Video entity recognition in compressed digital video streams

• US 8,634,652 B2
• Filed: 12/18/2012
• Issued: 01/21/2014
• Est. Priority Date: 03/07/2003
• Status: Active Grant

• Current Assignee: RPX Corporation
• Original Assignee: Technology Patents & Licensing Incorporated
• Inventors: Lienhart, Rainer W., Eldering, Charles A.
• Primary Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US13/718,151
• Publication Number:
  US 20130108173A1
• Time in Patent Office: 399 Days
• Field of Search: 382/382, 382/100, 382/181, 382/232, 382/233, 382/168, 382/124, 382/195, 348/E5.005, 348/E5.002, 348/E7.071, 348/E5.009, 348/E5.108, 348/E7.07, 348/E5.137, 348/335, 348/E5.007, 348/E7.036, 375/240.28, 375/240.25, 375/E7.211, 375/E7.024, 375/E7.025, 375/E7.268, 375/240.01, 375/E7.267, 375/E7.094, 375/E7.129, 375/E7.25, 375/E7.278, 375/E7.222, 725/32, 725/33, 725/34, 725/35, 725/36
• US Class Current: 382/195
• CPC Class Codes: G06F 16/785 using colour or luminescence
• CPC Class Codes: G06F 16/7864 using domain-transform features, e.g. DCT or wavelet transform coefficients
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0241 Advertisements
• 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 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/48 Matching video sequences
• CPC Class Codes: G06V 20/635 Overlay text, e.g. embedded captions in a TV program
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/59 of video recognising characters or patterns in general G06F18/00, G06V20/00
• CPC Class Codes: H04N 21/2143 located in a single building, e.g. hotel, hospital or museum arrangements specially adapted for plural spots in a confined site in broadcast systems H04H20/63; adaptations for transmission by electric cable for domestic distribution in television systems H04N7/106
• 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 21/23424 involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
• CPC Class Codes: H04N 21/2547 Third Party Billing, e.g. billing of advertiser
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• CPC Class Codes: H04N 21/41415 involving a public display, viewable by several users in a public space outside their home, e.g. movie theatre, information kiosk
• CPC Class Codes: H04N 21/4331 Caching operations, e.g. of an advertisement for later insertion during playback
• 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 21/44016 involving splicing one content stream with another content stream, e.g. for substituting a video clip
• CPC Class Codes: H04N 21/458 : Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations arrangements for replacing or switching information during the broadcast or during the distribution H04H20/10
• CPC Class Codes: H04N 21/812 : involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/8352 : involving content or source identification data, e.g. Unique Material Identifier [UMID]
• CPC Class Codes: H04N 21/84 : Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73
• CPC Class Codes: H04N 21/8405 : represented by keywords
• 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 21/8547 : involving timestamps for synchronizing content
• CPC Class Codes: H04N 7/088 : the inserted signal being digital
• CPC Class Codes: H04N 7/0887 : for the transmission of programme or channel identifying signals
• CPC Class Codes: H04N 7/162 : Authorising the user terminal, e.g. by paying; Registering the use of a subscription channel, e.g. billing

Abstract

A method and system for detection of video segments in compressed digital video streams is presented. The compressed digital video stream is examine to determine synchronization points, and the compressed video signal is analyzed following detection of the synchronization points to create video fingerprints that are subsequently compared against a library of stored fingerprints.

Claims

1. A method of detecting a video entity in a media stream having a plurality of video frames, the method comprising:

storing a plurality of known fingerprints in a memory, wherein each of the known fingerprints is based on a first set of image features corresponding to one or more frames of known video content;

receiving the media stream;

defining at least one region of interest in at least one of the video frames of the received media stream;

determining, using a computer, a fingerprint of the at least one video frame of the received media stream based on the at least one region of interest;

comparing, using the computer, the determined fingerprint to the plurality of known fingerprints; and

determining, based on the comparing, that the received media stream contains the video entity.

2. The method of claim 1, further comprising:

extracting a second set of image features from the at least one video frame of the received media stream, wherein determining the fingerprint is based on the second set of image features.

3. The method of claim 2, wherein the second set of images features used to determine the fingerprint are the same type of image features as the first set of image features on which the known fingerprints are based.

4. The method of claim 1, further comprising:

decomposing the received media stream into a plurality of representative video frames, wherein determining the fingerprint is based on the representative video frames.

5. The method of claim 1, further comprising:

defining a plurality of regions of interest within the at least one video frame of the received media stream, wherein determining the fingerprint comprises comparing image features of the plurality of regions of interest to each other.

6. The method of claim 1, wherein determining the fingerprint is based on an intra-frame comparison of image features.

7. The method of claim 1, wherein defining the at least one region of interest comprises defining a plurality of regions of interest in at least two separate frames of the received media stream, and wherein the fingerprint is determined based on the plurality of regions of interest.

8. The method of claim 1, wherein the first set of image features is extracted from the one or more frames of known video content.

9. The method of claim 1, wherein the known fingerprints are statistical parameterized representations of the corresponding one or more frames of known video content.

10. A computer program product, comprising a computer usable, non-transitory medium having a computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a method of detecting a video entity in a media stream having a plurality of video frames, said method comprising:

storing a plurality of known fingerprints, wherein each of the known fingerprints is based on a first set of image features corresponding to one or more frames of known video content;

defining at least one region of interest in at least one of the video frames of a received media stream;

determining a fingerprint of the at least one video frame of the received media stream based on the at least one region of interest;

comparing the determined fingerprint to the plurality of known fingerprints; and

determining, based on the comparing, that the received media stream contains the video entity.

11. The computer program product of claim 10, further comprising:

extracting a second set of image features from the at least one video frame of the received media stream, wherein determining the fingerprint is based on the second set of image features.

12. The computer program product of claim 10, further comprising:

decomposing the received media stream into a plurality of representative video frames, wherein determining the fingerprint is based on the representative video frames.

13. The computer program product of claim 10, further comprising:

defining a plurality of regions of interest within the at least one video frame of the received media stream, wherein determining the fingerprint comprises comparing image features of the plurality of regions of interest to each other.

14. The computer program product of claim 10, wherein determining the fingerprint is based on an intra-frame comparison of image features.

15. The computer program product of claim 10, wherein the first set of image features is extracted from the one or more frames of known video content.

16. The computer program product of claim 10, wherein the known fingerprints are statistical parameterized representations of the corresponding one or more frames of known video content.

17. A method of detecting a video entity in a media stream, the method comprising:

receiving a first media stream comprising a plurality of video frames;

defining at least one region of interest in at least one of the video frames of the first media stream;

determining, using a computer, a first fingerprint of the at least one video frame based on a first set of image features corresponding to the at least one region of interest;

submitting the first fingerprint to a database of known fingerprints of known media content;

receiving a second media stream comprising a plurality of video frames;

determining, using said computer, a second fingerprint corresponding to at least a portion of the second media stream;

comparing, using said computer, the second fingerprint to the known fingerprints of known media content; and

determining, based on the comparing, whether the second media stream contains the video entity.

18. The method of claim 17, further comprising:

defining at least one region of interest in at least one of the video frames of the second media stream, wherein determining the second fingerprint is based on a second set of image features corresponding to the at least one region of interest of the second media stream.

19. The method of claim 18, wherein the second set of images features used to determine the second fingerprint are the same type of image features as the first set of image features on which the first fingerprint are based.

20. The method of claim 17, wherein the first fingerprint is indicative of known video content.

21. The method of claim 17, further comprising:

decomposing the first media stream into a plurality of representative video frames, wherein determining the first fingerprint is based on the representative video frames.

22. The method of claim 17, further comprising:

defining a plurality of regions of interest within the at least one video frame of the first media stream, wherein determining the first fingerprint comprises comparing image features of the plurality of regions of interest to each other.

23. The method of claim 17, wherein determining the first fingerprint is based on an intra-frame comparison of image features.

24. The method of claim 17, wherein defining the at least one region of interest of the first media stream comprises defining a plurality of regions of interest in at least two separate frames of the first media stream, and wherein the first fingerprint is determined based on the plurality of regions of interest.

25. The method of claim 17, further comprising:

extracting a second set of image features from a plurality of video frames of the second media stream, wherein determining the second fingerprint is based on the second set of image features.

26. A computer program product, comprising a computer usable, non-transitory medium having a computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a method of detecting a video entity in a media stream, said method comprising:

defining at least one region of interest in at least one video frame of a first media stream comprising a plurality of video frames;

determining a first fingerprint of the at least one video frame based on a first set of image features corresponding to the at least one region of interest;

submitting the first fingerprint to a database of known fingerprints of known media content;

determining a second fingerprint corresponding to at least a portion of a second media stream comprising a plurality of video frames;

comparing the second fingerprint to the known fingerprints of known media content; and

determining, based on the comparing, whether the second media stream contains the video entity.

27. The computer program product of claim 26, further comprising:

defining at least one region of interest in at least one of the video frames of the second media stream, wherein determining the second fingerprint is based on a second set of image features corresponding to the at least one region of interest of the second media stream.

28. The computer program product of claim 26, wherein the first fingerprint is indicative of known video content.

29. The computer program product of claim 26, further comprising:

decomposing the first media stream into a plurality of representative video frames, wherein determining the first fingerprint is based on the representative video frames.

30. The computer program product of claim 26, further comprising:

defining a plurality of regions of interest within the at least one video frame of the first media stream, wherein determining the first fingerprint comprises comparing image features of the plurality of regions of interest to each other.

31. The computer program product of claim 26, wherein determining the first fingerprint is based on an intra-frame comparison of image features.

32. The computer program product of claim 26, further comprising:

extracting a second set of image features from a plurality of video frames of the second media stream, wherein determining the second fingerprint is based on the second set of image features.

33. A method of detecting a video entity in a media stream having a plurality of video frames, the method comprising:

storing a plurality of known fingerprints in a memory, wherein each of the known fingerprints is based on a first set of image features corresponding to one or more frames of known video content;

receiving the media stream;

defining at least one feature vector in at least one of the video frames of the received media stream;

determining, using a computer, a fingerprint of the at least one video frame of the received media stream based on the at least one feature vector;

comparing, using said computer, the determined fingerprint to the plurality of known fingerprints; and

determining, based on the comparing, that the received media stream contains the video entity.

34. The method of claim 33, further comprising:

extracting a second set of image features from the at least one video frame of the received media stream, wherein determining the fingerprint is based on the second set of image features.

35. The method of claim 33, further comprising:

decomposing the received media stream into a plurality of representative video frames, wherein determining the fingerprint is based on the representative video frames.

36. The method of claim 33, further comprising:

defining a plurality of feature vectors within the at least one video frame of the received media stream, wherein determining the fingerprint comprises aggregating the plurality of feature vectors.

37. The method of claim 33, wherein determining the fingerprint is based on luminance values of at least some of the pixels in the at least one feature vector.

38. The method of claim 33, wherein the first set of image features is extracted from the one or more frames of known video content.

39. A computer program product, comprising a computer usable, non-transitory medium having a computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a method of detecting a video entity in a media stream having a plurality of video frames, said method comprising:

storing a plurality of known fingerprints, wherein each of the known fingerprints is based on a first set of image features corresponding to one or more frames of known video content;

defining at least one feature vector in at least one of the video frames of a received media stream;

determining a fingerprint of the at least one video frame of the received media stream based on the at least one feature vector;

comparing the determined fingerprint to the plurality of known fingerprints; and

determining, based on the comparing, that the received media stream contains the video entity.

40. The computer program product of claim 39, further comprising:

extracting a second set of image features from the at least one video frame of the received media stream, wherein determining the fingerprint is based on the second set of image features.

41. The computer program product of claim 39, further comprising:

decomposing the received media stream into a plurality of representative video frames, wherein determining the fingerprint is based on the representative video frames.

42. The computer program product of claim 39, further comprising:

defining a plurality of feature vectors within the at least one video frame of the received media stream, wherein determining the fingerprint comprises aggregating the plurality of feature vectors.

43. The computer program product of claim 39, wherein determining the fingerprint is based on luminance values of at least some of the pixels in the at least one feature vector.

44. The computer program product of claim 39, wherein the first set of image features is extracted from the one or more frames of known video content.