# US 2026/0065697 A1 · Apparatus and method of video tracking

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

- Number: US 2026/0065697 A1
- Document ID: US20260065697A1
- Status: Published application
- Kind: A1
- Application number: 19/314,770
- Filed: 2025-08-29
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: Sony Interactive Entertainment Inc.
- Applicants: Sony Interactive Entertainment Inc.
- Inventors: Simon Andrew St. John Brislin; Nicholas Anthony Edward Ryan; Andrew Swann; Pritpal Singh Panesar; Andrew William Walker
- Web page: https://patentgrep.com/patent/US20260065697A1

## CPC

- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- G06V 20/635: {Overlay text, e.g. embedded captions in a TV programme}
- G06V 20/44: {Event detection}
- G06V 20/48: {Matching video sequences}
- G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images
- G06V 30/10: Character recognition
- G06V 30/1444: {Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields}
- G06V 30/242: Division of the character sequences into groups prior to recognition; Selection of dictionaries
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method of identifying text that appears within a sequence of images comprises the steps of defining one or more regions of respective images in which text will appear, detecting when text has appeared in one or more of the defined regions, identifying text within a defined region when text has been detected there, and selecting for output identified text that has appeared, or a respective image of the sequence of images that comprise such identified text.

## Claims

### Claim 1

A method of identifying text that appears within a sequence of images, comprising the steps of:
defining one or more regions of respective images in which text will appear;
detecting when text has appeared in one or more of the defined regions;
identifying text within a defined region when text has been detected there; and
selecting for output identified text that has appeared, or a respective image of the sequence of images that comprise such identified text.

### Claim 2 (depends on 1)

The method of claim 1, wherein detecting when text has appeared comprises:
identifying a change in content between successive images, within one or more of the defined regions, that exceeds a predetermined threshold.

### Claim 3 (depends on 1)

The method of claim 1, wherein detecting when text has appeared comprises:
comparing a perceptual hash of at least part of a defined region with a perceptual hash of reference text for the defined region, and detecting text when a match meets a predetermined threshold.

### Claim 4 (depends on 3)

The method of claim 3, wherein identifying text within a defined region comprises:
obtaining a text string associated with the perceptual hash of the reference text.

### Claim 5 (depends on 1)

The method of claim 1, wherein detecting when text has appeared comprises:
performing optical character recognition ‘OCR’ within at least part of a defined region, and detecting text when a predetermined number of characters is recognised.

### Claim 6 (depends on 1)

The method of claim 1, wherein identifying text within a defined region comprises:
performing OCR within at least part of a defined region.

### Claim 7 (depends on 6)

The method of claim 6, in which OCR is performed with reference to a dictionary comprising words obtained from one or more selected from the list consisting of:
i. data associated with the content from which the sequence of images is produced;
ii. data included within game code from which the sequence of images is produced; and
iii. prior OCR of a video of a sequence of images produced by the same content or game.

### Claim 8 (depends on 1)

The method of claim 1, wherein identifying text further comprises the step of identifying text in part of a defined region, or in another defined region, other than where text was detected in the detecting step.

### Claim 9 (depends on 1)

The method of claim 1, wherein detecting when text has appeared is performed with a periodicity shorter than the duration for which text is displayed by default.

### Claim 10 (depends on 9)

The method of claim 9, in which if text is displayed for a period less than the default, a defined region on an image prior to the text disappearing is captured for text identification.

### Claim 11 (depends on 1)

The method of claim 1, further comprising:
obtaining a database of data items each representing one of a plurality of events;
comparing data representing identified text with one or more data items in the database; and
identifying an event for output if the compared data matches a data item in the database to a predetermined matching threshold degree.

### Claim 12 (depends on 11)

The method of claim 11, in which:
the database comprises an event ID for at least some acknowledged events, and the method comprises the step of:
notifying the event ID of an identified acknowledged event to one or more selected from the list consisting of:
i. a user-help process;
ii. a game summarisation process;
iii. a social feed process;
iv. a save-game process;
v. a save video-feed process; and
vi. a telemetry process.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
storing a predetermined number of adjacent images within the sequence of images, including the image that comprises identified text, as a video clip of the graphically acknowledged event.

### Claim 14

A system configured to identify text that appears within a sequence of images, the system comprising: one or more computers; and
one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
defining one or more regions of respective images in which text will appear;
detecting when text has appeared in one or more of the defined regions;
identifying text within a defined region when text has been detected there; and
selecting for output identified text that has appeared, or a respective image of the sequence of images that comprise such identified text.

### Claim 15 (depends on 14)

The system of claim 14, wherein detecting when text has appeared comprises:
identifying a change in content between successive images, within one or more of the defined regions, that exceeds a predetermined threshold.

### Claim 16 (depends on 14)

The system of claim 14, wherein detecting when text has appeared comprises:
comparing a perceptual hash of at least part of a defined region with a perceptual hash of reference text for the defined region, and detecting text when a match meets a predetermined threshold.

### Claim 17 (depends on 16)

The system of claim 16, wherein identifying text within a defined region comprises:
obtaining a text string associated with the perceptual hash of the reference text.

### Claim 18

One or more computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
defining one or more regions of respective images in which text will appear;
detecting when text has appeared in one or more of the defined regions;
identifying text within a defined region when text has been detected there; and
selecting for output identified text that has appeared, or a respective image of the sequence of images that comprise such identified text.

### Claim 19 (depends on 18)

The computer-readable storage media of claim 18, wherein detecting when text has appeared comprises:
identifying a change in content between successive images, within one or more of the defined regions, that exceeds a predetermined threshold.

### Claim 20 (depends on 18)

The computer-readable storage media of claim 18, wherein detecting when text has appeared comprises:
comparing a perceptual hash of at least part of a defined region with a perceptual hash of reference text for the defined region, and detecting text when a match meets a predetermined threshold.