CN103714342A - An aerial-photo insulator chain automatic positioning method based on binary image shape features - Google Patents

Abstract

The invention discloses an insulator chain automatic positioning method based on binary image shape features and belongs to the field of image processing techniques and power transmission and transformation equipment running state maintenance. The method comprises the following specific steps: 1) performing morphological filtering and micro-region removing processing on a binary image; 2) performing digitalization description on three shape features of an insulator chain, and processing the image based on the above to remove the regions not satisfied with the three shape features and keep the regions satisfied with the three shape features; and 3) utilizing a minimum bounding rectangle to mark the regions satisfied with the shape features of the insulator chain and thus positioning is achieved. The problem that the positioning of the insulator chain in a complicated-background aerial image is difficult is solved by fully utilizing the shape features of the insulator chain and by adopting the method based on binary image shape feature description. The method is practicable and feasible; better positioning effect is achieved; time needed is short; no labour is needed; and the method provides a certain reference meaning for scheme design of related problems.

Description

The insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility

Technical field

The invention belongs to image processing techniques and the maintenance of power transmission and transforming equipment running status field, particularly a kind of insulator chain automatic positioning method based on bianry image shape facility.

Background technology

It is the gordian technique in the fields such as image processing, computer vision that interested target in image is positioned, and its objective is some the important goal position information in image to extract, thereby lays the foundation for the identification of this target and subsequent treatment.The insulator chain of taking photo by plane automatically location is the important prerequisite that realizes insulator state monitoring and fault diagnosis, has great practical significance.

Existing localization method has 3 classes substantially: (1) method based on cutting apart, original image is divided into a plurality of regions, and the interested region of mark; The problem that the method exists is the gray shade scale that needs manual Offered target place, and positioning precision is low, is applied in automatic monitoring comparatively difficult.(2) method based on rim detection, finds the profile of interesting target, realizes location; The problem that the method exists is to noise-sensitive, lower for the Aerial Images accuracy that background is complicated, resolution is low, noise is higher, and because the reasons such as background is complicated, and edge variation is various cause travelling speed slow.(3) method based on texture, analyzes the textural characteristics of interesting target, and as criterion, target location is extracted; The problem of the method maximum is to extract texture information to need the plenty of time, and is difficult to distinguish for some pseudo-target close with insulator chain textural characteristics.

Existing method is not considered the unique shape feature in the bianry image of insulator chain after cutting apart.The targets such as insulator chain and tower bar, circuit have obvious shape difference, and after binaryzation, this shape facility is more outstanding, if can it be used, can improve positioning precision, reduce consuming timely, improve robotization performance.

Summary of the invention

The problem existing for above-mentioned prior art, the present invention proposes a kind of insulator chain automatic positioning method based on bianry image shape facility, it is characterized in that, and the method concrete steps are as follows:

1) bianry image is carried out to Mathematical morphology filter and involve the processing of removal zonule;

2) 3 of insulator chain shape facilities are carried out to digitized description, on this basis image is processed, remove the region that does not meet 3 shape facilities, retain the region that meets 3 shape facilities;

3) adopt the region that meets insulator chain shape facility in minimum boundary rectangle marking image, realize location.

Described step 1) concrete steps are:

11) first the insulator image of taking photo by plane after binaryzation is carried out to morphological erosion computing, at very thin some place separating objects, remove the noise of minimum area;

12) carry out again morphological dilations computing, fill up target internal cavity, the border of level and smooth larger object; Wherein, in order better to reach the object of fully level and smooth object boundary, selecting the form parameter of filtering is " circle ";

13) after twice morphology operations, remain some zonules, remove region area and be less than m * n * 1.5 * 10 ^-5region, m wherein, n is respectively line number and the columns of bianry image.

Described step 2) in, 3 shape facilities of insulator chain are:

Shape facility 1: insulator chain comprises several umbrella disks, and each umbrella disk thickness equates;

Shape facility 2: the thickness at umbrella disk edge is less than the thickness at center, increases gradually from edge to center thickness;

Shape facility 3: the less and numerical value of spacing distance between each umbrella disk equates.

Described step 2) concrete steps are:

21) employing figure-number conversion method is carried out digitized description by shape facility, and the desired value in bianry image is made as to 1, and background value is made as 0, extracts target information;

22) each row of image are extracted respectively, obtain n group and only comprise 0 and 1 Serial No. { l ₁, l ₂,, l ₃..., l _j..., l _n, the columns that n is image;

23) these Serial No.s are carried out to shape facility description, from sequence, remove nonisulated sub-goal, then sequence is converted into matrix, reconstruct bianry image.

Described step 23) in to the description of shape facility 1 and be treated to:

A1) at sequence l _jmiddle search becomes 0 pixel from 1, the position of the pixel that record value is 0, and this point is marginal point;

B1) add up this marginal point number of continuous 1 before, be designated as O, establishing marginal point has s, records s O value { O ₁, O ₂, O ₃..., O _i..., O _s;

$\left\{\begin{array}{c}s\&GreaterEqual;N_{\min }\\ |O_i-O_{i+1}|<m\&times;t_1\end{array}\right.---\left(1\right)$

In formula: m is bianry image line number, t ₁umbrella disk thickness coefficient, N _minit is the minimum value of umbrella disk number in insulator chain;

When ordered series of numbers meets formula (1), think that this position marginal point belongs to true marginal point, retains this dot information; If do not meet, think that this position marginal point belongs to pseudo-edge point, carry out " removal " operation;

C1) take step b1) in criterion be foundation, traversal all sequences { l ₁, l ₂,, l ₃..., l _j..., l _n, the region of removing discontented sufficient shape facility 1.

Described step 23) in to the description of shape facility 2 and be treated to:

A2) after shape facility 1 is processed, image becomes a plurality of non-UNICOMs region, and She Fei UNICOM region has u, by All Ranges numbering 1,2,3 ..., i ..., u;

B2), for each region, to add up every train value be 1 number and save as vector, is designated as G={ G ₁, G ₂, G ₃..., G _i... G _p, vectorial G _imiddle element is the length of these every row in region, and p is the non-zero columns in this region; In calculating G, element is poor, and obtaining length is the vectorial H of p-1, as shown in formula (2):

H _i=G _i+1-G _i (2)

In formula (2), if element H in H _isymbol is equal timing, and it is large that the thickness in this region becomes gradually; If element H in H _isymbol is when all negative, and the thickness in this region diminishes gradually, thereby tentatively judges that this region belongs to insulator, retains this area information;

C2) according to sequence l _jin first value be that nonisulated sub-goal is further removed in the position of 1 appearance, for each region, adding up each, to be listed as first value be 1 position record, J={ J ₁, J ₂, J ₃..., J _i..., J _p; In calculating J, element is poor, and obtaining length is the vectorial K of p-1, as shown in formula (3):

K _i=J _i+1-J _i (3)

In formula (2) and (3), element H in H _isymbol is equal timing, K _ishould meet all negative; Element H in H _isymbol when all negative, K _iall just should meet; When region i meets above-mentioned condition, judge that this region belongs to insulator umbrella disc portion, retains this region;

D2) take step b2) and c2) in criterion be foundation, travel through all u region, remove the region of being discontented with sufficient shape facility 2.

Described step 23) in to the description of shape facility 3 and be treated to:

A3) image of shape facility 2 being processed again carries out figure-number conversion and obtains n group 0,1 Serial No. { f ₁, f ₂, f ₃..., f _j..., f _n, the columns that n is image;

B3) at sequence f _jin, search becomes 1 pixel from 0, and continuous 0 number is added up before the point that these marks cross in this position of mark, is designated as R; If gauge point has w, record w R value { R ₁, R ₂, R ₃..., R _i... R _w;

When R meets formula (4) conditional, think that this position belongs to the gap of insulator umbrella disk, is set to 1 by this position; Work as w<V _mintime think that this position does not belong to insulator,

$\left\{\begin{array}{c}w\&GreaterEqual;V_{\min }\\ |R_i-R_{i+1}|<m\&times;t_2\end{array}\right.---\left(4\right)$

In formula: m is bianry image line number, t ₂umbrella disk spread ratio, V _minthe minimum value that represents insulator chain intermediate gap number;

C3) take step b3) in criterion be foundation, traversal all sequences { f ₁, f ₂, f ₃..., f _j..., f _n, the region of removing discontented sufficient shape facility 3, describes after processing through shape facility 3, and insulator regional connectivity is as a whole, grows into the large region in full figure.

Described step 3) concrete steps are:

31) through step 2) shape facility treatment step after, there is large area UNICOM region in insulator chain position, and there is the nonisulated sub-goal that a lot of areas are less other position; Design suitable threshold value calculation method and ask for threshold value, delete the region that area is less than threshold value, obtain only comprising the bianry image of insulator chain information;

32) adopt minimum boundary rectangle to target mark frame, gained rectangle frame is insulator position;

33) rectangle frame is marked in original image, obtains the final positioning result automatically of insulator chain.

Described step 31) in, the calculating of threshold value adopts maximum region correlation method, and step is as follows:

311) calculate the area of regional, record the numerical value p in 4 regions of area maximum ₁, p ₂, p ₃, p ₄;

312) calculate the average of above-mentioned 4 areas

313) according to formula (5) calculated threshold s;

$s=\stackrel{\&OverBar;}{p}\&times;\frac{a}{m\&times;n}---\left(5\right)$

In formula: m is bianry image line number, and n is columns, a is area ratio coefficient.

The beneficial effect of the invention: compared with the conventional method, the present invention takes full advantage of the shape facility that insulator chain exists, and then adopts the method for describing based on bianry image shape facility, has solved the problem of insulator chain location difficulty in complex background Aerial Images; This invention is practical, and has obtained good locating effect, and required time is short, without artificial participation, the conceptual design of relevant issues is had to certain reference.

Accompanying drawing explanation

Fig. 1 is the process flow diagram that the present invention is based on the insulator chain automatic positioning method of taking photo by plane of bianry image shape facility;

Fig. 2 (a) is original Aerial Images;

Fig. 2 (b) is by the image after original Aerial Images binaryzation;

Fig. 2 (c) is morphologic filtering result figure;

Fig. 2 (d) removes zonule aftertreatment result figure;

Fig. 3 (a) is step 2) middle feature 1 description and result figure;

Fig. 3 (b) is step 2) middle feature 2 description and result figure;

Fig. 3 (c) is step 2) middle feature 3 description and result figure;

Fig. 4 (a) is step 3) in remove behind zonule, and with the image of minimum boundary rectangle mark;

Fig. 4 (b) is presented at minimum boundary rectangle frame in original-gray image, the positioning result image obtaining.

Embodiment

In order to understand better technical scheme of the present invention, below in conjunction with accompanying drawing, the present invention is further illustrated.

The whole flow process of the insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility can represent with Fig. 1.The method concrete steps are as follows:

1) bianry image is carried out to Mathematical morphology filter and involve the processing of removal zonule;

Concrete steps are:

11) first the insulator image of taking photo by plane after binaryzation is carried out to morphological erosion computing, at very thin some place separating objects, remove the noise of minimum area;

12) carry out again morphological dilations computing, fill up target internal cavity, the border of level and smooth larger object; Wherein, for fully level and smooth object boundary, in conjunction with insulator umbrella disk shape, selecting the form parameter of filtering is " circle ".

13) after twice morphology operations, remain some zonules, remove region area and be less than m * n * 1.5 * 10 ^-5region, m wherein, n is respectively line number and the columns of bianry image.

2) 3 of insulator chain shape facilities are carried out to digitized description, on this basis image is processed, remove the region that does not meet 3 shape facilities, retain the region that meets 3 shape facilities;

Wherein, 3 of insulator chain shape facilities are:

Shape facility 1: insulator chain comprises several umbrella disks, and each umbrella disk thickness is close;

Shape facility 2: the thickness at umbrella disk edge is less than the thickness at center, increases gradually from edge to center thickness;

Shape facility 3: spacing distance between each umbrella disk is less and numerical value is close.

Described step 2) concrete steps are:

21) employing figure-number conversion method is carried out digitized description by shape facility, and the desired value in bianry image is made as to 1, and background value is made as 0, extracts target information;

22) each row of image are extracted respectively, obtain n group and only comprise 0 and 1 Serial No. { l ₁, l ₂,, l ₃..., l _j..., l _n;

23) these Serial No.s are carried out to shape facility description, from sequence, remove nonisulated sub-goal, then sequence is converted into matrix, reconstruct bianry image.

Wherein, to the description of shape facility 1 and be treated to:

A1) at sequence l _jmiddle search becomes 0 pixel from 1, the position of the pixel that record value is 0, and this point is marginal point;

B1) add up this marginal point number of continuous 1 before, be designated as O, establishing marginal point has s, records s O value { O ₁, O ₂, O ₃..., O _i..., O _s;

$\left\{\begin{array}{c}s\&GreaterEqual;N_{\min }\\ |O_i-O_{i+1}|<m\&times;t_1\end{array}\right.---\left(1\right)$

In formula: m is bianry image line number, t ₁umbrella disk thickness coefficient, N _minit is the minimum value of umbrella disk number in insulator chain;

When ordered series of numbers meets formula (1) conditional, think that this position marginal point belongs to true marginal point, retains this dot information; If do not meet, think that s point belongs to pseudo-edge point, carry out " removal " operation;

C1) take step b1) in criterion be foundation, traversal all sequences { l ₁, l ₂,, l ₃..., l _j..., l _n, the region of removing discontented sufficient shape facility 1.

To the description of shape facility 2 and be treated to:

A2) after shape facility 1 is processed, image becomes a plurality of non-UNICOMs region, and She Fei UNICOM region has u, by All Ranges numbering 1,2,3 ..., i ..., u;

B2), for each region, to add up every train value be 1 number and save as vector, is designated as G={ G ₁, G ₂, G ₃..., G _i... G _p, vectorial G _imiddle element is the length of these every row in region, and p is the non-zero columns in this region; In calculating G, element is poor, and obtaining length is the vectorial H of p-1, as shown in formula (2):

H _i=G _i+1-G _i (2)

In formula (2), if element H in H _isymbol is equal timing, and it is large that the thickness in this region becomes gradually; If element H in H _isymbol is when all negative, and the thickness in this region diminishes gradually, thereby tentatively judges that this region belongs to insulator, retains this area information;

C2) according to sequence l _jin first value be that nonisulated sub-goal is further removed in the position of 1 appearance, for each region, adding up each, to be listed as first value be 1 position record, J={ J ₁, J ₂, J ₃..., J _i..., J _p; In calculating J, element is poor, and obtaining length is the vectorial K of p-1,

K _i=J _i+1-J _i (3)

In formula (2) and (3), element H in H _isymbol is equal timing, and K should meet all negative; Element H in H _isymbol is when all negative, and K just should meet all; When region i meets above-mentioned condition, judge that this region belongs to insulator umbrella disc portion, retains this region;

D2) take step b2) and c2) in criterion be foundation, travel through all u region, remove the region of being discontented with sufficient shape facility 2.

To the description of shape facility 3 and be treated to:

A3) image of shape facility 2 being processed again carries out figure-number conversion and obtains n group 0,1 Serial No. { f ₁, f ₂, f ₃..., f _j..., f _n, the columns that n is image;

B3) at sequence f _jin, search becomes 1 pixel from 0, and continuous 0 number is added up before the point that these marks cross in this position of mark, is designated as R; If gauge point has w, record w R value { R ₁, R ₂, R ₃..., R _i... R _w;

When R meets formula (4) conditional, think that this position belongs to the gap of insulator umbrella disk, is set to 1 by this position; Work as w<V _mintime think that this position does not belong to insulator,

$\left\{\begin{array}{c}w\&GreaterEqual;V_{\min }\\ |R_i-R_{i+1}|<m\&times;t_2\end{array}\right.---\left(4\right)$

In formula: m is bianry image line number, t ₂umbrella disk spread ratio, V _minthe minimum value that represents insulator chain intermediate gap number;

C3) take step b3) in criterion be foundation, traversal all sequences { f ₁, f ₂, f ₃..., f _j..., f _n, the region of removing discontented sufficient shape facility 3, describes after processing through shape facility 3, and insulator regional connectivity is as a whole, grows into the large region in full figure.

3) adopt the region that meets insulator chain shape facility in minimum boundary rectangle marking image, realize location.

Concrete steps are:

31) through step 2) shape facility treatment step after, there is large area UNICOM region in insulator chain position, and there is the nonisulated sub-goal that a lot of areas are less other position; Design suitable threshold value calculation method and ask for threshold value, delete the region that area is less than threshold value, obtain only comprising the bianry image of insulator chain information;

Wherein the calculating of threshold value adopts maximum region correlation method, and step is as follows:

311) calculate the area of regional, record the numerical value p in 4 regions of area maximum ₁, p ₂, p ₃, p ₄;

312) calculate the average of above-mentioned 4 areas

313) according to formula (5) calculated threshold s;

$s=\stackrel{\&OverBar;}{p}\&times;\frac{a}{m\&times;n}---\left(5\right)$

In formula: m is bianry image line number, and n is columns, a is area ratio coefficient.

32) adopt minimum boundary rectangle to target mark frame, gained rectangle frame is insulator position;

33) rectangle frame is marked in original image, obtains the final positioning result automatically of insulator chain.

Embodiment

Use the insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility to process true Aerial Images.Original image is as shown in Fig. 2 (a), and size is 640 * 353, and the image after binaryzation is as Fig. 2 (b); First adopt morphologic filtering method to carry out filtering, result, as Fig. 2 (c), is removed the region that area is less than setting value, and result is as Fig. 2 (d); Then carry out insulator chain shape facility digitized description, the result of feature 1, feature 2 and feature 3 is respectively as Fig. 3 (a), Fig. 3 (b), Fig. 3 (c); Adopt again maximum region correlation method calculated threshold, remove the region that area is less than threshold value, retain large area region, and with minimum boundary rectangle mark, result is as shown in Fig. 4 (a); Finally, rectangle posting is presented in original image, realizes insulator chain and automatically locate, result is as Fig. 4 (b).

The above; be only the present invention's embodiment preferably, but protection scope of the present invention is not limited to this, is anyly familiar with in technical scope that those skilled in the art disclose in the present invention; the variation that can expect easily or replacement, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.

Claims (9)

1. the insulator chain automatic positioning method based on bianry image shape facility, is characterized in that, the method concrete steps are as follows:

1) bianry image is carried out to Mathematical morphology filter and involve the processing of removal zonule;

2) 3 of insulator chain shape facilities are carried out to digitized description, on this basis image is processed, remove the region that does not meet 3 shape facilities, retain the region that meets 3 shape facilities;

3) adopt the region that meets insulator chain shape facility in minimum boundary rectangle marking image, realize location.

2. the insulator chain automatic positioning method based on bianry image shape facility according to claim 1, is characterized in that described step 1) concrete steps be:

11) first the insulator image of taking photo by plane after binaryzation is carried out to morphological erosion computing, at very thin some place separating objects, remove the noise of minimum area;

12) carry out again morphological dilations computing, fill up target internal cavity, the border of level and smooth larger object; Wherein, in order better to reach the object of fully level and smooth object boundary, selecting the form parameter of filtering is " circle ";

13) after twice morphology operations, remain some zonules, remove region area and be less than m * n * 1.5 * 10 ^-5region, m wherein, n is respectively line number and the columns of bianry image.

3. the insulator chain automatic positioning method based on bianry image shape facility according to claim 1, is characterized in that described step 2) in 3 shape facilities of insulator chain be:

Shape facility 1: insulator chain comprises several umbrella disks, and each umbrella disk thickness equates;

Shape facility 2: the thickness at umbrella disk edge is less than the thickness at center, increases gradually from edge to center thickness;

Shape facility 3: the less and numerical value of spacing distance between each umbrella disk equates.

4. the insulator chain automatic positioning method based on bianry image shape facility according to claim 1, is characterized in that described step 2) concrete steps be:

21) employing figure-number conversion method is carried out digitized description by shape facility, and the desired value in bianry image is made as to 1, and background value is made as 0, extracts target information;

22) each row of image are extracted respectively, obtain n group and only comprise 0 and 1 Serial No. { l ₁, l ₂,, l ₃..., l _j..., l _n, the columns that n is image;

23) these Serial No.s are carried out to shape facility description, from sequence, remove nonisulated sub-goal, then sequence is converted into matrix, reconstruct bianry image.

5. according to the insulator chain automatic positioning method based on bianry image shape facility described in claim 3 or 4, it is characterized in that described step 23) in to the description of shape facility 1 and be treated to:

A1) at sequence l _jmiddle search becomes 0 pixel from 1, the position of the pixel that record value is 0, and this point is marginal point;

B1) add up this marginal point number of continuous 1 before, be designated as O, establishing marginal point has s, records s O value { O ₁, O ₂, O ₃..., O _i..., O _s;

$\left\{\begin{array}{c}s\&GreaterEqual;N_{\min }\\ |O_i-O_{i+1}|<m\&times;t_1\end{array}\right.---\left(1\right)$

In formula: m is bianry image line number, t ₁umbrella disk thickness coefficient, N _minit is the minimum value of umbrella disk number in insulator chain;

When ordered series of numbers meets formula (1), think that this position marginal point belongs to true marginal point, retains this dot information; If do not meet, think that this position marginal point belongs to pseudo-edge point, carry out " removal " operation;

C1) take step b1) in criterion be foundation, traversal all sequences { l ₁, l ₂,, l ₃..., l _j..., l _n, the region of removing discontented sufficient shape facility 1.

6. according to the insulator chain automatic positioning method based on bianry image shape facility described in claim 3 or 4, it is characterized in that described step 23) in to the description of shape facility 2 and be treated to:

A2) after shape facility 1 is processed, image becomes a plurality of non-UNICOMs region, and She Fei UNICOM region has u, by All Ranges numbering 1,2,3 ..., i ..., u;

B2), for each region, to add up every train value be 1 number and save as vector, is designated as G={ G ₁, G ₂, G ₃..., G _i... G _p, vectorial G _imiddle element is the length of these every row in region, and p is the non-zero columns in this region; In calculating G, element is poor, and obtaining length is the vectorial H of p-1, as shown in formula (2):

H _i=G _i+1-G _i (2)

In formula (2), if element H in H _isymbol is equal timing, and it is large that the thickness in this region becomes gradually; If element H in H _isymbol is when all negative, and the thickness in this region diminishes gradually, thereby tentatively judges that this region belongs to insulator, retains this area information;

C2) according to sequence l _jin first value be that nonisulated sub-goal is further removed in the position of 1 appearance, for each region, adding up each, to be listed as first value be 1 position record, J={ J ₁, J ₂, J ₃..., J _i..., J _p; In calculating J, element is poor, and obtaining length is the vectorial K of p-1 _i, as shown in formula (3):

K _i=J _i+1-J _i (3)

In formula (2) and (3), element H in H _isymbol is equal timing, K _ishould meet all negative; Element H in H _isymbol when all negative, K _iall just should meet; When region i meets above-mentioned condition, judge that this region belongs to insulator umbrella disc portion, retains this region;

D2) take step b2) and c2) in criterion be foundation, travel through all u region, remove the region of being discontented with sufficient shape facility 2.

7. according to the insulator chain automatic positioning method based on bianry image shape facility described in claim 3 or 4, it is characterized in that described step 23) in to the description of shape facility 3 and be treated to:

A3) image of shape facility 2 being processed again carries out figure-number conversion and obtains n group 0,1 Serial No. { f ₁, f ₂, f ₃..., f _j..., f _n, the columns that n is image;

B3) at sequence f _jin, search becomes 1 pixel from 0, and continuous 0 number is added up before the point that these marks cross in this position of mark, is designated as R; If gauge point has w, record w R value { R ₁, R ₂, R ₃..., R _i... R _w;

When R meets formula (4) conditional, think that this position belongs to the gap of insulator umbrella disk, is set to 1 by this position; Work as w<V _mintime think that this position does not belong to insulator,

$\left\{\begin{array}{c}w\&GreaterEqual;V_{\min }\\ |R_i-R_{i+1}|<m\&times;t_2\end{array}\right.---\left(4\right)$

In formula: m is bianry image line number, t ₂umbrella disk spread ratio, V _minthe minimum value that represents insulator chain intermediate gap number;

C3) take step b3) in criterion be foundation, traversal all sequences { f ₁, f ₂, f ₃..., f _j..., f _n, the region of removing discontented sufficient shape facility 3, describes after processing through shape facility 3, and insulator regional connectivity is as a whole, grows into the large region in full figure.

8. the insulator chain automatic positioning method based on bianry image shape facility according to claim 1, is characterized in that described step 3) concrete steps be:

31) through step 2) shape facility treatment step after, there is large area UNICOM region in insulator chain position, and there is the nonisulated sub-goal that a lot of areas are less other position; Design suitable threshold value calculation method and ask for threshold value, delete the region that area is less than threshold value, obtain only comprising the bianry image of insulator chain information;

32) adopt minimum boundary rectangle to target mark frame, gained rectangle frame is insulator position;

33) rectangle frame is marked in original image, obtains the final positioning result automatically of insulator chain.

9. the insulator chain automatic positioning method based on bianry image shape facility according to claim 8, is characterized in that described step 31) in the calculating of threshold value adopt maximum region correlation method, step is as follows:

311) calculate the area of regional, record the numerical value p in 4 regions of area maximum ₁, p ₂, p ₃, p ₄;

312) calculate the average of above-mentioned 4 areas

313) according to formula (5) calculated threshold s;

$s=\stackrel{\&OverBar;}{p}\&times;\frac{a}{m\&times;n}---\left(5\right)$

In formula: m is bianry image line number, and n is columns, a is area ratio coefficient.

Images