IP Library › Granted Patent US 7,796,860
Granted Patent B2
US 7,796,860 · App. 11/360,253 · Granted Sep 14, 2010

Method and system for playing back videos at speeds adapted to content

Assignee: Mitsubishi Electric Research Laboratories, Inc.
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,796,860
App. No.
11/360,253
Granted
Sep 14, 2010
Kind
B2
Abstract

A method plays back a video at speeds adapted to content of the video. A video is partitioned into summary segments and skipped segments. The summary segments are played back sequentially at a normal play back speed, and the skipped segments are played back at varying speeds corresponding to a visual complexity of the skipped segments.

Claims (62)

1. A method for playing back a video at speeds adapted to content of the video, comprising the steps of:

partitioning a video into summary segments and skipped segments;

playing back sequentially the summary segments at a normal play back speed;

merging segments shorter than a threshold with adjacent segments, wherein the threshold is based on a total play back time; and

playing back the skipped segments at varying speeds corresponding to a visual complexity of the skipped segments, in which a total playback time is

T

play

=

∑

i

=

1

N

⁢

T

i

r

i

,

where T i are durations of the segments, r i are playback speeds with r=1 corresponding to normal play back speed and r>1 corresponding to a faster play back speed, and N is a number segments for a total duration T media of the video.

2. The method of claim 1 , in which the video includes a visual signal as a sequence of frames, and an audio signal, and further comprising:

detecting face features in the visual signal;

identifying audio classes in the audio signal; and

combining the face features and the audio classes to perform the partitioning.

3. The method of claim 1 , in which the video is compressed and includes I-frames and P-frames.

4. The method of claim 3 , in which the visual complexity is based on texture information from the I-frames and motion activity information from the P-frames.

5. The method of claim 1 , in which the varying speeds are relatively slow when the visual complexity is relatively high, and relatively fast when the visual complexity is relatively low.

6. The method of claim 1 , further comprising:

adjusting the varying speeds according to user parameters, play back device parameters, and a total play back time.

7. The method of claim 1 , further comprising:

quantizing the varying speeds.

8. The method of claim 2 , in which the face features include a number, size and location of faces in the frames.

9. The method of claim 1 , in which a base speed is R 0 and a speed spread is R d for the skipped segments, based on user preferences, and R min =R 0 −R d and R max =R 0 +R d are defined as minimum and maximum play back speeds, and the varying speeds are

r

i

′

=

(

r

i

-

r

min

)

⁢

R

max

-

R

min

r

max

-

r

mi

⁢

n

+

R

min

,

where r min and r max are the minimum and maximum values of the speed r i .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 23, 2006
From: PEKER, KADIR A.
To: MITSUBISHI ELECTRIC RESEARCH LABORATORIES, INC.
Reel/Frame 017589/0730 →
Continuity (1)
Related Publication 20070201817A1 · Aug 30, 2007