Methods and apparatus to specify regions of interest in video frames

• US 9,286,517 B2
• Filed: 09/14/2012
• Issued: 03/15/2016
• Est. Priority Date: 11/09/2007
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Deng, Kevin Keqiang, Greenberg, Barry
• Primary Examiner(s): Akhavannik, Hadi
• Application Number:
  US13/618,867
• Publication Number:
  US 20130011071A1
• Time in Patent Office: 1,278 Days
• Field of Search: 382/100, 382103-107, 382/141, 382/173, 382180-181, 382/188, 382195-196, 382/199, 382/204, 382224-227, 382/232, 382/236, 382/254, 382/266, 382275-276, 382/284, 382/287, 382/291, 382293-295, 382/305, 348/61, 348/135, 348/157, 348/164, 348/169, 348170-172, 348/578, 348/589, 348/700, 348/722, 345418-421, 345441-442, 702/92, 702/94
• US Class Current: 1/1
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/635 Overlay text, e.g. embedded captions in a TV program
• CPC Class Codes: G06V 2201/09 Recognition of logos

Abstract

Methods and apparatus to specify regions of interest in video frames are disclosed. Example disclosed methods to mark a region in a graphical presentation include selecting a first point located at a substantially central position within the region, selecting a plurality of second points to define a boundary of the region, and comparing a plurality of stored templates with the selected first and second points to identify a first one of the stored templates to represent the region.

Claims

1. A method to mark a region in a graphical presentation, the method comprising:

identifying, with a processor, a plurality of user-selected points selected in the graphical presentation with an input device;

determining, with the processor, that the plurality of user-selected points defines a boundary of the region;

responsive to a first user input received prior to or during selection of the plurality of user-selected points with the input device, comparing, with the processor, a plurality of stored templates with the plurality of user-selected points to identify a first one of the stored templates to mark the region; and

displaying, in the graphical presentation, the first one of the stored templates identified by the processor based on the comparing of the plurality of the stored templates with the plurality of user-selected points, prior to the first one of the stored templates being accepted for marking the region.

2. A method as defined in claim 1, further including:

identifying a subsequent user-selected point in the graphical presentation selected after the first one of the stored templates is identified to mark the region;

reshaping at least a portion of a depiction of the first one of the stored templates in the graphical presentation based on a location of the subsequent user-selected point to determine a reshaped depiction of the first one of the stored templates; and

marking the region in the graphical presentation based on the reshaped depiction of the first one of the stored templates.

3. A method as defined in claim 1, wherein the comparing of the plurality of stored templates with the plurality of user-selected points occurs in response to a key press detected prior to or during selection of a first one of the plurality of user-selected points.

4. A method as defined in claim 1, wherein the comparing of the plurality of stored templates with the plurality of user-selected points occurs in response to a selection of a virtual button on a graphical display detected prior to or during selection of a first one of the plurality of user-selected points.

5. A method as defined in claim 1, wherein the comparing of the plurality of stored templates with the plurality of user-selected points includes:

determining normalized cross-correlations of the plurality of user-selected points with respective ones of the plurality of stored templates; and

identifying a respective one of the plurality of stored templates associated with a largest normalized cross-correlation to be the first one of the stored templates.

6. A method as defined in claim 1, wherein the first one of the stored templates is identified by the comparing when not all vertices of a polygon bounding the region are included in the plurality of user-selected points.

19. A method as defined in claim 1, wherein the region is a first region, the plurality of user-selected points is a first plurality of user-selected points, and further including:

comparing the plurality of stored templates with a second plurality of user-selected points to identify a second one of the stored templates to mark a second region in the graphical presentation; and

responsive to a second user input, automatically determining a shape bounding a first set of pixels in the graphical presentation marked by the first one of the stored templates and a second set of pixels in the graphical presentation marked by the second one of the stored templates to mark a third region in the graphical presentation corresponding to a combination of the first region and the second region.

7. A computer readable storage device or storage disk comprising computer readable instructions which, when executed, cause a computer to at least:

identify a plurality of user-selected points selected in a graphical presentation with an input device;

determine that the plurality of user-selected points defines a boundary of a region to be marked in the graphical presentation;

responsive to a first user input received prior to or during selection of the plurality of user-selected points, compare a plurality of stored templates with the plurality of user-selected points to identify a first one of the stored templates to mark the region; and

display, in the graphical presentation, the first one of the stored templates identified by the computer based on the comparison of the plurality of the stored templates with the plurality of user-selected points, prior to the first one of the stored templates being accepted for marking the region.

8. A storage device or storage disk as defined in claim 7, wherein the instructions, when executed, further cause the computer to:

identify a subsequent user-selected point in the graphical presentation selected after the first one of the stored templates is identified to mark the region;

reshape at least a portion of a depiction of the first one of the stored templates in the graphical presentation based on a location of the subsequent user-selected point to determine a reshaped depiction of the first one of the stored templates; and

mark the region in the graphical presentation based on the reshaped depiction of the first one of the stored templates.

9. A storage device or storage disk as defined in claim 7, wherein the instructions, when executed, cause the computer to compare the plurality of stored templates with the plurality of user-selected points in response to a key press detected prior to or during selection of a first one of the plurality of user-selected points.

10. A storage device or storage disk as defined in claim 7, wherein the instructions, when executed, cause the computer to compare the plurality of stored templates with the plurality of user-selected points in response to a selection of a virtual button on a graphical display detected prior to or during selection of a first one of the plurality of user-selected points.

11. A storage device or storage disk as defined in claim 7, wherein to compare the plurality of stored templates with the plurality of user-selected points, the instructions, when executed, cause the computer to:

determine normalized cross-correlations of the plurality of user-selected points with respective ones of the plurality of stored templates; and

identify a respective one of the plurality of stored templates associated with a largest normalized cross-correlation to be the first one of the stored templates.

12. A storage device or storage disk as defined in claim 7, wherein the first one of the stored templates is identified when less than all vertices of a polygon bounding the region are included in the plurality of user-selected points.

20. A storage device or storage disk as defined in claim 7, wherein the region is a first region, the plurality of user-selected points is a first plurality of user-selected points, and the instructions, when executed, further cause the computer to:

compare the plurality of stored templates with a second plurality of user-selected points to identify a second one of the stored templates to mark a second region in the graphical presentation; and

responsive to a second user input, automatically determine a shape bounding a first set of pixels in the graphical presentation marked by the first one of the stored templates and a second set of pixels in the graphical presentation marked by the second one of the stored templates to mark a third region in the graphical presentation corresponding to a combination of the first region and the second region.

13. An apparatus to mark a region in a graphical presentation, the apparatus comprising:

an input device;

a processor to;

identify a plurality of user-selected points selected with the input device in the graphical presentation;

determine that the plurality of user-selected points defines a boundary of the region;

responsive to a first user input received prior to or during selection of the plurality of user-selected points, compare a plurality of stored templates with the plurality of user-selected points to identify a first one of the stored templates to mark the region; and

display, in the graphical presentation, the first one of the stored templates identified by the processor based on the comparison of the plurality of the stored templates with the plurality of user-selected points, prior to the first one of the stored templates being accepted for marking the region; and

memory to store the plurality of stored templates.

14. An apparatus as defined in claim 13, wherein the processor is further to:

identify a subsequent user-selected point in the graphical presentation selected after the first one of the stored templates is identified to mark the region;

reshape at least a portion of a depiction of the first one of the stored templates in the graphical presentation based on a location of the subsequent user-selected point to determine a reshaped depiction of the first one of the stored templates; and

mark the region in the graphical presentation based on the reshaped depiction of the first one of the stored templates.

15. An apparatus as defined in claim 13, wherein the processor is to compare the plurality of stored templates with the plurality of user-selected points in response to a key press detected prior to or during selection of a first one of the user-selected plurality of points.

16. An apparatus as defined in claim 13, wherein the processor is to compare the plurality of stored templates with the plurality of user-selected points in response to a selection of a virtual button detected prior to or during selection of a first one of the plurality of user-selected points, the virtual button included in a graphical user interface presented by the processor.

17. An apparatus as defined in claim 13, wherein to compare the plurality of stored templates with the plurality of user-selected points, the processor is to:

determine normalized cross-correlations of the plurality of user-selected points with respective ones of the plurality of stored templates; and

identify a respective one of the plurality of stored templates associated with a largest normalized cross-correlation to be the first one of the stored templates to mark the region.

18. An apparatus as defined in claim 13, wherein the processor is to identify the first one of the stored templates when not all vertices of a polygon bounding the region are included in the plurality of user-selected points.

21. An apparatus as defined in claim 13, wherein the region is a first region, the plurality of user-selected points is a first plurality of user-selected points, and the processor is further to:

compare the plurality of stored templates with a second plurality of user-selected points to identify a second one of the stored templates to mark a second region in the graphical presentation; and

responsive to a second user input, automatically determine a shape bounding a first set of pixels in the graphical presentation marked by the first one of the stored templates and a second set of pixels in the graphical presentation marked by the second one of the stored templates to mark a third region in the graphical presentation corresponding to a combination of the first region and the second region.