Methods and apparatus to detect commercial advertisements associated with media presentations
Methods and apparatus to detect commercial advertisements associated with media presentations are disclosed. An example method involves receiving a video frame and detecting a change in box-formatting between the video frame and a subsequent video frame. A transition between the video frame and the subsequent video frame is indicated as a commercial advertisement transition based on the detected change in box-formatting.
1. An apparatus comprising:
at least one memory;
instructions in the apparatus; and
processor circuitry to execute the instructions to:
generate a first hint value based on a first characteristic associated with a media presentation, the first characteristic indicative of a commercial transition;
generate a second hint value based on a second characteristic associated with the media presentation, the second characteristic indicative of the commercial transition;
determine an aggregated weighted hint value based on the first hint value and the second hint value; and
indicate a presence of the commercial transition associated with the media presentation based on a determination that the aggregated weighted hint value satisfies a threshold.
2. The apparatus of claim 1 , wherein the threshold is a first threshold, the first characteristic is an amount of audio randomness in an inter-segment audio frame of the media presentation, and the processor circuitry is to:
determine the amount of audio randomness being based on a random-factor ratio; and
generate the first hint value based on a comparison of the amount of audio randomness to a second threshold.
3. The apparatus of claim 1 , wherein the second characteristic is a presence of at least one of a change in box-formatting between consecutive video frames, an audio format change, an aspect ratio change, a timestamp discontinuity, a closed-captioning text discontinuity, or a commercial insertion opportunity code.
4. The apparatus of claim 3 , wherein the processor circuitry is to identify the change in the box-formatting between the consecutive video frames by monitoring for screen filler areas in edges in a video frame of the consecutive video frames.
5. The apparatus of claim 1 , wherein the processor circuitry is to determine the aggregated weighted hint value by:
generating, based on a first weighting value and the first hint value, a first weighted hint value, the first weighting value based on a first reliability of the first characteristic;
generating, based on a second weighting value and the second hint value, a second weighted hint value, the second weighting value based on a second reliability of the second characteristic; and
determining the aggregated weighted hint value based on the first weighted hint value and the second weighted hint value.
6. The apparatus of claim 1 , wherein the processor circuitry is to indicate the presence of the commercial transition by transmitting a message indicative of the commercial transition to a commercial identification system, the transmission of the message to cause the commercial identification system to identify a commercial following the commercial transition.
7. The apparatus of claim 1 , wherein the media presentation is associated with a monitored digital television feed.
8. A non-transitory computer readable medium comprising instructions that, when executed, cause at least one processor to at least:
generate a first hint value based on a first characteristic associated with a media presentation, the first characteristic indicative of a commercial transition;
generate a second hint value based on a second characteristic associated with the media presentation, the second characteristic indicative of the commercial transition;
determine an aggregated weighted hint value based on the first hint value and the second hint value; and
indicate a presence of the commercial transition associated with the media presentation based on a determination that the aggregated weighted hint value satisfies a threshold.
9. The non-transitory computer readable medium of claim 8 , wherein the threshold is a first threshold, the first characteristic is an amount of audio randomness in an inter-segment audio frame of the media presentation, and the instructions are to cause the at least one processor to:
determine the amount of audio randomness being based on a random-factor ratio; and
generate the first hint value based on a comparison of the amount of audio randomness to a second threshold.
10. The non-transitory computer readable medium of claim 8 , wherein the second characteristic is a presence of at least one of a change in box-formatting between consecutive video frames, an audio format change, an aspect ratio change, a timestamp discontinuity, a closed-captioning text discontinuity, or a commercial insertion opportunity code.
11. The non-transitory computer readable medium of claim 10 , wherein the instructions are to cause the at least one processor to identify the change in the box-formatting between the consecutive video frames by monitoring for screen filler areas in edges in a video frame of the consecutive video frames.
12. The non-transitory computer readable medium of claim 8 , wherein the instructions are to cause the at least one processor to:
generate, based on a first weighting value and the first hint value, a first weighted hint value, the first weighting value based on a first reliability of the first characteristic;
generate, based on a second weighting value and the second hint value, a second weighted hint value, the second weighting value based on a second reliability of the second characteristic; and
determine the aggregated weighted hint value based on the first weighted hint value and the second weighted hint value.
13. The non-transitory computer readable medium of claim 8 , wherein the instructions are to cause the at least one processor to transmit a message indicative of the commercial transition to a commercial identification system, the transmission of the message to cause the commercial identification system to identify a commercial following the commercial transition.
14. The non-transitory computer readable medium of claim 8 , wherein the media presentation is associated with a monitored digital television feed.
15. A method comprising:
generating, by executing an instruction with a processor, a first hint value based on a first characteristic associated with a media presentation, the first characteristic indicative of a commercial transition;
generating, by executing an instruction with the processor, a second hint value based on a second characteristic associated with the media presentation, the second characteristic indicative of the commercial transition;
determining, by executing an instruction with the processor, an aggregated weighted hint value based on the first and second hint values; and
indicating, by executing an instruction with the processor, a presence of the commercial transition associated with the media presentation based on a determination that the aggregated weighted hint value satisfies a threshold.
16. The method of claim 15 , wherein the threshold is a first threshold, the first characteristic is an amount of audio randomness in an inter-segment audio frame of the media presentation, and further including:
determining the amount of audio randomness being based on a random-factor ratio; and
generating, by executing an instruction with the processor, the first hint value based on a comparison of the amount of audio randomness to a second threshold.
17. The method of claim 15 , wherein the second characteristic is a presence of at least one of a change in box-formatting between consecutive video frames, an audio format change, an aspect ratio change, a timestamp discontinuity, a closed-captioning text discontinuity, or a commercial insertion opportunity code.
18. The method of claim 17 , further including identifying the change in the box-formatting between the consecutive video frames by monitoring for screen filler areas in edges in a video frame of the consecutive video frames.
19. The method of claim 15 , further including:
generating, based on a first weighting value and the first hint value, a first weighted hint value, the first weighting value based on a first reliability of the first characteristic;
generating, on a second weighting value and the second hint value, a second weighted hint value, the second weighting value based on a second reliability of the second characteristic; and
determining the aggregated weighted hint value based on the first weighted hint value and the second weighted hint value.
20. The method of claim 15 , further including transmitting a message indicative of the commercial transition to a commercial identification system, the transmission of the message to cause the commercial identification system to identify a commercial following the commercial transition.