
Based on the posture information acquired by the actual posture information acquisition unit and the bone length acquired by the bone length acquisition unit, the acceleration output from the acceleration sensor attached to the user as a query, Database generating means for generating a database for outputting user posture information;
A program characterized by functioning as

  DESCRIPTION OF SYMBOLS 1 ... Information processing apparatus, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... Bus, 15 ... Input / output interface, 16 ... Sensor part, 17 ... Input unit 18 ... Output unit 19 ... Storage unit 20 ... Communication unit 21 ... Drive 31 ... Removable media 41 ... Pre-processing unit 42 ... Actual operation unit 51 ... Bone length acquisition unit 52 ... Actual posture information acquisition unit 53 ... Database generation unit 54 ... Conversion function generation unit 61 ... Acceleration acquisition unit 62 ..Acceleration correction unit, 63 ... posture information acquisition unit, 64 ... posture estimation unit, 71 ... posture database, 72 ... conversion function storage unit

Claims (7)

Actual posture information acquisition means for acquiring the user's actual posture information;
Bone length acquisition means for acquiring a bone length indicating the bone length of the user;
Based on the posture information acquired by the actual posture information acquisition unit and the bone length acquired by the bone length acquisition unit, the acceleration output from the acceleration sensor attached to the user as a query, Database generating means for generating a database for outputting user posture information;
An information processing apparatus comprising: A conversion function generating means for generating a conversion function for converting an output value of the acceleration sensor based on an acceleration output from the acceleration sensor attached to the user taking a reference posture and an ideal acceleration;
The information processing apparatus according to claim 1, further comprising: Acceleration correction means for correcting the acceleration output from the acceleration sensor attached to the user using the conversion function generated by the conversion function generation means;
Attitude information acquisition means for acquiring attitude information of the user by referring to the database generated by the database generation means using the acceleration corrected by the acceleration correction means as a query;
The information processing apparatus according to claim 2, further comprising: The acceleration correction means further corrects the acceleration corrected using the conversion function by performing a filtering process.
The information processing apparatus according to claim 3. The bone length acquisition means obtains information on a combination of at least one of race, gender, height, age, and weight for the user, and executes a predetermined calculation using the information to obtain the bone The information processing apparatus according to claim 1, wherein a length is acquired. An information processing method executed by an information processing apparatus,
An actual posture information acquisition step for acquiring user's actual posture information;
A bone length acquisition step of acquiring a bone length indicating the length of the bone of the user;
Based on the posture information acquired in the actual posture information acquisition step and the bone length acquired in the bone length acquisition step, the acceleration output from the acceleration sensor attached to the user as a query, A database generation step for generating a database for outputting user posture information;
An information processing method comprising: Computer
Real posture information acquisition means for acquiring user's actual posture information;
Bone length acquisition means for acquiring a bone length indicating the bone length of the user;
Based on the posture information acquired by the actual posture information acquisition unit and the bone length acquired by the bone length acquisition unit, the acceleration output from the acceleration sensor attached to the user as a query, Database generating means for generating a database for outputting user posture information;
A program characterized by functioning as

Images