Video stream modification to defeat detection

• US 7,690,011 B2
• Filed: 05/02/2005
• Issued: 03/30/2010
• Est. Priority Date: 05/02/2005
• Status: Active Grant

• Current Assignee: RPX Corporation
• Original Assignee: Technology Patents & Licensing Incorporated
• Inventors: Eldering, Charles A., Lienhart, Rainer W., Konig, Richard
• Primary Examiner(s): Koenig, Andrew Y
• Assistant Examiner(s): Featherstone, Mark D
• Application Number:
  US11/120,095
• Publication Number:
  US 20060248569A1
• Time in Patent Office: 1,793 Days
• Field of Search: 725/32
• US Class Current: 725/25
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• 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 21/4402 involving reformatting operations of video signals for household redistribution, storage or real-time display details of conversion of video standards at pixel level H04N7/01; video transcoding H04N19/40; adapting incoming signals to the display format of the display terminal G09G5/005; media handling at the source in data packet switching networks H04L65/764
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 5/76 Television signal recording

Abstract

A method and system for detecting automatic ad detection is presented in which video streams are modified such that features cannot be automatically recognized or statistical parameters and fingerprints derived from the video stream cannot be matched against fingerprints of known video segments in a database.

Claims

1. A method for altering a video stream to prevent the detection of video segments, the video stream including a plurality of images, the method comprising:

receiving the video stream;

identifying a plurality of types of image modifications to be made to one or more images of the video stream, the modifications, when applied, causing a spatial alteration of the one or more images;

randomly selecting a first type of the types of image modifications; and

altering at least a portion of at least a first one of the images by applying the randomly selected first type of image modification to the at least first one of the images, wherein the altering reduces the ability to detect a video segment in the video stream.

2. The method of claim 1, wherein the altering of the at least first one of the images is accomplished by varying images which comprise at least a portion of scene breaks.

3. The method of claim 1, wherein the altering of the at least first one of the images is accomplished by varying images which comprise at least a portion of action content.

4. The method of claim 1, wherein the random altering includes at least one of stretching, warping and rotation about an axis.

5. The method of claim 1, wherein the random altering does not perceivably degrade the video stream quality.

6. The method of claim 1, wherein the random altering of the video stream is accomplished by varying a set of pixels to alter a color histogram associated with the video stream.

7. The method of claim 1, wherein the random altering of the video stream is accomplished by moving a region within the video stream.

8. The method of claim 1, wherein the plurality of types of image modifications includes at least one of scaling, shifting, cropping, rotation, stretching and warping of an image in the video stream.

9. The method of claim 1, further comprising:

randomly selecting a second type of the types of image modifications; and

altering at least a portion of at least a second one of the images by applying the randomly selected second type of image modification to the at least second one of the images.

10. The method of claim 9, wherein the second type of image modification is the same type of image modification as the first type of image modification.

11. The method of claim 9, wherein the alteration of the at least second one of the images occurs at a point in time after the alteration of the at least first one of the images.

12. The method of claim 9, wherein the second type of image modification is a different type of image modification as the first type of image modification.

13. The method of claim 10, wherein the application of the second type of image modification to the at least second one of the images results in the same alteration of the at least second one of the images as the application of the first type of image modification to the at least first one of the images produces in the at least first one of the images.

14. A system for altering a video stream to prevent the detection of a video segment, the video stream including a plurality of images, the system comprising:

a detection subsystem for detecting parameters associated with the video stream and indicative of the presence of the video segment; and

a modification subsystem for randomly modifying a portion of at least one image within the video stream to create a spatial modification within the at least one image to prevent detection of the presence of the video segment, wherein the spatial modification is randomly selected from a plurality of modifications.

15. The system of claim 14, wherein the modification subsystem alters the video stream to prevent detection of the presence of the video segment without significantly altering the video quality.

16. The system of claim 14, wherein the modification subsystem'"'"'s modifications include at least one of stretching, warping and rotation about an axis.

17. A method for altering a video stream to prevent the detection of video segments, the method comprising:

randomly selecting a spatial modification from a plurality of spatial modifications; and

randomly altering a portion of at least one image within the video stream using the selected spatial modification, wherein the random spatial modification substantially increases the dissimilarity between a video segment fingerprint derived from the video stream and a stored fingerprint representing the video segment.

18. The method of claim 17, wherein the spatial modification does not perceivably degrade the video stream quality.

19. The method of claim 17, further comprising:

analyzing the randomly altered video stream to determine if the randomly altered video stream has been sufficiently altered to substantially increase the dissimilarity between a video segment fingerprint derived from the video stream and a stored fingerprint representing the video segment.

20. The method of claim 17, wherein the altering of the video stream is accomplished by varying a set of pixels to alter a color histogram associated with the video stream.

21. The method of claim 17, wherein the altering of the video stream is accomplished by varying a set of pixels to alter a color coherence vector associated with the video stream.

22. The method of claim 17, wherein the varying of the video stream is accomplished by moving a region within the video stream.

23. A method for preventing automated advertisement detection of at least one advertisement in a video stream, the video stream including a plurality of images, the method comprising:

randomly altering a portion of at least one image within the video stream surrounding the at least one advertisement to create a random spatial modification within the at least one image, wherein the random spatial modification is randomly selected from a plurality of spatial modifications and the spatial modification causes a sufficient increase in the similarity between the video stream and the advertisement to render automated advertisement detection ineffective.