US6819796B2 — Method of and apparatus for segmenting a pixellat…

Claim 1

Independent Claim 139 words

A method of segmenting a pixellated image, comprising the steps of: (a) selecting at least one first region from a first reference image; (b) deriving from values of pixels of the at least one first region a first threshold such that a first predetermined proportion of the pixels have values on a first side of the first threshold; (c) forming a difference image as a difference between each pixel of the image and a corresponding pixel of an image of a non-occluded background; and (d) allocating each difference image pixel to at least one first type of region if the value of the difference image pixel is on the first side of the first threshold and the values of more than a first predetermined number of neighbouring difference image pixels are on the first side of the first threshold.

Claim 2

Independent Claim 139 words

A method of segmenting a pixellated image, comprising the steps of: (a) selecting at least one first region from a first reference image; (b) deriving from values of pixels of the at least one first region a first threshold such that a first predetermined proportion of the pixels have values on a first side of the first threshold; (c) forming a difference image as a difference between each pixel of the image and a corresponding pixel of an image of a non-occluded background; and (d) allocating each difference image pixel to at least one first type of region if the value of the difference image pixel is on the first side of the first threshold and the values of more than a first predetermined number of neighbouring difference image pixels are on the first side of the first threshold.

Claim 3

Dependent Claim 20 words

A method as claimed in claim 1 , characterised in that the first predetermined proportion is between 0.5 and 1.

Claim 4

Dependent Claim 20 words

A method as claimed in claim 2 , characterised in that the first predetermined proportion is substantially equal to 0.75.

Claim 5

Dependent Claim 27 words

A method as claimed in claim 2 , characterised in that the first predetermined number is substantially equal to half the number of neighbouring difference image pixels.

Claim 6

Dependent Claim 47 words

A method as claimed in claim 1 , characterised in that each of the at least one first region and the at least one first type of region comprises at least one background region and the first side of the first threshold is below the first threshold.

Claim 7

Dependent Claim 41 words

A method as claimed in claim 5 , characterised in that the first reference image comprises the difference between two images of the non-occluded background and the at least one first region comprises substantially the whole of the first reference image.

Claim 8

Dependent Claim 20 words

A method as claimed in claim 1 , characterised in that the at least one first region is automatically selected.

Claim 9

Dependent Claim 28 words

A method as claimed in claim 7 , characterised in that the at least one first region comprises at least one side portion of the first reference image.

Claim 10

Dependent Claim 20 words

A method as claimed in claim 1 , characterised in that the at least one first region is manually selected.

Claim 11

Dependent Claim 36 words

A method as claimed in claim 1 , characterised in that the neighbouring pixels in the step (d) are disposed in an array with the difference image pixel location substantially at the centre of the array.

Claim 12

Dependent Claim 25 words

A method as claimed in claim 1 , characterised by repeating the steps (a) to (d) for a sequence of images having a common background.

Claim 13

Dependent Claim 20 words

A method as claimed in claim 11 , characterised in that the first reference image is the preceding difference image.

Claim 14

Dependent Claim 31 words

A method as claimed in claim 12 , characterised in that the at least one first region comprises the at least one first type of region of the preceding step (d).

Claim 15

Dependent Claim 83 words

A method as claimed in claim 13 , characterised in that each step (d) comprises forming a first initial histogram of values of the difference image pixels allocated to the at least one first type of region and the step (b) derives the first threshold from a first resulting histogram which comprises the sum of the first initial histogram formed in the preceding step (d) and a first predetermined fraction less than one of the first resulting histogram of the preceding step (b).

Claim 16

Dependent Claim 18 words

A method as claimed in claim 14 , characterised in that the first predetermined fraction is a half.

Claim 17

Dependent Claim 133 words

A method as claimed in claim 1 , characterised by the steps of: (e) selecting at least one second region from a second reference image; (f) deriving from values of pixels of the at least one second region a second threshold such that a second predetermined proportion of the pixels have values on a second side opposite the first side of the second threshold; and (g) allocating each difference image pixel, which is not allocated to the at least one first type of region, to at least one second type of region if the value of the difference image pixel is on the second side of the second threshold and the values of more than a second predetermined number of neighbouring difference image pixels are on the second side of the second threshold.

Claim 18

Dependent Claim 20 words

A method as claimed in claim 16 , characterised in that the second predetermined proportion is between 0.5 and 1.

Claim 19

Dependent Claim 20 words

A method as claimed in claim 17 , characterised in that the second predetermined proportion is substantially equal to 0.75.

Claim 20

Dependent Claim 27 words

A method as claimed in claim 16 , characterised in that the second predetermined number is substantially equal to half the number of neighbouring difference image pixels.

Claim 21

Dependent Claim 47 words

A method an claimed in claim 16 , characterised in that each of the at least one second region and the at least one second type of region comprises at least one foreground region and the second side of the second threshold is above the second threshold.

Claim 22

Dependent Claim 20 words

A method as claimed in claim 16 , characterised in that the at least one second region is automatically selected.

Claim 23

Dependent Claim 26 words

A method as claimed in claim 21 , characterised in that the at least one second region comprises a middle portion of the second reference image.

Claim 24

Dependent Claim 20 words

A method as claimed in claim 16 , characterised in that the at least one second region is manually selected.

Claim 25

Dependent Claim 20 words

A method as claimed in claim 16 , characterised in that the second reference image comprises the first reference image.

Claim 26

Dependent Claim 36 words

A method as claimed in claim 16 , characterised in that the neighbouring pixels in the step (g) are disposed in an array with the difference image pixel location substantially at the centre of the array.

Claim 27

Dependent Claim 25 words

A method as claimed in claim 16 , characterised by repeating the steps (e) to (g) for a sequence of images having a common background.

Claim 28

Dependent Claim 20 words

A method as claimed in claim 26 , characterised in that the second reference image is the preceding difference image.

Claim 29

Dependent Claim 31 words

A method as claimed in claim 27 , characterised in that the at least one second region comprises the at least one second type of region of the preceding step (g).

Claim 30

Dependent Claim 83 words

A method as claimed in claim 28 , characterised in that each step (g) comprises forming a second initial histogram of values of the difference image pixels allocated to the at least one second type of region and the step (f) derives the second threshold from a second resulting histogram which comprises the sum of the second initial histogram formed in the preceding step (g) and a second predetermined fraction less than one of the second resulting histogram of the preceding step (f).

Claim 31

Dependent Claim 18 words

A method as claimed in claim 29 , characterised in that the second predetermined fraction is a half.

Claim 32

Dependent Claim 63 words

A method as claimed in claim 16 , characterised by allocating each difference image pixel, which is not allocated to the at least one first type of region and which is not allocated to the at least one second type of region, as a candidate first type of pixel if a value of the difference image pixel is less than a third threshold.

Claim 33

Dependent Claim 21 words

A method as claimed in claim 31 , characterised in that the third threshold is between the first and second thresholds.

Claim 34

Dependent Claim 24 words

A method as claimed in claim 32 , characterised in that the third threshold is the arithmetic mean of the first and second thresholds.

Claim 35

Dependent Claim 80 words

A method as claimed in claim 31 , characterised by allocating each difference image pixel, which is not allocated to the at least one first type of region and which is not allocated to the at least one second type of region, to the at least one first type of region if more than a third predetermined number of the neighbouring pixels are allocated to the at least one first type of region or as candidate first type of pixel.

Claim 36

Dependent Claim 32 words

A method as claimed in claim 34 , characterised in that the neighbouring pixels comprise an array of pixels with the difference image pixel location substantially at the centre of the array.

Claim 37

Dependent Claim 24 words

A method as claimed in claim 34 , characterised in that the third predetermined number is half the number of neighbouring difference image pixels.

Claim 38

Dependent Claim 51 words

A method as claimed in claim 34 , characterised by allocating each difference image pixel, which is not allocated to the at least one first type of region and which is not allocated to the at least one second type of region, to the at least one second type of region.

Claim 39

Dependent Claim 59 words

A method as claimed in claim 1 , characterised in that the or each image and the background image are grey level images and the step (c) forms the difference between each image pixel and the corresponding background pixel as the difference between the grey level of each image pixel and the grey level of the corresponding background pixel.

Claim 40

Dependent Claim 27 words

A method as claimed in claim 1 , characterised in that the step (c) comprises performing a moving window averaging step on the or each difference image.

Claim 41

Dependent Claim 57 words

A method as claimed in claim 1 , characterised in that the or each image and the background image are colour images and the step (c) forms the difference between each image pixel and the corresponding background pixel as a colour distance between the colour of each image pixel and the colour of the corresponding background pixel.

Claim 42

Dependent Claim 73 words

A method as claimed in claim 40 , characterised in that the colour distance is formed as: ∑ i = 1 n  α i   I i - B i  where n is the number of colour components of each pixel, I i is the ith colour component of an image pixel, B i is the ith colour component of a background pixel and α 1 is a weighting factor.

Claim 43

Dependent Claim 18 words

A method as claimed in claim 41 , characterised in that each α 1 is equal to one.

Claim 44

Dependent Claim 44 words

A method as claimed in claim 41 , characterised in that n is equal to 3, I 1 and B 1 are red colour components, I 2 and B 2 are green colour components and I 3 and B 3 are blue colour components.

Claim 45

Dependent Claim 38 words

A method as claimed in claim 41 , characterised in that the step (c) forms colour component difference images I i −B i and performs a moving window averaging step on each of the colour component difference images.

Claim 46

Dependent Claim 19 words

A method as claimed in claim 39 , characterised in that the window has a size of 3×3 pixels.

Claim 47

Dependent Claim 19 words

A method as claimed in claim 44 , characterised in that the window has a size of 3×3 pixels.

Claim 48

Dependent Claim 70 words

A method as claimed in claim 1 , characterised by forming a binary mask whose elements correspond to difference image pixels, each element having a first value if the corresponding difference image pixel is allocated to the at least one first type of region and a second value different from the first value if the corresponding difference image pixel is allocated to the at least one second type of region.

Claim 49

Dependent Claim 44 words

A method as claimed in claim 5 , characterised by replacing the value of each pixel of the or each image corresponding to a difference image pixel allocated to the at least one background region with the value of a corresponding background image pixel.

Claim 50

Dependent Claim 46 words

A method as claimed in claim 5 , characterised by replacing the value of each pixel of the or each image corresponding to a difference image pixel allocated to the at least one background region with the value of a corresponding pixel of a different background.

Claim 51

Dependent Claim 57 words

A method as claimed in claim 49 , characterised by replacing the value of each pixel of the or each image corresponding to a difference image pixel allocated to a boundary of at least one foreground region with a linear combination of the value of the image pixel and the value of the corresponding different background pixel.

Claim 52

Dependent Claim 28 words

A method as claimed in claim 50 , characterised in that the linear combination comprises the arithmetic mean of the or each pair of corresponding pixel component values.

Claim 53

Dependent Claim 83 words

A method as claimed in claim 5 , characterised by, for each colour component, forming a distribution of the differences between the colour component values of the pixels allocated to the at least one background region and the corresponding pixels of the non-occluded background image, determining a shift in the location of a peak in the distribution from a predetermined location, and correcting the colour component values of the pixels allocated to the at least one background region in accordance with the shift.

Claim 54

Independent Claim 141 words

An apparatus for segmenting a pixellated image, characterised by means for selecting at least one first region from a first reference image, means for deriving from values of pixels of the at least one first region a first threshold such that a first predetermined proportion of the pixels have values on a first side of the first threshold, means for forming a difference image as a difference between each pixel of the image and a corresponding pixel of an image of a non-occluded background, and means for allocating each difference image pixel to at least one first type of region if the value of the difference image pixel is on the first side of the first threshold and the values of more than a first predetermined number of neighbouring difference image pixels are on the first side of the first threshold.

Claim 55

Independent Claim 141 words

An apparatus for segmenting a pixellated image, characterised by means for selecting at least one first region from a first reference image, means for deriving from values of pixels of the at least one first region a first threshold such that a first predetermined proportion of the pixels have values on a first side of the first threshold, means for forming a difference image as a difference between each pixel of the image and a corresponding pixel of an image of a non-occluded background, and means for allocating each difference image pixel to at least one first type of region if the value of the difference image pixel is on the first side of the first threshold and the values of more than a first predetermined number of neighbouring difference image pixels are on the first side of the first threshold.

Claim 56

Dependent Claim 35 words

An apparatus for segmenting a pixellated image, characterised by a programmable data processor and a storage medium containing a program for controlling the data processor to perform a method as claimed in claim 1 .

Claim 57

Dependent Claim 21 words

A storage medium containing a program for controlling a data processor to perform a method as claimed in claim 1 .

Claim 58

Dependent Claim 17 words

A program for controlling a data processor to perform a method as claimed in claim 1 .

Claim 59

Dependent Claim 15 words

An image capture device characterised by including an apparatus as claimed in claim 53 .

Claim 60

Dependent Claim 15 words

An image capture device characterised by including an apparatus as claimed in claim 54 .

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	2007-11-16	2008-05-17	2008-11-16	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2011-11-16	2012-05-17	2012-11-16	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2015-11-16	2016-05-17	2016-11-16	$7700.00	Window Closed / Lapsed

Method of and apparatus for segmenting a pixellated image

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag