METHODS AND APPARATUS TO DETECT COMMERCIAL ADVERTISEMENTS ASSOCIATED WITH MEDIA PRESENTATIONS

• US 20170180789A1
• Filed: 03/03/2017
• Published: 06/22/2017
• Est. Priority Date: 12/31/2009
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Wright, David H., Heffernan, Ronan, Wilson, Scott, Schwerer, Ron
• Granted Patent: US 10,028,014 B2
• Time in Patent Office: Days
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: H04H 20/14 for monitoring programmes
• CPC Class Codes: H04H 60/375 Commercial
• CPC Class Codes: H04H 60/48 for recognising items expressed in broadcast information
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04H 60/59 of video recognising characters or patterns in general G06F18/00, G06V20/00
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/4402 involving reformatting operations of video signals for household redistribution, storage or real-time display details of conversion of video standards at pixel level H04N7/01; video transcoding H04N19/40; adapting incoming signals to the display format of the display terminal G09G5/005; media handling at the source in data packet switching networks H04L65/764
• CPC Class Codes: H04N 21/47202 for requesting content on demand, e.g. video on demand
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 5/147 Scene change detection

Abstract

Methods and apparatus to detect commercial advertisements associated with media presentations are disclosed. An example method includes comparing an amount of audio randomness in an inter-segment audio frame to a random level threshold, the amount of audio randomness being based on a random-factor ratio; and in response to the amount of randomness satisfying the random level threshold, indicating the inter-segment audio frame is associated with the commercial transition.

Claims

1. A method to detect a commercial transition associated with a media presentation, the method comprising:

comparing, by executing an instruction with a processor, an amount of audio randomness in an inter-segment audio frame to a random level threshold, the amount of audio randomness being based on a random-factor ratio; and

in response to the amount of randomness satisfying the random level threshold, indicating, by executing an instruction with the processor, the inter-segment audio frame is associated with the commercial transition.

2. The method as defined in claim 1, further including determining the random-factor ratio by:

determining a quantity of unique time-based distances between at least one of a plurality of amplitude peaks or a plurality of amplitude troughs in the inter-segment audio frame; and

determining the random-factor ratio by dividing the quantity of unique time-based distances by the quantity of total time-based distances between the at least one of the amplitude peaks or the amplitude troughs.

3. The method as defined in claim 1, wherein the commercial transition includes at least one of a transition between two commercial advertisements or a transition between a commercial advertisement and a media program.

4. The method as defined in claim 1, wherein the inter-segment audio frame is reconstructed from at least one of a television transmission, an internet-streamed video, or a video on demand video.

5. The method as defined in claim 1, wherein the amount of audio randomness of the inter-segment audio frame is indicative of an inter-segment blank frame occurring between two media program segments.

6. The method as defined in claim 1, further including:

determining a root-mean-squared value of audio in the inter-segment audio frame; and

determining the amount of audio randomness of the inter-segment audio frame in response to the root-mean-squared value of the audio exceeding a first threshold and being less than a second threshold.

7. The method as defined in claim 1, further including:

in response to the amount of audio randomness satisfying the random level threshold, generating a first hint value based on the amount of audio randomness, the amount of audio randomness being a first characteristic associated with the media presentation indicative of a possible commercial transition;

generating a second hint value in response to detecting a second characteristic associated with the media presentation indicative of the possible commercial transition;

weighting the first and second hint values;

determining an aggregate weighted hint value based on the first and second weighted hint values; and

confirming a presence of the commercial transition associated with the media presentation based on the aggregate weighted hint value.

8. The method as defined in claim 7, wherein the second characteristic is a change in box-formatting between consecutive video frames.

9. The method as defined in claim 8, further including adding a third weighted hint value to the aggregate weighted hint value, the third weighted hint value associated with detecting, in association with the media presentation, at least one of a frame aspect ratio change, an audio format change, a timestamp discontinuity, a closed-captioning text discontinuity, or a commercial insertion opportunity code.

10. A method as defined in claim 7, wherein the first hint value is weighted based on a reliability of the first characteristic as an indicator of an actual commercial transition and the second hint value is weighted based on the reliability of the second characteristic as an indicator of an actual commercial transition.

11. An apparatus to detect a commercial transition associated with a media presentation, the apparatus comprising:

an audio features detector to compare an amount of audio randomness in an inter-segment audio frame to a random level threshold, the amount of audio randomness being based on a random-factor ratio; and

an advertisement detector to indicate, in response to the amount of audio randomness satisfying the random level threshold, the inter-segment audio frame as occurring at the commercial transition.

12. The apparatus as defined in claim 11, wherein the audio features detector determines the random-factor ratio by:

determining a quantity of unique time-based distances between at least one of a plurality of amplitude peaks or a plurality of amplitude troughs in the inter-segment audio frame; and

determining the random-factor ratio by dividing the quantity of unique time-based distances by a quantity of total time-based distances between the at least one of the amplitude peaks or the amplitude troughs.

13. The apparatus as defined in claim 11, wherein the commercial transition includes at least one of a transition between two commercial advertisements or a transition between a commercial advertisement and a media program.

14. The apparatus as defined in claim 11, wherein the audio frame is reconstructed from at least one of a television transmission, an internet-streamed video, or a video on demand video.

15. A tangible machine readable medium comprising instructions that, when executed, cause a processor to at least:

compare an amount of audio randomness in an inter-segment audio frame of a media presentation to a random level threshold, the amount of audio randomness being based on a random-factor ratio; and

in response to the amount of audio randomness satisfying the random level threshold, indicate the inter-segment audio frame is associated with the commercial transition.

16. The machine readable medium as defined in claim 15, wherein the instructions further cause the processor to determine the amount of audio randomness by:

determining a quantity of unique time-based distances between at least one of a plurality of amplitude peaks or a plurality of amplitude troughs in the inter-segment audio frame; and

determining a random-factor ratio by dividing the quantity of unique time-based distances by a quantity of total time-based distances between the at least one of the amplitude peaks or the amplitude troughs.

17. The machine readable medium as defined in claim 15, wherein the audio frame is reconstructed from at least one of a television transmission, an internet-streamed video, or a video on demand video.

18. The machine readable medium as defined in claim 15, wherein the instructions further cause the processor to determine the amount of audio randomness of the audio frame in response to detecting quiet audio in the audio frame.

19. The machine readable medium as defined in claim 15, wherein the amount of audio randomness of the audio frame is indicative of an inter-scene blank frame occurring in a media program or an inter-segment blank frame occurring between two media program segments.

20. The machine readable medium as defined in claim 15, wherein the instructions further cause the processor to:

in response to the amount of audio randomness satisfying the random level threshold, generate a first hint value based on the amount of audio randomness, the amount of audio randomness being a first characteristic associated with the media presentation indicative of a possible commercial transition;

generate a second hint value in response to detecting a second characteristic associated with the media presentation indicative of the possible commercial transition;

weight the first and second hint values;

determine an aggregate weighted hint value based on the first and second weighted hint values; and

confirm a presence of the commercial transition associated with the media presentation based on the aggregate weighted hint value.