# US 2023/0267733 A1 · Methods and apparatus to measure brand exposure in media streams

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

- Number: US 2023/0267733 A1
- Document ID: US20230267733A1
- Status: Published application
- Kind: A1
- Application number: 18/308,092
- Filed: 2023-04-27
- Published: 2023-08-24
- Earliest claimed: 2007-11-09
- Assignees: The Nielsen Company (US), LLC
- Applicants: The Nielsen Company (US), LLC
- Inventors: Kevin Keqiang Deng; Barry Greenberg
- Web page: https://patentgrep.com/patent/US20230267733A1

## CPC

- G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44)
- G06V 20/635: {Overlay text, e.g. embedded captions in a TV programme}
- G06V 20/44: {Event detection}
- G06V 2201/09: Recognition of logos
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Methods and apparatus to measure brand exposure in media streams are disclosed. Example apparatus disclosed herein are to determine a first histogram based on at least one of luminance components or chrominance components of a first frame of video, and determine a second histogram based on at least one of luminance components or chrominance components of a second frame of the video. Disclosed example apparatus are also to detect a transition in the video based on the first histogram and the second histogram, and responsive to the detection of the transition in the video. Disclosed example apparatus are further to process a region of interest within at least one of the first frame or the second frame to detect a logo in the region of interest.

## Claims

### Claim 1

An audience measurement computing system for monitoring media output by a media device of a panelist household of an audience measurement entity, the audience measurement computing system comprising:
at least one memory storing computer-readable instructions; and
at least one processor configured to execute the computer-readable instructions to perform operations comprising:
determining a first pixel histogram based on at least one pixel characteristic of a first frame of a video output by the media device;
determining a second pixel histogram based on the at least one pixel characteristic of a second frame of the video;
detecting a scene change in the video based on the first pixel histogram and the second pixel histogram, wherein the first frame is from a first scene of the video and the second frame is from a second scene of the video; and
processing at least one of the first scene or the second scene to detect a brand identifier within at least one of the first scene or the second scene.

### Claim 2 (depends on 1)

The audience measurement computing system of claim 1, wherein the brand identifier comprises one or more of a product name, service name, or logo associated with an advertiser.

### Claim 3 (depends on 1)

The audience measurement computing system of claim 1, the operations further comprising:
generating a signature corresponding to the second scene based at least on the second frame; and
making a determination of whether the signature matches a reference signature associated with a known advertisement,
wherein the processing is performed based on the determination.

### Claim 4 (depends on 3)

The audience measurement computing system of claim 3, the operations further comprising:
classifying the second scene as an advertisement based on the determination.

### Claim 5 (depends on 1)

The audience measurement computing system of claim 1, further comprising an output device communicatively coupled to the at least one processor, the operations further comprising:
providing for display, via the output device, a graphical user interface including the detected brand identifier.

### Claim 6 (depends on 1)

The audience measurement computing system of claim 1, wherein the panelist household is statistically selected by the audience measurement entity, and wherein the audience measurement entity collects brand exposure data associated with the panelist household.

### Claim 7 (depends on 6)

The audience measurement computing system of claim 6, the operations further comprising:
classifying the second scene as an advertisement; and
based on the detected brand identifier and the classification of the second scene as an advertisement, generating a brand exposure report associated with the panelist household.

### Claim 8 (depends on 1)

The audience measurement computing system of claim 1, wherein determining the first pixel histogram based on the at least one pixel characteristic of the first frame comprises determining the first pixel histogram based on pixel luminance values of the first frame, and wherein determining the second pixel histogram based on the at least one pixel characteristic of the second frame comprises determining the second pixel histogram based on pixel luminance values of the second frame.

### Claim 9 (depends on 1)

The audience measurement computing system of claim 1, wherein determining the first pixel histogram based on the at least one pixel characteristic of the first frame comprises determining the first pixel histogram based on pixel chrominance values of the first frame, and wherein determining the second pixel histogram based on the at least one pixel characteristic of the second frame comprises determining the second pixel histogram based on pixel chrominance values of the second frame.

### Claim 10 (depends on 1)

The audience measurement computing system of claim 1, wherein detecting the scene change in the video comprises:
comparing the first pixel histogram of the first scene to the second pixel histogram of the second scene; and
based on the comparison, determining that the first and second scenes are different to detect the scene change in the video.

### Claim 11 (depends on 1)

The audience measurement computing system of claim 1, wherein processing the at least one of first scene or the second scene to detect the brand identifier comprises:
comparing a region of interest of the at least one first scene or second scene to at least one brand template from a brand library database stored in the at least one memory; and
verifying that the at least one brand template is included within the at least one first scene or the second scene to detect the brand identifier.

### Claim 12

An article of manufacture comprising computer-readable instructions that, when executed, cause at least one processor to perform operations comprising:
determining a first pixel histogram based on at least one pixel characteristic of a first frame of a video output by a media device;
determining a second pixel histogram based on the at least one pixel characteristic of a second frame of the video;
detecting a scene change in the video based on the first pixel histogram and the second pixel histogram, wherein the first frame is from a first scene of the video and the second frame is from a second scene of the video; and
processing at least one of the first scene or the second scene to detect a brand identifier within at least one of the first scene or the second scene.

### Claim 13 (depends on 12)

The article of manufacture of claim 12, wherein the brand identifier comprises one or more of a product name, service name, or logo associated with an advertiser.

### Claim 14 (depends on 12)

The article of manufacture of claim 12, the operations further comprising:
generating a signature corresponding to the second scene based at least on the second frame; and
making a determination of whether the signature matches a reference signature associated with a known advertisement,
wherein the processing is performed based on the determination.

### Claim 15 (depends on 14)

The article of manufacture of claim 14, the operations further comprising:
classifying the second scene as an advertisement based on the determination.

### Claim 16

A method performed by an audience measurement computing system configured for monitoring media output by a media device of a panelist household of an audience measurement entity, the method comprising:
determining a first pixel histogram based on at least one pixel characteristic of a first frame of a video output by the media device;
determining a second pixel histogram based on the at least one pixel characteristic of a second frame of the video;
detecting, by executing an instruction with at least one processor of the audience measurement computing system, a scene change in the video based on the first pixel histogram and the second pixel histogram, wherein the first frame is from a first scene of the video and the second frame is from a second scene of the video; and
processing, by executing an instruction with the at least one processor, at least one of the first scene or the second scene to detect a brand identifier within at least one of the first scene or the second scene.

### Claim 17 (depends on 16)

The method of claim 16, wherein the brand identifier comprises one or more of a product name, service name, or logo associated with an advertiser.

### Claim 18 (depends on 16)

The method of claim 16, further comprising:
generating a signature corresponding to the second scene based at least on the second frame;
making a determination of whether the signature matches a reference signature associated with a known advertisement; and
classifying the second scene as an advertisement based on the determination,
wherein the processing is performed based on the determination.

### Claim 19 (depends on 18)

The method of claim 18, wherein the video is output by a media device located within a household that is statistically selected by an audience measurement entity and from which the audience measurement entity collects brand exposure data associated with the household, the method further comprising:
based on the detected brand identifier and the classification of the second scene as an advertisement, generating a brand exposure report associated with the household.

### Claim 20 (depends on 16)

The method of claim 16, further comprising:
providing for display, via an output device, a graphical user interface including the detected brand identifier.
