Video fingerprint systems and methods

• US 8,259,177 B2
• Filed: 06/30/2008
• Issued: 09/04/2012
• Est. Priority Date: 06/30/2008
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Gits, Peter M., Rodriguez, Arturo A.
• Primary Examiner(s): SALAD, ABDULLAHI ELMI
• Application Number:
  US12/164,465
• Publication Number:
  US 20090328125A1
• Time in Patent Office: 1,527 Days
• Field of Search: 348/169, 382/173, 382/103, 725/105
• US Class Current: 348/169
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06F 16/7854 using shape G06F16/7837 takes precedence
• CPC Class Codes: G06F 16/786 using motion, e.g. object motion or camera motion
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: H04N 5/145 Movement estimation for video coding H04N19/51
• CPC Class Codes: H04N 5/913 for scrambling ; for copy protection

Abstract

A method that provides identification information for a portion of a video stream includes receiving a video stream, wherein the video stream includes one or more successive video scenes, wherein the one or more successive video scenes respectively corresponds to one or more sets of visual information, wherein each of the one or more successive video scenes includes plural successive pictures, wherein a first visual object is included in a first video scene, wherein the one or more successive video scenes includes the first video scene, detecting the first visual object over a first plurality of pictures of the first video scene, deriving information corresponding to one or more measured transitions of the first visual object over the first plurality of pictures of the first video scene, and providing identification information corresponding to the derived information.

Claims

1. A method for providing identification information for a portion of a video stream, the method comprising:

receiving a video stream, wherein the video stream includes one or more successive video scenes, wherein the one or more successive video scenes respectively corresponds to one or more sets of visual information, wherein each of the one or more successive video scenes includes plural successive pictures, wherein a first visual object is included in a first video scene, wherein the one or more successive video scenes includes the first video scene;

detecting the first visual object over a first plurality of pictures of the first video scene;

deriving information corresponding to one or more measured transitions of the first visual object over the first plurality of pictures of the first video scene, wherein deriving comprises measuring a respective spatial transition from a location of the first visual object in a first picture to a location of the first visual object in each respective picture in a second plurality of pictures, wherein the first picture is included in the first plurality of pictures of the first video scene, wherein the second plurality of pictures includes the first plurality of pictures of the first video scene except the first picture, and wherein each respective picture in the second plurality of pictures is after the first picture in a display order of the first plurality of pictures of the first video scene; and

providing identification information corresponding to the derived information.

2. The method of claim 1, further comprising associating the identification information with the first video scene.

3. The method of claim 2, further comprising associating the identification information with the first visual object.

4. The method of claim 2, wherein each measured transition of the first visual object is according to a location of a centroid of the first visual object in two pictures of the first video scene.

5. The method of claim 1, wherein the first plurality of pictures of the first video scene comprises all of the plural successive pictures of the first video scene.

6. The method of claim 1, wherein the number of pictures in the first plurality of pictures of the first video scene is less than the number of pictures of the plural successive pictures of the first video scene.

7. The method of claim 1, wherein each measured transition corresponds to changes in one or more of size of the first visual object, shape of the first visual object, color of the first visual object, and hue of the first visual object.

8. The method of claim 1, further comprising:

detecting a second visual object over the first plurality of pictures of the first video scene;

deriving second information corresponding to one or more measured transitions of the second visual object over the first plurality of pictures of the first video scene; and

providing second identification information corresponding to the derived second information.

9. The method of claim 1, further comprising excluding from transition measurement other visual objects which appear for less than a predetermined threshold number of pictures of the first plurality of pictures of the first video scene.

10. The method of claim 1, further comprising excluding from transition measurement other visual objects which appear for less than a predetermined window of time within a span of time of the first plurality of pictures of the first video scene.

11. The method of claim 1, further comprising excluding from transition measurement other visual objects which are of lower priority than the first visual object, the priority based on determined robustness to object detection circumvention.

12. The method of claim 1, further comprising validating the derived information corresponding to the one or more measured transitions of the first visual object over the first plurality of pictures of the first video scene by computing second order measurements of transitions corresponding to the one or more measured transitions.

13. A system that provides identification information for a portion of a video stream, the system comprising:

a memory having logic stored therein; and

a processor configured to execute the logic to;

receive a video stream, wherein the video stream includes one or more successive video scenes, wherein the one or more successive video scenes respectively corresponds to one or more sets of visual information, wherein each of the one or more successive video scenes includes plural successive pictures, wherein a first visual object is included in a first video scene, wherein the one or more successive video scenes includes the first video scene;

detect the first visual object over a first plurality of pictures of the first video scene;

derive information corresponding to one or more measured transitions of the first visual object over the first plurality of pictures of the first video scene, wherein deriving comprises measuring a respective spatial transition from a location of the first visual object in a first picture to a location of the first visual object in each respective picture in a second plurality of pictures, wherein the first picture is included in the first plurality of pictures of the first video scene, wherein the second plurality of pictures includes the first plurality of pictures of the first video scene except the first picture, and wherein each respective picture in the second plurality of pictures is after the first picture in a display order of the first plurality of pictures of the first video scene; and

provide identification information corresponding to the derived information.

14. The system of claim 13, wherein the processor is further configured to execute the logic to associate the identification information with the first video scene.

15. The system of claim 14, wherein the processor is further configured to execute the logic to associate the identification information with the first visual object.

16. The system of claim 13, wherein the processor is further configured to execute the logic to measure a spatial transition from a location of the first visual object in a first picture to a location of the first visual object in a second picture, wherein the first and second pictures are included in the first plurality of pictures of the first video scene, and wherein the second picture follows the first picture in display order of the first plurality of pictures of the first video scene.

17. The system of claim 13, wherein the processor is further configured to execute the logic to measure a respective spatial transition from a location of the first visual object in a first picture to a location of the first visual object in each respective picture in a second plurality of pictures, wherein the first picture is included in the first plurality of pictures of the first video scene, wherein the second plurality of pictures includes the first plurality of pictures of the first video scene except the first picture, and wherein each respective picture in the second plurality of pictures is after the first.

18. A system comprising:

means for receiving a video stream, wherein the video stream includes one or more successive video scenes, wherein each of the one or more successive video scenes includes plural successive pictures, wherein a first visual object is included in a first video scene, wherein the one or more successive video scenes includes the first video scene;

means for detecting the first visual object over a first plurality of pictures of the first video scene;

means for deriving information corresponding to one or more measured transitions of the first visual object over the first plurality of pictures of the first video scene, wherein deriving comprises measuring a respective spatial transition from a location of the first visual object in a first picture to a location of the first visual object in each respective picture in a second plurality of pictures, wherein the first picture is included in the first plurality of pictures of the first video scene, wherein the second plurality of pictures includes the first plurality of pictures of the first video scene except the first picture, and wherein each respective picture in the second plurality of pictures is after the first picture in a display order of the first plurality of pictures of the first video scene; and

means for providing identification information corresponding to the derived information.