WO2022168428A1 - 情報処理方法、情報処理装置およびプログラム - Google Patents
情報処理方法、情報処理装置およびプログラム Download PDFInfo
- Publication number
- WO2022168428A1 WO2022168428A1 PCT/JP2021/044934 JP2021044934W WO2022168428A1 WO 2022168428 A1 WO2022168428 A1 WO 2022168428A1 JP 2021044934 W JP2021044934 W JP 2021044934W WO 2022168428 A1 WO2022168428 A1 WO 2022168428A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- feature amount
- posture
- data
- information processing
- unit
- Prior art date
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 81
- 238000003672 processing method Methods 0.000 title claims abstract description 40
- 230000033001 locomotion Effects 0.000 claims abstract description 147
- 230000036544 posture Effects 0.000 claims description 100
- 238000000605 extraction Methods 0.000 claims description 43
- 238000012545 processing Methods 0.000 claims description 35
- 238000000034 method Methods 0.000 claims description 29
- 239000000284 extract Substances 0.000 claims description 22
- 238000005516 engineering process Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 description 45
- 230000006870 function Effects 0.000 description 45
- 238000010586 diagram Methods 0.000 description 44
- 238000012986 modification Methods 0.000 description 20
- 230000004048 modification Effects 0.000 description 20
- 238000004891 communication Methods 0.000 description 19
- 238000012790 confirmation Methods 0.000 description 10
- 210000000988 bone and bone Anatomy 0.000 description 7
- 241000282412 Homo Species 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241001465754 Metazoa Species 0.000 description 2
- 210000003423 ankle Anatomy 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 210000000707 wrist Anatomy 0.000 description 2
- OHVLMTFVQDZYHP-UHFFFAOYSA-N 1-(2,4,6,7-tetrahydrotriazolo[4,5-c]pyridin-5-yl)-2-[4-[2-[[3-(trifluoromethoxy)phenyl]methylamino]pyrimidin-5-yl]piperazin-1-yl]ethanone Chemical class N1N=NC=2CN(CCC=21)C(CN1CCN(CC1)C=1C=NC(=NC=1)NCC1=CC(=CC=C1)OC(F)(F)F)=O OHVLMTFVQDZYHP-UHFFFAOYSA-N 0.000 description 1
- JQMFQLVAJGZSQS-UHFFFAOYSA-N 2-[4-[2-(2,3-dihydro-1H-inden-2-ylamino)pyrimidin-5-yl]piperazin-1-yl]-N-(2-oxo-3H-1,3-benzoxazol-6-yl)acetamide Chemical compound C1C(CC2=CC=CC=C12)NC1=NC=C(C=N1)N1CCN(CC1)CC(=O)NC1=CC2=C(NC(O2)=O)C=C1 JQMFQLVAJGZSQS-UHFFFAOYSA-N 0.000 description 1
- HFGHRUCCKVYFKL-UHFFFAOYSA-N 4-ethoxy-2-piperazin-1-yl-7-pyridin-4-yl-5h-pyrimido[5,4-b]indole Chemical compound C1=C2NC=3C(OCC)=NC(N4CCNCC4)=NC=3C2=CC=C1C1=CC=NC=C1 HFGHRUCCKVYFKL-UHFFFAOYSA-N 0.000 description 1
- WTFUTSCZYYCBAY-SXBRIOAWSA-N 6-[(E)-C-[[4-[2-(2,3-dihydro-1H-inden-2-ylamino)pyrimidin-5-yl]piperazin-1-yl]methyl]-N-hydroxycarbonimidoyl]-3H-1,3-benzoxazol-2-one Chemical compound C1C(CC2=CC=CC=C12)NC1=NC=C(C=N1)N1CCN(CC1)C/C(=N/O)/C1=CC2=C(NC(O2)=O)C=C1 WTFUTSCZYYCBAY-SXBRIOAWSA-N 0.000 description 1
- DFGKGUXTPFWHIX-UHFFFAOYSA-N 6-[2-[4-[2-(2,3-dihydro-1H-inden-2-ylamino)pyrimidin-5-yl]piperazin-1-yl]acetyl]-3H-1,3-benzoxazol-2-one Chemical compound C1C(CC2=CC=CC=C12)NC1=NC=C(C=N1)N1CCN(CC1)CC(=O)C1=CC2=C(NC(O2)=O)C=C1 DFGKGUXTPFWHIX-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
- A61B5/1122—Determining geometric values, e.g. centre of rotation or angular range of movement of movement trajectories
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1123—Discriminating type of movement, e.g. walking or running
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
- A61B5/744—Displaying an avatar, e.g. an animated cartoon character
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/04815—Interaction with a metaphor-based environment or interaction object displayed as three-dimensional, e.g. changing the user viewpoint with respect to the environment or object
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/80—2D [Two Dimensional] animation, e.g. using sprites
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
- A61B2560/02—Operational features
- A61B2560/0223—Operational features of calibration, e.g. protocols for calibrating sensors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6814—Head
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6823—Trunk, e.g., chest, back, abdomen, hip
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6825—Hand
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6829—Foot or ankle
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P21/00—Testing or calibrating of apparatus or devices covered by the preceding groups
Definitions
- the present disclosure relates to an information processing method, an information processing device, and a program.
- motion capture technology for acquiring motion information that indicates user motion has been actively developed.
- Acquired motion information is used, for example, in sports to improve form, or in applications such as VR (Virtual Reality) or AR (Augmented Reality).
- VR Virtual Reality
- AR Augmented Reality
- an avatar image imitating the movement of the user is generated, and the avatar image is distributed.
- Patent Literature 1 discloses a motion capture technique realized by a sensor system. Note that the motion information is continuous time-series data of posture information indicating the posture of the user at one time.
- the acquired posture information may be inaccurate.
- inaccurate posture information is acquired when a sensor worn by the user is dropped or displaced.
- the accuracy of posture information can be degraded due to camera misalignment and drift.
- the application of motion capture technology is, for example, generation of avatar images, there is concern that avatar images may be generated with inappropriate postures or movements.
- the present disclosure proposes a new and improved information processing method, information processing apparatus, and program capable of coping with the generation of inappropriate posture information.
- acquiring posture information indicating a posture of a moving body extracting feature amounts from the posture information at one point in time or at a plurality of points in time, and extracting feature amounts, which are the extracted feature amounts, determining whether or not the extracted feature amount is included in the set range in the feature amount space; obtaining data as a quantity, and using the used feature quantity to generate data indicative of posture or movement.
- a posture information acquisition unit that acquires posture information indicating a posture of a moving body, a feature quantity extraction unit that extracts a feature quantity from the posture information at one time point or a plurality of time points, and the feature quantity a judging unit for judging whether or not the extracted feature amount, which is the feature amount extracted by the extracting unit, is included in a set range in the feature amount space; and the judgment unit if the extracted feature amount is not included in the set range.
- a data generation unit that generates data indicating a posture or a motion having a feature amount included in the set range based on the determination by the above.
- the computer includes a posture information acquisition unit that acquires posture information indicating a posture of a moving body, a feature amount extraction unit that extracts a feature amount from the posture information at one time point or at a plurality of time points, a judgment unit for judging whether or not the extracted feature amount, which is the feature amount extracted by the feature amount extraction unit, is included in a set range in the feature amount space;
- a program is provided for functioning as a data generation unit that generates data indicating a posture or movement having a feature amount included in the set range based on the determination by the determination unit.
- FIG. 1 is an explanatory diagram showing an information processing system according to an embodiment of the present disclosure
- FIG. 4 is an explanatory diagram showing a specific example of an avatar video V displayed on a viewing user terminal 40
- FIG. 2 is an explanatory diagram showing the configuration of a distribution user terminal 20 according to an embodiment of the present disclosure
- FIG. FIG. 4 is an explanatory diagram showing functions of a base tool 250
- FIG. 4 is an explanatory diagram showing a specific example of generation of raw skeleton data
- FIG. 11 is an explanatory diagram showing a specific example of corrected skeleton data generated by a data correction unit 258
- 3 is an explanatory diagram showing functions of an application unit 260
- FIG. 10 is a flow chart showing a first example of registering an additional usage range
- FIG. 10 is a flow chart showing a first example of registering an additional usage range
- FIG. 11 is a flow chart showing a second registration example of an additional usage range; FIG. FIG. 11 is a flow chart showing a third registration example of an additional usage range; FIG. FIG. 11 is an explanatory diagram showing a specific example of a pose selection screen; FIG. 10 is an explanatory diagram showing an example of a display screen for distribution users; FIG. 10 is an explanatory diagram showing an example of a display screen for distribution users; FIG.
- Skeleton data expressed by a skeleton structure representing the structure of the body, for example.
- Skeleton data includes information about parts and bones, which are line segments connecting parts.
- the parts in the skeleton structure correspond to, for example, terminal parts and joint parts of the body.
- the bones in the skeleton structure can correspond to, for example, human bones, but the positions and numbers of the bones do not necessarily match the actual human skeleton.
- the position of parts in skeleton data can be obtained by various motion capture technologies.
- a camera-type technology that attaches a marker to each part of the body and acquires the position of the marker using an external camera or the like, or a motion sensor attached to the part of the body, and the sensor data acquired by the motion sensor
- sensor-based technologies that acquire the position information of motion sensors based on.
- time-series data of skeleton data is used for form improvement in sports, and for applications such as VR (Virtual Reality) or AR (Augmented Reality).
- time-series data of skeleton data is used to generate an avatar image imitating a user's movement, and the avatar image is distributed.
- an embodiment of the present disclosure a configuration example of an information processing system that generates skeleton data using a motion sensor and distributes an avatar video based on the skeleton data will be described.
- an embodiment of the present disclosure is applicable to other motion capture techniques and other applications as well.
- humans are mainly described below as an example of a moving object, the embodiments of the present disclosure are similarly applicable to other moving objects such as animals and robots.
- FIG. 1 is an explanatory diagram showing an information processing system according to an embodiment of the present disclosure.
- an information processing system according to an embodiment of the present disclosure has six sensor devices 10A-10F, a distribution user terminal 20, a distribution server 30 and a viewing user terminal .
- User U1 shown in FIG. 1 is a distribution user who distributes avatar videos, and users U2 and U3 are viewing users who view avatar videos.
- Network 12 is a wired or wireless transmission path for information transmitted from devices connected to network 12 .
- the network 12 may include a public line network such as the Internet, a telephone line network, a satellite communication network, various LANs (Local Area Networks) including Ethernet (registered trademark), WANs (Wide Area Networks), and the like.
- the network 12 may also include a dedicated line network such as IP-VPN (Internet Protocol-Virtual Private Network).
- the sensor device 10 includes an inertial sensor (IMU: Inertial Measurement Unit) such as an acceleration sensor that acquires acceleration and a gyro sensor (angular velocity sensor) that acquires angular velocity. )including.
- IMU Inertial Measurement Unit
- the sensor device 10 may also include sensors such as a geomagnetic sensor, an ultrasonic sensor, and an atmospheric pressure sensor.
- the sensor devices 10A to 10F are desirably attached to reference joints of the body (for example, the waist and head) or near extremities of the body (wrists, ankles, head, etc.).
- the sensor device 10A is worn on the waist of the distribution user U1
- the sensor devices 10B and 10E are worn on the wrists
- the sensor devices 10C and 10D are worn on the ankles
- the sensor device 10F is worn on the head.
- the part of the body to which the sensor device 10 is attached may also be referred to as the attachment part.
- the number of sensor devices 10 and mounting positions are not limited to the example shown in FIG. .
- Such a sensor device 10 acquires the acceleration or angular velocity of the mounting site as sensor data, and transmits the sensor data to the delivery user terminal 20.
- the distribution user terminal 20 is an example of an information processing device used by the distribution user U1.
- the distribution user terminal 20 receives the sensor data from the sensor device 10, and uses the received sensor data to generate an avatar image of the distribution user U1.
- the delivery user terminal 20 acquires mounting site information indicating the position and orientation of each mounting site based on the sensor data, and based on the mounting site information, position information and position information of each site in the skeleton structure. Generate skeleton data with pose information.
- the distribution user terminal 20 generates an avatar image having the posture indicated by the skeleton data.
- the distribution user terminal 20 transmits the generated avatar video to the distribution server 30 and requests the distribution server 30 to distribute the avatar video.
- the skeleton data is an example of posture information indicating the posture of distribution user U1, and in this specification, the skeleton data at point 1 may also be referred to as pose.
- time-series data of poses at consecutive n points of time may be referred to as motion.
- a notebook PC Personal Computer
- the distribution user terminal 20 may be another information processing device such as a smart phone or a desktop PC.
- the distribution server 30 distributes the avatar video to the viewing user terminal 40 based on the request from the distribution user terminal 20 .
- FIG. 1 shows one distribution server 30 that implements a distribution service provided by a certain business operator, there may be a plurality of business operators providing distribution services and a plurality of distribution servers 30.
- the distribution user terminal 20 can request the distribution server 30, which provides the distribution service specified by the distribution user U1, to distribute the avatar video.
- the viewing user terminal 40 is an information processing device used by viewing users (for example, user U2 and user U3 shown in FIG. 1).
- the viewing user terminal 40 has a display unit that displays various screens, an operation unit that detects the operation of the viewing user, and a control unit that controls the overall operation of the viewing user terminal 40 .
- the viewing user terminal 40 requests the distribution server 30 to distribute the avatar video of the distribution user U1 based on the operation of the viewing user, and displays the avatar video distributed from the distribution server 30 .
- FIG. 2 is an explanatory diagram showing a specific example of the avatar video V displayed on the viewing user terminal 40.
- FIG. 2 the video of the two-dimensional character is displayed as the avatar video V on the viewing user terminal 40, for example.
- the posture of the avatar video V reflects the posture of distribution user U1. That is, the avatar video V changes according to the movement of the delivery user U1.
- motion capture techniques can produce inaccurate skeletal data.
- inaccurate skeleton data is generated when a sensor device worn by a distribution user is dropped or displaced.
- the accuracy of posture information can be degraded due to camera misalignment and drift.
- the application of motion capture technology is, for example, generation of avatar images, there is concern that avatar images may be generated with inappropriate postures or movements.
- the inventors have come to create an embodiment of the present disclosure by focusing on the above circumstances.
- generation of inappropriate skeleton data can be addressed.
- the configuration and operation of the distribution user terminal 20 according to an embodiment of the present disclosure will be sequentially described in detail.
- FIG. 3 is an explanatory diagram showing the configuration of the distribution user terminal 20 according to one embodiment of the present disclosure.
- the distribution user terminal 20 includes an operation unit 216, a display unit 220, a communication unit 230, and a control unit 240.
- the operation unit 216 is configured to be operated by the distribution user for inputting instructions or information to the distribution user terminal 20 .
- the display unit 220 displays various display screens. For example, the display unit 220 displays a display screen including the avatar image generated by the control unit 240.
- FIG. Communication unit 230 communicates with distribution server 30 via network 12 . For example, the communication section 230 transmits the avatar video generated by the control section 240 to the distribution server 30 via the network 12 .
- the control unit 240 controls the overall operation of the distribution user terminal 20.
- the control unit 240 according to an embodiment of the present disclosure has a function of generating skeleton data of the distribution user based on sensor data received from the sensor device 10 and generating an avatar image having the posture indicated by the skeleton data. have.
- the control unit 240 according to an embodiment of the present disclosure also has a function of modifying skeleton data. These functions of the control unit 240 are realized by the base tool 250 and the application unit 260 shown in FIG.
- the base tool 250 has a function of generating skeleton data from sensor data and a function of correcting skeleton data.
- skeleton data generated from sensor data may be referred to as raw skeleton data
- skeleton data generated by modifying the raw skeleton data may be referred to as corrected skeleton data.
- Raw skeleton data and corrected skeleton data are sometimes simply referred to as skeleton data without any particular distinction.
- the base tool 250 supplies raw skeleton data or modified skeleton data to the application section 260 .
- the application unit 260 realizes various functions in cooperation with the base tool 250.
- the application unit 260 generates an avatar image based on the skeleton data supplied from the base tool 250 and requests the distribution server 30 to distribute the avatar image.
- the application unit 260 may request the distribution server 30 to distribute a combination of the avatar video and other content data.
- Other content data includes, for example, background data and music data.
- the developer of the base tool 250 and the developer of the application unit 260 may be the same or different. The functions of the base tool 250 and application unit 260 will be described in more detail below.
- FIG. 4 is an explanatory diagram showing the functions of the base tool 250.
- the base tool 250 includes a sensor data acquisition unit 251, a calibration unit 252, a skeleton data generation unit 253, a feature amount extraction unit 254, an application interface 255, a basic usage range storage unit 256, a usage range determination It has a section 257 and a data correction section 258 .
- the sensor data acquisition unit 251 acquires sensor data indicating the acceleration or angular velocity of the attachment site from the sensor device 10 .
- the calibration unit 252 calibrates sensor data acquired by the sensor data acquisition unit 251 .
- the calibration unit 252 may perform the calibration when starting to use the base tool 250, or may perform the calibration according to the operation by the distribution user.
- Skeleton data generator 253 Skeleton data generator 253 acquires attachment site information indicating the position and orientation of each attachment site based on the sensor data acquired by sensor data acquisition section 251, and based on the attachment site information, determines each site in the skeleton structure. Generate raw skeleton data including position and orientation information. Generation of raw skeleton data will be described in more detail below with reference to FIG.
- FIG. 5 is an explanatory diagram showing a specific example of generating raw skeleton data.
- the skeleton data generation unit 253 Based on the sensor data, the skeleton data generation unit 253 generates mounting site information PD100 including position information and orientation information of the mounting sites P101 to P106 on which the sensor devices 10A to 10F are mounted, as shown in the left diagram of FIG. to get
- the skeleton data generation unit 253 generates raw skeleton data SD100 including position information and posture information of each part in the skeleton structure, as shown in the right diagram of FIG. to get
- the raw skeleton data SD100 includes not only the information of the mounting part SP101 corresponding to the mounting part P101 and the mounting part SP102 corresponding to the mounting part P102, but also the information of the non-mounting part SP107.
- raw skeleton data may also include bone information (position information, posture information, etc.).
- the raw skeleton data SD100 may include information on the bone SB101.
- the skeleton data generation unit 253 can specify bone information between parts based on position information and posture information of parts in the skeleton structure.
- the feature quantity extraction unit 254 extracts a feature quantity from the bare skeleton data (distribution user posture information) generated by the feature quantity extraction unit 254 .
- the feature amount extracting unit 254 extracts a pose feature amount, which is the feature amount of the pose, from the pose, which is raw skeleton data at time 1 .
- the pose feature amount extracted by the feature amount extraction unit 254 is a feature amount that is located close to each other in the pose feature amount space between similar poses.
- the feature amount extraction unit 254 may extract the pose feature amount using a discriminator such as a DNN (Deep Neural Network) that has been trained to enable such pose feature amount extraction.
- a discriminator such as a DNN (Deep Neural Network) that has been trained to enable such pose feature amount extraction.
- the feature amount extraction unit 254 extracts a motion feature amount, which is the feature amount of the motion, from the motion, which is the time-series data of the pose.
- the motion feature amount extracted by the feature amount extraction unit 254 is a feature amount that is located close to each other in the motion feature amount space between similar motions.
- the feature amount extraction unit 254 may extract the motion feature amount using a discriminator such as a DNN trained to enable extraction of such motion feature amount.
- the application interface 255 is an interface with the application section 260 .
- the application interface 255 may be configured as an API (Application Programming Interface).
- the application interface 255 returns skeleton data of the delivery user to the application section 260 in response to a request from the application section 260 .
- the application interface 255 returns the corrected skeleton data to the application unit 260 when the corrected skeleton data is generated by the data correction unit 258 described later, and returns the corrected skeleton data to the application unit 260 when the corrected skeleton data is not generated.
- Skeleton data may be returned to application unit 260 .
- the application interface 255 acquires information indicating an additional use range, which will be described later, from the application unit 260 and passes the information indicating the additional use range to the use range determination unit 257 .
- the basic usage range storage unit 256 stores information indicating a basic usage range, which is an example of a set range.
- the basic usage range is a partial range in the pose feature space or motion feature space.
- the basic use range of poses may be a range that includes feature amounts of poses that humans can take in the pose feature amount space and does not include feature amounts of poses that humans are not normally expected to take.
- the basic usage range of motion may be a range that includes motion features that humans can take in the motion feature space, but does not include motion features that are not normally assumed to be taken by humans.
- the basic usage range may be a range that is indirectly specified by storing information indicating the range of feature amounts that are not included in the basic usage range.
- Data correction unit 258 Based on the fact that the use range determination unit 257 has determined that the feature amount extracted by the feature amount extraction unit 254 is not included in the use range, the data correction unit 258 uses the feature amount included in the use range as the use feature amount. and generate corrected skeleton data indicating pose or motion using the used feature amount. For example, the data correcting unit 258 adjusts the usage range according to the positional relationship (i.e., Euclidean distance) in the feature amount space between the feature amount extracted by the feature amount extraction unit 254 and each feature amount included in the usage range. Get the used features from the included features.
- positional relationship i.e., Euclidean distance
- the data correction unit 258 may acquire the feature amount closest to the feature amount extracted by the feature amount extraction unit 254, among the feature amounts included in the use range, as the use feature amount.
- a specific example of corrected skeleton data generated by the data corrector 258 will now be described with reference to FIG.
- FIG. 6 is an explanatory diagram showing a specific example of corrected skeleton data generated by the data correction unit 258.
- FIG. The left diagram of FIG. 6 shows the raw skeleton data SD101 generated by the skeleton data generator 253 .
- the left hand portion has a bent shape, and the left hand portion of a human does not normally take this shape.
- Inappropriate raw skeleton data SD101 may be generated in this way when sensor device 10 is displaced or dropped.
- the use range determination unit 257 determines that the pose feature amount of the raw skeleton data SD101 is not included in the use range of the pose, and the data correction unit 258 generates the corrected skeleton data MSD101 shown in the right diagram of FIG. 6, for example. do.
- the modified skeleton data MSD101 is skeleton data generated using the feature amounts included in the use range in the pose feature amount space, and the left-hand bend is corrected to be a straight line.
- the data correction unit 258 can also generate corrected skeleton data for each motion, which is time-series data of a plurality of poses. is.
- the data correction unit 258 may use the feature amount (extracted feature amount) extracted from the raw skeleton data by the feature amount extraction unit 254 in addition to the feature amount acquired from the use range when generating the corrected skeleton data. good. For example, the data correction unit 258 may mix the feature amount obtained from the usage range and the extracted feature amount to generate a mixed feature amount, and generate corrected skeleton data indicating a pose or motion having the mixed feature amount.
- the data correction unit 258 determines the mixing ratio of the feature amount acquired from the usage range and the extracted feature amount according to the duration of time during which the extracted feature amount is determined not to be included in the usage range. may For example, the longer the duration for which it is determined that the extracted feature quantity is not included in the usage range, the more the mixing ratio of the feature quantity acquired from the usage range may increase.
- the original corrected skeleton data in which the extracted features were judged not to be included in the usable range almost matched the raw skeleton data, and the duration of the judgment that the extracted features were not included in the usable range was long. As it becomes larger, the difference between the corrected skeleton data and the raw skeleton data becomes larger.
- the data correction unit 258 also corrects the mixed feature amount. Generating the modified skeleton data used may continue. For example, the data correction unit 258 may decrease the mixing ratio of the feature amounts acquired from the use range as the elapsed time after it is determined that the extracted feature amount is included in the use range increases. In this case, the difference between the corrected skeleton data and the raw skeleton data becomes smaller as the elapsed time after it is determined that the extracted feature amount is included in the use range becomes longer. Then, the data correction unit 258 may terminate the generation of corrected skeleton data when the elapsed time from when it is determined that the extracted feature amount is included in the use range reaches a predetermined time.
- FIG. 7 is an explanatory diagram showing the functions of the application section 260.
- the application section 260 has a base tool plug-in 261 , an additional usage range storage section 262 , an additional usage range registration section 263 , a retargeting section 265 , a display control section 267 and a distribution control section 268 .
- Base tool plug-in 261 is an interface with base tool 250 .
- the platform tool plug-in 261 receives data from the platform tool 250 and converts the data into a format that can be handled by the application section 260 .
- infrastructure tool plug-in 261 receives skeleton data, such as raw skeleton data or modified skeleton data, from infrastructure tool 250 .
- the additional usage range storage unit 262 stores information indicating an additional usage range, which is an example of the set range.
- the additional use range is a partial range in the pose feature space or motion feature space.
- the additional use range may be, for example, a range that includes pose or motion feature values suitable for a character used as an avatar image.
- the additional use range may be a range that is indirectly specified by storing information indicating the range of feature amounts not included in the additional use range.
- the additional use range registration unit 263 has a function of registering an additional use range in the additional use range storage unit 262 .
- the additional usage range registration unit 263 may register the additional usage range in the additional usage range storage unit 262 using various methods. Several method examples for the additional use range registration unit 263 to register the additional use range of poses in the additional use range storage unit 262 will be described below.
- FIG. 8 is a flowchart showing a first registration example of the additional usage range.
- the additional usage range registration unit 263 acquires recorded motions (that is, a set of poses at each of a plurality of consecutive points in time) (S302).
- the feature amount extraction unit 254 of the base tool 250 acquires the recorded motion from the additional use range registration unit 263 via the application interface 255, and extracts the pose feature amount of each pose that constitutes the motion (S304). ).
- the additional use range registration unit 263 receives the pose feature amount of each pose that constitutes the motion from the base tool 250 via the base tool plug-in 261, and registers the range including the pose feature amount of each pose as an additional use range of the pose. is registered in the additional usage range storage unit 262 (S306).
- the additional use range of poses may be a range in which the Euclidean distance between each pose and the pose feature amount is equal to or less than a predetermined length. Further, the pose additional usage range may exist continuously or discretely in the feature amount space.
- the feature amount extraction unit 254 extracts the motion feature amount of the motion
- the additional use range registration unit 263 extracts the motion feature amount from the base tool 250 via the base tool plug-in 261.
- a motion feature amount is received, and a range including the motion feature amount is registered in the additional use range storage unit 262 as an additional use range of motion.
- FIG. 9 is a flow chart showing a second registration example of the additional usage range.
- the distribution user designates a motion name such as walking or running by operating the operation unit 216 (S312). It is assumed that the base tool 250 or the application unit 260 is prepared in advance with a database in which motions and motion names are associated with each other.
- the additional usage range registration unit 263 searches the database for a motion corresponding to the designated motion name (S314). Then, the feature amount extraction unit 254 of the base tool 250 acquires the retrieved motion from the additional use range registration unit 263 via the application interface 255, and extracts the pose feature amount of each pose that constitutes the motion (S316). ).
- the additional use range registration unit 263 receives the pose feature amount of each pose that constitutes the motion from the base tool 250 via the base tool plug-in 261, and registers the range including the pose feature amount of each pose as an additional use range of the pose. is registered in the additional usage range storage unit 262 (S318).
- the feature amount extraction unit 254 extracts the motion feature amount of the motion
- the additional use range registration unit 263 extracts the motion feature amount from the base tool 250 via the base tool plug-in 261.
- a motion feature amount is received, and a range including the motion feature amount is registered in the additional use range storage unit 262 as an additional use range of motion.
- FIG. 10 is a flowchart showing a third registration example of the additional usage range.
- display unit 220 first displays a pose selection screen including a plurality of poses, and the distribution user selects two or more poses on the pose selection screen by operating operation unit 216 (S322). ).
- S322 operating operation unit 216
- FIG. 11 is an explanatory diagram showing a specific example of the pose selection screen.
- the pose selection screen includes a plurality of pose displays 71A-71C, selection buttons 72A-72C corresponding to the pose displays 71A-71C, and a new registration button 73.
- the distribution user sequentially selects selection buttons 72 corresponding to pose displays 71 indicating two or more desired poses, and presses a new registration button 73 . If the pose selection screen does not include a pose display indicating a desired pose, the distribution user can register a new pose by himself/herself.
- the additional use range registration unit 263 derives a motion that joins two or more poses selected by the distribution user according to the selected order (S324).
- the feature amount extraction unit 254 of the base tool 250 acquires the derived motion from the additional usage range registration unit 263 via the application interface 255, and extracts the pose feature amount of each pose that constitutes the motion ( S326).
- the additional use range registration unit 263 receives the pose feature amount of each pose that constitutes the motion from the base tool 250 via the base tool plug-in 261, and registers the range including the pose feature amount of each pose as an additional use range of the pose. is registered in the additional usage range storage unit 262 (S328).
- the feature amount extraction unit 254 extracts the motion feature amount of the motion
- the additional use range registration unit 263 extracts the motion feature amount from the base tool 250 via the base tool plug-in 261.
- a motion feature amount is received, and a range including the motion feature amount is registered in the additional use range storage unit 262 as an additional use range of motion.
- the retargeting unit 265 receives the distribution user's skeleton data from the base tool plug-in 261 and retargets the skeleton data to generate an avatar image having the posture or movement indicated by the skeleton data.
- the display control unit 267 generates various display screens and causes the display unit 220 to display the generated display screens. For example, the display control unit 267 generates the pose selection screen described above and causes the display unit 220 to display the pose selection screen. The display control unit 267 also generates an avatar display screen including the avatar video generated by the retargeting unit 265 and causes the display unit 220 to display the avatar display screen.
- the distribution control unit 268 transmits the distribution of the avatar video generated by the retargeting unit 265 to the distribution server 30 and requests the distribution server 30 to distribute the avatar video. After that, when the distribution of the avatar video is started, the display control unit 267 generates a display screen for the distribution user and causes the display unit 220 to display the display screen. A specific example of the display screen generated by the display control unit 267 will be described below.
- FIG. 12 is an explanatory diagram showing an example of a display screen for distribution users.
- the left diagram of FIG. 12 shows a distribution confirmation screen 81, and the distribution confirmation screen 81 includes an avatar video V being distributed, a live display 811 indicating that the avatar video V is being distributed in real time, and an abnormality notification icon 813.
- the avatar image V is an image generated from raw skeleton data, and the left leg is bent outward.
- the abnormality notification icon 813 indicates that the usage range determination unit 257 of the base tool 250 has determined that the feature amount extracted from the raw skeleton data is not included in the usage range.
- an abnormality notification icon 813 may be displayed as shown in the left diagram of FIG. 12 .
- the display control unit 267 causes the display unit 220 to display the skeleton display screen 82 shown in the right diagram of FIG.
- the skeleton display screen 82 includes a display 822 showing raw skeleton data, a display 823 showing an avatar image obtained when modified skeleton data is applied, and a correction button 824 .
- a skeleton display screen 83 including a display 832 showing modified skeleton data and a display 833 showing an avatar image is displayed on display unit 220 .
- the left leg of the avatar video V is straightened because the target of retargeting is switched to the modified skeleton data, and the abnormality notification icon 813 shown in FIG. 12 disappears.
- the display control unit 267 issues a calibration as a predetermined notification based on the number of occurrences or frequency of occurrence of determination that the feature amount extracted from the raw skeleton data is not included in the use range exceeds the threshold.
- a calibration icon that guides calibration may be displayed on the display unit 220 .
- FIG. 14 is an explanatory diagram showing a specific example of the distribution confirmation screen 85 including the calibration icon.
- the distribution confirmation screen 85 includes an avatar video V generated from corrected skeleton data, a live display 811, and a calibration icon 851.
- the skeleton display screen 86 includes a display 862 showing raw skeleton data, a display 863 showing avatar video, and a calibration button 864 .
- the display 862 showing the raw skeleton data as indicated by the dashed-dotted line, parts considered to pose inappropriately may be displayed by distinguishing them from other parts by color, thickness, or the like. Furthermore, the color, thickness, etc. may be distinguished according to the degree of inappropriate poses.
- the calibration section 252 of the base tool 250 performs calibration regarding the sensor device 10 . After the calibration is executed, a delivery confirmation screen that includes the avatar video V and does not include the calibration icon 851 is displayed.
- FIG. 15 is a flow chart showing the operation of the base tool 250.
- the skeleton data generation unit 253 of the base tool 250 generates raw skeleton data at the current time based on the sensor data acquired by the sensor data acquisition unit 251 (S404).
- the feature quantity extraction unit 254 extracts the pose feature quantity of the raw skeleton data (S408).
- the use range determination unit 257 determines whether the pose feature amount extracted by the feature amount extraction unit 254 is within the use range in the feature amount space (S412). If the extracted pose feature amount is within the usable range in the feature amount space (S412/Yes), the application interface 255 supplies raw skeleton data to the application section 260 (S416).
- the data correction unit 258 acquires the pose feature amount within the use range (S420). Then, the data correction unit 258 generates corrected skeleton data using the pose feature amount within the usable range (S430).
- the data correction unit 258 may generate modified skeleton data indicating a pose having pose feature amounts within the use range, or pose feature amounts extracted from the pose feature amounts within the use range and raw skeleton data. may be mixed to generate a mixed feature, and modified skeleton data indicating a pose having the mixed feature may be generated. The latter operation will be specifically described with reference to FIG.
- FIG. 16 is a flow chart showing a specific example of a method for generating corrected skeleton data.
- the data correction unit 258 determines the mixture ratio of the pose feature amount extracted from the raw skeleton data and the pose feature amount within the use range (S432). For example, the data correction unit 258 may determine the mixing ratio according to the duration during which the pose feature amount extracted from the raw skeleton data is determined not to be included in the use range. For example, the data correction unit 258 may increase the mixing ratio of pose feature amounts within the use range as the duration increases.
- the data correction unit 258 mixes the two pose feature amounts according to the determined mixing ratio to generate a mixed feature amount (S434). Furthermore, the data correction unit 258 generates corrected skeleton data having mixed features (S436).
- the application interface 255 supplies the corrected skeleton data to the application unit 260 (S440).
- the usage range determination unit 257 increments the counter value (S444). If the counter value exceeds the threshold (S448/Yes), the application interface 255 outputs a calibration recommendation notification indicating that execution of calibration is recommended to the application unit 260 (S452). After that, or when the counter value is below the threshold (S448/No), the process from S404 is repeated.
- the number of times the extracted pose feature is determined to be out of the usable range in the feature space is managed by a counter value. It is possible to manage the occurrence frequency (occurrence frequency per unit time) of the judgment that it is not within the range, and output a calibration recommendation notice when the occurrence frequency exceeds a threshold.
- FIG. 17 is a flow chart showing the operation of the application unit 260.
- skeleton data is supplied from the base tool 250 to the base tool plug-in 261 (S504). If the base tool 250 has not generated corrected skeleton data, the raw skeleton data is supplied, and if the base tool 250 has generated corrected skeleton data, the corrected skeleton data is supplied. If modified skeleton data has been generated in the base tool 250, raw skeleton data may be supplied in addition to the modified skeleton data.
- the retargeting unit 265 generates an avatar video by retargeting the skeleton data supplied from the base tool 250 (S508).
- the retargeting unit 265 retargets the raw skeleton data when the modified skeleton data is not generated.
- the retargeting unit 265 switches the target of retargeting to the corrected skeleton data automatically or based on the operation from the distribution user.
- the distribution control unit 268 transmits the avatar video generated by the retargeting unit 265 to the distribution server 30, and requests the distribution server 30 to distribute the avatar video (S512).
- the display control unit 267 displays a distribution confirmation screen including a calibration icon as described with reference to FIG. 14 (S520). Then, when execution of calibration is instructed by the operation of the distribution user (S524/Yes), the application unit 260 requests the execution of calibration to the base tool 250 (S528). If there is no calibration recommendation notification (S516/No), if the execution of calibration is not instructed by the operation of the distribution user (S524/No), or after S528, until an operation to end distribution is performed, the The process is repeated (S548).
- the corrected skeleton data is generated using the feature amount included in the usage range. be done. Therefore, even if inappropriate pose skeleton data is generated when the sensor device 10 worn by the distribution user is dropped or dislocated, an appropriate and natural avatar image can be obtained by using the corrected skeleton data. It is possible to provide When live distribution of avatar video is being performed, it is possible to continue the live distribution without a sense of discomfort. In addition, even if the distribution user takes an ethically inappropriate pose or motion, the modified skeleton data can be used to prevent inappropriate avatar images from being distributed.
- the data correction unit 258 acquires feature amounts included in the use range according to the positional relationship in the feature amount space between the feature amount extracted from the raw skeleton data and each feature amount included in the set range. For example, the data correction unit 258 acquires the feature amount closest to the feature amount extracted from the raw skeleton data, among the feature amounts included in the usage range. According to such a configuration, the data correction unit 258 can generate corrected skeleton data having poses or motions similar to the poses or motions intended by the distribution user.
- the data correction unit 258 can generate a mixed feature amount by mixing the feature amount within the use range and the feature amount extracted from the raw skeleton data. For example, the data correction unit 258 determines the mixing ratio of the pose feature amount within the use range according to the duration during which the pose feature amount extracted from the raw skeleton data is determined not to be included in the use range. According to this configuration, when the target of retargeting is switched from the raw skeleton data to the corrected skeleton data, the difference between the raw skeleton data and the corrected skeleton data can be reduced, so that the discomfort given to the viewing user can be reduced. is.
- the base tool 250 outputs a calibration recommendation notice when the number of occurrences or the frequency of occurrence of the determination that the feature amount extracted from the bare skeleton data is not included in the usage range exceeds a threshold. According to such a configuration, it is expected that calibration will be performed and the feature amount extracted from the raw skeleton data will be easily included in the usage range. In this case, since the avatar video is generated using the bare skeleton data, it is possible to generate the avatar video having poses or motions closer to the intent of the distribution user.
- the retargeting unit 265 can switch retargeting targets based on an operation from the distribution user. According to this configuration, even if the feature amount extracted from the bare skeleton data is not included in the usage range, the distribution user can have the option of generating the avatar video using the bare skeleton data.
- the additional usage range registration unit 263 can set an additional usage range, and various setting methods can be applied to the setting stage of setting the additional usage range. According to such a configuration, the distribution user can easily set the additional use range according to the application.
- FIG. 18 is a flow chart showing a first modification of the operation of the base tool 250.
- FIG. The processes of S404-S412 and S420-S452 are as described with reference to FIG.
- the data correction unit 258 determines whether the pose feature amount extracted by the feature amount extraction unit 254 is within the use range. (S413).
- the predicted feature amount is a feature amount of a predicted future pose or motion of the distribution user.
- the data correction unit 258 may input the current pose feature amount extracted by the feature amount extraction unit 254 to a classifier such as a DNN, thereby acquiring the expected feature amount output from the classifier. .
- the data correction unit 258 generates corrected skeleton data using the predicted feature amount (S414).
- the data correction unit 258 may generate corrected skeleton data indicating a pose having the predicted feature amount, or mix the predicted feature amount and the pose feature amount extracted from the raw skeleton data to generate a mixed feature amount, Modified skeleton data representing poses with mixed features may be generated.
- the application interface 255 then supplies the corrected skeleton data to the application unit 260 (S415). As a result, even when the pose feature amount extracted from the raw skeleton data is within the usable range, the avatar image can be generated from the corrected skeleton data generated by prediction.
- Such a first modification is useful in applications where real-time avatar video is important and low delay is desired.
- a distribution user performs a dance or the like with a limited number of possible motions, it is possible to predict modified skeleton data with high accuracy and reduce delays in distribution based on the modified skeleton data.
- Second modification> it is determined whether or not the feature amount of the raw skeleton data of the whole body is within the use range, and the modified skeleton data is generated for each whole body. may This example will be described as a second modified example with reference to FIG.
- FIG. 19 is a flow chart showing a second modification of the operation of the base tool 250.
- the skeleton data generation unit 253 of the base tool 250 generates raw skeleton data for each part at the current time based on the sensor data acquired by the sensor data acquisition unit 251 (S604). ).
- the feature quantity extraction unit 254 extracts the pose feature quantity of the raw skeleton data of each part (S608).
- the parts include the right arm, left arm, left leg, right leg, body, and the like.
- the use range is set for each part, and the use range determination unit 257 determines whether or not the pose feature amounts of all parts are within the use range of each part ( S612). If the pose feature amounts of all parts are within the use range (S612/Yes), the application interface 255 supplies the raw skeleton data of each part to the application unit 260 (S616).
- the data correction unit 258 corrects the part whose pose feature value is outside the use range. is acquired within the use range of (S620). Then, the data correction unit 258 generates corrected skeleton data outside the use range using the pose feature amount within the use range (S630).
- the application interface 255 supplies to the application unit 260 the corrected skeleton data of the parts outside the use range and the raw skeleton data of the parts whose pose feature values were within the use range (S640).
- the usage range determination unit 257 increments the counter value (S644). If the counter value exceeds the threshold (S648/Yes), the application interface 255 outputs a calibration recommendation notification indicating that execution of calibration is recommended to the application unit 260 (S652). After that, or when the counter value is below the threshold (S648/No), the process from S604 is repeated.
- the base tool 250 manages the basic usage range and the application unit 260 manages the additional usage range. Management of the additional use range in the may not be performed. In this case, the usage range may be only the basic usage range or the additional usage range.
- the viewing user may set the usage range.
- the viewing user may operate the viewing user terminal 40 to select poses to allow or prohibit for the avatar video, and set the user usage range including the feature amount of the selected pose.
- the judgment using the user usage range and generation of corrected skeleton data may be performed in the viewing user terminal 40, or may be performed in the distribution server 30 by managing the user usage range in the distribution server 30. good too. According to such a configuration, it is possible to prevent a pose or motion that the viewing user does not desire in the avatar image from being displayed on the viewing user terminal 40 .
- the base tool 250 when the feature amount extracted from the bare skeleton data is out of the usable range, the base tool 250 outputs a predetermined notification to the application unit 260, and the application unit 260 outputs a predetermined notification to the avatar image based on the notification.
- Image processing may be applied.
- the predetermined image processing may be mosaic processing for applying a mosaic to the avatar video, particle processing, or the like. With such a configuration, it is also possible to reduce discomfort felt by the viewing user.
- the application unit 260 performs the above image processing on the avatar video based on the notification from the platform tool 250, for example, until the avatar video based on the corrected skeleton data starts to be displayed by the distribution user's operation. may
- the usage range determination unit 257 determines whether or not the feature amount extracted from each raw skeleton data is included in the usage range.
- the data correction unit 258 does not use the feature amount determined not to be included in the usage range, and generates corrected skeleton data using the feature amount determined to be included in the usage range.
- the data correction unit 258 generates a mixed feature amount by mixing the two or more feature amounts, and generates corrected skeleton data having the mixed feature amount. may be generated.
- the data correction unit 258 may mix feature amounts of raw skeleton data obtained by a more highly accurate motion capture technique at a higher mixing ratio. Such a configuration can also prevent inappropriate avatar videos from being distributed.
- FIG. 20 is an explanatory diagram showing a second configuration example of the information processing system.
- the information processing system according to the second configuration example has a distribution user terminal 20-2 and a processing terminal 50-2.
- the distribution user terminal 20-2 and the processing terminal 50-2 are connected via the network 12.
- FIG. The distribution user terminal 20 - 2 has the base tool 250 and does not have the application section 260 .
- the application unit 260 is installed in the processing terminal 50-2.
- the distribution user terminal 20-2 transmits raw skeleton data or corrected skeleton data to the processing terminal 50-2.
- the application unit 260 of the processing terminal 50 - 2 generates an avatar image from the raw skeleton data or the corrected skeleton data, and distributes the avatar image to the viewing user terminal 40 via the distribution server 30 .
- the developer of the base tool 250 and the developer of the application unit 260 may be the same or different.
- FIG. 21 is an explanatory diagram showing a third configuration example of the information processing system.
- the information processing system according to the third configuration example has a distribution user terminal 20-3 and a processing terminal 50-3.
- the distribution user terminal 20-3 and the processing terminal 50-3 are connected via the network 12.
- FIG. The distribution user terminal 20-3 has a base tool 250 and an application section 260-3.
- the application unit 260-3 does not have the retargeting unit 265 and the delivery control unit 268 in the configuration of the application unit 260 described with reference to FIG. Instead, processing terminal 50-3 has retargeting unit 265 and delivery control unit 268.
- FIG. 21 is an explanatory diagram showing a third configuration example of the information processing system.
- the information processing system according to the third configuration example has a distribution user terminal 20-3 and a processing terminal 50-3.
- the distribution user terminal 20-3 and the processing terminal 50-3 are connected via the network 12.
- the distribution user terminal 20-3 has a base tool 250 and an application section 260-3.
- the distribution user terminal 20-3 transmits raw skeleton data or corrected skeleton data to the processing terminal 50-3. Then, the retargeting unit 265 of the processing terminal 50-3 generates an avatar image from the raw skeleton data or the modified skeleton data, and the distribution control unit 268 distributes the avatar image to the viewing user terminal 40 via the distribution server 30.
- the developer of the base tool 250, the developer of the application unit 260-3, the developer of the retargeting unit 265, and the developer of the distribution control unit 268 may be the same, can be different.
- FIG. 22 is an explanatory diagram showing a fourth configuration example of the information processing system.
- the information processing system according to the fourth configuration example has a distribution user terminal 20-4 and a processing terminal 50-4.
- the distribution user terminal 20-4 and the processing terminal 50-4 are connected via the network 12.
- FIG. The distribution user terminal 20-4 has a base tool 250.
- FIG. The processing terminal 50-4 has an application section 260-4.
- the application unit 260-4 does not include the function of the distribution control unit 268, and the processing terminal 50-4 has the function of the distribution control unit 268 separately.
- the distribution user terminal 20-4 transmits raw skeleton data or modified skeleton data to the processing terminal 50-4. Then, the application unit 260-4 of the processing terminal 50-4 generates an avatar image from the raw skeleton data or the corrected skeleton data, and the distribution control unit 268 distributes the avatar image to the viewing user terminal 40 via the distribution server 30.
- the developer of the base tool 250, the developer of the application unit 260-4, and the developer of the distribution control unit 268 may be the same or different.
- FIG. 23 is an explanatory diagram showing a fifth configuration example of the information processing system.
- the information processing system according to the fifth configuration example has a distribution user terminal 20-5 and a processing terminal 50-5.
- the distribution user terminal 20-5 and the processing terminal 50-5 are connected via the network 12.
- FIG. The distribution user terminal 20-5 has a base tool 250.
- FIG. The processing terminal 50-5 has an application section 260-5.
- the application unit 260-5 does not include the functions of the retargeting unit 265 and the distribution control unit 268, and the processing terminal 50-5 has the functions of the retargeting unit 265 and the distribution control unit 268 separately.
- the distribution user terminal 20-5 transmits raw skeleton data or modified skeleton data to the processing terminal 50-5. Then, the application unit 260-5 supplies the raw skeleton data or the modified skeleton data to the retargeting unit 265, the retargeting unit 265 generates an avatar image from the raw skeleton data or the modified skeleton data, and the distribution control unit 268 controls the distribution server. 30 to deliver the avatar video to the viewing user terminal 40 .
- the developer of the base tool 250, the developer of the application unit 260-5, the developer of the retargeting unit 265, and the developer of the distribution control unit 268 may be the same or different. may
- FIG. 24 is an explanatory diagram showing a sixth configuration example of the information processing system.
- the information processing system according to the sixth configuration example has a first mobile terminal 61 , a second mobile terminal 62 and a third mobile terminal 63 .
- the functions of the control unit 240 that is, the functions of the base tool 250 and the application unit 260 are implemented in the first mobile terminal 61 .
- the first mobile terminal 61 also has a communication section for communicating with other second mobile terminals 62 and third mobile terminals 63 .
- First mobile terminal 61 generates an avatar image of user U1 based on sensor data acquired from sensor device 10 and transmits the avatar image to second mobile terminal 62 and third mobile terminal 63 .
- 24 shows an example in which the first mobile terminal 61, the second mobile terminal 62 and the third mobile terminal 63 communicate via the network 12, the first mobile terminal 61, the second mobile terminal 62 and The third portable terminal 63 may communicate directly without going through the network 12 .
- the functions of the display unit 220 and the communication unit 230 are implemented in the second mobile terminal 62 .
- the second mobile terminal 62 receives the avatar image from the first mobile terminal 61 and displays a display screen including the avatar image on the display unit 220 . Thereby, the user U4 using the second mobile terminal 62 can check the avatar video.
- the display screen displayed on the second mobile terminal 62 may be the same as the display screen described with reference to FIGS. It may be a screen.
- the functions of the operation unit 216 and the communication unit 230 are implemented in the third mobile terminal 63 .
- the third mobile terminal 63 Information indicating the operation is transmitted to the first mobile terminal 61 .
- the third mobile terminal 63 may also have the function of the display unit 220 that displays a display screen including an avatar image for the above operation.
- the functions of the second mobile terminal 62 and the functions of the third mobile terminal 63 may be collectively implemented in one mobile terminal.
- the second mobile terminal 62 and the third mobile terminal 63 may also have the function of the application section 260 .
- the first mobile terminal 61 transmits skeleton data to the second mobile terminal 62 and the third mobile terminal 63 instead of the avatar video
- the second mobile terminal 62 and the third mobile terminal 63 transmit the avatar video from the skeleton data. can be generated and displayed.
- a part or all of the functions of the application unit 260 may be implemented in each mobile terminal.
- the function of the additional use range storage unit 262 is implemented in the first mobile terminal 61 and the third mobile terminal 63
- the function of the additional use range registration unit 263 is implemented in the third mobile terminal 63
- the function of the display control unit 267 is implemented. may be implemented in the second mobile terminal 62 and the third mobile terminal 63 .
- Use cases of the sixth configuration example of the information processing system include, for example, shooting outdoors, shooting while moving, and shooting in a specific environment.
- the use of a mobile terminal eliminates the need to secure a power supply and transport equipment, making it possible to perform motion capture and data processing with lighter clothing.
- the user U1 who is a performer carries the first mobile terminal 61, and the first mobile terminal 61 transmits skeleton data or avatar images to each of the second mobile terminals 62 owned by a plurality of users such as producers or directors. This makes it possible to immediately check skeleton data or avatar images in multiple environments.
- the first mobile terminal 61 can acquire the orientation of the face of the user U1.
- the first mobile terminal 61 can also perform motion capture of the user U1 from images obtained by the camera.
- the first mobile terminal 61 uses the data acquired by the built-in function of the first mobile terminal 61. Corrected skeleton data may be generated. For example, the first mobile terminal 61 acquires, as a use feature amount, a feature amount that satisfies data acquired by a function built into the first mobile terminal 61, from among the feature amounts included in the use range, and uses the use feature amount as the use feature amount. may be used to generate modified skeleton data.
- the first mobile terminal 61 can estimate the position and movement of the user U1 by GNSS (Global Navigation Satellite System) or SLAM (Simultaneous Localization and Mapping) or the like, generating corrected skeleton data using the estimation result. is also possible. For example, when it is estimated that the user U1 is moving at a low speed, it is considered that the user U1 is walking, so the first mobile terminal 61 generates modified skeleton data having a walking posture. can.
- GNSS Global Navigation Satellite System
- SLAM Simultaneous Localization and Mapping
- FIG. 25 is a block diagram showing the hardware configuration of the distribution user terminal 20.
- the distribution user terminal 20 comprises a CPU (Central Processing Unit) 201 , a ROM (Read Only Memory) 202 , a RAM (Random Access Memory) 203 and a host bus 204 .
- the distribution user terminal 20 also includes a bridge 205 , an external bus 206 , an interface 207 , an input device 208 , an output device 210 , a storage device (HDD) 211 , a drive 212 and a communication device 215 .
- a CPU Central Processing Unit
- ROM Read Only Memory
- RAM Random Access Memory
- the distribution user terminal 20 also includes a bridge 205 , an external bus 206 , an interface 207 , an input device 208 , an output device 210 , a storage device (HDD) 211 , a drive 212 and a communication device 215 .
- HDMI storage device
- the CPU 201 functions as an arithmetic processing device and a control device, and controls the general operations within the distribution user terminal 20 according to various programs.
- the CPU 201 may be a microprocessor.
- the ROM 202 stores programs, calculation parameters, and the like used by the CPU 201 .
- the RAM 203 temporarily stores programs used in the execution of the CPU 201, parameters that change as appropriate during the execution, and the like. These are interconnected by a host bus 204 comprising a CPU bus or the like. Functions such as the base tool 250 and the application unit 260 described with reference to FIG.
- the host bus 204 is connected via a bridge 205 to an external bus 206 such as a PCI (Peripheral Component Interconnect/Interface) bus.
- an external bus 206 such as a PCI (Peripheral Component Interconnect/Interface) bus.
- PCI Peripheral Component Interconnect/Interface
- the input device 208 includes input means for the user to input information, such as a mouse, keyboard, touch panel, button, microphone, switch, and lever, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 201 . etc.
- input information such as a mouse, keyboard, touch panel, button, microphone, switch, and lever
- input control circuit that generates an input signal based on the user's input and outputs it to the CPU 201 . etc.
- the user of the distribution user terminal 20 can input various data to the distribution user terminal 20 and instruct processing operations.
- the output device 210 includes, for example, a display device such as a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, and a lamp.
- output device 210 includes audio output devices such as speakers and headphones.
- the output device 210 outputs reproduced content, for example.
- the display device displays various information such as reproduced video data as text or images.
- the audio output device converts reproduced audio data and the like into audio and outputs the audio.
- the storage device 211 is a data storage device configured as an example of the storage unit of the delivery user terminal 20 according to this embodiment.
- the storage device 211 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like.
- the storage device 211 is composed of, for example, an HDD (Hard Disk Drive).
- the storage device 211 drives a hard disk and stores programs executed by the CPU 201 and various data.
- the drive 212 is a reader/writer for storage media, and is built in or externally attached to the distribution user terminal 20 .
- the drive 212 reads out information recorded in the attached removable storage medium 24 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and outputs the information to the RAM 203 .
- Drive 212 can also write information to removable storage medium 24 .
- the communication device 215 is, for example, a communication interface configured with a communication device or the like for connecting to the network 12 .
- the communication device 215 may be a wireless LAN (Local Area Network) compatible communication device, an LTE (Long Term Evolution) compatible communication device, or a wire communication device that performs wired communication.
- LTE Long Term Evolution
- each functional block in the base tool 250 described with reference to FIG. 4 may be distributed and implemented in a plurality of terminals.
- each functional block in the application unit 260 described with reference to FIG. 7 may be distributed in multiple terminals.
- each step in the processing of the distribution user terminal 20 in this specification does not necessarily have to be processed in chronological order according to the order described as the flowchart.
- each step in the processing of the distribution user terminal 20 may be processed in an order different from that described in the flow chart, or may be processed in parallel.
- the following configuration also belongs to the technical scope of the present disclosure.
- a method of processing information comprising: (2) Generating the data acquires the used feature amount from the feature amount included in the set range according to the positional relationship in the feature amount space between the extracted feature amount and each feature amount included in the set range.
- the information processing method according to (1) above comprising: (3) Acquiring the used feature amount from the feature amount included in the set range means that the feature amount closest to the extracted feature amount in the feature amount space is selected from the feature amounts included in the set range as the used feature amount.
- the information processing method according to (2) above including acquiring as (4) Generating the data includes mixing the extracted feature quantity and the used feature quantity to generate a mixed feature quantity, and generating data indicating posture or movement having the mixed feature quantity, wherein (1)
- Generating the mixed feature amount includes mixing the extracted feature amount and the used feature amount at a rate corresponding to the duration for which the extracted feature amount is determined not to be included in the set range, The information processing method according to (4) above.
- generating the mixed feature includes increasing a ratio of mixing the used feature as the duration increases.
- generating the mixed feature amount includes: Any one of (4) to (6) above, including reducing the ratio of mixing the used feature amount as the elapsed time after it is determined that the extracted feature amount is included in the set range increases. or the information processing method according to item 1.
- the information processing method according to (8), wherein the predetermined notification is a notification for inducing calibration of a sensor for acquiring the posture information.
- (10) obtaining a predicted feature value indicating a future posture or movement of the moving body predicted from the feature value included in the set range based on determination that the extracted feature value is included in the set range;
- the information processing method according to any one of (1) to (9), further comprising generating data indicating posture or movement using the predicted feature amount.
- (11) generating the data includes outputting a notification to a user indicating that the extracted feature amount is not included in the set range based on determination that the extracted feature amount is not included in the set range; and generating data indicating the posture or the motion using the used feature amount based on the user performing an operation to instruct the adjustment of the posture or the motion.
- the information processing method according to any one of the items.
- the information processing method according to any one of (1) to (11) above, wherein the information processing method is executed for each of one or more parts among a plurality of parts that constitute a moving body. (13) further comprising a setting step of setting the setting range; The setting step includes: obtaining posture information indicating the posture of a moving body; extracting a feature amount from the posture information at one time point or at a plurality of time points; setting the setting range so as to include the extracted feature quantity; The information processing method according to any one of (1) to (12) above, comprising: (14) further comprising a setting step of setting the setting range; The setting step includes: obtaining posture information indicating the posture of a moving body; extracting a motion feature value connecting the posture information at a plurality of points in time or a feature value of each posture constituting the motion; setting the setting range so as to include the extracted feature quantity; The information processing method according to any one of (1) to (12) above, comprising: (15) further comprising a setting step of setting the setting range; The setting step includes: any one
- the information processing method according to the item. (16) The information processing method according to any one of (1) to (15) above, further comprising generating an avatar image having the posture or movement indicated by the generated data. (17) The information processing method according to (16) above, further comprising distributing the avatar video via a network. (18) obtaining the pose information includes obtaining pose information for each motion capture technique using different motion capture techniques; Generating the data is determined to be included in the set range based on determination that the extracted feature amount of posture information obtained by any motion capture technology is not included in the set range. The information processing method according to (1) above, including generating the data using an extracted feature amount obtained by another motion capture technique as the used feature amount.
- a posture information acquisition unit that acquires posture information indicating the posture of a moving object; a feature quantity extraction unit that extracts a feature quantity from the posture information at one time point or at a plurality of time points; a determination unit that determines whether or not the extracted feature amount, which is the feature amount extracted by the feature amount extraction unit, is included in a set range in the feature amount space; a data generation unit that generates data indicating a posture or movement having a feature amount included in the set range based on the determination by the determination unit that the extracted feature amount is not included in the set range; An information processing device.
- a posture information acquisition unit that acquires posture information indicating the posture of a moving object
- a feature quantity extraction unit that extracts a feature quantity from the posture information at one time point or at a plurality of time points
- a determination unit that determines whether or not the extracted feature amount, which is the feature amount extracted by the feature amount extraction unit, is included in a set range in the feature amount space
- a data generation unit that generates data indicating a posture or movement having a feature amount included in the set range based on the determination by the determination unit that the extracted feature amount is not included in the set range
- the feature amount included in the set range is
- An information processing apparatus comprising a display control unit that generates an avatar image having a posture or movement indicated by data indicated by the display control unit.
- sensor device 20 distribution user terminal 216 operation unit 220 display unit 230 communication unit 240 control unit 250 base tool 251 sensor data acquisition unit 252 calibration unit 253 skeleton data generation unit 254 feature amount extraction unit 255 application interface 256 basic usage range storage unit 257 use range determination unit 258 data correction unit 260 application unit 261 base tool plug-in 262 additional use range storage unit 263 additional use range registration unit 265 retargeting unit 267 display control unit 268 distribution control unit 30 distribution server 40 viewing user terminal 50 processing terminal
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Social Psychology (AREA)
- Geometry (AREA)
- Processing Or Creating Images (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Description
1.情報処理システムの概要
2.配信ユーザ端末の構成
2-1.全体構成
2-2.基盤ツールの機能
2-3.アプリケーション部の機能
3.動作
3-1.基盤ツールの動作
3-2.アプリケーション部の動作
4.小括
5.変形例
4-1.第1の変形例
4-2.第2の変形例
4-3.その他の変形例
6.情報処理システムの他の構成例
5-1.第2の構成例
5-2.第3の構成例
5-3.第4の構成例
5-4.第5の構成例
5-5.第6の構成例
7.ハードウェア構成
8.補足
人間や動物等の動体の動きの情報を可視化するため、例えば身体の構造を示すスケルトン構造により表現されるスケルトンデータが用いられる。スケルトンデータは、部位の情報と、部位間を結ぶ線分であるボーンを含む。なお、スケルトン構造における部位は、例えば身体の末端部位や関節部位等に対応する。また、スケルトン構造におけるボーンは例えば人間の骨に相当し得るが、ボーンの位置や数は必ずしも実際の人間の骨格と整合していなくてもよい。
センサ装置10は、例えば加速度(Acceleration)を取得する加速度センサや角速度(Angular velocity)を取得するジャイロセンサ(角速度センサ)等の慣性センサ(IMU:Inertial Measurement Unit)を含む。)を含む。また、センサ装置10は、地磁気センサ、超音波センサ、気圧センサなどのセンサを含んでもよい。
配信ユーザ端末20は、配信ユーザU1が利用する情報処理装置の一例である。配信ユーザ端末20は、センサ装置10からセンサデータを受信し、受信したセンサデータを用いて配信ユーザU1のアバター映像を生成する。詳細については後述するが、配信ユーザ端末20は、センサデータに基づいて各装着部位の位置および姿勢を示す装着部位情報を取得し、装着部位情報に基づいて、スケルトン構造における各部位の位置情報および姿勢情報を含むスケルトンデータを生成する。さらに、配信ユーザ端末20は、スケルトンデータが示す姿勢を有するアバター映像を生成する。配信ユーザ端末20は、生成したアバター映像を配信サーバ30に送信し、配信サーバ30にアバター映像の配信を要求する。
配信サーバ30は、配信ユーザ端末20からの要求に基づき、アバター映像を視聴ユーザ端末40に配信する。図1においては、ある事業者により提供される配信サービスを実現する1つの配信サーバ30が示されているが、配信サービスを提供する複数の事業者および複数の配信サーバ30が存在してもよい。この場合、配信ユーザ端末20は、配信ユーザU1により指定された配信サービスを提供する配信サーバ30にアバター映像の配信を要求し得る。
視聴ユーザ端末40は、視聴ユーザ(例えば、図1に示したユーザU2およびユーザU3)が利用する情報処理装置である。視聴ユーザ端末40は、各種画面を表示する表示部、視聴ユーザの操作を検出する操作部、および視聴ユーザ端末40の動作全般を制御する制御部を有する。視聴ユーザ端末40は、例えば、視聴ユーザの操作に基づいて配信サーバ30に配信ユーザU1のアバター映像の配信を要求し、配信サーバ30から配信されたアバター映像を表示する。
しかし、モーションキャプチャ技術では、生成されるスケルトンデータが不正確になる場合がある。例えば、センサ方式においては、配信ユーザが装着していたセンサ装置が落下またはズレた場合に、不正確なスケルトンデータが生成される。光学式およびカメラ式においても、カメラのズレやドリフトの発生により姿勢情報の精度が劣化し得る。結果、モーションキャプチャ技術の適用先が例えばアバター映像の生成である場合には、不適切な姿勢または動きでアバター映像が生成されることが懸念される。
<2-1.全体構成>
図3は、本開示の一実施形態による配信ユーザ端末20の構成を示す説明図である。図3に示したように、本開示の一実施形態による配信ユーザ端末20は、操作部216と、表示部220と、通信部230と、制御部240と、を備える。
図4は、基盤ツール250の機能を示す説明図である。図4に示したように、基盤ツール250は、センサデータ取得部251、キャリブレーション部252、スケルトンデータ生成部253、特徴量抽出部254、アプリケーションインタフェース255、基本使用範囲記憶部256、使用範囲判断部257およびデータ修正部258を有する。
センサデータ取得部251は、センサ装置10から、装着部位の加速度または角速度などを示すセンサデータを取得する。
キャリブレーション部252は、センサデータ取得部251により取得されるセンサデータのキャリブレーションを行う。キャリブレーション部252は、基盤ツール250の使用開始時にキャリブレーションを実行してもよいし、配信ユーザによる操作に従ってキャリブレーションを実行してもよい。
スケルトンデータ生成部253は、センサデータ取得部251により取得されたセンサデータに基づいて各装着部位の位置および姿勢を示す装着部位情報を取得し、装着部位情報に基づいて、スケルトン構造における各部位の位置情報および姿勢情報を含む素スケルトンデータを生成する。以下、図5を参照して、素スケルトンデータの生成についてより具体的に説明する。
特徴量抽出部254は、特徴量抽出部254により生成された素スケルトンデータ(配信ユーザの姿勢情報)から特徴量を抽出する。例えば、特徴量抽出部254は、1の時点における素スケルトンデータであるポーズから、当該ポーズの特徴量であるポーズ特徴量を抽出する。特徴量抽出部254により抽出されるポーズ特徴量は、類似するポーズ同士ではポーズ特徴量空間において近くに位置する特徴量である。特徴量抽出部254は、そのようなポーズ特徴量の抽出を可能とするように学習された、DNN(Deep Neural Network)のような識別器を用いてポーズ特徴量を抽出してもよい。
アプリケーションインタフェース255は、アプリケーション部260とのインタフェースである。アプリケーションインタフェース255は、API(Application Programming Interface)として構成されてもよい。例えば、アプリケーションインタフェース255は、アプリケーション部260からの要求に応じて配信ユーザのスケルトンデータをアプリケーション部260に返す。具体的には、アプリケーションインタフェース255は、後述するデータ修正部258により修正スケルトンデータが生成されている場合には修正スケルトンデータをアプリケーション部260に返し、修正スケルトンデータが生成されていない場合には素スケルトンデータをアプリケーション部260に返してもよい。また、アプリケーションインタフェース255は、アプリケーション部260から後述する追加使用範囲を示す情報を取得し、追加使用範囲を示す情報を使用範囲判断部257に渡す。
基本使用範囲記憶部256は、設定範囲の一例である基本使用範囲を示す情報を記憶する。基本使用範囲は、ポーズ特徴量空間またはモーション特徴量空間における一部の範囲である。例えば、ポーズの基本使用範囲は、ポーズ特徴量空間において人間がとり得るポーズの特徴量を含み、人間がとることが通常は想定されないポーズの特徴量を含まない範囲であってもよい。同様に、モーションの基本使用範囲は、モーション特徴量空間において人間がとり得るモーションの特徴量を含み、人間がとることが通常は想定されないモーションの特徴量を含まない範囲であってもよい。なお、基本使用範囲は、基本使用範囲に含まれない特徴量の範囲を示す情報が記憶されることで間接的に特定される範囲であってもよい。
使用範囲判断部257は、特徴量抽出部254により抽出された特徴量である抽出特徴量が、特徴量空間における使用範囲(設定範囲)に含まれるか否かを判断する。使用範囲は、基本使用範囲および追加使用範囲の論理和で形成される範囲であってもよい。例えば、使用範囲判断部257は、特徴量抽出部254により抽出されたポーズ特徴量が、ポーズ特徴量空間におけるポーズの使用範囲に含まれるか否かを判断する。また、使用範囲判断部257は、特徴量抽出部254により抽出されたモーション特徴量が、モーション特徴量空間におけるモーションの使用範囲に含まれるか否かを判断する。
データ修正部258は、特徴量抽出部254により抽出された特徴量が使用範囲に含まれないと使用範囲判断部257に判断されたことに基づき、使用範囲に含まれる特徴量を使用特徴量として取得し、当該使用特徴量を用いてポーズまたはモーションを示す修正スケルトンデータを生成する。例えば、データ修正部258は、特徴量抽出部254により抽出された特徴量と使用範囲に含まれる各特徴量との、特徴量空間における位置関係(すなわち、ユークリッド距離)に応じて、使用範囲に含まれる特徴量から使用特徴量を取得する。より具体的には、データ修正部258は、使用範囲に含まれる特徴量のうちで、特徴量抽出部254により抽出された特徴量に最も近い特徴量を使用特徴量として取得してもよい。ここで、図6を参照して、データ修正部258により生成される修正スケルトンデータの具体例を説明する。
以上、基盤ツール250の機能を説明した。続いて、図7を参照し、アプリケーション部260の機能を説明する。
基盤ツールプラグイン261は、基盤ツール250とのインタフェースである。基盤ツールプラグイン261は、基盤ツール250からデータを受け取り、当該データをアプリケーション部260で扱えるフォーマットに変換する。例えば、基盤ツールプラグイン261は、基盤ツール250から素スケルトンデータまたは修正スケルトンデータなどのスケルトンデータを受け取る。
追加使用範囲記憶部262は、設定範囲の一例である追加使用範囲を示す情報を記憶する。追加使用範囲は、ポーズ特徴量空間またはモーション特徴量空間における一部の範囲である。追加使用範囲は、例えば、アバター映像として使用されるキャラクターにとって適切なポーズまたはモーションの特徴量を含む範囲であってもよい。なお、追加使用範囲は、追加使用範囲に含まれない特徴量の範囲を示す情報が記憶されることで間接的に特定される範囲であってもよい。
追加使用範囲登録部263は、追加使用範囲記憶部262に追加使用範囲を登録する機能を有する。追加使用範囲登録部263は、多様な方法により追加使用範囲記憶部262に追加使用範囲を登録し得る。以下、追加使用範囲登録部263がポーズの追加使用範囲を追加使用範囲記憶部262に登録するための幾つかの方法例を説明する。
リターゲティング部265は、基盤ツールプラグイン261から配信ユーザのスケルトンデータを受け取り、当該スケルトンデータをリターゲットすることで、スケルトンデータが示す姿勢または動きを有するアバター映像を生成する。
表示制御部267は、多様な表示画面を生成し、生成した表示画面を表示部220に表示させる。例えば、表示制御部267は、上述したポーズ選択画面を生成し、ポーズ選択画面を表示部220に表示させる。また、表示制御部267は、リターゲティング部265により生成されたアバター映像を含むアバター表示画面を生成し、当該アバター表示画面を表示部220に表示させる。
配信制御部268は、リターゲティング部265により生成されたアバター映像の配信を配信サーバ30に送信し、配信サーバ30にアバター映像の配信を要求する。以下、アバター映像の配信が開始されると、表示制御部267は、配信ユーザ用の表示画面を生成し、表示画面を表示部220に表示させる。以下、表示制御部267により生成される表示画面の具体例を説明する。
以上、本開示の一実施形態による情報処理システムの構成を説明した。続いて、本開示の一実施形態による情報処理システムの動作を説明する。なお、以下では主にポーズ単位で修正スケルトンデータが生成される例を説明するが、以下に説明する動作は、モーション単位で修正スケルトンデータが生成される場合にも同様に適用可能である。
図15は、基盤ツール250の動作を示すフローチャートである。図15に示したように、まず、基盤ツール250のスケルトンデータ生成部253が、センサデータ取得部251により取得されたセンサデータに基づいて現在時刻における素スケルトンデータを生成する(S404)。そして、特徴量抽出部254が、素スケルトンデータのポーズ特徴量を抽出する(S408)。
図17は、アプリケーション部260の動作を示すフローチャートである。図17に示したように、まず、基盤ツールプラグイン261に基盤ツール250からスケルトンデータが供給される(S504)。基盤ツール250において修正スケルトンデータが生成されていない場合には素スケルトンデータが供給され、基盤ツール250において修正スケルトンデータが生成されている場合には修正スケルトンデータが供給される。基盤ツール250において修正スケルトンデータが生成されている場合には、修正スケルトンデータに加えて素スケルトンデータが供給されてもよい。
以上説明した本開示の一実施形態によれば、多様な作用効果が得られる。例えば、本開示の一実施形態によれば、素スケルトンデータから抽出された特徴量が特徴量空間における使用範囲に含まれない場合に、使用範囲に含まれる特徴量を用いて修正スケルトンデータが生成される。従って、配信ユーザが装着していたセンサ装置10が落下またはズレが生じた場合などに不適切なポーズの素スケルトンデータが生成された場合でも、修正スケルトンデータを用いることで適切かつ自然なアバター映像を提供することが可能である。アバター映像のライブ配信を行っている場合には、ライブ配信を違和感なく続行することが可能である。また、配信ユーザが倫理的に不適切なポーズまたはモーションをとった場合にも、修正スケルトンデータが用いられることにより、不適切なアバター映像が配信されることを防止できる。
以上、本開示の一実施形態を説明した。以下では、上述した実施形態の幾つかの変形例を説明する。なお、以下に説明する各変形例は、単独で上述した実施形態に適用されてもよいし、組み合わせで上述した実施形態に適用されてもよい。また、各変形例は、上述した構成に代えて適用されてもよいし、上述した構成に対して追加的に適用されてもよい。
上記では、素スケルトンデータから抽出された特徴量が使用範囲に含まれる場合には修正スケルトンデータが生成されない例を説明した。しかし、データ修正部258は、素スケルトンデータから抽出された特徴量が使用範囲に含まれる場合であっても、修正スケルトンデータを生成してもよい。本例を、第1の変形例として、図18を参照して説明する。
上記では、全身の素スケルトンデータの特徴量が使用範囲内であるか否かが判断され、修正スケルトンデータが全身単位で生成される例を説明したが、これら判断および生成は部位ごとに行われてもよい。本例を、第2の変形例として、図19を参照して説明する。
その他、上述した実施形態には多様な変形例を適用可能である。例えば、上述した実施形態では、基盤ツール250において基本使用範囲が管理され、アプリケーション部260において追加使用範囲が管理される例を説明したが、基盤ツール250における基本使用範囲の管理、またはアプリケーション部260における追加使用範囲の管理は行われなくてもよい。この場合、使用範囲は、基本使用範囲または追加使用範囲のみであってもよい。
上記では、情報処理システムの第1の構成例として、配信ユーザ端末20が基盤ツール250およびアプリケーション部260を有する構成例を説明した。しかし、本開示の情報処理システムには他の構成例も考えられる。以下、情報処理システムの他の構成例を説明する。
図20は、情報処理システムの第2の構成例を示す説明図である。図20に示したように、第2の構成例による情報処理システムは、配信ユーザ端末20-2および処理端末50-2を有する。配信ユーザ端末20-2と処理端末50-2はネットワーク12を介して接続されている。配信ユーザ端末20-2は、基盤ツール250を有し、アプリケーション部260を有さない。アプリケーション部260は、処理端末50-2に実装されている。
図21は、情報処理システムの第3の構成例を示す説明図である。図21に示したように、第3の構成例による情報処理システムは、配信ユーザ端末20-3および処理端末50-3を有する。配信ユーザ端末20-3と処理端末50-3はネットワーク12を介して接続されている。配信ユーザ端末20-3は、基盤ツール250およびアプリケーション部260-3を有する。アプリケーション部260-3は、図7を参照して説明したアプリケーション部260が有する構成のうち、リターゲティング部265および配信制御部268を有さない。代わりに、処理端末50-3がリターゲティング部265および配信制御部268を有する。
図22は、情報処理システムの第4の構成例を示す説明図である。図22に示したように、第4の構成例による情報処理システムは、配信ユーザ端末20-4および処理端末50-4を有する。配信ユーザ端末20-4と処理端末50-4はネットワーク12を介して接続されている。配信ユーザ端末20-4は、基盤ツール250を有する。処理端末50-4は、アプリケーション部260-4を有する。アプリケーション部260-4は配信制御部268の機能を含まず、処理端末50-4は別途配信制御部268の機能を有する。
図23は、情報処理システムの第5の構成例を示す説明図である。図23に示したように、第5の構成例による情報処理システムは、配信ユーザ端末20-5および処理端末50-5を有する。配信ユーザ端末20-5と処理端末50-5はネットワーク12を介して接続されている。配信ユーザ端末20-5は、基盤ツール250を有する。処理端末50-5は、アプリケーション部260-5を有する。アプリケーション部260-5はリターゲティング部265および配信制御部268の機能を含まず、処理端末50-5は別途リターゲティング部265および配信制御部268の機能を有する。
上記では、主に、PC型の配信ユーザ端末20に操作部216、表示部220、通信部230および制御部240などの機能が実装される例を説明したが、これらの機能は、スマートフォンのような携帯端末に実装されてもよい。また、上記機能は、複数の携帯端末に分散的に実装されてもよいし、分散的かつ重複的に実装されてもよい。図24を参照し、第6の構成例として、上記機能が複数の携帯端末に分散的に実装される例を説明する。
以上、本開示の実施形態を説明した。上述したスケルトンデータの生成および特徴量の抽出などの情報処理は、ソフトウェアと、以下に説明する配信ユーザ端末20のハードウェアとの協働により実現される。
以上、添付図面を参照しながら本開示の好適な実施形態について詳細に説明したが、本開示はかかる例に限定されない。本開示の属する技術の分野における通常の知識を有する者であれば、請求の範囲に記載された技術的思想の範疇内において、各種の変更例または修正例に想到し得ることは明らかであり、これらについても、当然に本開示の技術的範囲に属するものと了解される。
(1)
動体の姿勢を示す姿勢情報を取得することと、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出することと、
抽出された特徴量である抽出特徴量が、特徴量空間における設定範囲に含まれるか否かを判断することと、
前記抽出特徴量が前記設定範囲に含まれないと判断されたことに基づき、前記設定範囲に含まれる特徴量を使用特徴量として取得し、当該使用特徴量を用いて姿勢または動きを示すデータを生成することと、
を含む、情報処理方法。
(2)
前記データを生成することは、前記抽出特徴量と前記設定範囲に含まれる各特徴量との前記特徴量空間における位置関係に応じて、前記設定範囲に含まれる特徴量から前記使用特徴量を取得することを含む、前記(1)に記載の情報処理方法。
(3)
前記設定範囲に含まれる特徴量から前記使用特徴量を取得することは、前記設定範囲に含まれる特徴量の内で、前記特徴量空間において前記抽出特徴量に最も近い特徴量を前記使用特徴量として取得することを含む、前記(2)に記載の情報処理方法。
(4)
前記データを生成することは、前記抽出特徴量と前記使用特徴量を混合して混合特徴量を生成し、混合特徴量を有する姿勢または動きを示すデータを生成することを含む、前記(1)~(3)のいずれか一項に記載の情報処理方法。
(5)
前記混合特徴量を生成することは、前記抽出特徴量が前記設定範囲に含まれないと判断されている継続時間に応じた割合で前記抽出特徴量と前記使用特徴量を混合することを含む、前記(4)に記載の情報処理方法。
(6)
前記混合特徴量を生成することは、前記継続時間が長くなるほど前記使用特徴量を混合する割合を増加させることを含む、前記(5)に記載の情報処理方法。
(7)
前記抽出特徴量が前記設定範囲に含まれないと判断された後、前記抽出特徴量が前記設定範囲に含まれると判断されるようになった場合、前記混合特徴量を生成することは、前記抽出特徴量が前記設定範囲に含まれると判断されるようになってからの経過時間が長くなるほど前記使用特徴量を混合する割合を減少させることを含む、前記(4)~(6)のいずれか一項に記載の情報処理方法。
(8)
前記抽出特徴量が前記設定範囲に含まれないと判断されたことの発生回数または発生頻度が閾値を上回ったことに基づき、ユーザへの所定の通知の出力を制御することをさらに含む、前記(1)~(7)のいずれか一項に記載の情報処理方法。
(9)
前記所定の通知は、前記姿勢情報を取得するためのセンサのキャリブレーションを誘導する通知である、前記(8)に記載の情報処理方法。
(10)
前記抽出特徴量が前記設定範囲に含まれると判断されたことに基づき、前記設定範囲内に含まれる特徴量から予測された前記動体の未来の姿勢または動きを示す予測特徴量を取得し、前記予測特徴量を用いて姿勢または動きを示すデータを生成することとをさらに含む、前記(1)~(9)のいずれか一項に記載の情報処理方法。
(11)
前記データを生成することは、前記抽出特徴量が前記設定範囲に含まれないと判断されたことに基づき前記抽出特徴量が前記設定範囲に含まれないことを示す通知をユーザに出力すること、および、ユーザにより姿勢または動きの調整を指示する操作が行われたことに基づき前記使用特徴量を用いて姿勢または動きを示すデータを生成すること、を含む、前記(1)~(10)のいずれか一項に記載の情報処理方法。
(12)
動体を構成する複数の部位のうちの1または2以上の部位ごとに実行される、前記(1)~(11)のいずれか一項に記載の情報処理方法。
(13)
前記設定範囲を設定する設定段階をさらに含み、
前記設定段階は、
動体の姿勢を示す姿勢情報を取得することと、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出することと、
抽出された特徴量が含まれるように前記設定範囲を設定することと、
を含む、前記(1)~(12)のいずれか一項に記載の情報処理方法。
(14)
前記設定範囲を設定する設定段階をさらに含み、
前記設定段階は、
動体の姿勢を示す姿勢情報を取得することと、
複数の時点における前記姿勢情報を繋ぐ動きの特徴量、または当該動きを構成する各姿勢の特徴量を抽出することと、
抽出された特徴量が含まれるように前記設定範囲を設定することと、
を含む、前記(1)~(12)のいずれか一項に記載の情報処理方法。
(15)
前記設定範囲を設定する設定段階をさらに含み、
前記設定段階は、
事前に登録されている姿勢または動きのうちでユーザにより指定された姿勢または動きの特徴量が含まれるように前記設定範囲を設定することを含む、前記(1)~(12)のいずれか一項に記載の情報処理方法。
(16)
生成された前記データが示す姿勢または動きを有するアバター映像を生成することをさらに含む、前記(1)~(15)のいずれか一項に記載の情報処理方法。
(17)
ネットワークを介して前記アバター映像を配信することをさらに含む、前記(16)に記載の情報処理方法。
(18)
前記姿勢情報を取得することは、異なるモーションキャプチャ技術を用いてモーションキャプチャ技術ごとに姿勢情報を取得することを含み、
前記データを生成することは、いずれかのモーションキャプチャ技術により得られた姿勢情報の抽出特徴量が前記設定範囲に含まれないと判断されたことに基づき、前記設定範囲に含まれると判断された他のモーションキャプチャ技術により得られた抽出特徴量を前記使用特徴量として用いて前記データを生成することを含む、前記(1)に記載の情報処理方法。
(19)
動体の姿勢を示す姿勢情報を取得する姿勢情報取得部と、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出する特徴量抽出部と、
前記特徴量抽出部により抽出された特徴量である抽出特徴量が、特徴量空間における設定範囲に含まれるか否かを判断する判断部と、
前記抽出特徴量が前記設定範囲に含まれないと前記判断部により判断されたことに基づき、前記設定範囲に含まれる特徴量を有する姿勢または動きを示すデータを生成するデータ生成部と、
を備える、情報処理装置。
(20)
コンピュータを、
動体の姿勢を示す姿勢情報を取得する姿勢情報取得部と、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出する特徴量抽出部と、
前記特徴量抽出部により抽出された特徴量である抽出特徴量が、特徴量空間における設定範囲に含まれるか否かを判断する判断部と、
前記抽出特徴量が前記設定範囲に含まれないと前記判断部により判断されたことに基づき、前記設定範囲に含まれる特徴量を有する姿勢または動きを示すデータを生成するデータ生成部と、
として機能させるための、プログラム。
(21)
1の時点または複数の時点における動体の姿勢情報から特徴量を抽出された特徴量である抽出特徴量が、特徴量空間における設定範囲に含まれない場合に、前記設定範囲に含まれる特徴量を用いて生成された示すデータが示す姿勢または動きを有するアバター映像を生成する表示制御部を備える、情報処理装置。
20 配信ユーザ端末
216 操作部
220 表示部
230 通信部
240 制御部
250 基盤ツール
251 センサデータ取得部
252 キャリブレーション部
253 スケルトンデータ生成部
254 特徴量抽出部
255 アプリケーションインタフェース
256 基本使用範囲記憶部
257 使用範囲判断部
258 データ修正部
260 アプリケーション部
261 基盤ツールプラグイン
262 追加使用範囲記憶部
263 追加使用範囲登録部
265 リターゲティング部
267 表示制御部
268 配信制御部
30 配信サーバ
40 視聴ユーザ端末
50 処理端末
Claims (20)
- 動体の姿勢を示す姿勢情報を取得することと、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出することと、
抽出された特徴量である抽出特徴量が、特徴量空間における設定範囲に含まれるか否かを判断することと、
前記抽出特徴量が前記設定範囲に含まれないと判断されたことに基づき、前記設定範囲に含まれる特徴量を使用特徴量として取得し、当該使用特徴量を用いて姿勢または動きを示すデータを生成することと、
を含む、情報処理方法。 - 前記データを生成することは、前記抽出特徴量と前記設定範囲に含まれる各特徴量との前記特徴量空間における位置関係に応じて、前記設定範囲に含まれる特徴量から前記使用特徴量を取得することを含む、請求項1に記載の情報処理方法。
- 前記設定範囲に含まれる特徴量から前記使用特徴量を取得することは、前記設定範囲に含まれる特徴量の内で、前記特徴量空間において前記抽出特徴量に最も近い特徴量を前記使用特徴量として取得することを含む、請求項2に記載の情報処理方法。
- 前記データを生成することは、前記抽出特徴量と前記使用特徴量を混合して混合特徴量を生成し、混合特徴量を有する姿勢または動きを示すデータを生成することを含む、請求項1に記載の情報処理方法。
- 前記混合特徴量を生成することは、前記抽出特徴量が前記設定範囲に含まれないと判断されている継続時間に応じた割合で前記抽出特徴量と前記使用特徴量を混合することを含む、請求項4に記載の情報処理方法。
- 前記混合特徴量を生成することは、前記継続時間が長くなるほど前記使用特徴量を混合する割合を増加させることを含む、請求項5に記載の情報処理方法。
- 前記抽出特徴量が前記設定範囲に含まれないと判断された後、前記抽出特徴量が前記設定範囲に含まれると判断されるようになった場合、前記混合特徴量を生成することは、前記抽出特徴量が前記設定範囲に含まれると判断されるようになってからの経過時間が長くなるほど前記使用特徴量を混合する割合を減少させることを含む、請求項4に記載の情報処理方法。
- 前記抽出特徴量が前記設定範囲に含まれないと判断されたことの発生回数または発生頻度が閾値を上回ったことに基づき、ユーザへの所定の通知の出力を制御することをさらに含む、請求項1に記載の情報処理方法。
- 前記所定の通知は、前記姿勢情報を取得するためのセンサのキャリブレーションを誘導する通知である、請求項8に記載の情報処理方法。
- 前記抽出特徴量が前記設定範囲に含まれると判断されたことに基づき、前記設定範囲内に含まれる特徴量から予測された前記動体の未来の姿勢または動きを示す予測特徴量を取得し、前記予測特徴量を用いて姿勢または動きを示すデータを生成することとをさらに含む、請求項1に記載の情報処理方法。
- 前記データを生成することは、前記抽出特徴量が前記設定範囲に含まれないと判断されたことに基づき前記抽出特徴量が前記設定範囲に含まれないことを示す通知をユーザに出力すること、および、ユーザにより姿勢または動きの調整を指示する操作が行われたことに基づき前記使用特徴量を用いて姿勢または動きを示すデータを生成すること、を含む、請求項1に記載の情報処理方法。
- 動体を構成する複数の部位のうちの1または2以上の部位ごとに実行される、請求項1に記載の情報処理方法。
- 前記設定範囲を設定する設定段階をさらに含み、
前記設定段階は、
動体の姿勢を示す姿勢情報を取得することと、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出することと、
抽出された特徴量が含まれるように前記設定範囲を設定することと、
を含む、請求項1に記載の情報処理方法。 - 前記設定範囲を設定する設定段階をさらに含み、
前記設定段階は、
動体の姿勢を示す姿勢情報を取得することと、
複数の時点における前記姿勢情報を繋ぐ動きの特徴量、または当該動きを構成する各姿勢の特徴量を抽出することと、
抽出された特徴量が含まれるように前記設定範囲を設定することと、
を含む、請求項1に記載の情報処理方法。 - 前記設定範囲を設定する設定段階をさらに含み、
前記設定段階は、
事前に登録されている姿勢または動きのうちでユーザにより指定された姿勢または動きの特徴量が含まれるように前記設定範囲を設定することを含む、請求項1に記載の情報処理方法。 - 生成された前記データが示す姿勢または動きを有するアバター映像を生成することをさらに含む、請求項1に記載の情報処理方法。
- ネットワークを介して前記アバター映像を配信することをさらに含む、請求項16に記載の情報処理方法。
- 前記姿勢情報を取得することは、異なるモーションキャプチャ技術を用いてモーションキャプチャ技術ごとに姿勢情報を取得することを含み、
前記データを生成することは、いずれかのモーションキャプチャ技術により得られた姿勢情報の抽出特徴量が前記設定範囲に含まれないと判断されたことに基づき、前記設定範囲に含まれると判断された他のモーションキャプチャ技術により得られた抽出特徴量を前記使用特徴量として用いて前記データを生成することを含む、請求項1に記載の情報処理方法。 - 動体の姿勢を示す姿勢情報を取得する姿勢情報取得部と、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出する特徴量抽出部と、
前記特徴量抽出部により抽出された特徴量である抽出特徴量が、特徴量空間における設定範囲に含まれるか否かを判断する判断部と、
前記抽出特徴量が前記設定範囲に含まれないと前記判断部により判断されたことに基づき、前記設定範囲に含まれる特徴量を有する姿勢または動きを示すデータを生成するデータ生成部と、
を備える、情報処理装置。 - コンピュータを、
動体の姿勢を示す姿勢情報を取得する姿勢情報取得部と、
1の時点または複数の時点における前記姿勢情報から特徴量を抽出する特徴量抽出部と、
前記特徴量抽出部により抽出された特徴量である抽出特徴量が、特徴量空間における設定範囲に含まれるか否かを判断する判断部と、
前記抽出特徴量が前記設定範囲に含まれないと前記判断部により判断されたことに基づき、前記設定範囲に含まれる特徴量を有する姿勢または動きを示すデータを生成するデータ生成部と、
として機能させるための、プログラム。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180091883.XA CN116829065A (zh) | 2021-02-02 | 2021-12-07 | 信息处理方法、信息处理装置和程序 |
EP21924813.5A EP4290347A1 (en) | 2021-02-02 | 2021-12-07 | Information processing method, information processing device, and program |
KR1020237024037A KR20230135061A (ko) | 2021-02-02 | 2021-12-07 | 정보 처리 방법, 정보 처리 장치 및 프로그램 |
JP2022579362A JPWO2022168428A1 (ja) | 2021-02-02 | 2021-12-07 | |
US18/269,144 US20240077938A1 (en) | 2021-02-02 | 2021-12-07 | Information processing method, information processing device, and program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021014952 | 2021-02-02 | ||
JP2021-014952 | 2021-02-02 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022168428A1 true WO2022168428A1 (ja) | 2022-08-11 |
Family
ID=82741082
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/044934 WO2022168428A1 (ja) | 2021-02-02 | 2021-12-07 | 情報処理方法、情報処理装置およびプログラム |
Country Status (6)
Country | Link |
---|---|
US (1) | US20240077938A1 (ja) |
EP (1) | EP4290347A1 (ja) |
JP (1) | JPWO2022168428A1 (ja) |
KR (1) | KR20230135061A (ja) |
CN (1) | CN116829065A (ja) |
WO (1) | WO2022168428A1 (ja) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009070314A (ja) * | 2007-09-18 | 2009-04-02 | Sony Corp | 画像処理装置および画像処理方法、並びにプログラム |
JP2013257656A (ja) * | 2012-06-11 | 2013-12-26 | Kddi Corp | 動き類似度算出装置、動き類似度算出方法およびコンピュータプログラム |
CN105513114A (zh) * | 2015-12-01 | 2016-04-20 | 深圳奥比中光科技有限公司 | 三维动画生成的方法和装置 |
WO2019203188A1 (ja) | 2018-04-17 | 2019-10-24 | ソニー株式会社 | プログラム、情報処理装置、及び情報処理方法 |
US20200184668A1 (en) * | 2018-12-05 | 2020-06-11 | Qualcomm Incorporated | Systems and methods for three-dimensional pose determination |
-
2021
- 2021-12-07 KR KR1020237024037A patent/KR20230135061A/ko unknown
- 2021-12-07 US US18/269,144 patent/US20240077938A1/en active Pending
- 2021-12-07 CN CN202180091883.XA patent/CN116829065A/zh active Pending
- 2021-12-07 EP EP21924813.5A patent/EP4290347A1/en active Pending
- 2021-12-07 JP JP2022579362A patent/JPWO2022168428A1/ja active Pending
- 2021-12-07 WO PCT/JP2021/044934 patent/WO2022168428A1/ja active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009070314A (ja) * | 2007-09-18 | 2009-04-02 | Sony Corp | 画像処理装置および画像処理方法、並びにプログラム |
JP2013257656A (ja) * | 2012-06-11 | 2013-12-26 | Kddi Corp | 動き類似度算出装置、動き類似度算出方法およびコンピュータプログラム |
CN105513114A (zh) * | 2015-12-01 | 2016-04-20 | 深圳奥比中光科技有限公司 | 三维动画生成的方法和装置 |
WO2019203188A1 (ja) | 2018-04-17 | 2019-10-24 | ソニー株式会社 | プログラム、情報処理装置、及び情報処理方法 |
US20200184668A1 (en) * | 2018-12-05 | 2020-06-11 | Qualcomm Incorporated | Systems and methods for three-dimensional pose determination |
Also Published As
Publication number | Publication date |
---|---|
CN116829065A (zh) | 2023-09-29 |
EP4290347A1 (en) | 2023-12-13 |
JPWO2022168428A1 (ja) | 2022-08-11 |
KR20230135061A (ko) | 2023-09-22 |
US20240077938A1 (en) | 2024-03-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7169405B2 (ja) | 複合現実システムのための位置特定の決定 | |
Papagiannakis et al. | A survey of mobile and wireless technologies for augmented reality systems | |
CN110917614B (zh) | 基于区块链系统的云游戏系统及云游戏的控制方法 | |
US20180374268A1 (en) | Interactive mixed reality system for a real-world event | |
US10241565B2 (en) | Apparatus, system, and method of controlling display, and recording medium | |
US7576742B2 (en) | Picture display controller, moving-picture information transmission/reception system, picture display controlling method, moving-picture information transmitting/receiving method, and computer program | |
CN107948664A (zh) | 直播间视频播放控制方法、装置及终端 | |
CN112533017B (zh) | 直播方法、装置、终端及存储介质 | |
EP4161067A1 (en) | A method, an apparatus and a computer program product for video encoding and video decoding | |
CN112581571A (zh) | 虚拟形象模型的控制方法、装置、电子设备及存储介质 | |
WO2022168428A1 (ja) | 情報処理方法、情報処理装置およびプログラム | |
CN114005511A (zh) | 一种康复训练方法、系统、训练自助设备和存储介质 | |
JP2023153790A (ja) | プログラム | |
US20230269482A1 (en) | Information processing system, communication system, and image sharing method | |
WO2022215313A1 (ja) | 情報処理方法、情報処理装置およびプログラム | |
JP7433126B2 (ja) | 画像表示システム、画像表示装置、サーバ、画像表示方法およびプログラム | |
JP5359950B2 (ja) | 運動支援装置、運動支援方法およびプログラム | |
CN114100121A (zh) | 操作控制方法、装置、设备、存储介质及计算机程序产品 | |
Arai et al. | Wi-Foto 2: Heterogeneous device controller using Wi-Fi positioning and template matching | |
WO2021044851A1 (ja) | 情報処理装置、及び情報処理方法 | |
EP4250744A1 (en) | Display terminal, communication system, method for displaying, method for communicating, and carrier means | |
US11556308B2 (en) | Information processing system, information processing apparatus including circuitry to store position information of users present in a space and control environment effect production, information processing method, and room | |
EP4294019A1 (en) | Display terminal, communication system, display method, and communication method | |
US20240179267A1 (en) | Display terminal, communication system, and display method | |
JP7458731B2 (ja) | 画像生成システム、画像処理装置、情報処理装置、画像生成方法、及びプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21924813 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022579362 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18269144 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180091883.X Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021924813 Country of ref document: EP Effective date: 20230904 |