Iterative, maximally probable, batch-mode commercial detection for audiovisual content
Identification of starting and ending times of commercial breaks and commercials within those commercial breaks found in audiovisual content is disclosed. A solution to a “batch optimization” problem is used in which commercial locations within a set of audiovisual content are detected as a group by choosing a set of commercial locations which optimizes a cost function which can include considerations of, for example, 1) one or more cues, 2) relative locations of commercials within the audiovisual content, and/or 3) probability models based on statistics obtained regarding characteristics of typical commercial and commercial breaks. Optimization can be done over the total set of commercial location decisions, rather than on a per-commercial basis. Additionally, the cost function can be iteratively evaluated and many more types of cues and combinations of cues can be used in detection of commercials.
1. A method of processing an audiovisual signal containing audiovisual content, comprising:
identifying a set of candidate times in the audiovisual content contained in the audiovisual signal, wherein each of the set of candidate times corresponds to a potential commercial boundary and the set of candidate times includes at least a first candidate time;
determining a probability based at least in part on information associated with the first candidate time in the context of at least one member of a set of identified commercial boundaries;
determining whether the probability satisfies a threshold; and
including the first candidate time in the set of identified commercial boundaries when the probability is determined to satisfy the threshold.
2. A method as recited in claim 1 , wherein the audiovisual signal is obtained from a storage device.
3. A method as recited in claim 1 , wherein the audiovisual signal is transmitted.
4. A method as recited in claim 1 , wherein the first candidate time occurs earlier in the audiovisual content compared to the at least one member of the set of identified commercial boundaries.
5. A method as recited in claim 1 further including generating a new audiovisual signal, wherein the new audiovisual signal does not include a commercial identified by the set of identified commercial boundaries.
6. A method as recited in claim 1 further including displaying the audiovisual signal with a commercial identified by the set of identified commercial boundaries removed.
7. A method as recited in claim 1 further including displaying a commercial identified by the set of identified commercial boundaries.
8. A method as recited in claim 1 , wherein content of a commercial included in the audiovisual content is unknown during processing of the audiovisual signal.
9. A method as recited in claim 1 , wherein an identified commercial boundary may be removed from the set of identified commercial boundaries.
10. A method as recited in claim 1 further including determining a score for each of the set of candidate times.
11. A method as recited in claim 1 further including determining a score for each of the set of candidate times, including using a cue.
12. A method as recited in claim 1 further including determining a score for each of the set of candidate times, including using a cue associated with video content.
13. A method as recited in claim 1 further including determining a score for each of the set of candidate times, including using a cue associated with audio content.
14. A method as recited in claim 1 further including determining a score for each of the set of candidate times, including using a cue associated with close captioning content.
15. A method as recited in claim 1 , wherein the probability is further based at least in part on statistical information associated with historical commercial data.
16. A method as recited in claim 1 , wherein the probability is associated with a duration of a commercial.
17. A method as recited in claim 1 , wherein the probability is associated with a duration of a commercial break.
18. A method as recited in claim 1 , wherein the probability is associated with a time between a first commercial break and a second commercial break.
19. A method as recited in claim 1 , wherein the probability is associated with a location of a commercial break in a program.
20. A system for processing an audiovisual signal containing audiovisual content, comprising:
a processor configured to:
identify a set of candidate times in the audiovisual content contained in the audiovisual signal, wherein each of the set of candidate times corresponds to a potential commercial boundary and the set of candidate times includes at least a first candidate time;
determine a probability based at least in part on information associated with the first candidate time in the context of at least one member of a set of identified commercial boundaries;
determine whether the probability satisfies a threshold; and
include the first candidate time in the set of identified commercial boundaries when the probability is determined to satisfy the threshold.
21. A computer program product for processing an audiovisual signal containing audiovisual content, the computer program product being embodied in a tangible computer readable storage medium and comprising computer-executable instructions for:
identifying a set of candidate times in the audiovisual content contained in the audiovisual signal, wherein each of the set of candidate times corresponds to a potential commercial boundary and the set of candidate times includes at least a first candidate time;
determining a probability based at least in part on information associated with the first candidate time in the context of at least one member of a set of identified commercial boundaries;
determining whether the probability satisfies a threshold; and
including the first candidate time in the set of identified commercial boundaries when the probability is determined to satisfy the threshold.