Method for Computing a Fingerprint of a Video Sequence

• US 20080317278A1
• Filed: 01/16/2007
• Published: 12/25/2008
• Est. Priority Date: 01/16/2006
• Status: Active Grant

• Current Assignee: Thomson Licensing (Vantiva SA)
• Original Assignee: Thomson Licensing (Vantiva SA)
• Inventors: Lefebvre, Frederic, Oisel, Lionel, Massoudi, Ayoub, Demarty, Claire-Helene
• Granted Patent: US 8,103,050 B2
• Time in Patent Office: Days
• US Class Current: 382/100
• CPC Class Codes: G06F 16/7847 using low-level visual features of the video content
• CPC Class Codes: G06F 21/16 Program or content traceability, e.g. by watermarking
• CPC Class Codes: G06V 10/421 by analysing segments intersecting the pattern
• CPC Class Codes: G06V 10/449 Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• 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

Abstract

The invention concerns a method for computing a fingerprint of a video sequence. The method comprises the steps of—Computation of a visual digest for each frame of the video, —Computation of the distance between the visual digest of each frame of the video in order to detect shots, —Detection, for each detected shot of the video, of a frame, called stable frame, having the smallest content variation of the shot, —Calculation of a local fingerprint for said stable frame.

Claims

1. Method for computing a fingerprint of a video sequence wherein it comprises the steps of

Computation of a visual digest for each frame of the video,

Computation of the distance between the visual digest of each frame of the video in order to detect shots,

Detection, for each detected shot of the video, of a frame, called stable frame, having the smallest content variation of the shot,

Calculation of a local fingerprint for said stable frame.

2. Method according to claim 1 wherein the computation of a visual digest for each frame is based on the computation of a visual hash function.

3. Method according to claim 2 wherein the said visual hash function comprises the sub-steps of

selection of a set of pixels, said set of pixels being the pixels belonging to the ellipse of maximum size centered in the center of the frame comprised in said frame,

calculation of a visual digest for each angular orientation (θ

) from 0 to 179 degrees,

the global visual digest of said frame being the set of all the visual digests of the different angular orientations.

4. Method according to claim 3 wherein the visual digest for one orientation is based on the luminance of the pixels in the strip of said orientation.

5. Method according to claim 3 wherein the step of detecting the shots comprise the sub-steps of:

defining a pseudo-global threshold for each frame, computed on a large sliding window centered on said frame, based on the mean and on the variance of the distance between said frame (i) and the frames in said window,

defining a local and adaptive threshold for each frame, computed on a small sliding window centered on said frame (i), based on the second maximum value of the distance between two frames in said window.

6. Method according to claim 5 wherein the shots are defined as being the frames which distance with their neighbor frame is lower than the maximum of the said two thresholds.

7. Method according to claim 6 wherein the step of detection of a stable frame comprises the sub-steps of:

computing, for each frame of each shot, an average of the content image distance defined in an interval comprising a predetermined number of frames (2 L3+1),

determining the stable frame as being the frame verifying the following conditions;

the said calculated distance is the minimum of the calculated distance

the entropy of the visual digest of said frame is higher than a predetermined threshold.

8. Method according to claim 7 wherein the step of calculation of a local fingerprint for said stable frame comprises the sub-steps of

detection of a set of interest points in said frame, said interest points being detected by applying a difference of Gaussian of successive filtered frames,

Computation of a descriptor for each of the interest points.

9. Method according to claim 8 wherein the computation of a descriptor comprises the following sub-steps

determining the gradient of each interest point orientation in a small disc around the interest point, by computing its magnitude and its orientation,

division into nine regions of a circle centered around each interest point;

computation for each region of a local histogram of the gradients orientation,

the set of each local histogram representing the descriptor of each interest point.

10. Method according to claim 9 wherein the local fingerprint of a stable frame is the set of the descriptors of all the interest points of said stable frame.

11. Method according to claim 10 wherein the video fingerprint is the set of the local fingerprints of all the stable frames.