US4783833A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method of extracting an image of a moving object
Assignee: Hitachi Ltd
•
Filing: 1986-11-26
•
Granted: 1988-11-08
•
Expires: 2006-11-26
Abstract
Abstract A method of extracting an image of a moving object comprises the steps of extracting edge-enhanced input image from an input image taken by an image pick-up element moving in a plane perpendicular to an optical axis, recollecting a background edge-enhanced image from the input edge image, transfer in parallel horizontally and vertically the background edge-enhanced edge image so to correspond to an input edge-enhanced image forwarded successively; extracting an edge image of a moving object by extracting the background edge-enhanced image from the input edge-enhanced image, and renewing the background edge enhanced image based on weighted mean of the background edge enhanced image and the input edge image.
Inventors
- 👤 Atsushi Kawabata
- 👤 Shinya Tanifuji
- 👤 Yasuo Morooka
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-23 05:34
CPC Classifications
G; G08; G08B; G08B13/00; G08B13/18; G08B13/189; G08B13/194; G08B13/196; G08B13/19602; G06; G06T; G06T7/00; G06T7/20; G06T7/254; G08B13/19604
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
169 words
A method of extracting an image of a moving object from an image inputted successively, said method comprising the steps of: extracting a feature parameter of said inputted image; storing said feature parameter of said input image as a feature paramter of a background image, said feature parameter of said background image being unchanged or slowly changing; transferring said feature parameter of said background image so as to correspond positionally to a feature parameter of an image successively inputted; forming a feature parameter of background image free of any moving object images, based on a weighted mean between said transferred feature parameter of said background image and said feature parameter of said image inputted successively, only said transferred feature parameter of said background image being weighted; and extracting information relating to an image of said moving object from said feature parameter of said image through comparison of said feature parameter of said background image free of any moving object image and said feature parameter of said image inputted successively.
Claim 2
Independent Claim
169 words
A method of extracting an image of a moving object from an image inputted successively, said method comprising the steps of: extracting a feature parameter of said inputted image; storing said feature parameter of said input image as a feature paramter of a background image, said feature parameter of said background image being unchanged or slowly changing; transferring said feature parameter of said background image so as to correspond positionally to a feature parameter of an image successively inputted; forming a feature parameter of background image free of any moving object images, based on a weighted mean between said transferred feature parameter of said background image and said feature parameter of said image inputted successively, only said transferred feature parameter of said background image being weighted; and extracting information relating to an image of said moving object from said feature parameter of said image through comparison of said feature parameter of said background image free of any moving object image and said feature parameter of said image inputted successively.
Claim 3
Dependent Claim
63 words
A method of extracting an image of a moving object according to claim 1, wherein said feature parameter of said background image is transferred in parallel longitudinally and laterally so as to correspond positionally to said feature parameter of said input image according to a correlated value between said feature parameter of said background image and said feature parameter of said input image.
Claim 4
Dependent Claim
32 words
A method of extracting an image of a moving object according to claim 2, wherein an image obtained by extraction of said feature parameter from said input image is an edge image.
Claim 5
Dependent Claim
71 words
A method of extracting an image of a moving object, according to claim 3, further including a step of renewing said feature parameter of said background image based on a weighted mean calculated from said feature parameter of said background image free of any moving object image and a feature parameter of an input image successively inputted, said feature parameter of said background free of any moving object image being weighted.
Claim 6
Independent Claim
347 words
A method of extracting an image of a moving object from a picture inputted successively, said method comprising the steps of; taking a picture by means of an image pick-up element moving within a plane perpendicular to an optical axis so as to output video signals; converting the video signals into digital signals and storing the digital signals as data of an input image; extracting a feature parameter from said input image data to provide data representing an edge enhanced image, said edge enhanced image data including data of a moving object and a background; storing data of the edge enhanced image for one frame of the input image in a first memory as data of a background edge image; storing data of the edge enhanced image for another frame in a second memory data of an input edge image; calculating a correlation between the background edge image stored in said first memory and data of an edge enhanced image forwarded successively and stored in said second memory to produce transferring data necessary to make the background edge image correspond positionally to the input edge image; transferring the background edge image so that the background edge image corresponds positionally to the input edge image, based on the transferring data; forming a background edge image free of any moving object edge image by obtaining a weighted mean between data of the input edge image from said second memory and data of the background edge image from said first memory, and storing the weighted mean thus obtained in said first memory as said background edge image; extracting data of an edge image of a moving object through comparison between the data of the background edge image transferred on the basis of said transferring data and the data of an input edge image successively inputted and including the moving object edge image and the background edge image; and renewing the background edge image in said first memory based on a weighted mean between the background edge image in said first memory and the input edge image in said second memory.
Claim 7
Independent Claim
347 words
A method of extracting an image of a moving object from a picture inputted successively, said method comprising the steps of; taking a picture by means of an image pick-up element moving within a plane perpendicular to an optical axis so as to output video signals; converting the video signals into digital signals and storing the digital signals as data of an input image; extracting a feature parameter from said input image data to provide data representing an edge enhanced image, said edge enhanced image data including data of a moving object and a background; storing data of the edge enhanced image for one frame of the input image in a first memory as data of a background edge image; storing data of the edge enhanced image for another frame in a second memory data of an input edge image; calculating a correlation between the background edge image stored in said first memory and data of an edge enhanced image forwarded successively and stored in said second memory to produce transferring data necessary to make the background edge image correspond positionally to the input edge image; transferring the background edge image so that the background edge image corresponds positionally to the input edge image, based on the transferring data; forming a background edge image free of any moving object edge image by obtaining a weighted mean between data of the input edge image from said second memory and data of the background edge image from said first memory, and storing the weighted mean thus obtained in said first memory as said background edge image; extracting data of an edge image of a moving object through comparison between the data of the background edge image transferred on the basis of said transferring data and the data of an input edge image successively inputted and including the moving object edge image and the background edge image; and renewing the background edge image in said first memory based on a weighted mean between the background edge image in said first memory and the input edge image in said second memory.
Claim 8
Dependent Claim
59 words
A method according to claim 5, wherein the correlation is calculated for each picture element on the basis of nine adjacent picture elements, and the background edge image is transferred in the first memory through a parallel transfer so that the background edge image corresponds to one of the nine adjacent picture elements that has the highest correlated value.
Claim 9
Dependent Claim
35 words
The method according to claim 5, wherein the background edge image is transferred in the first memory within one picture element in each of at most two directions of right, left, up and down directions.
Claim 10
Dependent Claim
44 words
The method according to claim 5, wherein the edge image of the moving object is extracted from the edge enhanced input image of an input picture by subtracting the background edge image transferred based on the correlated value from the edge enhanced input image.
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) | 1991-11-08 | 1992-05-09 | 1992-11-08 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1995-11-08 | 1996-05-09 | 1996-11-08 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1999-11-08 | 2000-05-09 | 2000-11-08 | $7700.00 | Window Closed / Lapsed |