Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
114 words
A method of extracting an image of a moving object from an image inputted successively, characterized by comprising the steps of: extracting a feature parameter of said inputted image; storing at least a part of said feature parameter of said input image as a feature parameter 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 to a feature parameter of an image successively inputted; and extracting information relating to an image of said moving object through comparison of said feature parameter of said background image and said feature parameter of an image inputted every moment.
Claim 2
Independent Claim
114 words
A method of extracting an image of a moving object from an image inputted successively, characterized by comprising the steps of: extracting a feature parameter of said inputted image; storing at least a part of said feature parameter of said input image as a feature parameter 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 to a feature parameter of an image successively inputted; and extracting information relating to an image of said moving object through comparison of said feature parameter of said background image and said feature parameter of an image inputted every moment.
Claim 3
Independent Claim
62 words
A method of extracting an image of a moving object according to claim l, wherein said feature parameter of said background image is transferred in parallel longitudinally and laterally so as to correspond 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
51 words
A method of extracting an image of a moving object, according to claim 3, wherein further included is 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 and said feature parameter of said input image.
Claim 6
Independent Claim
242 words
A method of extracting an image of a moving object from a picture inputted successively, characterized by comprising the steps of; taking a picture by an image pick-up element moving within a perpendicular plane to an optical axis 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 of an edge enhanced image, said edge image data including data of a moving object and a background; storing data of the edge image by one frame of the input image in a memory; storing data of the edge image in another memory as data of a background edge image; calculating correlation between the background edge image and data of an edge image forwarded successively to produce transferring data necessary to make the background edge image correspond to the edge image; transferring the background edge image so that the background edge image correspond to the edge image, based on the transferring data; extracting data of an edge image of a moving object through comparison between the data of the background edge image transferred based on the transferring data and the data of an edge image successively forwarded and including the moving object edge image and the background edge image; and renewing the background edge image based on with a weighted mean between the background edge image and the edge image.
Claim 7
Independent Claim
242 words
A method of extracting an image of a moving object from a picture inputted successively, characterized by comprising the steps of; taking a picture by an image pick-up element moving within a perpendicular plane to an optical axis 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 of an edge enhanced image, said edge image data including data of a moving object and a background; storing data of the edge image by one frame of the input image in a memory; storing data of the edge image in another memory as data of a background edge image; calculating correlation between the background edge image and data of an edge image forwarded successively to produce transferring data necessary to make the background edge image correspond to the edge image; transferring the background edge image so that the background edge image correspond to the edge image, based on the transferring data; extracting data of an edge image of a moving object through comparison between the data of the background edge image transferred based on the transferring data and the data of an edge image successively forwarded and including the moving object edge image and the background edge image; and renewing the background edge image based on with a weighted mean between the background edge image and the edge image.
Claim 8
Dependent Claim
45 words
A method according to claim 5, wherein the correlation is calculated on nine-neighbors, and the background edge image is transferred in the memory through a parallel transfer so that the background edge image correspond to one of the nine-neighbors that has the highest correlated valve.
Claim 9
Dependent Claim
34 words
The method according to claim 5, wherein the background edge image is transferred in the 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.