# US 2025/0148705 A1 · Locking and showing moving objects in virtual reality

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

- Number: US 2025/0148705 A1
- Document ID: US20250148705A1
- Status: Published application
- Kind: A1
- Application number: 18/501,066
- Filed: 2023-11-03
- Published: 2025-05-08
- Earliest claimed: 2023-11-03
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Raymund Lin; Nan Chen; Li Na Wang; Ye Chuan Wang; Ju Ling Liu
- Web page: https://patentgrep.com/patent/US20250148705A1

## CPC

- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 7/11: Region-based segmentation
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/20: in augmented reality scenes
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30241: Trajectory
- G06V 2201/07: Target detection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

According to one embodiment, a method, computer system, and computer program product for physical object tracking in virtual reality is provided. The present invention may include receiving input from a user identifying a specific physical object during a virtual reality session in a virtual reality environment; identifying the specific physical object in the physical proximity of the user; tracking the location of the specific physical object relative to the user; and responsive to receiving a command from the user, displaying the specific physical object to the user through a portal in the virtual reality environment.

## Claims

### Claim 1

A processor-implemented method for physical object tracking in virtual reality, the method comprising:
receiving input from a user identifying a specific physical object during a virtual reality session in a virtual reality environment;
identifying the specific physical object in a physical proximity of the user;
tracking the location of the specific physical object relative to the user; and
responsive to receiving a command from the user, displaying the specific physical object to the user through a portal in the virtual reality environment.

### Claim 2 (depends on 1)

The method of claim 1, wherein the identifying further comprises:
identifying one or more physical objects of a same type as the specific physical object in the physical proximity to the user using a generic object recognition model; and
identifying the specific physical object from among the located physical objects using a specific object recognition model.

### Claim 3 (depends on 2)

The method of claim 2, wherein the specific object recognition model is trained using a few-shot image classification process.

### Claim 4 (depends on 2)

The method of claim 2, wherein the specific object recognition model is trained using a method comprising:
responsive to prompting the user to record a plurality of images of the specific physical object and a background, receiving the plurality of images;
processing the received images into training images;
training the specific object recognition model on the training images.

### Claim 5 (depends on 4)

The method of claim 4, wherein the processing further comprises:
dividing the received images of the background into a plurality of regions to create a plurality of negative examples; and
compositing images of the specific physical object onto the plurality of regions to create a plurality of positive examples, wherein the training images comprise the plurality of negative examples and the plurality of positive examples.

### Claim 6 (depends on 1)

The method of claim 1, wherein the tracking further comprises;
Responsive to determining that the specific physical object has moved, utilizing a moving path prediction algorithm to select the most likely location of the specified physical object based on a movement history of the specific physical object.

### Claim 7 (depends on 1)

The method of claim 1, wherein the tracking is persistent across multiple virtual reality experiences.

### Claim 8

A computer system for physical object tracking in virtual reality, the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
receiving input from a user identifying a specific physical object during a virtual reality session in a virtual reality environment;
identifying the specific physical object in a physical proximity of the user;
tracking a location of the specific physical object relative to the user; and
responsive to receiving a command from the user, displaying the specific physical object to the user through a portal in the virtual reality environment.

### Claim 9 (depends on 8)

The computer system of claim 8, wherein the identifying further comprises:
identifying one or more physical objects of a same type as the specific physical object in the physical proximity to the user using a generic object recognition model; and
identifying the specific physical object from among the located physical objects using a specific object recognition model.

### Claim 10 (depends on 9)

The computer system of claim 9, wherein the specific object recognition model is trained using a few-shot image classification process.

### Claim 11 (depends on 9)

The computer system of claim 9, wherein the specific object recognition model is trained using a method comprising:
responsive to prompting the user to record a plurality of images of the specific physical object and a background, receiving the plurality of images;
processing the received images into training images;
training the specific object recognition model on the training images.

### Claim 12 (depends on 11)

The computer system of claim 11, wherein the processing further comprises:
dividing the received images of the background into a plurality of regions to create a plurality of negative examples; and
compositing images of the specific physical object onto the plurality of regions to create a plurality of positive examples, wherein the training images comprise the plurality of negative examples and the plurality of positive examples.

### Claim 13 (depends on 8)

The computer system of claim 8, wherein the tracking further comprises;
Responsive to determining that the specific physical object has moved, utilizing a moving path prediction algorithm to select the most likely location of the specified physical object based on a movement history of the specific physical object.

### Claim 14 (depends on 8)

The computer system of claim 8, wherein the tracking is persistent across multiple virtual reality experiences.

### Claim 15

A computer program product for physical object tracking in virtual reality, the computer program product comprising:
one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor to cause the processor to perform a method comprising:
receiving input from a user identifying a specific physical object during a virtual reality session in a virtual reality environment;
identifying a specific physical object in a physical proximity of the user;
tracking a location of the specific physical object relative to the user; and
responsive to receiving a command from the user, displaying the specific physical object to the user through a portal in the virtual reality environment.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein the identifying further comprises:
identifying one or more physical objects of a same type as the specific physical object in the physical proximity to the user using a generic object recognition model; and
identifying the specific physical object from among the located physical objects using a specific object recognition model.

### Claim 17 (depends on 16)

The computer program product of claim 16, wherein the specific object recognition model is trained using a few-shot image classification process.

### Claim 18 (depends on 16)

The computer program product of claim 16, wherein the specific object recognition model is trained using a method comprising:
responsive to prompting the user to record a plurality of images of the specific physical object and a background, receiving the plurality of images;
processing the received images into training images;
training the specific object recognition model on the training images.

### Claim 19 (depends on 18)

The computer program product of claim 18, wherein the processing further comprises:
dividing the received images of the background into a plurality of regions to create a plurality of negative examples; and
compositing images of the specific physical object onto the plurality of regions to create a plurality of positive examples, wherein the training images comprise the plurality of negative examples and the plurality of positive examples.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein the tracking further comprises;
Responsive to determining that the specific physical object has moved, utilizing a moving path prediction algorithm to select the most likely location of the specified physical object based on a movement history of the specific physical object.
