CN102663384A - Curve identification method based on Bezier control point searching and apparatus thereof - Google Patents

Curve identification method based on Bezier control point searching and apparatus thereof Download PDF

Info

Publication number
CN102663384A
CN102663384A CN2012100911886A CN201210091188A CN102663384A CN 102663384 A CN102663384 A CN 102663384A CN 2012100911886 A CN2012100911886 A CN 2012100911886A CN 201210091188 A CN201210091188 A CN 201210091188A CN 102663384 A CN102663384 A CN 102663384A
Authority
CN
China
Prior art keywords
hessian
image
point
bezier curve
curve
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN2012100911886A
Other languages
Chinese (zh)
Other versions
CN102663384B (en
Inventor
李党
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Netposa Technologies Ltd
Original Assignee
Beijing Zanb Science & Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zanb Science & Technology Co Ltd filed Critical Beijing Zanb Science & Technology Co Ltd
Priority to CN201210091188.6A priority Critical patent/CN102663384B/en
Publication of CN102663384A publication Critical patent/CN102663384A/en
Application granted granted Critical
Publication of CN102663384B publication Critical patent/CN102663384B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

Provided in the invention is a curve identification method based on Bezier control point searching. The method comprises the following steps that: gaussian smoothing processing, Hessian calculation, and Hessian image thinning processing are carried out on a current image to obtain a Hessian thinning image; according to an actual curve position, a user calibrates three control points on a video image; according to the three control points, a Bezier curve construction model is employed to obtain a Bezier curve; and according to the Bezier curve and the three control points, a detection curve on the Hessian thinning image is obtained and is output. According to the invention, detection on a curve inside a video image can be realized.

Description

Curves Recognition method and device based on the search of Bezier reference mark
Technical field
The present invention relates to Flame Image Process, particularly Curves Recognition method and device.
Background technology
Blood vessel in the medical domain detects, palmmprint detects, cell detection, and the high voltage transmission line in the power domain detects or the like, all need be applied to the curve tracking technique in the above-mentioned field, so the research of curve tracking technique has great significance.
There is following problem in traditional curve tracking technique: 1) responsive to noise image; 2) responsive to the image that has background interference; 3) can't accurately identify cross curve; 4) can't discern the curve that fracture occurs; 5) situation that appearance changes for image can't accurately be discerned curve to be detected; 6) can't identify the curve that exists in the image in real time; 7) in case the curve detection mistake does not have automatic correction mechanism identification curve.
In sum, press at present and propose a kind ofly simply, effectively to follow the tracks of Curves Recognition method and the device in the complex connection scene.
Summary of the invention
In view of this, fundamental purpose of the present invention be to realize can be simple, the curve in the effective recognition actual scene.
For achieving the above object, according to first aspect of the present invention, a kind of Curves Recognition method based on the search of Bezier reference mark is provided, the method comprising the steps of:
First step carries out Gauss's smoothing processing, Hessian calculating and the operation of Hessian image thinning to present image, obtains the Hessian refined image;
Second step, the user demarcates 3 reference mark according to the actual curve position on video image;
Third step according to 3 reference mark, adopts the Bezier curve to make up modelling and obtains the Bezier curve;
The 4th step is obtained detection curve and output on the Hessian refined image according to Bezier curve and 3 reference mark.
Gauss's smoothing processing is to adopt Gauss's smooth function to present image (wherein in the wherein said first step; The image that present image receives in the time of can being true-time operation; Also can be one section current frame image in the video) carry out Filtering Processing; To obtain current smoothed image; Specific as follows: as to establish present image for
Figure 314818DEST_PATH_IMAGE002
(
Figure 512056DEST_PATH_IMAGE002
is the gray-scale value of point
Figure 678595DEST_PATH_IMAGE004
in the present image), do through the smoothed image
Figure 710136DEST_PATH_IMAGE006
(
Figure 320240DEST_PATH_IMAGE006
is the gray-scale value of the interior point of smoothed image of present image) that obtains after the Filtering Processing
Figure 977935DEST_PATH_IMAGE008
Wherein, The level and smooth kernel function of
Figure 50933DEST_PATH_IMAGE010
expression Gauss, representes convolution algorithm.The value of
Figure 246532DEST_PATH_IMAGE014
is relevant with the width of line in the level and smooth kernel function of Gauss; Satisfy , wherein the pixel wide of
Figure 578473DEST_PATH_IMAGE018
expression line.
Hessian calculates and comprises in the said first step:
Step a) utilizes the second order Grad of the gray-scale value of every point in the current smoothed image to make up Hessian matrix
Figure 286983DEST_PATH_IMAGE020
; Calculate the eigenwert
Figure 85306DEST_PATH_IMAGE022
of Hessian matrix; Wherein, ,
Figure 361663DEST_PATH_IMAGE026
,
Figure 477386DEST_PATH_IMAGE028
the expression point
Figure 130216DEST_PATH_IMAGE004
and the shade of gray difference of eight adjacent side points on every side, its computing formula is following:
Figure 610875DEST_PATH_IMAGE030
Figure 965633DEST_PATH_IMAGE032
Figure 635780DEST_PATH_IMAGE034
Wherein, the gray-scale value of
Figure 392384DEST_PATH_IMAGE036
remarked pixel point ;
If step b) is the eigenwert
Figure 964628DEST_PATH_IMAGE040
of certain any Hessian matrix in the smoothed image; TH1 ∈ [4.2; 4.9]; Think that then this point is the Hessian point, otherwise this point of filtering, thereby the Hessian image obtained.
The operation of Hessian image thinning is that the Hessian image is carried out the morphology Refinement operation in the said first step, to obtain the Hessian refined image.
Said third step is according to 3 reference mark
Figure 169956DEST_PATH_IMAGE042
; Adopt the Bezier curve to make up modelling and confirm the Bezier curve, its formula is following:
Figure 781066DEST_PATH_IMAGE044
。
Said the 4th step further comprises:
Step 1041; Simultaneously 3 reference mark carried out integral translation on
Figure 11508DEST_PATH_IMAGE046
, , ,
Figure 561066DEST_PATH_IMAGE052
four direction; ; ; Wherein k1, n are threshold parameter; K1 ∈ [4; 6] and be integer; N ∈ [2; 4] and be integer, can make up the new Bezier curve of 4n bar according to the new reference mark after the integral translation;
Step 1042; Respectively to every new Bezier curve; Every bit on this Bezier curve is searched for nearest Hessian point in
Figure 510546DEST_PATH_IMAGE058
scope; and be integer;
Figure 791802DEST_PATH_IMAGE062
and be integer, add up on this Bezier curve distance that whole points and Hessian recently order and;
Step 1043; The distance of more every new Bezier curve statistics and size, selected distance is 3 benchmark reference mark with corresponding 3 reference mark
Figure 145555DEST_PATH_IMAGE064
of minimum Bezier curve;
Step 1044, maintaining
Figure 523446DEST_PATH_IMAGE066
two reference control points unchanged, respectively
Figure 186509DEST_PATH_IMAGE068
6 pixels around the pixel is within the scope of the temporary control points, and according to the temporary control point and
Figure 462900DEST_PATH_IMAGE066
build Bezier curves, Bezier curves to calculate the length, and the Bezier curve on the image at the Hessian refinement number of valid points, namely statistical point of the Bezier curve belongs to refine the image before the Hessian number of attractions and calculate the effective number of points with the Bezier curve length ratio, if the ratio is greater than k2, k2 ∈ [0.5,0.6], then the temporary control point as a reference control point
Figure 869611DEST_PATH_IMAGE068
The best control points
Figure 177708DEST_PATH_IMAGE070
; simultaneously with the same methods were used to obtain the reference control point The best control points
Figure 775360DEST_PATH_IMAGE072
;
Step 1045; Make up the Bezier curve according to optimum controlling point
Figure 720182DEST_PATH_IMAGE074
, and this Bezier curve is also exported as detection curve.
According to another aspect of the present invention, a kind of Curves Recognition square law device based on the search of Bezier reference mark is provided, this device comprises:
Hessian refined image acquiring unit is used for present image is carried out Gauss's smoothing processing, Hessian calculating and the operation of Hessian image thinning, obtains the Hessian refined image;
The unit is demarcated at 3 reference mark, is used for the user according to the actual curve position, on video image, demarcates 3 reference mark;
Bezier curve acquisition unit is used for according to 3 reference mark, adopts the Bezier curve to make up modelling and obtains the Bezier curve;
Detection curve obtains and output unit, is used for obtaining detection curve and output on the Hessian refined image according to Bezier curve and 3 reference mark.
Wherein, Gauss's smoothing processing is to adopt Gauss's smooth function to present image (wherein in the said Hessian refined image acquiring unit; The image that present image receives in the time of can being true-time operation; Also can be one section current frame image in the video) carry out Filtering Processing; To obtain current smoothed image; Specific as follows: as to establish present image for
Figure 885715DEST_PATH_IMAGE002
( is the gray-scale value of point
Figure 875985DEST_PATH_IMAGE004
in the present image), do through the smoothed image
Figure 562181DEST_PATH_IMAGE006
( is the gray-scale value of the interior point
Figure 755058DEST_PATH_IMAGE004
of smoothed image of present image) that obtains after the Filtering Processing
Wherein, The level and smooth kernel function of
Figure 779963DEST_PATH_IMAGE010
expression Gauss, representes convolution algorithm.The value of
Figure 476020DEST_PATH_IMAGE014
is relevant with the width of line in the level and smooth kernel function
Figure 266756DEST_PATH_IMAGE010
of Gauss; Satisfy
Figure 317068DEST_PATH_IMAGE016
, wherein the pixel wide of
Figure 560968DEST_PATH_IMAGE018
expression line.
Hessian calculates and comprises in the said Hessian refined image acquiring unit:
Step a) utilizes the second order Grad of the gray-scale value of every point in the current smoothed image
Figure 826340DEST_PATH_IMAGE004
to make up Hessian matrix
Figure 726162DEST_PATH_IMAGE020
; Calculate the eigenwert
Figure 354590DEST_PATH_IMAGE022
of Hessian matrix; Wherein,
Figure 203728DEST_PATH_IMAGE024
, ,
Figure 826788DEST_PATH_IMAGE028
the expression point
Figure 6709DEST_PATH_IMAGE004
and the shade of gray difference of eight adjacent side points on every side, its computing formula is following:
Figure 975933DEST_PATH_IMAGE030
Figure 835305DEST_PATH_IMAGE032
Figure 257190DEST_PATH_IMAGE034
Wherein, the gray-scale value of
Figure 227420DEST_PATH_IMAGE036
remarked pixel point
Figure 238101DEST_PATH_IMAGE038
;
If step b) is the eigenwert
Figure 19107DEST_PATH_IMAGE040
of certain any Hessian matrix in the smoothed image; TH1 ∈ [4.2; 4.9]; Think that then this point is the Hessian point, otherwise this point of filtering, thereby the Hessian image obtained.
The operation of Hessian image thinning is that the Hessian image is carried out the morphology Refinement operation in the said Hessian refined image acquiring unit, to obtain the Hessian refined image.
In the said Bezier curve acquisition unit according to 3 reference mark
Figure 177555DEST_PATH_IMAGE042
; Adopt the Bezier curve to make up modelling and confirm the Bezier curve, its formula is following:
Figure 761596DEST_PATH_IMAGE044
。
Said detection curve obtains with output unit and specifically is used to realize following steps:
Step 1041; Simultaneously 3 reference mark
Figure 892363DEST_PATH_IMAGE042
carried out integral translation on
Figure 844270DEST_PATH_IMAGE046
,
Figure 224435DEST_PATH_IMAGE048
,
Figure 552780DEST_PATH_IMAGE050
,
Figure 600370DEST_PATH_IMAGE052
four direction;
Figure 723178DEST_PATH_IMAGE054
;
Figure 590640DEST_PATH_IMAGE056
; Wherein k1, n are threshold parameter; K1 ∈ [4; 6] and be integer; N ∈ [2; 4] and be integer, can make up the new Bezier curve of 4n bar according to the new reference mark after the integral translation;
Step 1042; Respectively to every new Bezier curve; Every bit on this Bezier curve is searched for nearest Hessian point in
Figure 477604DEST_PATH_IMAGE058
scope;
Figure 317384DEST_PATH_IMAGE060
and be integer;
Figure 860361DEST_PATH_IMAGE062
and be integer, add up on this Bezier curve distance that whole points and Hessian recently order and;
Step 1043; The distance of more every new Bezier curve statistics and size, selected distance is 3 benchmark reference mark with corresponding 3 reference mark
Figure 231430DEST_PATH_IMAGE064
of minimum Bezier curve;
Step 1044, maintaining
Figure 885265DEST_PATH_IMAGE066
two reference control points unchanged, respectively
Figure 658180DEST_PATH_IMAGE068
6 pixels around the pixel is within the scope of the temporary control points, and according to the temporary control point and
Figure 372059DEST_PATH_IMAGE066
build Bezier curves, Bezier curves to calculate the length, and the Bezier curve on the image at the Hessian refinement number of valid points, namely statistical point of the Bezier curve belongs to refine the image before the Hessian number of attractions and calculate the effective number of points with the Bezier curve length ratio, if the ratio is greater than k2, k2 ∈ [0.5,0.6], then the temporary control point as a reference control point
Figure 964845DEST_PATH_IMAGE068
The best control points
Figure 422371DEST_PATH_IMAGE070
; simultaneously with the same methods were used to obtain the reference control point
Figure 46863DEST_PATH_IMAGE066
The best control points
Figure 931642DEST_PATH_IMAGE072
;
Step 1045; Make up the Bezier curve according to optimum controlling point , and this Bezier curve is also exported as detection curve.
Can identify the curve in the video image simply, exactly according to Curves Recognition method and the device based on the search of Bezier reference mark of the present invention.
Description of drawings
Fig. 1 shows the process flow diagram according to the Curves Recognition method based on Bezier reference mark search of the present invention;
Fig. 2 shows the frame diagram according to the Curves Recognition device based on Bezier reference mark search of the present invention.
Embodiment
For making the object of the invention, technical scheme and advantage clearer, below in conjunction with embodiment and accompanying drawing, to further explain of the present invention.
Fig. 1 representes the process flow diagram according to the Curves Recognition method based on Bezier reference mark search of the present invention.As shown in Figure 1, comprise according to the Curves Recognition method based on the search of Bezier reference mark of the present invention:
First step 101 carries out Gauss's smoothing processing, Hessian calculating and the operation of Hessian image thinning to present image, obtains the Hessian refined image;
Second step 102, the user demarcates 3 reference mark according to the actual curve position on video image;
Third step 103 according to 3 reference mark, adopts the Bezier curve to make up modelling and obtains the Bezier curve;
The 4th step 104 is obtained detection curve and output on the Hessian refined image according to Bezier curve and 3 reference mark.
First step:
Said Gauss's smoothing processing is to adopt Gauss's smooth function to present image (wherein; The image that present image receives in the time of can being true-time operation; Also can be one section current frame image in the video) carry out Filtering Processing; To obtain current smoothed image; Specific as follows: as to establish present image for
Figure 210625DEST_PATH_IMAGE002
;
Figure 941821DEST_PATH_IMAGE002
is the gray-scale value of point
Figure 748234DEST_PATH_IMAGE004
in the present image, through the smoothed image
Figure 564880DEST_PATH_IMAGE006
( is the gray-scale value of the interior point
Figure 966223DEST_PATH_IMAGE004
of smoothed image of present image) that obtains after the Filtering Processing does
Figure 940607DEST_PATH_IMAGE008
Wherein, The level and smooth kernel function of
Figure 244550DEST_PATH_IMAGE010
expression Gauss,
Figure 785253DEST_PATH_IMAGE012
representes convolution algorithm.The value of
Figure 639256DEST_PATH_IMAGE014
is relevant with the width of line in the level and smooth kernel function
Figure 976194DEST_PATH_IMAGE010
of Gauss; Satisfy
Figure 915648DEST_PATH_IMAGE016
, wherein the pixel wide of
Figure 135408DEST_PATH_IMAGE018
expression line.
Hessian calculates and comprises:
Step a) utilizes the second order Grad of the gray-scale value of every point in the current smoothed image
Figure 430123DEST_PATH_IMAGE004
to make up Hessian matrix
Figure 11889DEST_PATH_IMAGE020
; Calculate the eigenwert
Figure 24845DEST_PATH_IMAGE022
of Hessian matrix; Wherein,
Figure 907350DEST_PATH_IMAGE024
,
Figure 72883DEST_PATH_IMAGE026
,
Figure 77748DEST_PATH_IMAGE028
the expression point
Figure 328732DEST_PATH_IMAGE004
and the shade of gray difference of eight adjacent side points on every side, its computing formula is following:
Figure 77245DEST_PATH_IMAGE030
Figure 97285DEST_PATH_IMAGE032
Figure 273052DEST_PATH_IMAGE034
Wherein, the gray-scale value of remarked pixel point
Figure 295027DEST_PATH_IMAGE038
;
If step b) is the eigenwert
Figure 622103DEST_PATH_IMAGE040
of certain any Hessian matrix in the smoothed image; TH1 ∈ [4.2; 4.9]; Think that then this point is the Hessian point, otherwise this point of filtering, thereby the Hessian image obtained.
The operation of Hessian image thinning is that the Hessian image is carried out the morphology Refinement operation, to obtain the Hessian refined image.Wherein, the morphology Refinement operation can be with reference to " Digital Image Processing, Paul Gonzales, Electronic Industry Press ".
Third step:
Said third step is according to 3 reference mark ; Adopt the Bezier curve to make up modelling and confirm the Bezier curve, its formula is following:
Figure 928768DEST_PATH_IMAGE044
。
The 4th step:
Said the 4th step further comprises:
Step 1041; Simultaneously 3 reference mark
Figure 832133DEST_PATH_IMAGE042
carried out integral translation on
Figure 826765DEST_PATH_IMAGE046
, ,
Figure 788697DEST_PATH_IMAGE050
,
Figure 354807DEST_PATH_IMAGE052
four direction;
Figure 718793DEST_PATH_IMAGE054
;
Figure 157995DEST_PATH_IMAGE056
; Wherein k1, n are threshold parameter; K1 ∈ [4; 6] and be integer; N ∈ [2; 4] and be integer, can make up the new Bezier curve of 4n bar according to the new reference mark after the integral translation;
Step 1042; Respectively to every new Bezier curve; Every bit on this Bezier curve is searched for nearest Hessian point in scope; and be integer; and be integer, add up on this Bezier curve distance that whole points and Hessian recently order and;
Step 1043; The distance of more every new Bezier curve statistics and size, selected distance is 3 benchmark reference mark with corresponding 3 reference mark of minimum Bezier curve;
Step 1044, maintaining
Figure 24451DEST_PATH_IMAGE066
two reference control points unchanged, respectively
Figure 742484DEST_PATH_IMAGE068
6 pixels around the pixel is within the scope of the temporary control points, and according to the temporary control point and
Figure 753165DEST_PATH_IMAGE066
build Bezier curves, Bezier curves to calculate the length, and the Bezier curve on the image at the Hessian refinement number of valid points, namely statistical point of the Bezier curve belongs to refine the image before the Hessian number of attractions and calculate the effective number of points with the Bezier curve length ratio, if the ratio is greater than k2, k2 ∈ [0.5,0.6], then the temporary control point as a reference control point
Figure 783438DEST_PATH_IMAGE068
The best control points
Figure 692620DEST_PATH_IMAGE070
; simultaneously with the same methods were used to obtain the reference control point
Figure 466541DEST_PATH_IMAGE066
The best control points
Figure 144778DEST_PATH_IMAGE072
;
Step 1045; Make up the Bezier curve according to optimum controlling point , and this Bezier curve is also exported as detection curve.
Preferably, when the power transmission line curve detection, can choose k1=4, n=3, k2=0.55.
Fig. 2 shows the frame diagram according to the Curves Recognition device based on Bezier reference mark search of the present invention.As shown in Figure 2, comprise according to the Curves Recognition device based on the search of Bezier reference mark of the present invention:
Hessian refined image acquiring unit 1 is used for present image is carried out Gauss's smoothing processing, Hessian calculating and the operation of Hessian image thinning, obtains the Hessian refined image;
Unit 2 is demarcated at 3 reference mark, is used for the user according to the actual curve position, on video image, demarcates 3 reference mark;
Bezier curve acquisition unit 3 is used for according to 3 reference mark, adopts the Bezier curve to make up modelling and obtains the Bezier curve;
Detection curve obtains and output unit 4, is used for obtaining detection curve and output on the Hessian refined image according to Bezier curve and 3 reference mark.
Wherein, Gauss's smoothing processing is to adopt Gauss's smooth function to present image (wherein in the said Hessian refined image acquiring unit 1; The image that present image receives in the time of can being true-time operation; Also can be one section current frame image in the video) carry out Filtering Processing; To obtain current smoothed image; Specific as follows: as to establish present image for ;
Figure 320041DEST_PATH_IMAGE002
is the gray-scale value of point in the present image, through the smoothed image
Figure 221931DEST_PATH_IMAGE006
( is the gray-scale value of the interior point
Figure 159111DEST_PATH_IMAGE004
of smoothed image of present image) that obtains after the Filtering Processing does
Wherein, The level and smooth kernel function of
Figure 354917DEST_PATH_IMAGE010
expression Gauss,
Figure 975254DEST_PATH_IMAGE012
representes convolution algorithm.The value of
Figure 136425DEST_PATH_IMAGE014
is relevant with the width of line in the level and smooth kernel function
Figure 379822DEST_PATH_IMAGE010
of Gauss; Satisfy
Figure 887123DEST_PATH_IMAGE016
, wherein the pixel wide of
Figure 729177DEST_PATH_IMAGE018
expression line.
Hessian calculates and comprises in the said Hessian refined image acquiring unit 1:
Step a) utilizes the second order Grad of the gray-scale value of every point in the current smoothed image to make up Hessian matrix
Figure 814125DEST_PATH_IMAGE020
; Calculate the eigenwert
Figure 449636DEST_PATH_IMAGE022
of Hessian matrix; Wherein, ,
Figure 790936DEST_PATH_IMAGE026
,
Figure 522132DEST_PATH_IMAGE028
the expression point
Figure 325615DEST_PATH_IMAGE004
and the shade of gray difference of eight adjacent side points on every side, its computing formula is following:
Figure 79944DEST_PATH_IMAGE030
Figure 879273DEST_PATH_IMAGE032
Figure 215708DEST_PATH_IMAGE034
Wherein, the gray-scale value of
Figure 707869DEST_PATH_IMAGE036
remarked pixel point
Figure 762544DEST_PATH_IMAGE038
;
If step b) is the eigenwert
Figure 99984DEST_PATH_IMAGE040
of certain any Hessian matrix in the smoothed image; TH1 ∈ [4.2; 4.9]; Think that then this point is the Hessian point, otherwise this point of filtering, thereby the Hessian image obtained.
The operation of Hessian image thinning is that the Hessian image is carried out the morphology Refinement operation in the said Hessian refined image acquiring unit 1, to obtain the Hessian refined image.Wherein, the morphology Refinement operation can be with reference to " Digital Image Processing, Paul Gonzales, Electronic Industry Press ".
In the said Bezier curve acquisition unit 3 according to 3 reference mark
Figure 556504DEST_PATH_IMAGE042
; Adopt the Bezier curve to make up modelling and confirm the Bezier curve, its formula is following:
Figure 953988DEST_PATH_IMAGE044
。
Said detection curve obtains with output unit 4 and specifically is used to realize following steps:
Step 1041; Simultaneously 3 reference mark
Figure 493029DEST_PATH_IMAGE042
carried out integral translation on ,
Figure 945187DEST_PATH_IMAGE048
,
Figure 716834DEST_PATH_IMAGE050
,
Figure 542839DEST_PATH_IMAGE052
four direction;
Figure 487661DEST_PATH_IMAGE054
; ; Wherein k1, n are threshold parameter; K1 ∈ [4; 6] and be integer; N ∈ [2; 4] and be integer, can make up the new Bezier curve of 4n bar according to the new reference mark after the integral translation;
Step 1042; Respectively to every new Bezier curve; Every bit on this Bezier curve is searched for nearest Hessian point in
Figure 658059DEST_PATH_IMAGE058
scope;
Figure 906113DEST_PATH_IMAGE060
and be integer;
Figure 389047DEST_PATH_IMAGE062
and be integer, add up on this Bezier curve distance that whole points and Hessian recently order and;
Step 1043; The distance of more every new Bezier curve statistics and size, selected distance is 3 benchmark reference mark with corresponding 3 reference mark
Figure 674666DEST_PATH_IMAGE064
of minimum Bezier curve;
Step 1044, maintaining
Figure 663482DEST_PATH_IMAGE066
two reference control points unchanged, respectively
Figure 588713DEST_PATH_IMAGE068
6 pixels around the pixel is within the scope of the temporary control points, and according to the temporary control point and
Figure 875338DEST_PATH_IMAGE066
build Bezier curves, Bezier curves to calculate the length, and the Bezier curve on the image at the Hessian refinement number of valid points, namely statistical point of the Bezier curve belongs to refine the image before the Hessian number of attractions and calculate the effective number of points with the Bezier curve length ratio, if the ratio is greater than k2, k2 ∈ [0.5,0.6], then the temporary control point as a reference control point
Figure 812201DEST_PATH_IMAGE068
The best control points
Figure 906671DEST_PATH_IMAGE070
; simultaneously with the same methods were used to obtain the reference control point
Figure 381515DEST_PATH_IMAGE066
The best control points
Figure 222563DEST_PATH_IMAGE072
;
Step 1045; Make up the Bezier curve according to optimum controlling point
Figure 466463DEST_PATH_IMAGE074
, and this Bezier curve is also exported as detection curve.
Preferably, when the power transmission line curve detection, can choose k1=4, n=3, k2=0.55.
Can identify the curve in the video image simply, exactly according to Curves Recognition method and the device based on the search of Bezier reference mark of the present invention.
The above; Being merely preferred embodiment of the present invention, is not to be used to limit protection scope of the present invention, is to be understood that; The present invention is not limited to described implementation here, and these implementation purpose of description are to help those of skill in the art to put into practice the present invention.Any those of skill in the art are easy to further improving without departing from the spirit and scope of the present invention and perfect; Therefore the present invention only receives the restriction of the content and the scope of claim of the present invention, and its intention contains all and is included in alternatives and equivalent in the spirit and scope of the invention that is limited accompanying claims.

Claims (12)

1. based on the Curves Recognition method of Bezier reference mark search, it is characterized in that this method comprises:
First step carries out Gauss's smoothing processing, Hessian calculating and the operation of Hessian image thinning to present image, obtains the Hessian refined image;
Second step, the user demarcates 3 reference mark according to the actual curve position on video image;
Third step according to 3 reference mark, adopts the Bezier curve to make up modelling and obtains the Bezier curve;
The 4th step is obtained detection curve and output on the Hessian refined image according to Bezier curve and 3 reference mark.
2. the method for claim 1; Gauss's smoothing processing is specific as follows in the said first step: establish present image for
Figure 734034DEST_PATH_IMAGE002
, through the smoothed image
Figure 935208DEST_PATH_IMAGE004
that obtains after the Filtering Processing do
Figure 328756DEST_PATH_IMAGE006
Wherein, is the gray-scale value of point
Figure 501428DEST_PATH_IMAGE008
in the present image; is the gray-scale value of the interior point
Figure 570327DEST_PATH_IMAGE008
of smoothed image of present image; The level and smooth kernel function of expression Gauss;
Figure 398267DEST_PATH_IMAGE012
representes convolution algorithm; The value of
Figure 735149DEST_PATH_IMAGE014
is relevant with the width of line in the level and smooth kernel function
Figure 754293DEST_PATH_IMAGE010
of Gauss; Satisfy
Figure 654564DEST_PATH_IMAGE016
, wherein the pixel wide of
Figure 221287DEST_PATH_IMAGE018
expression line.
3. the method for claim 1, Hessian calculates and comprises in the said first step:
Step a) utilizes the second order Grad of the gray-scale value of every point in the current smoothed image
Figure 685897DEST_PATH_IMAGE008
to make up Hessian matrix
Figure 793531DEST_PATH_IMAGE020
; Calculate the eigenwert
Figure 1789DEST_PATH_IMAGE022
of Hessian matrix; Wherein,
Figure 488265DEST_PATH_IMAGE024
,
Figure 409864DEST_PATH_IMAGE026
,
Figure 739214DEST_PATH_IMAGE028
the expression point
Figure 547902DEST_PATH_IMAGE008
and the shade of gray difference of eight adjacent side points on every side, its computing formula is following:
Figure 164139DEST_PATH_IMAGE032
Figure 715206DEST_PATH_IMAGE034
Wherein, the gray-scale value of
Figure 527917DEST_PATH_IMAGE036
remarked pixel point ;
If step b) is the eigenwert
Figure 153250DEST_PATH_IMAGE040
of certain any Hessian matrix in the smoothed image; TH1 ∈ [4.2; 4.9]; Think that then this point is the Hessian point, otherwise this point of filtering, thereby the Hessian image obtained.
4. the method for claim 1, the operation of Hessian image thinning is that the Hessian image is carried out the morphology Refinement operation in the said first step, to obtain the Hessian refined image.
5. the method for claim 1; Said third step is according to 3 reference mark
Figure 270242DEST_PATH_IMAGE042
; Adopt the Bezier curve to make up modelling and confirm the Bezier curve, its formula is following:
Figure 686311DEST_PATH_IMAGE044
The method of claim 1, said the 4th step further comprises:
Step 1041; Simultaneously 3 reference mark carried out integral translation on
Figure 537385DEST_PATH_IMAGE046
,
Figure 813776DEST_PATH_IMAGE048
,
Figure 158170DEST_PATH_IMAGE050
,
Figure 718464DEST_PATH_IMAGE052
four direction; ;
Figure 316116DEST_PATH_IMAGE056
; Wherein k1, n are threshold parameter; K1 ∈ [4; 6] and be integer; N ∈ [2; 4] and be integer, can make up the new Bezier curve of 4n bar according to the new reference mark after the integral translation;
Step 1042; Respectively to every new Bezier curve; Every bit on this Bezier curve is searched for nearest Hessian point in
Figure 11671DEST_PATH_IMAGE058
scope;
Figure 426471DEST_PATH_IMAGE060
and be integer; and be integer, add up on this Bezier curve distance that whole points and Hessian recently order and;
Step 1043; The distance of more every new Bezier curve statistics and size, selected distance is 3 benchmark reference mark with corresponding 3 reference mark
Figure 413812DEST_PATH_IMAGE064
of minimum Bezier curve;
Step 1044, maintaining
Figure 913057DEST_PATH_IMAGE066
two reference constant control points, respectively, 6 pixels around the pixel is within the scope of the temporary control points, and according to the temporary control point and
Figure 108863DEST_PATH_IMAGE066
Build Bezier curves, Bezier curves to calculate the length, and the refinement of the Bezier curve on the image at the Hessian number of valid points, namely statistical point of the Bezier curve belongs to refine the image before the Hessian number of attractions and calculate the effective point The number of the Bezier curve length ratio, if the ratio is greater than k2, k2 ∈ [0.5,0.6], then the temporary control point as a reference control point
Figure 96411DEST_PATH_IMAGE068
The best control points
Figure 133768DEST_PATH_IMAGE070
; simultaneously with the same methods were used to obtain the reference control point
Figure 523161DEST_PATH_IMAGE066
The best control points
Figure 617632DEST_PATH_IMAGE072
;
Step 1045; Make up the Bezier curve according to optimum controlling point
Figure 764579DEST_PATH_IMAGE074
, and this Bezier curve is also exported as detection curve.
6. based on the Curves Recognition device of Bezier reference mark search, it is characterized in that this device comprises:
Hessian refined image acquiring unit is used for present image is carried out Gauss's smoothing processing, Hessian calculating and the operation of Hessian image thinning, obtains the Hessian refined image;
The unit is demarcated at 3 reference mark, is used for the user according to the actual curve position, on video image, demarcates 3 reference mark;
Bezier curve acquisition unit is used for according to 3 reference mark, adopts the Bezier curve to make up modelling and obtains the Bezier curve;
Detection curve obtains and output unit, is used for obtaining detection curve and output on the Hessian refined image according to Bezier curve and 3 reference mark.
7. device as claimed in claim 7; It is characterized in that; Gauss's smoothing processing is specific as follows in the said Hessian refined image acquiring unit: establish present image for
Figure 854895DEST_PATH_IMAGE002
, through the smoothed image
Figure 849527DEST_PATH_IMAGE004
that obtains after the Filtering Processing do
Figure 367096DEST_PATH_IMAGE006
Wherein,
Figure 79968DEST_PATH_IMAGE002
is the gray-scale value of point
Figure 708395DEST_PATH_IMAGE008
in the present image;
Figure 429970DEST_PATH_IMAGE004
is the gray-scale value of the interior point
Figure 56124DEST_PATH_IMAGE008
of smoothed image of present image; The level and smooth kernel function of
Figure 239981DEST_PATH_IMAGE010
expression Gauss,
Figure 422831DEST_PATH_IMAGE012
representes convolution algorithm.
8. the value of
Figure 251427DEST_PATH_IMAGE014
is relevant with the width of line in the level and smooth kernel function
Figure 641323DEST_PATH_IMAGE010
of Gauss; Satisfy
Figure 922580DEST_PATH_IMAGE016
, wherein the pixel wide of
Figure 830493DEST_PATH_IMAGE018
expression line.
9. device as claimed in claim 7 is characterized in that, Hessian calculates and comprises in the said Hessian refined image acquiring unit:
Step a) utilizes the second order Grad of the gray-scale value of every point in the current smoothed image to make up Hessian matrix ; Calculate the eigenwert
Figure 590748DEST_PATH_IMAGE022
of Hessian matrix; Wherein,
Figure 364669DEST_PATH_IMAGE024
,
Figure 308485DEST_PATH_IMAGE026
,
Figure 509660DEST_PATH_IMAGE028
the expression point and the shade of gray difference of eight adjacent side points on every side, its computing formula is following:
Figure 218170DEST_PATH_IMAGE030
Figure 16493DEST_PATH_IMAGE032
Figure 388568DEST_PATH_IMAGE034
Wherein, the gray-scale value of
Figure 3833DEST_PATH_IMAGE036
remarked pixel point
Figure 119556DEST_PATH_IMAGE038
;
If step b) is the eigenwert
Figure 959336DEST_PATH_IMAGE040
of certain any Hessian matrix in the smoothed image; TH1 ∈ [4.2; 4.9]; Think that then this point is the Hessian point, otherwise this point of filtering, thereby the Hessian image obtained.
10. device as claimed in claim 7 is characterized in that, the operation of Hessian image thinning is that the Hessian image is carried out the morphology Refinement operation in the said Hessian refined image acquiring unit, to obtain the Hessian refined image.
11. device as claimed in claim 7; It is characterized in that; In the said Bezier curve acquisition unit according to 3 reference mark
Figure 253045DEST_PATH_IMAGE042
; Adopt the Bezier curve to make up modelling and confirm the Bezier curve, its formula is following:
Figure 686432DEST_PATH_IMAGE044
。
12. device as claimed in claim 7 is characterized in that, said detection curve obtains with output unit and specifically is used to realize following steps:
Step 1041; Simultaneously 3 reference mark
Figure 340267DEST_PATH_IMAGE042
carried out integral translation on
Figure 113182DEST_PATH_IMAGE046
,
Figure 764743DEST_PATH_IMAGE048
, , four direction; ;
Figure 347765DEST_PATH_IMAGE056
; Wherein k1, n are threshold parameter; K1 ∈ [4; 6] and be integer; N ∈ [2; 4] and be integer, can make up the new Bezier curve of 4n bar according to the new reference mark after the integral translation;
Step 1042; Respectively to every new Bezier curve; Every bit on this Bezier curve is searched for nearest Hessian point in scope;
Figure 689065DEST_PATH_IMAGE060
and be integer;
Figure 420260DEST_PATH_IMAGE062
and be integer, add up on this Bezier curve distance that whole points and Hessian recently order and;
Step 1043; The distance of more every new Bezier curve statistics and size, selected distance is 3 benchmark reference mark with corresponding 3 reference mark of minimum Bezier curve;
Step 1044, maintaining
Figure 981003DEST_PATH_IMAGE066
two reference constant control points, respectively,
Figure 856030DEST_PATH_IMAGE068
6 pixels around the pixel is within the scope of the temporary control points, and according to the temporary control point and Build Bezier curves, Bezier curves to calculate the length, and the refinement of the Bezier curve on the image at the Hessian number of valid points, namely statistical point of the Bezier curve belongs to refine the image before the Hessian number of attractions and calculate the effective point The number of the Bezier curve length ratio, if the ratio is greater than k2, k2 ∈ [0.5,0.6], then the temporary control point as a reference control point
Figure 294413DEST_PATH_IMAGE068
The best control points
Figure 411405DEST_PATH_IMAGE070
; simultaneously with the same methods were used to obtain the reference control point
Figure 14424DEST_PATH_IMAGE066
The best control points ;
Step 1045; Make up the Bezier curve according to optimum controlling point
Figure 678548DEST_PATH_IMAGE074
, and this Bezier curve is also exported as detection curve.
CN201210091188.6A 2012-03-31 2012-03-31 Curve identification method based on Bezier control point searching and apparatus thereof Active CN102663384B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210091188.6A CN102663384B (en) 2012-03-31 2012-03-31 Curve identification method based on Bezier control point searching and apparatus thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210091188.6A CN102663384B (en) 2012-03-31 2012-03-31 Curve identification method based on Bezier control point searching and apparatus thereof

Publications (2)

Publication Number Publication Date
CN102663384A true CN102663384A (en) 2012-09-12
CN102663384B CN102663384B (en) 2014-01-22

Family

ID=46772868

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210091188.6A Active CN102663384B (en) 2012-03-31 2012-03-31 Curve identification method based on Bezier control point searching and apparatus thereof

Country Status (1)

Country Link
CN (1) CN102663384B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103971101A (en) * 2014-05-21 2014-08-06 国家电网公司 Curve identification method based on Bethel control point searching
CN104462715A (en) * 2014-12-24 2015-03-25 黑龙江科技大学 Photovoltaic cell output characteristic modeling method based on Bezier function
CN105046705A (en) * 2015-07-13 2015-11-11 浙江工业大学 Crack edge detection method based on fuzzy theory
CN105493149A (en) * 2013-04-30 2016-04-13 微软技术许可有限责任公司 Tessellation of two-dimensional curves using a graphics pipeline
CN106557770A (en) * 2015-09-29 2017-04-05 奥多比公司 By comparing Bezier come the shape in identification image
CN106600663A (en) * 2016-12-30 2017-04-26 浙江工业大学 Simple curve smoothening method based on secondary B-spline curve
CN107907048A (en) * 2017-06-30 2018-04-13 长沙湘计海盾科技有限公司 A kind of binocular stereo vision method for three-dimensional measurement based on line-structured light scanning
CN113313724A (en) * 2021-05-27 2021-08-27 深圳企业云科技股份有限公司 Line detection processing method for resisting resampling of mobile phone camera

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1449638A (en) * 2000-08-29 2003-10-15 迪吉塔亚丽雅有限公司 Method and system for processing moving picture data based upon vector graphic on wireless network
CN101393644A (en) * 2008-08-15 2009-03-25 华中科技大学 Hepatic portal vein tree modeling method and system thereof
CN101923725A (en) * 2009-04-21 2010-12-22 索尼电脑娱乐公司 The generation of cubic Bezier control points in computer graphics system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1449638A (en) * 2000-08-29 2003-10-15 迪吉塔亚丽雅有限公司 Method and system for processing moving picture data based upon vector graphic on wireless network
CN101393644A (en) * 2008-08-15 2009-03-25 华中科技大学 Hepatic portal vein tree modeling method and system thereof
CN101923725A (en) * 2009-04-21 2010-12-22 索尼电脑娱乐公司 The generation of cubic Bezier control points in computer graphics system

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105493149B (en) * 2013-04-30 2018-11-16 微软技术许可有限责任公司 Using graphics pipeline to the thinning method of two-dimensional curve, system and storage medium
CN105493149A (en) * 2013-04-30 2016-04-13 微软技术许可有限责任公司 Tessellation of two-dimensional curves using a graphics pipeline
CN103971101A (en) * 2014-05-21 2014-08-06 国家电网公司 Curve identification method based on Bethel control point searching
CN104462715B (en) * 2014-12-24 2017-09-15 黑龙江科技大学 A kind of modeling method of the photovoltaic cell output characteristic based on Bezier functions
CN104462715A (en) * 2014-12-24 2015-03-25 黑龙江科技大学 Photovoltaic cell output characteristic modeling method based on Bezier function
CN105046705B (en) * 2015-07-13 2017-07-25 浙江工业大学 A kind of crack edge detection method based on fuzzy theory
CN105046705A (en) * 2015-07-13 2015-11-11 浙江工业大学 Crack edge detection method based on fuzzy theory
CN106557770A (en) * 2015-09-29 2017-04-05 奥多比公司 By comparing Bezier come the shape in identification image
CN106557770B (en) * 2015-09-29 2021-08-27 奥多比公司 Identifying shapes in images by comparing bezier curves
CN106600663B (en) * 2016-12-30 2019-07-09 浙江工业大学 A kind of simple curve smoothing method based on quadratic b-spline curve
CN106600663A (en) * 2016-12-30 2017-04-26 浙江工业大学 Simple curve smoothening method based on secondary B-spline curve
CN107907048A (en) * 2017-06-30 2018-04-13 长沙湘计海盾科技有限公司 A kind of binocular stereo vision method for three-dimensional measurement based on line-structured light scanning
CN113313724A (en) * 2021-05-27 2021-08-27 深圳企业云科技股份有限公司 Line detection processing method for resisting resampling of mobile phone camera
CN113313724B (en) * 2021-05-27 2022-04-08 深圳企业云科技股份有限公司 Line detection processing method for resisting resampling of mobile phone camera

Also Published As

Publication number Publication date
CN102663384B (en) 2014-01-22

Similar Documents

Publication Publication Date Title
CN102663384A (en) Curve identification method based on Bezier control point searching and apparatus thereof
CN107705288B (en) Infrared video detection method for dangerous gas leakage under strong interference of pseudo-target motion
CN103714345B (en) A kind of method and system of binocular stereo vision detection finger fingertip locus
CN103927016B (en) Real-time three-dimensional double-hand gesture recognition method and system based on binocular vision
CN107067382A (en) A kind of improved method for detecting image edge
WO2016127736A1 (en) Computing method for area of fingerprint overlapping area and electronic apparatus
EP2916291B1 (en) Method, apparatus and computer program product for disparity map estimation of stereo images
CN105405142A (en) Edge defect detection method and system for glass panel
CN103218605B (en) A kind of fast human-eye positioning method based on integral projection and rim detection
CN106446952A (en) Method and apparatus for recognizing score image
CN102147857A (en) Image processing method for detecting similar round by using improved hough transformation
KR101635896B1 (en) Device and method for tracking people based depth information
CN105139391B (en) A kind of haze weather traffic image edge detection method
CN103226824B (en) Maintain the video Redirectional system of vision significance
TW201516969A (en) Visual object tracking method
CN103577828B (en) A kind of Approach for road detection based on edge feature
WO2015024257A8 (en) Unstructured road boundary detection
CN102855617A (en) Method and system for processing adaptive images
CN105404874A (en) Vehicle window recognition system based on projection and hough straight line detection
CN105787470A (en) Method for detecting power transmission line tower in image based on polymerization multichannel characteristic
CN106327464A (en) Edge detection method
CN108918499A (en) The method of Raman baseline drift is removed in Raman map
CN102073872A (en) Image-based method for identifying shape of parasite egg
CN103337073B (en) A kind of two dimensional image threshold segmentation method based on three-dimensional entropy
CN104392211A (en) Skin recognition method based on saliency detection

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
ASS Succession or assignment of patent right

Owner name: NETPOSA TECHNOLOGIES, LTD.

Free format text: FORMER OWNER: BEIJING ZANB SCIENCE + TECHNOLOGY CO., LTD.

Effective date: 20150716

C41 Transfer of patent application or patent right or utility model
TR01 Transfer of patent right

Effective date of registration: 20150716

Address after: 100102, Beijing, Chaoyang District, Tong Tung Street, No. 1, Wangjing SOHO tower, two, C, 26 floor

Patentee after: NETPOSA TECHNOLOGIES, Ltd.

Address before: 100048 Beijing city Haidian District Road No. 9, building 4, 5 layers of international subject

Patentee before: Beijing ZANB Technology Co.,Ltd.

PP01 Preservation of patent right
PP01 Preservation of patent right

Effective date of registration: 20220726

Granted publication date: 20140122