Patent US6690725B1 successfully refreshed from Google Patents.
US6690725B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and a system for generating summarized video
Assignee: Telefonaktiebolaget LM Ericsson AB
•
Filing: 2000-06-15
•
Granted: 2004-02-10
•
Expires: 2020-06-15
Abstract
Abstract An algorithm for video summarization is described. The algorithm combines photometric and motion information. According to the algorithm, the correspondence between feature points is used to detect shot boundaries and to select key frames. Thus, the rate of feature points, which are lost or initiated, is used as an indication if a shot transition occurred or not. Key frames are selected as frames where the activity change is low.
Inventors
- 👤 Yousri Abdeljaoud
- 👤 Touradj Ebrahimi
- 👤 Charilaos Christopoulos
- 👤 Ignacio Mas Ivars
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 15:33
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/20; G06T7/246
Claims Analysis
Total Claims: 25
Claim 1
Independent Claim
87 words
A method of extracting key frames from a video signal, comprising: extracting feature points from frames in the video signal, tracking feature points between consecutive frames, measuring the number of new or lost feature points between consecutive frames, determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value, and selecting as a key frame, a frame located between two shot boundaries for which the number of new or lost feature points matches a predetermined criterion.
Claim 2
Independent Claim
87 words
A method of extracting key frames from a video signal, comprising: extracting feature points from frames in the video signal, tracking feature points between consecutive frames, measuring the number of new or lost feature points between consecutive frames, determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value, and selecting as a key frame, a frame located between two shot boundaries for which the number of new or lost feature points matches a predetermined criterion.
Claim 3
Dependent Claim
78 words
A method according to claim 1 , wherein the threshold value is defined as the maximum between terminated and initiated feature points calculated as a percentage, where the percentage of initiated feature points is the number of new feature points divided by the total number of feature points in the current frame, and the percentage of terminated feature points is the number of removed feature points divided by the total number of feature points in the previous frame.
Claim 4
Dependent Claim
40 words
A method according to claim 1 , wherein the key frame is selected as one of the frames for which the number of new or lost feature points is constant for a number of consecutive frames in the video signal.
Claim 5
Dependent Claim
45 words
A method according to claim 1 , wherein the key frame is selected as a frame for which the number of new or lost feature points corresponds to a local minima between two shot boundaries or where the number below a certain pre-set threshold value.
Claim 6
Dependent Claim
37 words
A method according to claim 1 , wherein when the video signal is a compressed video signal comprising I-frames, only the I-frames are decoded and used as input frames for determining shot boundaries and selecting key frames.
Claim 7
Dependent Claim
31 words
A method according to claim 1 , wherein the feature points in the frames of the video signal are extracted using both kinematic components and photometric components of the video signal.
Claim 8
Independent Claim
61 words
A method of shot boundary detection in a video signal, comprising: extracting feature points from frames in the video signal, tracking feature points between consecutive frames, measuring the number of new or lost feature points between consecutive frames, and determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value.
Claim 9
Independent Claim
61 words
A method of shot boundary detection in a video signal, comprising: extracting feature points from frames in the video signal, tracking feature points between consecutive frames, measuring the number of new or lost feature points between consecutive frames, and determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value.
Claim 10
Dependent Claim
78 words
A method according to claim 7 , wherein the threshold value is defined as a maximum between terminated and initiated feature points calculated as a percentage, where the percentage of initiated feature points is the number of new feature points divided by the total number of feature points in the current frame, and the percentage of terminated feature points is the number of removed feature points divided by the total number of feature points in the previous frame.
Claim 11
Dependent Claim
26 words
A method according to claim 7 , wherein feature points in the frames of the video signal are extracted using both kinematic components and photometric components.
Claim 12
Dependent Claim
37 words
A method according to claim 7 , wherein when the video signal is a compressed video signal comprising I-frames, only the I-frames are decoded and used as input frames for determining shot boundaries and selecting key frames.
Claim 13
Independent Claim
77 words
An apparatus for extracting key frames from a video signal, comprising: means for measuring the number of new or lost feature points between consecutive frames, means for determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value, and means for selecting as a key frame, a frame located between two shot boundaries when the number of new or lost feature points matches a predetermined criteria.
Claim 14
Independent Claim
77 words
An apparatus for extracting key frames from a video signal, comprising: means for measuring the number of new or lost feature points between consecutive frames, means for determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value, and means for selecting as a key frame, a frame located between two shot boundaries when the number of new or lost feature points matches a predetermined criteria.
Claim 15
Dependent Claim
78 words
An apparatus according to claim 11 , wherein the threshold value is defined as a maximum between terminated and initiated feature points calculated as a percentage, where the percentage of initiated feature points is the number of new feature points divided by the total number of feature points in the current frame, and the percentage of terminated feature points is the number of removed feature points divided by the total number of feature points in the previous frame.
Claim 16
Dependent Claim
40 words
An apparatus according to claim 11 , further comprising: means for selecting the key frame as a frame for which the number of new or lost feature points is constant for a number of consecutive frames in the video signal.
Claim 17
Dependent Claim
49 words
An apparatus according to claim 11 , further comprising: means for selecting the key frame as a frame for which the number of new or lost feature points corresponds to a local minima between two shot boundaries or for which the number is below a certain pre-set threshold value.
Claim 18
Dependent Claim
44 words
An apparatus according to claim 11 , wherein when the video signal is a compressed video signal comprising I-frames, the apparatus further comprises: means for only decoding the I-frames and using the I-frames as input frames for determining shot boundaries and selecting key frames.
Claim 19
Dependent Claim
32 words
An apparatus according to claim 11 , further comprising: means for extracting feature points in the frames of the video signal using both kinematic components and photometric components of the video signal.
Claim 20
Independent Claim
50 words
An apparatus for shot boundary detection in a video signal, comprising: means for measuring the number of new or lost feature points between consecutive frames, and means for determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value.
Claim 21
Independent Claim
50 words
An apparatus for shot boundary detection in a video signal, comprising: means for measuring the number of new or lost feature points between consecutive frames, and means for determining shot boundaries in the video signal when the number of new or lost feature points is above a certain threshold value.
Claim 22
Dependent Claim
78 words
An apparatus according to claim 17 , wherein the threshold value is defined as a maximum between terminated and initiated feature points calculated as a percentage, where the percentage of initiated feature points is the number of new feature points divided by the total number of feature points in the current frame, and the percentage of terminated feature points is the number of removed feature points divided by the total number of feature points in the previous frame.
Claim 23
Dependent Claim
32 words
An apparatus according to claim 17 , further comprising: means for extracting feature points in the frames of the video signal using both kinematic components and photometric components of the video signal.
Claim 24
Dependent Claim
41 words
An apparatus according to claim 17 , wherein when the video signal is a compressed video signal comprising I-frames, the apparatus further comprising: means for only decoding the I-frames and using the decoded I-frames as input frames for determining shot boundaries.
Claim 25
Dependent Claim
13 words
A system for video summarization comprising an apparatus according to claim 11 .
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-02-09 | 2007-08-11 | 2008-02-10 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-02-09 | 2011-08-11 | 2012-02-10 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-02-09 | 2015-08-11 | 2016-02-10 | $7700.00 | Window Closed / Lapsed |