Systems and methods for identifying a scene-change/non-scene-change transition between frames

• US 9,275,683 B1
• Filed: 04/24/2014
• Issued: 03/01/2016
• Est. Priority Date: 09/30/2011
• Status: Active Grant

• Current Assignee: Tribune Broadcasting Company Incorporated (Nexstar Media Group, Inc.)
• Original Assignee: Tribune Broadcasting Company Incorporated (Nexstar Media Group, Inc.)
• Inventors: Hundemer, Hank J., Lasher, Dana A.
• Primary Examiner(s): Alavi, Amir
• Application Number:
  US14/261,169
• Time in Patent Office: 677 Days
• US Class Current: 1/1
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G10L 19/008 Multichannel audio signal coding or decoding using interchannel correlation to reduce redundancy, e.g. joint-stereo, intensity-coding or matrixing
• CPC Class Codes: G10L 25/57 for processing of video signals
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence
• CPC Class Codes: G11B 27/32 on separate auxiliary tracks of the same or an auxiliary record carrier
• CPC Class Codes: H03G 3/20 Automatic control H03G3/005 takes precedence; combined with volume compression or expansion H03G7/00
• CPC Class Codes: H04N 17/00 Diagnosis, testing or measuring for television systems or their details
• CPC Class Codes: H04N 19/70 characterised by syntax aspects related to video coding, e.g. related to compression standards
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/26283 for associating distribution time parameters to content, e.g. to generate electronic program guide data
• CPC Class Codes: H04N 21/435 Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/8455 involving pointers to the content, e.g. pointers to the I-frames of the video stream
• CPC Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments
• CPC Class Codes: H04N 5/607 for more than one sound signal, e.g. stereo, multilanguages H04N5/602 takes precedence
• CPC Class Codes: H04N 7/0122 the input and the output signals having different aspect ratios
• CPC Class Codes: H04N 7/0125 one of the standards being a high definition standard
• CPC Class Codes: H04N 7/025 Systems for the transmission of digital non-picture data, e.g. of text during the active part of a television frame transmission of digital non-picture data during the vertical blanking interval only H04N7/088
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308

Abstract

Disclosed are systems and methods for identifying a scene-change/non-scene-change transition between frames. One embodiment takes the form of a method including receiving a first frame of video; defining a first region of the first frame, wherein the first region is associated with a first plurality of pixels of the first frame; receiving a second frame of video; defining a second region of the second frame, wherein the second region is associated with a second plurality of pixels of the second frame; using (i) a first plurality of luma values associated with the first plurality of pixels and (ii) a second plurality of luma values associated with the second plurality of pixels, as a basis to identify the pair of the first and second frames as having a particular scene-change/non-scene-change attribute; and storing in a memory an indication that the pair of the first and second frames has the identified attribute.

Claims

1. A frame-processing device comprising a processor and a non-transitory computer-readable medium containing instructions that, when executed by the processor, cause a set of steps to be carried out, the set of steps comprising:

receiving a first frame of video from a video source device;

defining a first region of the received first frame, wherein the first region is associated with a first plurality of pixels of the received first frame;

receiving a second frame of video from the video source device;

defining a second region of the received second frame, wherein the second region is associated with a second plurality of pixels of the received second frame;

using (i) a first plurality of luma values associated with the first plurality of pixels and (ii) a second plurality of luma values associated with the second plurality of pixels, as a basis to identify the pair of the received first and second frames as having a particular scene-change/non-scene-change attribute; and

storing in a memory an indication that the pair of the received first and second frames has the identified particular scene-change/non-scene-change attribute.

2. The frame-processing device of claim 1, wherein the received first frame and the received second frame are adjacent frames.

3. The frame-processing device of claim 1, further comprising a video input connection, wherein receiving the first frame of video from the video source device comprises receiving, via the video input connection, the first frame of video from the video source device, and wherein receiving the second frame of video from the video source device comprises receiving, via the video input connection, the second frame of video from the video source device.

4. The frame-processing device of claim 1, wherein the first region is a generally rectangular-shaped portion of the received first frame, and wherein the second region is a generally rectangular-shaped portion of the received second frame.

5. The frame-processing device of claim 4, wherein the first and second regions are defined by a left-bound column, a right-bound column, a top-bound row, and a bottom-bound row.

6. The frame-processing device of claim 5, wherein the received first and second frames include a row count of 1080 and a column count of 1920, both defining a resolution of the first and second frames, and wherein the left-bound column is a value in a range 8-30, the right-bound column is a value in a range 1890-1912, the top-bound row is a value in a range 0-30, and the bottom-bound row is a value in a range 1050-1080.

7. The frame-processing device of claim 1, wherein using (i) the first plurality of luma values associated with the first plurality of pixels and (ii) the second plurality of luma values associated with the second plurality of pixels, as the basis to identify the pair of the received first and second frames as having the particular scene-change/non-scene-change attribute comprises identifying the pair of the received first and second frames as having the particular scene-change/non-scene-change attribute responsive to every condition in a condition set being satisfied.

8. The frame-processing device of claim 7, the set of steps further comprising:

generating a first luma value table based on the first region and a second luma value table based on the second region, wherein the luma value tables each have a luma value counter for each luma value in a luma range, and wherein each luma value counter is based on the luma values in the corresponding region;

for each luma value in the luma value range, (i) calculating a first value as a first function of the corresponding luma value counter in the first luma table and the corresponding luma value counter in the second luma value table, (ii) calculating a second value as a second function of the calculated first value, and (iii) adding the calculated second value to an accumulator; and

calculating a third value as a third function of the accumulator,

wherein the condition set comprises a condition that the calculated third value is less than a scene-change threshold.

9. The frame-processing device of claim 8, wherein the second function is an inverse of the third function.

10. A non-transitory computer-readable medium containing instructions that, when executed by the processor, cause performance of a set of steps comprising:

receiving a first frame of video from a video source device;

defining a first region of the received first frame, wherein the first region is associated with a first plurality of pixels of the received first frame;

receiving a second frame of video from the video source device;

defining a second region of the received second frame, wherein the second region is associated with a second plurality of pixels of the received second frame;

using (i) a first plurality of luma values associated with the first plurality of pixels and (ii) a second plurality of luma values associated with the second plurality of pixels, as a basis to identify the pair of the received first and second frames as having a particular scene-change/non-scene-change attribute; and

storing in a memory an indication that the pair of the received first and second frames has the identified particular scene-change/non-scene-change attribute.

11. The non-transitory computer-readable medium of claim 10, wherein the received first frame and the received second frame are adjacent frames.

12. The non-transitory computer-readable medium of claim 10, wherein the first region is a generally rectangular-shaped portion of the received first frame, and wherein the second region is a generally rectangular-shaped portion of the received second frame.

13. A method comprising:

receiving a first frame of video from a video source device;

defining a first region of the received first frame, wherein the first region is associated with a first plurality of pixels of the received first frame;

receiving a second frame of video from the video source device;

defining a second region of the received second frame, wherein the second region is associated with a second plurality of pixels of the received second frame;

using (i) a first plurality of luma values associated with the first plurality of pixels and (ii) a second plurality of luma values associated with the second plurality of pixels, as a basis to identify the pair of the received first and second frames as having a particular scene-change/non-scene-change attribute; and

storing in a memory an indication that the pair of the received first and second frames has the identified particular scene-change/non-scene-change attribute.

14. The method of claim 13, wherein the received first frame and the received second frame are adjacent frames.

15. The method of claim 13, wherein the first region is a generally rectangular-shaped portion of the received first frame, and wherein the second region is a generally rectangular-shaped portion of the received second frame.

16. The method of claim 15, wherein the first and second regions are defined by a left-bound column, a right-bound column, a top-bound row, and a bottom-bound TOW.

17. The method of claim 16, wherein the received first and second frames include a row count of 1080 and a column count of 1920, both defining a resolution of the first and second frames, and wherein the left-bound column is a value in a range 8-30, the right-bound column is a value in a range 1890-1912, the top-bound row is a value in a range 0-30, and the bottom-bound row is a value in a range 1050-1080.

18. The method of claim 13, wherein using (i) the first plurality of luma values associated with the first plurality of pixels and (ii) the second plurality of luma values associated with the second plurality of pixels, as the basis to identify the pair of the received first and second frames as having the particular scene-change/non-scene-change attribute comprises identifying the pair of the received first and second frames as having the particular scene-change/non-scene-change attribute responsive to every condition in a condition set being satisfied.

19. The method of claim 18, further comprising:

generating a first luma value table based on the first region and a second luma value table based on the second region, wherein the luma value tables each have a luma value counter for each luma value in a luma range, wherein each luma value counter is based on the luma values in the corresponding region;

for each luma value in the luma value range, (i) calculating a first value as a first function of the corresponding luma value counter in the first luma table and the corresponding luma value counter in the second luma value table, (ii) calculating a second value as a second function of the calculated first value, and (iii) adding the calculated second value to an accumulator; and

calculating a third value as a third function of the accumulator,

wherein the condition set comprises a condition that the calculated third value is less than a scene-change threshold.

20. The method of claim 19, wherein the second function is an inverse of the third function.