Iterative, maximally probable, batch-mode commercial detection for audiovisual content
First Claim
1. A non-transitory computer-readable medium storing computer-readable instructions to perform a method for detecting a commercial in a set of audiovisual content spanning a duration of time, the method comprising:
- selecting a candidate time within the duration of time spanned by the set of audiovisual content,wherein the candidate time is identified based on the detection of one or more predetermined cues in a first set of cues, andwherein the candidate time represents a possible boundary time of a commercial;
assigning a value to the candidate time; and
analyzing the candidate time to determine a likelihood that the candidate time is a commercial boundary time,wherein the analysis is performed on processing circuitry and includes;
adjusting the value based on one or more cues in a second set of cues occurring within a time interval proximate to the candidate time, andfurther adjusting the value based on one or more characteristics of audiovisual content and associated probabilities.
1 Assignment
0 Petitions
Accused Products
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.
-
Citations
9 Claims
-
1. A non-transitory computer-readable medium storing computer-readable instructions to perform a method for detecting a commercial in a set of audiovisual content spanning a duration of time, the method comprising:
-
selecting a candidate time within the duration of time spanned by the set of audiovisual content, wherein the candidate time is identified based on the detection of one or more predetermined cues in a first set of cues, and wherein the candidate time represents a possible boundary time of a commercial; assigning a value to the candidate time; and analyzing the candidate time to determine a likelihood that the candidate time is a commercial boundary time, wherein the analysis is performed on processing circuitry and includes; adjusting the value based on one or more cues in a second set of cues occurring within a time interval proximate to the candidate time, and further adjusting the value based on one or more characteristics of audiovisual content and associated probabilities. - View Dependent Claims (2, 3)
-
-
4. A system for detecting a commercial in a set of audiovisual content spanning a duration of time, comprising:
-
a data storage medium to store the set of audiovisual content; and a processor coupled to the data storage medium and configured to; select a candidate time within the duration of time spanned by the set of audiovisual content, wherein the candidate time is identified based on the detection of one or more predetermined cues in a first set of cues, and wherein the candidate time represents a possible boundary time of a commercial; assign a value to the candidate time; and analyze the candidate time to determine a likelihood that the candidate time is a commercial boundary time, wherein the analysis is performed on processing circuitry and includes; adjusting the value based on one or more cues in a second set of cues occurring within a time interval proximate to the candidate time, and further adjusting the value based on one or more characteristics of audiovisual content and associated probabilities. - View Dependent Claims (5, 6)
-
-
7. A computer-implemented method for detecting an advertisement in a set of audiovisual content spanning a duration of time, the method comprising:
-
receiving the set of audiovisual content; selecting a candidate time identified within the duration of time spanned by the set of audiovisual content, wherein the candidate time is identified based on the detection of one or more predetermined cues in a first set of cues, and wherein the candidate time represents a possible boundary time of an advertisement within the audiovisual content; assigning a value to the candidate time; analyzing the candidate time to determine a likelihood that the candidate time is an advertisement boundary time, wherein the analysis is performed by processing circuitry; and adjusting the value of the candidate time based on one or more predetermined cues in a second set of cues, wherein the second set of cues occur during a time interval proximate to the candidate time. - View Dependent Claims (8, 9)
-
Specification