Patent US6748158B1 successfully refreshed from Google Patents.
US6748158B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for classifying and searching video databases based on 3-D camera motion
Assignee: GVBB Holdings SARL
•
Filing: 2000-02-01
•
Granted: 2004-06-08
•
Expires: 2020-02-01
Abstract
Abstract A method of indexing and searching a video database having a plurality of video shots uses 3-D camera motion parameters. For each video shot the 3-D camera motion parameters are estimated, rates of tracking, booming, dollying, panning, tilting, rolling and zooming are computed, and the results are indexed in a metadata index file in the video database according to the types of camera. The video database is searched by selecting one of the types of camera motion and submitting a query. The query is processed to identify those video shots in the video database that satisfy the query in order of priority. The highest priority video shots are displayed for the user.
Inventors
- 👤 Radu S. Jasinschi
- 👤 Thumpudi Naveen
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 12:29
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/70; G06F16/78; G06F16/783; G06F16/7847; G06F16/786
Claims Analysis
Total Claims: 7
Claim 1
Independent Claim
181 words
A method of indexing and searching a video database containing a plurality of video shots comprising the steps of: for each video shot estimating 3-D camera motion parameters from successive pairs of images in the video shot; computing a rate of motion for each image from the video shot using the 3-D camera motion parameters; indexing the video shot by types of camera motion based on the rate of motion and a sign of the 3-D camera motion parameters; and repeating the estimating, computing and indexing steps for each video shot in the video database, wherein said estimation step comprises the additional steps of: computing image feature points from each consecutive pair of images in the video shot; computing image intensity contrast variation to select pixels from the images to be used; tracking the image feature points from image to image in the given shot to identify matched feature points; pruning the matched feature points using the image intensity contrast variation; and computing iteratively from the matched feature points a best set of matrices representing translation and rotation of the images.
Claim 2
Independent Claim
181 words
A method of indexing and searching a video database containing a plurality of video shots comprising the steps of: for each video shot estimating 3-D camera motion parameters from successive pairs of images in the video shot; computing a rate of motion for each image from the video shot using the 3-D camera motion parameters; indexing the video shot by types of camera motion based on the rate of motion and a sign of the 3-D camera motion parameters; and repeating the estimating, computing and indexing steps for each video shot in the video database, wherein said estimation step comprises the additional steps of: computing image feature points from each consecutive pair of images in the video shot; computing image intensity contrast variation to select pixels from the images to be used; tracking the image feature points from image to image in the given shot to identify matched feature points; pruning the matched feature points using the image intensity contrast variation; and computing iteratively from the matched feature points a best set of matrices representing translation and rotation of the images.
Claim 3
Dependent Claim
31 words
The method as recited in claim 1 further comprising the step of searching for video shots within the video database based on a selected one of the types of camera motion.
Claim 4
Dependent Claim
28 words
The method as recited in claim 2 wherein the types of camera motion are selected from the group consisting of tracking, booming, dollying, panning, rolling, tilting and zooming.
Claim 5
Dependent Claim
87 words
The method as recited in claim 1 wherein the computing step comprises the steps of: computing rates of tracking, booming and dollying from the translation matrix for each image feature point; computing a focus of interest as a point in each image at which all image motions converge as a function of the translation matrix; and obtaining a vector descriptor for each consecutive pair of images as a function of the rates of tracking, booming and zooming, and the focus of interest as the rate of motion.
Claim 6
Dependent Claim
76 words
The method as recited in claim 4 wherein the indexing step comprises the steps of: computing how much larger the tracking and booming rates are compared to the dollying rate as a first ratio; computing how much larger the dollying rate is compared to the tracking and booming rates as a second ratio; generating an index file for the video shot containing a string of ones and zeros for each of the types of camera motion.
Claim 7
Dependent Claim
62 words
The method as recited in claim 5 wherein the searching step comprises the steps of: querying the video database with a selected one of the types of camera motion; processing the selected one of the types of camera motion to find the video shots satisfying selected one of the types of camera motion; and displaying the video shots satisfying the processing step.
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) | 2007-06-08 | 2007-12-08 | 2008-06-08 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-06-08 | 2011-12-08 | 2012-06-08 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-06-08 | 2015-12-08 | 2016-06-08 | $7700.00 | Window Closed / Lapsed |