Method and apparatus for estimating shot boundaries in a digital video sequence

• US 7,551,234 B2
• Filed: 07/28/2005
• Issued: 06/23/2009
• Est. Priority Date: 07/28/2005
• Status: Expired due to Fees

• Current Assignee: Seiko Epson Corporation (Seiko Group)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: Zhou, Hui, Wong, Alexander Sheung Lai
• Primary Examiner(s): Bali; Vikkram
• Assistant Examiner(s): Park; Soo Jin
• Application Number:
  US11/191,458
• Publication Number:
  US 20070025615A1
• Time in Patent Office: 1,426 Days
• Field of Search: 382/270, 715/723, 348/700
• US Class Current: 348/700
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: H04N 5/147 Scene change detection

Abstract

A method of estimating a shot boundary in a digital video sequence comprises calculating a measurement of dissimilarity between each frame in the video sequence and its previous frame based on at least one of de-emphasized luminance differences and absolute color differences. Each frame is tested against shot boundary dissimilarity thresholds using the dissimilarity measurement for the frame thereby to detect the shot boundary.

Claims

1. A method of measuring dissimilarity between adjacent frames in a digital video sequence, comprising:

using a computer processing unit to perform the steps of;

determining pixel accumulations at respective luminance and chrominance color component levels for each of said frames, wherein during said determining, LUV colorspace histograms for said frames are generated;

calculating a dissimilarity measurement by comparing corresponding ones of said accumulations while de-emphasizing dissimilarities in luminance between said frames, wherein said corresponding ones of said accumulations are common ranges of respective ones of luminance and chrominance, and wherein during said calculating, said LUV color-space histograms are compared; and

wherein said dissimilarity measurement is calculated according to the formula;

2. A method of establishing a maximum shot boundary threshold for a candidate frame in a digital video sequence, comprising:

using a computer processing unit to perform the steps of;

calculating a sequence average of inter-frame dissimilarity measurements;

calculating a window average of inter-frame dissimilarity measurements, said window comprising a subset of sequential frames in said sequence prior to said candidate frame, said subset comprising a plurality of sequential frames;

in the event that said window average is inconsistent with said sequence average, calculating a maximum shot boundary threshold as a factor of said sequence average; and

otherwise

calculating said maximum shot boundary threshold as a factor of said window average; and

wherein said maximum shot boundary threshold is calculated according to the pseudocode;

IF ADM_{Frame Avg}<

X % of ADM_{Group Avg} THEN

Max threshold=min(Y*ADM_{Group Avg}, Tc) ELSE

Max threshold=min(Z*ADM_{Frame Avg}, Tc) where;

ADM is an average pair-to-pair histogram dissimilarity measurement;

ADM_{Frame Avg} is an average ADM of the frames within said window;

ADM_{Group Avg} is an average ADM of the frames within said sequence;

X is a pre-defined percentage of the ADM;

Y and Z are multiplication factors; and

Tc is an absolute maximum shot boundary dissimilarity threshold.

3. The method of claim 2, wherein Y and Z are multiplication factors in a range between about 4 and about 6.

4. The method of claim 2, wherein Tc is an absolute maximum shot boundary dissimilarity threshold in a range between about 0.7 and about 0.9.

5. The method of claim 2, wherein X is about 50%.

6. The method of claim 2 wherein Y is about 4.

7. The method of claim 2, wherein Z is about 4.7.

8. The method of claim 2, wherein Tc is about 0.75.

9. The method of claim 2, wherein X is about 50%, Y is about 4, Z is about 4.7, and Tc is about 0.75.