Patent US5867584A successfully refreshed from Google Patents.
US5867584A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Video object tracking method for interactive multimedia applications
Assignee: NEC Corp
•
Filing: 1996-02-22
•
Granted: 1999-02-02
•
Expires: 2016-02-22
Abstract
Abstract A system for automatically tracking objects through a video sequence uses a method which automatically tracks an object by estimating the location of the object in a subsequent frame, comparing test windows in the subsequent frame with an object window encompassing the object in the original frame, and selecting the best match window which is most similar to the object window. The location of the best match window corresponds to the location of the object in each frame of the video sequence. The resulting location information can be combined with the video sequence to create interactive video applications in which an user of the application can select individual objects in the interactive video sequence.
Inventors
- 👤 Xiaoping Hu
- 👤 Jun Takamura
- 👤 Mark Hall
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-07 13:50
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/20; G06T7/246; G06V; G06V10/00; G06V10/20; G06V10/24; H; H04; H04N; H04N21/00; H04N21/40; H04N21/47; H04N21/472
Claims Analysis
Total Claims: 7
Claim 1
Independent Claim
183 words
An object tracking method for automatically tracking an object in a video sequence, the object being chosen by an user, comprising: specifying an object window enveloping said object in a first frame of said video sequence; estimating a position of said object in a second frame of said video sequence; determining a plurality of test windows in said second frame within a predetermined distance of said estimated position of said object; comparing said object window with each of said test windows, comprising calculating a distance between said object window and each of said test windows; and selecting a best match window from said plurality of test windows, said best match window having a lowest distance between said object window and said test windows; comparing said lowest distance to a predetermined match threshold; displaying a warning if said lowest distance is greater than said predetermined match threshold; comparing said lowest distance to a predetermined replacement threshold; and specifying a replacement object window if said lowest distance is greater than said predetermined replacement threshold and said lowest distance is less than said predetermined match threshold.
Claim 2
Dependent Claim
183 words
An object tracking method for automatically tracking an object in a video sequence, the object being chosen by an user, comprising: specifying an object window enveloping said object in a first frame of said video sequence; estimating a position of said object in a second frame of said video sequence; determining a plurality of test windows in said second frame within a predetermined distance of said estimated position of said object; comparing said object window with each of said test windows, comprising calculating a distance between said object window and each of said test windows; and selecting a best match window from said plurality of test windows, said best match window having a lowest distance between said object window and said test windows; comparing said lowest distance to a predetermined match threshold; displaying a warning if said lowest distance is greater than said predetermined match threshold; comparing said lowest distance to a predetermined replacement threshold; and specifying a replacement object window if said lowest distance is greater than said predetermined replacement threshold and said lowest distance is less than said predetermined match threshold.
Claim 3
Dependent Claim
187 words
An object tracking method for automatically tracking an object in a video sequence, the object being chosen by an user, comprising: specifying an object window enveloping said object in a first frame; processing a plurality of sequential subsequent frames, each of said sequential subsequent frames having a set of previous frames, by, for each of said sequential subsequent frames, estimating a position of said object in each of said sequential subsequent frames by fitting the position of said object in each of said previous frames in a quadratic polynomial having coefficient vectors i, j, and k, approximating i, j, and k using a selected fitting method, and calculating said position of said object in said sequential subsequent frame using i, j, and k in a quadratic polynomial; determining a plurality of test windows in each of said sequential subsequent frames within a predetermined distance of said estimated position of said object; comparing said object window with each of said test windows in each of said sequential subsequent frames; and selecting a best match window from said plurality of test windows for each of said sequential subsequent frames.
Claim 4
Dependent Claim
187 words
An object tracking method for automatically tracking an object in a video sequence, the object being chosen by an user, comprising: specifying an object window enveloping said object in a first frame; processing a plurality of sequential subsequent frames, each of said sequential subsequent frames having a set of previous frames, by, for each of said sequential subsequent frames, estimating a position of said object in each of said sequential subsequent frames by fitting the position of said object in each of said previous frames in a quadratic polynomial having coefficient vectors i, j, and k, approximating i, j, and k using a selected fitting method, and calculating said position of said object in said sequential subsequent frame using i, j, and k in a quadratic polynomial; determining a plurality of test windows in each of said sequential subsequent frames within a predetermined distance of said estimated position of said object; comparing said object window with each of said test windows in each of said sequential subsequent frames; and selecting a best match window from said plurality of test windows for each of said sequential subsequent frames.
Claim 5
Dependent Claim
19 words
An object tracking method as in claim 2, wherein said selected fitting method is a least squares fitting method.
Claim 6
Dependent Claim
210 words
An object tracking method for automatically tracking an object in a video sequence, the object being chosen by an user, comprising: specifying an object window enveloping said object in a first frame; processing a plurality of sequential subsequent frames by, for each of said sequential subsequent frames; estimating a position of said object in each of said sequential subsequent frames; determining a plurality of test windows in each of said sequential subsequent frames within a predetermined distance of said estimated position of said object; comparing said object window with each of said test windows in each of said sequential subsequent frames, by calculating a distance between said object window and each of said test windows, and selecting a best match window from said plurality of test windows for each of said sequential subsequent frames, said best match window having a lowest distance between said object window and said test windows; comparing said lowest distance to a predetermined match threshold; displaying a warning if said lowest distance is greater than said predetermined match threshold; comparing said lowest distance to a predetermined replacement threshold; and specifying a replacement object window if said lowest distance is greater than said predetermined replacement threshold and said lowest distance is less than said predetermined match threshold.
Claim 7
Dependent Claim
210 words
An object tracking method for automatically tracking an object in a video sequence, the object being chosen by an user, comprising: specifying an object window enveloping said object in a first frame; processing a plurality of sequential subsequent frames by, for each of said sequential subsequent frames; estimating a position of said object in each of said sequential subsequent frames; determining a plurality of test windows in each of said sequential subsequent frames within a predetermined distance of said estimated position of said object; comparing said object window with each of said test windows in each of said sequential subsequent frames, by calculating a distance between said object window and each of said test windows, and selecting a best match window from said plurality of test windows for each of said sequential subsequent frames, said best match window having a lowest distance between said object window and said test windows; comparing said lowest distance to a predetermined match threshold; displaying a warning if said lowest distance is greater than said predetermined match threshold; comparing said lowest distance to a predetermined replacement threshold; and specifying a replacement object window if said lowest distance is greater than said predetermined replacement threshold and said lowest distance is less than said predetermined match threshold.
References Cited (Backward Citations)
US4868871A
Cited
US5243418A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2002-02-01 | 2002-08-03 | 2003-02-02 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2006-02-01 | 2006-08-03 | 2007-02-02 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2010-02-01 | 2010-08-03 | 2011-02-02 | $7700.00 | Window Closed / Lapsed |