Granted Patent B2

US 12,564,783 · App. 17/768,278 · Granted Mar 3, 2026

Inventors: Yoshinori Ohashi (Tokyo, JP); Keita Mochizuki (Tokyo, JP); Yasutaka Fukumoto (Tokyo, JP)

Assignees: Sony Group Corporation; Sony Interactive Entertainment Inc.

A63F13/212A63F13/211G06T7/20G06T7/70

Abstract

Claims (59)

1 . An information processing apparatus comprising:

a processor configured to:

acquire, from a plurality of sensors attached to a plurality of body parts and configured to connect to the information processing apparatus, information regarding movement acceleration and posture angular velocity of a body part of the plurality of body parts;

estimate, on a basis of the information, a movement velocity in a predetermined coordinate system of the body part of the plurality of body parts;

estimate, for the body part of the plurality of body parts, a position by fusing position information derived from the estimated movement velocity, and directly acquired position information for the body part, the fusing comprising dynamically weighting a contribution of each source based on elapsed time since a last direct position measurement of the body part; and

subject information regarding the estimated position of the body part to a predetermined process that estimates a posture of a target person by performing an inverse kinematics model computation.

2 . The information processing apparatus according to claim 1 , wherein the processor is further configured to:

estimate a direction of gravity in the predetermined coordinate system, using information regarding the direction of gravity to correct the movement acceleration; and

estimate, on a basis of the information regarding the movement acceleration, a movement velocity in the predetermined coordinate system of the body part.

3 . The information processing apparatus according to claim 1 , wherein the processor is further configured to:

estimate the movement velocity of the body part using information that is related to temporal changes in the movement acceleration and posture angular velocity in the predetermined coordinate system of the body part and is estimated on a basis of the information regarding the movement acceleration and posture angular velocity.

4 . The information processing apparatus according to claim 1 , wherein the processor is further configured to:

acquire information regarding the position of the body part and posture of the body parts of the target person that are estimated by the inverse kinematics model computation; and

estimate the position of the body part by combining the information regarding the position of the body part and the information regarding the movement velocity of the body part.

5 . The information processing apparatus according to claim 1 , wherein the processor is further configured to:

estimate the position of the body parts by combining the information regarding the movement acceleration and posture angular velocity and the information regarding the movement velocity of the body part with a weight applied to each piece of the information.

6 . The information processing apparatus according to claim 5 , wherein the processor is further configured to determine the weight according to a length of time elapsed since the position of the body part has not been acquired.

7 . The information processing apparatus according to claim 5 , wherein the processor is further configured to determine the weight on a basis of at least one of an amount of movement, movement velocity, and movement acceleration of the body part.

8 . The information processing apparatus according to claim 1 , wherein

the body part includes a hand of a target person, and

wherein the processor is further configured to estimate a posture of a wrist by performing the inverse kinematics model computation on a predetermined human body model on a basis of information regarding posture angular velocity and movement acceleration of the hand, to estimate a position of the wrist on a basis of the posture of the wrist, and further configured to estimate a position of the hand on a basis of information regarding the position of the wrist.

9 . A method comprising:

acquiring, from a plurality of sensors attached to a plurality of body parts, at least information regarding movement acceleration of a body part of the plurality of body parts and posture angular velocity of the body part of the plurality of body parts;

estimating, on a basis of the information a movement velocity in a predetermined coordinate system of the body part of the plurality of body parts;

estimating, for the body part of the plurality of body parts, a position by fusing position information derived from the estimated movement velocity, and directly acquired position information for the body part, the fusing comprising dynamically weighting a contribution of each source based on elapsed time since a last direct position measurement of the body part; and

subjecting the information regarding the position of the body part to a predetermined process that estimates a posture of a target person by inverse kinematics model computation.

10 . A non-transitory, computer readable storage medium containing a program for an information processing apparatus, when executed, causing the information processing apparatus to carry out actions, comprising:

acquiring, from a plurality of sensors attached to a plurality of body parts, at least information regarding movement acceleration of a body part of the plurality of body parts and posture angular velocity of the body part of the plurality of body parts;

estimating, on a basis of the information, movement velocity in a predetermined coordinate system of the body part of the body parts;

estimating, for the body part of the plurality of body parts, a position by fusing position information derived from the estimated movement velocity, and directly acquired position information for the body part, the fusing comprising dynamically weighting a contribution of each source based on elapsed time since a last direct position measurement of the body part; and

subjecting information regarding the estimated position of the body part to a predetermined process that estimates a posture of a target person by performing an inverse kinematics model computation.

11 . The method of claim 9 , wherein estimating the movement velocity further comprises:

estimating a direction of gravity in the predetermined coordinate system, using information regarding the direction of gravity to correct the movement acceleration; and

estimating, on a basis of the information regarding the movement acceleration, a movement velocity in the predetermined coordinate system of the body part.

12 . The method of claim 9 , wherein estimating the movement velocity further comprises:

estimating the movement velocity of the body part using information that is related to temporal changes in the movement acceleration and posture angular velocity in the predetermined coordinate system of the body part and is estimated on a basis of the information regarding the movement acceleration and posture angular velocity.

13 . The method of claim 9 , further comprising:

acquiring information regarding the position of the body part and posture of the body part of the target person that are estimated by the inverse kinematics model computation; and

estimating the position of the body part by combining the information regarding the position of the body part and the information regarding the movement velocity of the body part.

14 . The method of claim 9 , further comprising:

estimating the position of the body part by combining the information regarding the movement acceleration and posture angular velocity and the information regarding the movement velocity of the body part with a weight applied to each piece of the information.

15 . The method of claim 9 , further comprising:

estimating a posture of a wrist by performing the inverse kinematics model computation on a predetermined human body model on a basis of information regarding posture angular velocity and movement acceleration of a hand among the plurality of the body parts;

estimating a position of the wrist on a basis of the posture of the wrist; and

estimating a position of the hand on a basis of information regarding the position of the wrist.

16 . The non-transitory, computer readable storage medium of claim 10 , wherein estimating the movement velocity further comprises:

estimating a direction of gravity in the predetermined coordinate system, using information regarding the direction of gravity to correct the movement acceleration; and

estimating, on a basis of the information regarding the movement acceleration, a movement velocity in the predetermined coordinate system of the body part.

17 . The non-transitory, computer readable storage medium of claim 10 , wherein estimating the movement velocity further comprises:

estimating the movement velocity of the body part using information that is related to temporal changes in the movement acceleration and posture angular velocity in the predetermined coordinate system of the body part and is estimated on a basis of the information regarding the movement acceleration and posture angular velocity.

18 . The non-transitory, computer readable storage medium of claim 10 , wherein the actions further comprise:

acquiring information regarding the position of the body part and posture of the body part of the target person that are estimated by the inverse kinematics model computation; and

estimating the position of the body part by combining the information regarding the position of the body part and the information regarding the movement velocity of the body part.

19 . The non-transitory, computer readable storage medium of claim 10 , wherein the actions further comprise:

estimating the position of the body part by combining the information regarding the movement acceleration and posture angular velocity and the information regarding the movement velocity of the body part with a weight applied to each piece of the information.

20 . The non-transitory, computer readable storage medium of claim 10 , wherein the actions further comprise:

estimating a posture of a wrist by performing the inverse kinematics model computation on a predetermined human body model on a basis of information regarding posture angular velocity and movement acceleration of a hand among the plurality of the body parts;

estimating a position of the wrist on a basis of the posture of the wrist; and

estimating a position of the hand on a basis of information regarding the position of the wrist.

Assignments (1)

Continuity (1)

References Cited (27)