Efficient and robust algorithm for video sequence matching

• US 7,486,827 B2
• Filed: 01/21/2005
• Issued: 02/03/2009
• Est. Priority Date: 01/21/2005
• Status: Expired due to Fees

• Current Assignee: Seiko Epson Corporation (Seiko Group)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: Kim, Changick
• Primary Examiner(s): Bali; Vikkram
• Assistant Examiner(s): Thomas; Mia M
• Application Number:
  US11/040,569
• Publication Number:
  US 20060182368A1
• Time in Patent Office: 1,474 Days
• Field of Search: None
• US Class Current: 382/209
• CPC Class Codes: G06F 16/7847 using low-level visual features of the video content
• CPC Class Codes: G06V 20/48 Matching video sequences
• CPC Class Codes: G06V 30/2504 Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches
• CPC Class Codes: Y10S 707/99931 Database or file accessing

Abstract

A two-step matching technique is embodied in a video-copy-detection algorithm that detects copies of video sequences. The two-step matching technique uses ordinal signatures of frame partitions and their differences from partition mean values. The algorithm of this invention is not only robust to intensity/color variations it can also effectively handle various format conversions, thereby providing robustness regardless of the video dynamics of the frame shots.

Claims

1. A method using a central processing unit for detecting whether all or a portion of target video data containing a plurality of frames and sub-sequences matches query video data, the method comprising the steps of:

(a) calculating using the central processing unit a first distance between the query video data and a specified one of the sub-sequences of the target video data, wherein the first distance is based on a distance between a first rank matrix of a frame of the query video data and a second rank matrix of a frame of the sub-sequences of the target video data, the first rank matrix is based on a 2×

2 partition of a frame of the query video data, the second rank matrix is based on a 2×

2 partition of a frame of the sub-sequences of the target video data, each element of the first and second rank matrix is related to a rank of a partition in a particular frame relative to the other partitions in the particular frame;

(b) determining using the central processing unit if the first distance is less than a threshold;

if so, calculating a second distance between the query video data and the specified sub-sequence of the target video data, wherein the second distance is based on the distance between a third rank matrix of a frame of the query video data and a fourth rank matrix of a frame of the sub-sequences of the target video data, the third rank matrix is based on differential values of a frame of the query video data, the fourth rank matrix is based on differential values of a frame of the sub-sequences of the target video data,

otherwise, assign a value greater than said threshold that exceeds a corresponding value of the second distance;

(c) repeating, using the central processing unit, steps (a) and (b) for each sub-sequence of the target video data;

(d) finding, using the central processing unit, a local minima from among the second distance values in the central processing unit; and

(e) performing copy detection based on the local minima found.

2. A method as recited in claim 1, wherein step (e) comprised comparing each local minimum with a second threshold, and determining which, if any, of the local minima is/are less than the second threshold.

3. A method as recited in claim 1, wherein the calculation using the central processing unit of the first and second distances in steps (a) and (b) respectively are each based on a 2×

2 partitioning of each of the frames in the query video data and the target video data.

4. A method as recited in claim 1, wherein the detection using the central processing unit, is robust to select modifications applied to one or more frames of the target video data, the select modifications including display format conversion, pixel level boost, and histogram equalization.

5. A computer-readable storage medium embodying a program of instructions for directing a device to perform the method recited in claim 1.

6. A device configured to perform the method recited in claim 1, wherein the device comprised a central processing unit and a system memory.