Detection of Transitions Between Text and Non-Text Frames in a Video Stream

• US 20120099795A1
• Filed: 10/20/2010
• Published: 04/26/2012
• Est. Priority Date: 10/20/2010
• Status: Active Grant

• Current Assignee: Comcast Cable Communications LLC (Comcast Corporation)
• Original Assignee: Comcast Cable Communications LLC (Comcast Corporation)
• Inventors: Jojic, Oliver, Houghton, David F.
• Granted Patent: US 8,989,499 B2
• Time in Patent Office: Days
• US Class Current: 382/199
• CPC Class Codes: G06V 20/635 Overlay text, e.g. embedded captions in a TV program
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/036 Insert-editing
• CPC Class Codes: H04N 21/4316 for displaying supplemental content in a region of the screen, e.g. an advertisement in a separate window
• CPC Class Codes: H04N 21/4334 Recording operations recording of a television signal H04N5/76; arrangements for recording or accumulating broadcast information or broadcast-related information H04H60/27
• 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 21/4583 Automatically resolving scheduling conflicts, e.g. when a recording by reservation has been programmed for two programs in the same time slot
• CPC Class Codes: H04N 21/47214 for content reservation or setting reminders; for requesting event notification, e.g. of sport results or stock market stock exchange data over packet-switching network H04L12/1804; push services over packet-switching network H04L12/1859; notification of incoming messages in packet switching networks H04L51/224
• CPC Class Codes: H04N 21/488 Data services, e.g. news ticker systems specially adapted for using meteorological information in broadcast systems H04H60/71
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 5/445 for displaying additional information H04N5/50 takes precedence
• CPC Class Codes: H04N 5/76 Television signal recording

Abstract

Detecting the start of a credit roll within video program may allow for the automatic extension of video recordings among other functions. The start of the credit roll may be detected by determining the number of text blocks within a sequence of frames and identifying a point in the sequence of frames where a difference between the number of text blocks in frames occurring before the point and the number of text blocks in frames occurring after the point is greatest and exceeds a specified threshold. Text blocks may be identified within each frame by partitioning the frame into one or more segments and recording the segments having a pixel of a sufficiently high contrast. Contiguous segments may be merged or combined into single blocks, which may then be filtered to remove noise and false positives. Additional content may be inserted into the credit roll frames.

Claims

1. A method comprising:

determining, by a computing system, a contrast of one or more pixels in a plurality of video frames of a video program, the video program comprising a credits portion;

determining, by the computing system, a number of text blocks within each of the plurality of video frames based on the determined contrast of the one or more pixels;

determining, by the computing system, a boundary between the credits portion of the video program and a remainder of the video program based on the determined number of text blocks within each of the plurality of video frames.

2. The method of claim 1, wherein determining the number of text blocks within each of the plurality of video frames includes:

defining a size of a text detection window;

partitioning a video frame into a plurality of sections based on the size of the text detection window;

determining each of the plurality of sections of the video frame in which a pixel has a contrast that is greater than a contrast threshold; and

combining contiguous determined sections of the video frame to form a text block.

3. The method of claim 2, wherein defining the text detection window includes defining a height of the text detection window to be less than the width of the text detection window when a language of the text is intended to be read in a horizontal manner.

4. The method of claim 3, wherein defining the text detection window includes defining a width of the text detection window to be less than the height of the text detection window when a language of the text is intended to be read in a vertical manner.

5. The method of claim 2, further comprising:

determining a density of points in the text block having a contrast greater than the specified contrast threshold; and

removing the text block as a false positive in response to determining that the determined density is lower than a contrast density threshold.

6. The method of claim 5, wherein the contrast density threshold is greater than the width of the text block divided by the width of the text detection window.

7. The method of claim 1, further comprising automatically extending a recordation of the video program until at least a time corresponding to the determined boundary.

8. The method of claim 1, further comprising inserting content different from the video program into the video program at a point past the determined boundary.

9. The method of claim 8, wherein the inserted content overlays the credits portion and includes an advertisement.

10. The method of claim 2, further comprising filtering out one or more determined sections that does not meet at least one of:

a height threshold and a width threshold.

11. A method comprising:

determining, by a computing system, a number of text blocks in each of a plurality of frames in a video content stream, wherein the video content stream corresponds to a program with a predefined end time;

determining, by the computing system, whether a beginning of a credits portion of the program has been detected, wherein detection of the beginning of the credits portion is performed based on the determined number of text blocks in each of the plurality of frames; and

extending, by the computing system, a recording time until at least the beginning of the credits portion is detected.

12. The method of claim 11, wherein the recording time is extended for a predefined amount of time past a time corresponding to the beginning of the credits portion.

13. The method of claim 11, wherein the detection of the beginning of the credits portion includes:

partitioning a video frame into a plurality of sections;

determining each of the plurality of sections of the video frame in which a pixel has a contrast that is greater than a specified contrast threshold; and

combining contiguous determined sections of the video frame to form a text block.

14. The method of claim 11, further comprising:

prior to determining the number of text blocks in each of the plurality of frames;

determining whether a predefined amount of time prior to the predefined end time has been reached; and

in response to determining that the predefined amount of time prior the end time has been reached, extracting the plurality of frames from a set of all recorded frames of the video program.

15. The method of claim 14, wherein the plurality of frames comprises less than all of the recorded frames of the video program.

16. The method of claim 11, wherein the plurality of frames comprises 2 frames per second of a most recently recorded portion of the video program.

17. A method comprising:

defining, by a computing system, a size of a text detection window;

partitioning, by the computing system, a video frame into a plurality of sections using the text detection window, wherein the video frame is part of a video program having a plurality of video frames;

identifying each of the plurality of sections of the video frame in which a pixel has a contrast that is greater than a specified contrast threshold; and

combining contiguous identified sections of the video frame to form one or more text blocks.

18. The method of claim 17, further comprising filtering the one or more text blocks by:

determining a density of pixels having a contrast above the specified contrast threshold within a text block of the one or more text blocks; and

discarding the text block in response to determining that the determined density is lower than a density threshold.

19. The method of claim 18, wherein the density threshold is greater than a size of the text block divided by the size of the text detection window.

20. The method of claim 17, further comprising:

determining a number of text blocks in each of a sequence of video frames; and

applying a wavelet to the determined number of text blocks of each of the sequence of video frames to identify a beginning of a credit roll in the video program.

21. The method of claim 20, wherein applying the wavelet includes:

positioning the wavelet at a first point in the sequence of video frames;

determining a negative sum of the number of text blocks determined for each of a plurality of video frames that are chronologically prior to the first point;

determining a positive sum of the number of text blocks determined for each of a plurality of video frames that are chronologically after the first point; and

determining a difference between the positive sum and the negative sum.

22. The method of claim 21, wherein the wavelet is applied to multiple points in the sequence of frames and wherein the beginning of the credit roll corresponds to a point having the greatest difference between the positive sum and the negative sum.