# US 2025/0157092 A1 · Dynamic modification of video content

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

- Number: US 2025/0157092 A1
- Document ID: US20250157092A1
- Status: Published application
- Kind: A1
- Application number: 18/945,977
- Filed: 2024-11-13
- Published: 2025-05-15
- Earliest claimed: 2023-11-13
- Assignees: Reincubate Limited
- Applicants: Reincubate Limited
- Inventors: Aidan Fitzpatrick; Hlynur Sveinbjornsson; Andrew Dancy
- Web page: https://patentgrep.com/patent/US20250157092A1

## CPC

- G06T 11/00: Two-dimensional [2D] image generation
- H04N 7/147: {Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals (selecting H04Q)}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 7/11: Region-based segmentation
- G06T 7/194: involving foreground-background segmentation
- G06T 7/73: using feature-based methods
- G11B 27/031: Electronic editing of digitised analogue information signals, e.g. audio or video signals
- G11B 27/28: by using information signals recorded by the same method as the main recording {(G11B27/22 takes precedence)}
- G11B 27/34: Indicating arrangements {(indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D)}
- H04L 65/403: Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15)
- H04N 7/15: Conference systems
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/10016: Video; Image sequence
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Video processing devices, systems and methods are disclosed. A video processing device for processing a source video stream under the control of a video alteration application is provided. A user interface (UI) is presented via which a user specifies a change to be applied to the source video stream. Conditions for the change to be applied to the source video stream are determined. The content of the source video stream is analysed to determine when conditions for the change have been met, and the location within the source video stream to which the change is to be applied. In response, the source video stream is processed to dynamically apply the specified change at the determined location thereby to generate an output video stream.

## Claims

### Claim 1

A video processing system for dynamically altering content of real-time video communications, the system comprising:
a video processing device for processing a source video stream, the video processing device comprising a display unit and a media source for generating the source video stream; and
a video alteration application, executed on the video processing device, configuring the video processing device to:
present a user interface (UI) via the display unit via which a user specifies a change to be applied to the source video stream;
determine conditions for the change to be applied to the source video stream;
analyse the content of the source video stream to determine when conditions for the change have been met, and the location within the source video stream to which the change is to be applied; and in response:
process the source video stream to dynamically apply the specified change at the determined location thereby to generate an output video stream; and
display the output video stream on the display unit of the video processing device.

### Claim 2 (depends on 1)

The system of claim 1, wherein the media source comprises a camera, and determining the location within the source video stream to which the change is to be applied comprises: determining a foreground region and a background region of the source video stream, the change comprising at least one of: a foreground change being applied to the foreground region, and a background change being applied to the background region.

### Claim 3 (depends on 2)

The system of claim 2, wherein the change comprises applying both the foreground change and the background change, the foreground change and background change being applied in dependence on, and in complement with one another, including at least one of complementary changes to: brightness, contrast, lighting, colour, hue, saturation and intensity.

### Claim 4 (depends on 2)

The system of claim 2, wherein determining a foreground region comprises continuously monitoring the source video stream to detect a participant via at least one of: facial recognition, facial movement detection, and user movement relative to the background region.

### Claim 5 (depends on 2)

The system of claim 2, wherein, determining at least one of the foreground region and the background region of the source video stream comprises performing a depth estimation routine; and
the video processing device comprises at least one supplementary camera having an overlapping field of view with the camera generating the source video stream, the depth estimation routine comprising computing differences between outputs of the camera generating the source video stream and the at least one supplementary camera.

### Claim 6 (depends on 2)

The system of claim 2, wherein determining a background region comprises forming a background image from the source video stream;
wherein forming the background image comprises progressively adding to the background image by continuously monitoring the source video stream to detect background areas previously occluded by the foreground region;
wherein forming the background image comprises performing an infill operation in which the content of background areas occluded by the foreground region is automatically generated in dependence on the content of background areas not occluded by the foreground region; and
wherein the infill operation comprises passing the content of background areas not occluded by the foreground region to a neural network infill model trained on a library of background images, the output of the infill model enabling the formation of the background image.

### Claim 7 (depends on 2)

The system of claim 2, wherein determining a foreground region and a background region of the source video stream is performed, at least in part, by an AI segmentation module, the AI segmentation module comprising a neural network trained to receive a source video stream, and output: at least one background image associated with the background region and/or at least one foreground image associated with the foreground region.

### Claim 8 (depends on 2)

The system of claim 2, wherein the background change applied to the background region comprises applying an effect to the background image, the effect being controlled, at least in part, by the change specified by the user via the UI; and wherein the background change applied to the background region comprises: performing a spatial analysis of the background image to determine the size, position and/or orientation of objects and surfaces displayed in the background image, and controlling the effect applied to preserve the size, position and/or orientation of at least part of those objects and surfaces.

### Claim 9 (depends on 8)

The system of claim 8, wherein the UI enables a user to specify a descriptive prompt, passed as an input together with the background image, to a background transformation model, the background transformation model comprising a transformational neural network trained with images and associated descriptors to alter the background image to accord with the descriptive prompt.

### Claim 10 (depends on 1)

The system of claim 1, wherein the video alteration application configures the video processing device to transmit the source video stream to a state monitoring module, the state monitoring module being configured to analyse the source video stream, and in response output a category of detected state for use in determining conditions for the change to be applied to the source video stream.

### Claim 11 (depends on 10)

The system of claim 10, wherein the media source comprises a subject application stream, such as a game stream, and the state monitoring module is configured to determine which subject application forms the basis of the subject application stream; and wherein the user interface is configured to present user-selectable options for controlling at least one of: a change to be applied to the source video stream, and conditions for the change to be applied to the source video stream; wherein the options presented are dependent on the determined subject application.

### Claim 12 (depends on 1)

The system of claim 1, wherein the video processing device comprises a plurality of media sources, each for generating a respective source video stream; the application configuring the video processing device to:
combine an output of the media sources together to form a composite video stream according to a first composition template; and
analyse at least one of the source video streams to determine when conditions for a change have been met and, in response, reform the composite video stream according to a second composition template.

### Claim 13 (depends on 1)

The system of claim 1, wherein the video processing device is configured by the application to: receive an effector input, and in response to determining whether the effector input fulfils a condition, apply a change to the source video stream; wherein the effector input originates from at least one of:
a communication feed, such as an audience participation feed; an internal monitored state of the video processing device; a peripheral device connected to the video processing device; and a compliance report of the video processing device, such as the security level of the video processing device.

### Claim 14 (depends on 13)

The system of claim 13, wherein the compliance report is determined by an analysis by the video alteration application of the video processing device; and
the change applied to the source video stream comprises adding a visual and/or audio certificate, that certifies the determined compliance report.

### Claim 15 (depends on 14)

The system of claim 14, wherein the certificate comprises at least one of: a time component, correlating to the time at which the compliance report was determined; and a machine-readable code, such as a barcode, that contains a link to a certificate authority;
wherein the certificate is independently verifiable by a receiver of the output video stream by checking the certificate with a certificate authority.

### Claim 16 (depends on 13)

The system of claim 13, wherein the compliance report comprises a verification of the identity of a participant of the real-time video communication, and the change applied to the source video stream comprises including a reference to the identity of the participant, such as their name, position and qualification;
wherein the video alteration application is configured to verify the identity of the participant via biometric analysis, such as facial analysis, of the source video stream, the identity verification being used to compile the compliance report.

### Claim 17 (depends on 1)

The system of claim 1, wherein processing the source video stream to dynamically apply the specified change at the determined location comprises at least one of: obfuscating content at that location, such as applying a blur function; applying a sound alteration function; and adding an overlay to at least the determined location of the source video stream.

### Claim 18 (depends on 1)

The system of claim 1, wherein the video processing device is in communication with at least one scene alteration peripheral, such as background lighting, the video alteration application configuring the video processing device to analyse the content of the source video stream to determine when conditions for controlling the at least one scene alteration peripheral have been met, and in response send a control signal to the at least one scene alteration peripheral to cause a scene change in the source video stream.

### Claim 19

A video processing method suitable for dynamically altering content of real-time video communications, comprising:
providing a source video stream;
presenting a user interface (UI) via which a user specifies a change to be applied to the source video stream;
determining conditions for the change to be applied to the source video stream;
analysing the content of the source video stream to determine when conditions for the change have been met, and the location within the source video stream to which the change is to be applied; and in response:
processing the source video stream to dynamically apply the specified change at the determined location thereby to generate an output video stream; and
displaying the output video stream.

### Claim 20

A computer program comprising instructions which, when executed on a video processing device, configures the video processing device to:
present a user interface (UI) via which a user specifies a change to be applied to a source video stream;
determine conditions for the change to be applied to the source video stream;
analyse the content of the source video stream to determine:
when conditions for the change have been met;
the location within the source video stream to which the change is to be applied; and in response:
process the source video stream to dynamically apply the specified change at the determined location thereby to generate an output video stream.
