Methods and apparatus for identifying primary media content in a post-production media content presentation

1. A computer-implemented method to detect primary media content included in a secondary media content presentation, the method comprising:

determining a first image corresponding to the secondary media content presentation, the first image comprising a plurality of image subregions, each image subregion representative of an inter-frame variation associated with a corresponding subregion of the secondary media content presentation;

selecting a region of the first image comprising a plurality of connected image subregions of the first image together exhibiting a first type of inter-frame variation;

when a shape of the selected region of the first image corresponds to a first predefined shape, processing a region of the secondary media content presentation corresponding to the selected region of the first image to detect the primary media content;

determining a second image corresponding to the secondary media content presentation;

selecting a region of the second image comprising a plurality of connected image subregions of the second image together exhibiting a second type of inter-frame variation; and

when the shape of the selected region of the first image corresponds to the first predefined shape and a shape of the selected region of the second image corresponds to a second predefined shape different from the first predefined shape, determining that the primary media content corresponds to a commercial.

2. A computer-implemented method as defined in claim 1 wherein possible types of inter-frame variation include substantially uniform variation, substantially non-uniform variation and substantially no variation, and wherein the first type of inter-frame variation corresponds to substantially non-uniform variation.

3. A computer-implemented method as defined in claim 1 wherein each subregion of the first image corresponds to a respective pixel of the first image.

4. A computer-implemented method as defined in claim 1 wherein determining the first image comprises encoding each subregion of the first image to represent the inter-frame variation associated with the corresponding subregion of the secondary media content presentation.

5. A computer-implemented method as defined in claim 1 further comprising comparing a first captured representation of the secondary media content presentation with a previous second captured representation of the secondary media content presentation to determine the inter-frame variation associated with each subregion of the first image.

6. A computer-implemented method as defined in claim 1 wherein the secondary media content presentation is derived from Moving Picture Experts Group (MPEG) data, and further comprising using at least one of motion vectors or static macroblocks included in the MPEG data to determine the inter-frame variation associated with each subregion of the first image.

7. A computer-implemented method as defined in claim 1 further comprising:

segmenting the first image into a plurality of regions, each region comprising a respective plurality of connected image subregions of the first image; and

charactering each region as exhibiting one of substantially uniform variation, substantially non-uniform variation or substantially no variation.

8. A computer-implemented method as defined in claim 7 further comprising performing at least one of line detection or edge detection to segment the first image into the plurality of regions.

9. A computer-implemented method as defined in claim 1 wherein the first predefined shape comprises a rectangle having a predefined aspect ratio.

10. A computer-implemented method as defined in claim 1 wherein the first predefined shape corresponds to a stored profile representative of a possible secondary media content presentation layout.

11. A computer-implemented method as defined in claim 1 further comprising:

generating a monitored signature from the processed region of the secondary media content presentation; and

identifying the primary media content as corresponding to particular reference content when the monitored signature substantially matches a reference signature representative of the particular reference content.

12. A computer-implemented method as defined in claim 1 further comprising detecting a watermark embedded in the processed region of the secondary media content presentation to identify the primary media content.

13. A computer-implemented method as defined in claim 1 wherein possible types of inter-frame variation include substantially uniform variation, substantially non-uniform variation or substantially no variation, and wherein the first and second types of inter-frame variation both correspond to substantially non-uniform variation.

14. A computer-implemented method as defined in claim 1 wherein the first predefined shape corresponds to a first stored profile representative of a first possible secondary media content presentation layout and the second predefined shape corresponds to a second stored profile representative of a second possible secondary media content presentation layout.

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

determine a first synthetic image corresponding to a first captured image representative of a secondary media content presentation including primary media content and other media content, the first synthetic image comprising a plurality of synthetic image subregions, each synthetic image subregion encoded to represent motion associated with a corresponding subregion of the first captured image;

select a region of the first synthetic image comprising a plurality of connected synthetic image subregions of the first synthetic image together exhibiting substantially non-uniform motion;

obtain a shape of the selected region of the first synthetic image and a shape of a selected region of a second synthetic image, the second synthetic image corresponding to a second captured image preceding the first captured image;

when the shape of the selected region of the first synthetic image corresponds to a first predefined shape, extract a region of the first captured image corresponding to the selected region of the first synthetic image to identify the primary media content; and

when the shape of the selected region of the first synthetic image corresponds to the first predefined shape and the shape of the selected region of the second synthetic image corresponds to a second predefined shape different from the first predefined shape, determine that the primary media content corresponds to a commercial.

16. A machine readable storage medium as defined in claim 15 wherein the machine readable instructions, when executed, further cause the machine to detect a watermark embedded in the extracted region of the first captured image to identify the primary media content.

17. A machine readable storage medium as defined in claim 15 wherein the machine readable instructions, when executed, further cause the machine to:

segment the first synthetic image into a plurality of regions, each region comprising a respective plurality of connected synthetic image subregions of the first synthetic image; and

characterize each region as exhibiting one of substantially uniform motion, substantially non-uniform motion or substantially no motion.

18. A machine readable storage medium as defined in claim 15 wherein the machine readable instructions, when executed, further cause the machine to:

generate a monitored signature from the extracted region of the first captured image; and

identify the primary media content as corresponding to particular reference content when the monitored signature substantially matches a reference signature representative of the particular reference content.

19. A media content monitoring unit comprising:

an image pre-processor to:

determine a first synthetic image corresponding to a first captured image representative of a secondary media content presentation monitored by the media content monitoring unit, the first synthetic image comprising a plurality of synthetic image subregions, each synthetic image subregion encoded to represent motion associated with a corresponding subregion of the first captured image;

select a region of the first synthetic image comprising a plurality of connected synthetic image subregions of the first synthetic image together exhibiting substantially non-uniform motion, the selected region excluding a portion of the first synthetic image; and

when a shape of the selected region of the first synthetic image corresponds to a predefined shape, extract a region of the first captured image corresponding to the selected region of the first synthetic image to identify primary media content included in the secondary media content presentation;

a signature generator to generate a signature from the region of the first captured image extracted by the image pre-processor; and

a hint processor to process hint information associated with the region of the first captured image extracted by the image pre-processor to determine whether the primary media content corresponds to a commercial, wherein the hint processor is to:

obtain a plurality of signatures generated by the signature generator and corresponding to a respective plurality of extracted regions from successive captured images, and

determine whether at least one of the obtained plurality of signatures is representative of a blank frame separating commercial content from non-commercial content.

20. A media content monitoring unit comprising:

an image pre-processor to:

determine a first synthetic image corresponding to a first captured image representative of a secondary media content presentation monitored by the media content monitoring unit, the first synthetic image comprising a plurality of synthetic image subregions, each synthetic image subregion encoded to represent motion associated with a corresponding subregion of the first captured image;

select a region of the first synthetic image comprising a plurality of connected synthetic image subregions of the first synthetic image together exhibiting substantially non-uniform motion, the selected region excluding a portion of the first synthetic image; and

when a shape of the selected region of the first synthetic image corresponds to a first predefined shape, extract a region of the first captured image corresponding to the selected region of the first synthetic image to identify primary media content included in the secondary media content presentation;

a signature generator to generate a signature from the region of the first captured image extracted by the image pre-processor; and

a hint processor to process hint information associated with the region of the first captured image extracted by the image pre-processor to determine whether the primary media content corresponds to a commercial, wherein the hint processor is to:

obtain the shape of the selected region of the first synthetic image and a shape of a selected region of a second synthetic image, the second synthetic image corresponding to a second captured image preceding the first captured image; and

when the shape of the selected region of the first synthetic image corresponds to the first predefined shape and the shape of the selected region of the second synthetic image corresponds to a second predefined shape different from the first predefined shape, determine that the primary media content corresponds to a commercial.

21. A media content monitoring unit as defined in claim 20 wherein the first predefined shape corresponds to a first stored profile representative of a first possible secondary media content presentation layout associated with a commercial presentation and the second predefined shape corresponds to a second stored profile representative of a second possible secondary media content presentation layout associated with a non-commercial presentation.