Iterative, maximally probable, batch-mode commercial detection for audiovisual content

• US 8,995,820 B2
• Filed: 01/14/2014
• Issued: 03/31/2015
• Est. Priority Date: 11/18/1999
• Status: Active Grant

• Current Assignee: Interval Licensing LLC
• Original Assignee: Interval Licensing LLC
• Inventors: Harville, Michael L.
• Primary Examiner(s): HARVEY, DAVID E
• Application Number:
  US14/154,999
• Publication Number:
  US 20140126887A1
• Time in Patent Office: 441 Days
• Field of Search: 386/249, 386/250, 386/251, 386/278
• US Class Current: 386/250
• CPC Class Codes: G11B 27/031 Electronic editing of digitised analogue information signals, e.g. audio or video signals
• CPC Class Codes: H04N 21/438 Interfacing the downstream path of the transmission network originating from a server, e.g. retrieving encoded video stream packets from an IP network
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 5/76 Television signal recording
• CPC Class Codes: H04N 5/781 on disks or drums
• CPC Class Codes: H04N 5/782 on tape
• CPC Class Codes: H04N 5/85 on discs or drums
• CPC Class Codes: H04N 5/907 using static stores, e.g. storage tubes or semiconductor memories H04N5/91 takes precedence
• CPC Class Codes: H04N 7/163 by receiver means only
• CPC Class Codes: H04N 9/87 Regeneration of colour television signals H04N9/80 takes precedence
• CPC Class Codes: Y10S 358/908 Pause control, i.e. "commercial killers"

Abstract

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.

Claims

1. A method for detecting boundary times for at least one commercial break in a set of audiovisual content, the method comprising:

selecting a current set of commercial boundary times,

wherein the current set of commercial boundary times includes multiple possible commercial boundary times within a duration of time spanned by the set of audiovisual content;

forming a revised set of commercial boundary times,

wherein the revised set of commercial boundary times includes the current set of commercial boundary times and at least one additional time within the duration of time spanned by the set of audiovisual content;

compare, based on probabilities, the revised set of commercial boundary times and the current set of commercial boundary times,

wherein the comparing is to determine whether the revised set of commercial boundary times is a better set of commercial boundary times than the current set of commercial boundary times, and

wherein the comparing is performed on processing circuitry and includes comparing values associated with commercial boundary times in the revised set of commercial boundary times and the current set of commercial boundary times; and

designating the revised set of commercial boundary times as the current set of commercial boundary times.

2. The method as in claim 1, wherein the step of comparing further comprises:

identifying a candidate time within the current set of commercial boundary times, wherein the candidate time represents a possible boundary time of a commercial in the current set of commercial boundary times; and

assigning an initial value to the candidate time based on an evaluation of the candidate time to determine a likelihood that the candidate time is a commercial boundary time.

3. The method of claim 2, wherein the candidate time is identified based on the detection of one more predetermined cues in a first set of cues and wherein the evaluation is based on the one or more predetermined cues used to detect the candidate time.

4. The method of claim 2, wherein the initial value associated with the candidate time is adjusted based on one or more predetermined cues in a second set of cues occurring within a time interval proximate to the candidate time.

5. The method as in claim 2, wherein the at least one additional commercial boundary time within the revised set of commercial boundary times is identified as a candidate time.

6. The method of claim 1, wherein the values are based at least in part on an evaluation of one or more characteristics of audiovisual content occurring within the duration of time spanned by the audiovisual content.

7. The method of claim 1, wherein the values are based at least in part on an evaluation of one or more characteristics of audiovisual content occurring before the candidate time or after the candidate time.

8. The method as in claim 1, wherein the value is adjusted based on a relationship of the candidate time to all other candidate times within the duration of time spanning the set of audiovisual content.

9. The method as in claim 1, wherein the method is iterative.

10. A system for detecting at least one commercial in a set of audiovisual content, the system comprising:

an interface for receiving data including the set of audiovisual content;

at least one processor capable of executing instructions

select a current set of commercial boundary times in the set of audiovisual content,

wherein the current set of commercial boundary times include candidate times identified within a duration of time spanned by the audiovisual content;

form a revised set of commercial boundary times,

wherein the revised set of commercial boundary times include the current set of commercial boundary times and at least one additional candidate time within the duration of time spanned by the audiovisual content;

analyze the revised set of commercial boundary times and the current set of commercial boundary times to determine whether the revised set of commercial boundary times is more probable to include as a commercial boundary time than the current set of commercial boundary times set,

wherein the analysis includes comparing values assigned to candidate times in the revised set of commercial boundary times and the current set of commercial boundary times, and

wherein the values are associated with probabilities related to the candidate times; and

designate the revised set of commercial boundary times as the current set of commercial boundary times.

11. The system of claim 10, wherein the at least one processor is further configured to detect one or more predetermined cues in a first set of cues within the duration of time spanned by the audiovisual content, wherein a candidate time is identified based on the one or more predetermined cues, and wherein a value assigned to the candidates times is based at least in part on the one or more predetermined cues used to identify that candidate time.

12. The system of claim 10, wherein the values assigned to the candidates times are adjusted based on one or more predetermined cues in a second set of cues.

13. The system of claim 10, wherein the at least one processor is configured to decompress data received at the interface.

14. The system of claim 10, further comprising a data storage medium configured to store the data including the set of audiovisual content.

15. The system of claim 10, wherein the data includes any one or more of audio data, visual data, and closed-captioning data.

16. The system of claim 10, wherein the data including the set of audiovisual content is live.

17. A non-transitory computer-readable medium encoded with computer-readable instructions that when performed by a processor perform a method for detecting a commercial in a set of audiovisual content, the method comprising:

selecting a current set of commercial boundary times,

wherein the current set of commercial boundary times includes multiple possible commercial boundary times within a duration of time spanned by the set of audiovisual content;

forming a revised set of commercial boundary times,

wherein the revised set of commercial boundary times include the current set of commercial boundary times and at least one additional time within the duration of time spanned by the set of audiovisual content;

analyzing the revised set of commercial boundary times and the current set of commercial boundary times,

wherein the analysis includes comparing scores associated with commercial boundary times in the revised set of commercial boundary times and the current set of commercial boundary times, and

wherein the scores are associated with probabilities related to the commercial boundary times; and

designating the revised set of commercial boundary times as the current set of commercial boundary times.

18. The computer-readable medium as in claim 17, wherein the method further comprises:

identifying candidate times within the duration of time spanned by the set of audiovisual content, wherein the candidate times are identified based on the detection of one or more predetermined cues; and

assigning a score with the candidate time based on an evaluation of the candidate time to determine a likelihood that the candidate time is a commercial boundary time, wherein the candidate time represents a possible commercial boundary time in the set of audiovisual content.

19. The computer-readable medium as in claim 17, wherein the analyzing includes determining whether the revised set of commercial boundary times or the current set of commercial boundary times is more probable to include as a commercial boundary time, and wherein the score for the candidate time is dependent on a confidence level associated with each of the one or more predetermined cues used to identify the candidate time.