# US 2025/0155965 A1 · System and method for providing virtual reality service

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0155965 A1
- Document ID: US20250155965A1
- Status: Published application
- Kind: A1
- Application number: 18/763,858
- Filed: 2024-07-03
- Published: 2025-05-15
- Earliest claimed: 2023-11-09
- Assignees: Electronics and Telecommunications Research Institute
- Applicants: Electronics and Telecommunications Research Institute
- Inventors: Seong Min Baek; Youn Hee Gil; Hee Sook Shin; Cho Rong Yu; Yong Ho Lee; Sung Jin Hong
- Web page: https://patentgrep.com/patent/US20250155965A1

## CPC

- G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)}
- G06F 1/163: {Wearable computers, e.g. on a belt}
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 2207/10024: Color image
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/20212: Image combination
- G06T 2207/30196: Human being; Person
- G06T 2207/30201: Face
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system and method for providing a virtual reality service is provided. For the system and method capable of realizing an interaction image of a user's full body, the system includes a head-mounted device mounted on the head of the user, a first RGB-D sensor configured to be installed on the head-mounted device, generate first image data of the user, and be arranged to face the user, a second RGB-D sensor configured to be installed on the head-mounted device, generate second image data of the user, and be arranged to face the user, and a calculation device configured to obtain a skeleton image of the user on the basis of the first image data and the second image data, obtain posture information of the user on the basis of the skeleton image of the user, and generate an interaction image on the basis of the posture information of the user.

## Claims

### Claim 1

A system for providing a virtual reality service, the system comprising:
a head-mounted device mounted on the head of a user;
a first RGB-D sensor configured to be installed on the head-mounted device, generate first image data of the user, and be arranged to face the user;
a second RGB-D sensor configured to be installed on the head-mounted device, generate second image data of the user, and be arranged to face the user; and
a calculation device configured to obtain a skeleton image of the user on the basis of the first image data and the second image data, obtain posture information of the user on the basis of the skeleton image of the user, and generate an interaction image on the basis of the posture information of the user.

### Claim 2 (depends on 1)

The system of claim 1, wherein the calculation device unifies a coordinate system of the first image data and a coordinate system of the second image data into one coordinate system.

### Claim 3 (depends on 2)

The system of claim 2, wherein the calculation device merges the first image data and the second image data to generate merged image data comprising an image of the user's full body, and changes a viewpoint of the merged image data.

### Claim 4 (depends on 3)

The system of claim 3, wherein the calculation device inputs a virtual face image corresponding to a face area of the user into the merged image data.

### Claim 5 (depends on 4)

The system of claim 4, wherein the calculation device inputs the merged image data comprising the input virtual face image into a learning model and obtains a first skeleton image of the user from the learning model.

### Claim 6 (depends on 5)

The system of claim 5, wherein the calculation device defines the virtual face image as the highest level joint node and obtains a second skeleton image comprising lower level joint nodes defined on the basis of the highest level joint node.

### Claim 7 (depends on 6)

The system of claim 6, wherein the calculation device obtains the posture information of the user on the basis of one of the first skeleton image and the second skeleton image.

### Claim 8 (depends on 1)

The system of claim 1, further comprising:
a third RGB-D sensor configured to be installed on the head-mounted device, generate third image data of the user, and be arranged to face the user.

### Claim 9 (depends on 8)

The system of claim 8, wherein the calculation device obtains the skeleton image of the user on the basis of the first image data to the third image data.

### Claim 10 (depends on 9)

The system of claim 9, wherein the first image data comprises an image of an upper half of the user's body,
the second image data comprises an image of a lower half of the user's body viewed from a first direction, and
the third image data comprises an image of the lower half of the user's body viewed from a second direction.

### Claim 11

A method for providing a virtual reality service to a user on the basis of image data received from a plurality of sensors installed on a head-mounted device mounted on the user's head, the method comprising:
receiving first image data comprising an image of an upper half of the user's body from a first RGB-D sensor among the plurality of sensors;
receiving second image data comprising an image of a lower half of the user's body viewed from a first direction from a second RGB-D sensor among the plurality of sensors;
obtaining a skeleton image of the user on the basis of the first image data and the second image data;
obtaining posture information of the user on the basis of the skeleton image of the user; and
generating an interaction image on the basis of the posture information of the user.

### Claim 12 (depends on 11)

The method of claim 11, wherein the obtaining of the skeleton image of the user unifies a coordinate system of the first image data and a coordinate system of the second image data into one coordinate system.

### Claim 13 (depends on 12)

The method of claim 12, wherein the obtaining of the skeleton image of the user comprises:
merging the first image data and the second image data to generate merged image data comprising an image of the user's full body; and
changing a viewpoint of the merged image data.

### Claim 14 (depends on 13)

The method of claim 13, wherein the obtaining of the skeleton image of the user further comprises:
inputting a virtual face image corresponding to a face area of the user into the merged image data after the viewpoint is changed.

### Claim 15 (depends on 14)

The method of claim 14, wherein the obtaining of the skeleton image of the user further comprises:
inputting the merged image data comprising the input virtual face image into a learning model and obtaining a first skeleton image from the learning model.

### Claim 16 (depends on 15)

The method of claim 15, wherein the obtaining of the skeleton image of the user further comprises:
defining the virtual face image as the highest level joint node and obtaining a second skeleton image comprising the highest level joint node and lower level joint nodes.

### Claim 17 (depends on 16)

The method of claim 16, wherein the obtaining of the posture information of the user further comprises:
obtaining the posture information of the user on the basis of one of the first skeleton image and the second skeleton image.

### Claim 18 (depends on 11)

The method of claim 11, further comprising:
receiving third image data of the user from a third RGB-D sensor among the plurality of sensors.

### Claim 19 (depends on 18)

The method of claim 18, wherein the obtaining of the skeleton image of the user obtains the skeleton image of the user on the basis of the first third image data to the third image data.

### Claim 20 (depends on 19)

The method of claim 19, wherein the third image data comprises an image of the lower half of the user's body viewed from a second direction intersecting the first direction.
