CN103714342B - Insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility - Google Patents
Insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility Download PDFInfo
- Publication number
- CN103714342B CN103714342B CN201310711333.0A CN201310711333A CN103714342B CN 103714342 B CN103714342 B CN 103714342B CN 201310711333 A CN201310711333 A CN 201310711333A CN 103714342 B CN103714342 B CN 103714342B
- Authority
- CN
- China
- Prior art keywords
- region
- shape facility
- insulator chain
- image
- bianry image
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses and belong to image processing techniques and a kind of based on bianry image shape facility the insulator chain automatic positioning method in power transmission and transforming equipment running status maintenance field, the method concretely comprises the following steps: bianry image 1) carries out Mathematical morphology filter and involves the process of removal zonule；2) 3 shape facilities to insulator chain are digitized describing, and process image on this basis, remove the region being unsatisfactory for 3 shape facilities, retain the region meeting 3 shape facilities；3) employing minimum enclosed rectangle labelling image meets the region of insulator chain shape facility, it is achieved location.The present invention takes full advantage of the shape facility that insulator chain exists, and then uses the method described based on bianry image shape facility, solves the problem of insulator chain location difficulty in complex background Aerial Images；This invention is practical, and achieves preferable locating effect, and required time is short, it is not necessary to manually participate in, and the conceptual design of relevant issues is had certain reference.
Description
Technical field
The invention belongs to image processing techniques and power transmission and transforming equipment running status maintenance field, particularly to a kind of insulator chain automatic positioning method based on bianry image shape facility.
Background technology
Positioning target interested in image is the key technology in the field such as image procossing, computer vision, its objective is to extract some the important goal position information in image, thus lays the foundation for this target recognition and subsequent treatment.It is to realize insulator state monitoring and the important prerequisite of fault diagnosis that insulator chain of taking photo by plane is automatically positioned, and has important practical significance.
Existing localization method generally has 3 classes: original image, based on the method split, is divided into multiple region, and the region that labelling is interested by (1)；The method there is problems of the tonal gradation needing manually to arrange target place, and positioning precision is low, is applied in automatic monitoring more difficulty.(2) method based on rim detection, finds the profile of interesting target, it is achieved location；The method there is problems of noise-sensitive, and the Aerial Images accuracy complicated for background, resolution is low, noise is higher is relatively low, and owing to background is complicated, the reasons such as edge variation is various cause the speed of service slow.(3) method based on texture, analyzes the textural characteristics of interesting target, and is extracted target location as criterion；The problem of the method maximum is to extract texture information to need the plenty of time, and is difficult to differentiate between for some pseudo-target close with insulator chain textural characteristics.
Existing method does not accounts for the unique shape feature in insulator chain bianry image after singulation.The targets such as insulator chain and tower bar, circuit have obvious shape difference, and after binaryzation, this shape facility is more prominent, if it can be used, can improve positioning precision, reduce time-consuming, improve automatization's performance.
Summary of the invention
The problem existed 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 characterised in that the method specifically comprises the following steps that
1) bianry image is carried out Mathematical morphology filter and involves the process of removal zonule；
2) 3 shape facilities to insulator chain are digitized describing, and process image on this basis, remove the region being unsatisfactory for 3 shape facilities, retain the region meeting 3 shape facilities；
3) employing minimum enclosed rectangle labelling image meets the region of insulator chain shape facility, it is achieved location.
Described step 1) concretely comprise the following steps:
11) first the insulator image of taking photo by plane after binaryzation is carried out morphological erosion computing, separating objects at very thin point, remove the noise of minimum area；
12) carry out morphological dilations computing again, fill up target internal cavity, the border of smooth larger object；Wherein, in order to preferably reach fully to smooth the purpose of object boundary, the form parameter selecting filtering is " circular "；
13) after twice morphology operations, remain some zonules, remove region area less than m × n × 1.5 × 10-5Region, wherein m, n are respectively line number and the columns of bianry image.
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 is equal；
Shape facility 2: the thickness at umbrella disk edge, less than the thickness at center, is gradually increased from edge to center thickness；
Shape facility 3: the spacing distance between each umbrella disk is less and numerical value is equal.
Described step 2) concretely comprise the following steps:
21) shape facility is digitized describing by employing figure-number conversion method, and the desired value in bianry image is set to 1, and background value is set to 0, extracts target information；
22) every string of image is extracted respectively, obtain the Serial No. { l that n group only comprises 0 and 11, l2, l3..., lj..., ln, n is the columns of image；
23) these Serial No.s are carried out shape facility description, from sequence, remove nonisulated sub-goal, then by Sequence Transformed for matrix, reconstruct bianry image.
Described step 23) in the description of shape facility 1 and be processed as:
A1) in sequence ljMiddle search is become the pixel of 0 from 1, and record value is the position of the pixel of 0, and this point is marginal point；
B1) before adding up this marginal point, the number of continuous 1, is designated as O, if marginal point has s, then and s O value { O of record1, O2, O3..., Oi..., Os}；
In formula: m is bianry image line number, t1It is umbrella disk thickness coefficient, NminIt it is the minima of umbrella disk number in insulator chain；
When ordered series of numbers meets formula (1), it is believed that this position marginal point belongs to true marginal point, retains this dot information；If being unsatisfactory for, then it is assumed that this position marginal point belongs to pseudo-edge point, perform " removal " operation；
C1) with step b1) in criterion as foundation, travel through all sequences { l1, l2, l3..., lj..., ln, remove the region being unsatisfactory for shape facility 1.
Described step 23) in the description of shape facility 2 and be processed as:
A2) after shape facility 1 processes, image becomes multiple non-interconnected region, if there is u in non-interconnected region, by all zone numbers 1, and 2,3 ..., i ..., u；
B2) for each region, add up number that every train value is 1 and save as vector, being designated as G={G1, G2, G3..., Gi... Gp, vector GiMiddle element is the length of this region each column, and p is the non-zero columns in this region；Calculate the difference of element in G, obtain the vectorial H of a length of p-1, as shown in formula (2):
Hi=Gi+1-Gi (2)
In formula (2), if element H in HiSymbol is equal timing, and the thickness in this region becomes larger；If element H in HiWhen symbol is for all bearing, the thickness in this region tapers into, thus tentatively judges that this region belongs to insulator, retains this area information；
C2) according to sequence ljIn first value be that the position of 1 appearance removes nonisulated sub-goal further, for each region, add up position record that the first value of every string is 1, J={J1, J2, J3..., Ji..., Jp}；Calculate the difference of element in J, obtain the vectorial K of a length of p-1, as shown in formula (3):
Ki=Ji+1-Ji (3)
In formula (2) and (3), as element H in HiSymbol is equal timing, KiShould meet the most negative；As element H in HiWhen symbol is for all bearing, KiThe most just should meet；When region i meets above-mentioned condition, it is judged that this region belongs to insulator umbrella disc portion, retain this region；
D2) with step b2) and c2) in criterion as foundation, travel through all u regions, remove the region being unsatisfactory for shape facility 2.
Described step 23) in the description of shape facility 3 and be processed as:
A3) image processing shape facility 2 again carries out figure-number conversion and obtains n group 0,1 Serial No. { f1, f2, f3..., fj..., fn, n is the columns of image；
B3) in sequence fjIn, search is become the pixel of 1, this position of labelling from 0, adds up the number of continuous 0 before these labeled points, is designated as R；Bidding note point has w, then w R value { R of record1, R2, R3..., Ri... Rw}；
When R meets formula (4) conditional, it is believed that this position belongs to the gap of insulator umbrella disk, and this position is set to 1；As w < VminTime think that this position is not belonging to insulator,
In formula: m is bianry image line number, t2It is umbrella disk spread ratio, VminRepresent the minima of insulator chain intermediate gap number；
C3) with step b3) in criterion as foundation, travel through all sequences { f1, f2, f3..., fj..., fn, remove the region being unsatisfactory for shape facility 3, after shape facility 3 description processes, insulator regional connectivity is an entirety, grows into the big region in full figure.
Described step 3) concretely comprise the following steps:
31) through step 2) shape facility process after step, there is large area connected region in insulator chain position, and there is the nonisulated sub-goal that a lot of area is less other position；Design suitable threshold value calculation method and ask for threshold value, delete the area region less than threshold value, only comprised the bianry image of insulator chain information；
32) using minimum enclosed rectangle to target mark frame, gained rectangle frame is insulator position；
33) being marked in original image by rectangle frame, obtain insulator chain is finally automatically positioned result.
Described step 31) in threshold value calculating use maximum region method of correlation, step is as follows:
311) area of regional, the numerical value p in 4 regions that record area is maximum are calculated1, p2, p3, p4；
312) average of above-mentioned 4 areas is calculated
313) threshold value s is calculated according to formula (5)；
In formula: m is bianry image line number, n is columns, and 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 uses the method described based on bianry image shape facility, solves the problem of insulator chain location difficulty in complex background Aerial Images；This invention is practical, and achieves preferable locating effect, and required time is short, it is not necessary to manually participate in, and the conceptual design of relevant issues is had certain reference.
Accompanying drawing explanation
Fig. 1 is the flow chart of present invention insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility；
Fig. 2 (a) is original Aerial Images；
Fig. 2 (b) be by original Aerial Images binaryzation after image；
Fig. 2 (c) is morphologic filtering result figure；
Fig. 2 (d) is to remove zonule post processing result figure；
Fig. 3 (a) is step 2) in feature 1 describe and result figure；
Fig. 3 (b) is step 2) in feature 2 describe and result figure；
Fig. 3 (c) is step 2) in feature 3 describe and result figure；
Fig. 4 (a) is step 3) in remove behind zonule, and with the image of minimum enclosed rectangle labelling；
Fig. 4 (b) is to show in original-gray image by minimum enclosed rectangle frame, the positioning result image obtained.
Detailed description of the invention
In order to be more fully understood that technical scheme, the present invention is further illustrated below in conjunction with the accompanying drawings.
The whole flow process taking photo by plane insulator chain automatic positioning method based on bianry image shape facility can represent with Fig. 1.The method specifically comprises the following steps that
1) bianry image is carried out Mathematical morphology filter and involves the process of removal zonule；
Concretely comprise the following steps:
11) first the insulator image of taking photo by plane after binaryzation is carried out morphological erosion computing, separating objects at very thin point, remove the noise of minimum area；
12) carry out morphological dilations computing again, fill up target internal cavity, the border of smooth larger object；Wherein, for the most smooth object boundary, in conjunction with insulator umbrella disk shape, the form parameter selecting filtering is " circular ".
13) after twice morphology operations, remain some zonules, remove region area less than m × n × 1.5 × 10-5Region, wherein m, n are respectively line number and the columns of bianry image.
2) 3 shape facilities to insulator chain are digitized describing, and process image on this basis, remove the region being unsatisfactory for 3 shape facilities, retain the region meeting 3 shape facilities；
Wherein, 3 shape facilities of insulator chain 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, less than the thickness at center, is gradually increased from edge to center thickness；
Shape facility 3: the spacing distance between each umbrella disk is less and numerical value is close.
Described step 2) concretely comprise the following steps:
21) shape facility is digitized describing by employing figure-number conversion method, and the desired value in bianry image is set to 1, and background value is set to 0, extracts target information；
22) every string of image is extracted respectively, obtain the Serial No. { l that n group only comprises 0 and 11, l2, l3..., lj..., ln}；
23) these Serial No.s are carried out shape facility description, from sequence, remove nonisulated sub-goal, then by Sequence Transformed for matrix, reconstruct bianry image.
Wherein, to the description of shape facility 1 and be processed as:
A1) in sequence ljMiddle search is become the pixel of 0 from 1, and record value is the position of the pixel of 0, and this point is marginal point；
B1) before adding up this marginal point, the number of continuous 1, is designated as O, if marginal point has s, then and s O value { O of record1, O2, O3..., Oi..., Os}；
In formula: m is bianry image line number, t1It is umbrella disk thickness coefficient, NminIt it is the minima of umbrella disk number in insulator chain；
When ordered series of numbers meets formula (1) conditional, it is believed that this position marginal point belongs to true marginal point, retains this dot information；If being unsatisfactory for, then it is assumed that s point belongs to pseudo-edge point, perform " removal " operation；
C1) with step b1) in criterion as foundation, travel through all sequences { l1, l2, l3..., lj..., ln, remove the region being unsatisfactory for shape facility 1.
To the description of shape facility 2 and be processed as:
A2) after shape facility 1 processes, image becomes multiple non-interconnected region, if there is u in non-interconnected region, by all zone numbers 1, and 2,3 ..., i ..., u；
B2) for each region, add up number that every train value is 1 and save as vector, being designated as G={G1, G2, G3..., Gi... Gp, vector GiMiddle element is the length of this region each column, and p is the non-zero columns in this region；Calculate the difference of element in G, obtain the vectorial H of a length of p-1, as shown in formula (2):
Hi=Gi+1-Gi (2)
In formula (2), if element H in HiSymbol is equal timing, and the thickness in this region becomes larger；If element H in HiWhen symbol is for all bearing, the thickness in this region tapers into, thus tentatively judges that this region belongs to insulator, retains this area information；
C2) according to sequence ljIn first value be that the position of 1 appearance removes nonisulated sub-goal further, for each region, add up position record that the first value of every string is 1, J={J1, J2, J3..., Ji..., Jp}；Calculate the difference of element in J, obtain the vectorial K of a length of p-1,
Ki=Ji+1-Ji (3)
In formula (2) and (3), as element H in HiSymbol is equal timing, and K should meet the most negative；As element H in HiWhen symbol is for all bearing, K the most just should meet；When region i meets above-mentioned condition, it is judged that this region belongs to insulator umbrella disc portion, retain this region；
D2) with step b2) and c2) in criterion as foundation, travel through all u regions, remove the region being unsatisfactory for shape facility 2.
To the description of shape facility 3 and be processed as:
A3) image processing shape facility 2 again carries out figure-number conversion and obtains n group 0,1 Serial No. { f1, f2, f3..., fj..., fn, n is the columns of image；
B3) in sequence fjIn, search is become the pixel of 1, this position of labelling from 0, adds up the number of continuous 0 before these labeled points, is designated as R；Bidding note point has w, then w R value { R of record1, R2, R3..., Ri... Rw}；
When R meets formula (4) conditional, it is believed that this position belongs to the gap of insulator umbrella disk, and this position is set to 1；As w < VminTime think that this position is not belonging to insulator,
In formula: m is bianry image line number, t2It is umbrella disk spread ratio, VminRepresent the minima of insulator chain intermediate gap number；
C3) with step b3) in criterion as foundation, travel through all sequences { f1, f2, f3..., fj..., fn, remove the region being unsatisfactory for shape facility 3, after shape facility 3 description processes, insulator regional connectivity is an entirety, grows into the big region in full figure.
3) employing minimum enclosed rectangle labelling image meets the region of insulator chain shape facility, it is achieved location.
Concretely comprise the following steps:
31) through step 2) shape facility process after step, there is large area connected region in insulator chain position, and there is the nonisulated sub-goal that a lot of area is less other position；Design suitable threshold value calculation method and ask for threshold value, delete the area region less than threshold value, only comprised the bianry image of insulator chain information；
Wherein the calculating of threshold value uses maximum region method of correlation, and step is as follows:
311) area of regional, the numerical value p in 4 regions that record area is maximum are calculated1, p2, p3, p4；
312) average of above-mentioned 4 areas is calculated
313) threshold value s is calculated according to formula (5)；
In formula: m is bianry image line number, n is columns, and a is area ratio coefficient.
32) using minimum enclosed rectangle to target mark frame, gained rectangle frame is insulator position；
33) being marked in original image by rectangle frame, obtain insulator chain is finally automatically positioned result.
Embodiment
With insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility, true Aerial Images is processed.Shown in original image such as Fig. 2 (a), size is 640 × 353, the such as Fig. 2 (b) of the image after binaryzation；It is filtered initially with morphologic filtering method, result such as Fig. 2 (c), removes the area region less than setting value, result such as Fig. 2 (d)；Then carrying out insulator chain shape facility digitized description, the result of feature 1, feature 2 and feature 3 is respectively such as Fig. 3 (a), Fig. 3 (b), Fig. 3 (c)；Use maximum region method of correlation to calculate threshold value again, remove the area region less than threshold value, retain large area region, and use minimum enclosed rectangle labelling, shown in result such as Fig. 4 (a)；Finally, rectangle posting is shown in original image, it is achieved insulator chain is automatically positioned, result such as Fig. 4 (b).
The above; being only the present invention preferably detailed description of the invention, but protection scope of the present invention is not limited thereto, any those familiar with the art is in the technical scope that the invention discloses; the change that can readily occur in or replacement, all should contain within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with scope of the claims.
Claims (6)
1. insulator chain automatic positioning method based on bianry image shape facility, it is characterised in that the method specifically comprises the following steps that
1) bianry image is carried out Mathematical morphology filter and involves the process of removal zonule；
2) 3 shape facilities to insulator chain are digitized describing, and process image on this basis, remove the region being unsatisfactory for 3 shape facilities, retain the region meeting 3 shape facilities；
3) employing minimum enclosed rectangle labelling image meets the region of insulator chain shape facility, it is achieved location；
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 is equal；
Shape facility 2: the thickness at umbrella disk edge, less than the thickness at center, is gradually increased from edge to center thickness；
Shape facility 3: the spacing distance between each umbrella disk is less and numerical value is equal；
Described step 2) concretely comprise the following steps:
21) shape facility is digitized describing by employing figure-number conversion method, and the desired value in bianry image is set to 1, and background value is set to 0, extracts target information；
22) every string of image is extracted respectively, obtain the Serial No. { l that n group only comprises 0 and 11, l2, l3..., lj..., ln, n is the columns of image；
23) these Serial No.s are carried out shape facility description, from sequence, remove nonisulated sub-goal, then by Sequence Transformed for matrix, reconstruct bianry image；
Described step 23) in the description of shape facility 1 and be processed as:
A1) in sequence ljMiddle search is become the pixel of 0 from 1, and record value is the position of the pixel of 0, and this point is marginal point；
B1) before adding up this marginal point, the number of continuous 1, is designated as O, if marginal point has s, then and s O value { O of record1, O2, O3..., Oi..., Os}；
In formula: m is bianry image line number, t1It is umbrella disk thickness coefficient, NminIt it is the minima of umbrella disk number in insulator chain；
When ordered series of numbers meets formula (1), it is believed that this position marginal point belongs to true marginal point, retains this dot information；If being unsatisfactory for, then it is assumed that this position marginal point belongs to pseudo-edge point, perform " removal " operation；
C1) with step b1) in criterion as foundation, travel through all sequences { l1, l2, l3..., lj..., ln, remove the region being unsatisfactory for shape facility 1.
Insulator chain automatic positioning method based on bianry image shape facility the most according to claim 1, it is characterised in that described step 1) concretely comprise the following steps:
11) first the insulator image of taking photo by plane after binaryzation is carried out morphological erosion computing, separating objects at very thin point, remove the noise of minimum area；
12) carry out morphological dilations computing again, fill up target internal cavity, the border of smooth larger object；Wherein, in order to preferably reach fully to smooth the purpose of object boundary, the form parameter selecting filtering is " circular "；
13) after twice morphology operations, remain some zonules, remove region area less than m × n × 1.5 × 10-5Region, wherein m, n are respectively line number and the columns of bianry image.
Insulator chain automatic positioning method based on bianry image shape facility the most according to claim 1, it is characterised in that described step 23) in the description of shape facility 2 and be processed as:
A2) after shape facility 1 processes, image becomes multiple non-interconnected region, if there is u in non-interconnected region, by all zone numbers 1, and 2,3 ..., i ..., u；
B2) for each region, add up number that every train value is 1 and save as vector, being designated as G={G1, G2, G3..., Gi... Gp, vector GiMiddle element is the length of this region each column, and p is the non-zero columns in this region；Calculate the difference of element in G, obtain the vectorial H of a length of p-1, as shown in formula (2):
Hi=Gi+1-Gi (2)
In formula (2), if element H in HiSymbol is equal timing, and the thickness in this region becomes larger；If element H in HiWhen symbol is for all bearing, the thickness in this region tapers into, thus tentatively judges that this region belongs to insulator, retains this area information；
C2) according to sequence ljIn first value be that the position of 1 appearance removes nonisulated sub-goal further, for each region, add up position record that the first value of every string is 1, J={J1, J2, J3..., Ji..., Jp}；Calculate the difference of element in J, obtain the vectorial K of a length of p-1i, as shown in formula (3):
Ki=Ji+1-Ji (3)
In formula (2) and (3), as element H in HiSymbol is equal timing, KiShould meet the most negative；As element H in HiWhen symbol is for all bearing, KiThe most just should meet；When region i meets above-mentioned condition, it is judged that this region belongs to insulator umbrella disc portion, retain this region；
D2) with step b2) and c2) in criterion as foundation, travel through all u regions, remove the region being unsatisfactory for shape facility 2.
Insulator chain automatic positioning method based on bianry image shape facility the most according to claim 1, it is characterised in that described step 23) in the description of shape facility 3 and be processed as:
A3) image processing shape facility 2 again carries out figure-number conversion and obtains n group 0,1 Serial No. { f1, f2, f3..., fj..., fn, n is the columns of image；
B3) in sequence fjIn, search is become the pixel of 1, this position of labelling from 0, adds up the number of continuous 0 before these labeled points, is designated as R；Bidding note point has w, then w R value { R of record1, R2, R3..., Ri..., Rw}；
When R meets formula (4) conditional, it is believed that this position belongs to the gap of insulator umbrella disk, and this position is set to 1；As w < VminTime think that this position is not belonging to insulator,
In formula: m is bianry image line number, t2It is umbrella disk spread ratio, VminRepresent the minima of insulator chain intermediate gap number；
C3) with step b3) in criterion as foundation, travel through all sequences { f1, f2, f3..., fj..., fn, remove the region being unsatisfactory for shape facility 3, after shape facility 3 description processes, insulator regional connectivity is an entirety, grows into the big region in full figure.
Insulator chain automatic positioning method based on bianry image shape facility the most according to claim 1, it is characterised in that described step 3) concretely comprise the following steps:
31) through step 2) shape facility process after step, there is large area connected region in insulator chain position, and there is the nonisulated sub-goal that a lot of area is less other position；Ask for threshold value with threshold value calculation method, delete the area region less than threshold value, only comprised the bianry image of insulator chain information；
32) using minimum enclosed rectangle to target mark frame, gained rectangle frame is insulator position；
33) being marked in original image by rectangle frame, obtain insulator chain is finally automatically positioned result.
Insulator chain automatic positioning method based on bianry image shape facility the most according to claim 5, it is characterised in that described step 31) in threshold value calculating use maximum region method of correlation, step is as follows:
311) area of regional, the numerical value p in 4 regions that record area is maximum are calculated1, p2, p3, p4；
312) average of above-mentioned 4 areas is calculated
313) threshold value s is calculated according to formula (5)；
In formula: m is bianry image line number, n is columns, and a is area ratio coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310711333.0A CN103714342B (en) | 2013-12-20 | 2013-12-20 | Insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310711333.0A CN103714342B (en) | 2013-12-20 | 2013-12-20 | Insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103714342A CN103714342A (en) | 2014-04-09 |
| CN103714342B true CN103714342B (en) | 2016-10-05 |
Family
ID=50407299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310711333.0A Expired - Fee Related CN103714342B (en) | 2013-12-20 | 2013-12-20 | Insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103714342B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957077B (en) * | 2015-04-29 | 2019-01-15 | 国网河南省电力公司电力科学研究院 | The electric line foreign matter detection method of view-based access control model significance analysis |
| CN105069461B (en) * | 2015-07-24 | 2018-11-06 | 华北电力大学（保定） | Based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint |
| CN105957081B (en) * | 2016-04-28 | 2019-01-08 | 华北电力大学（保定） | A kind of glass insulator falls to go here and there fault detection method |
| CN108256517B (en) * | 2016-12-28 | 2021-05-28 | 深圳供电局有限公司 | Laser radar-based insulator string identification method |
| CN106980816B (en) * | 2017-02-22 | 2020-08-25 | 贵州电网有限责任公司凯里供电局 | Automatic insulator string identification method based on optical image |
| CN107492094A (en) * | 2017-07-21 | 2017-12-19 | 长安大学 | A kind of unmanned plane visible detection method of high voltage line insulator |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116747A (en) * | 2013-03-11 | 2013-05-22 | 山东农业大学 | Method and system for automatically recognizing images of stalks and leaves of corns |
| CN103136531A (en) * | 2013-03-26 | 2013-06-05 | 华北电力大学（保定） | Automatic identification method of insulator chain infrared image |
-
2013
- 2013-12-20 CN CN201310711333.0A patent/CN103714342B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116747A (en) * | 2013-03-11 | 2013-05-22 | 山东农业大学 | Method and system for automatically recognizing images of stalks and leaves of corns |
| CN103136531A (en) * | 2013-03-26 | 2013-06-05 | 华北电力大学（保定） | Automatic identification method of insulator chain infrared image |
Non-Patent Citations (2)
| Title |
|---|
| 图像处理技术在架空线路绝缘子破损检测系统中的应用研究;朱珠;《中国优秀硕士学位论文全文数据库信息科技辑》;20080915;摘要及第11-55页 * |
| 基于航拍图像的输电线路识别与状态检测方法研究;仝卫国;《中国博士学位论文全文数据库信息科技辑》;20120315;第66页第1行，第71页倒数第1-3行 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103714342A (en) | 2014-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103714342B (en) | Insulator chain automatic positioning method of taking photo by plane based on bianry image shape facility | |
| Zhao et al. | Localization of multiple insulators by orientation angle detection and binary shape prior knowledge | |
| CN104156951B (en) | A kind of white blood cell detection method for BAL fluid smear | |
| CN109816664B (en) | Three-dimensional point cloud segmentation method and device | |
| CN106447658A (en) | Significant target detection method based on FCN (fully convolutional network) and CNN (convolutional neural network) | |
| CN103295018B (en) | A kind of branches and leaves block fruit precise recognition method | |
| CN110334692B (en) | Blind road identification method based on image processing | |
| CN105741310A (en) | Heart's left ventricle image segmentation system and method | |
| CN109886937B (en) | Insulator defect detection method based on super-pixel segmentation image recognition | |
| Lin et al. | Image segmentation using the k-means algorithm for texture features | |
| CN110717900B (en) | Pantograph abrasion detection method based on improved Canny edge detection algorithm | |
| CN102609688A (en) | Multidirectional moving population flow estimation method on basis of generalized regression neural network | |
| CN109753969A (en) | A kind of insulator based on shape feature and image segmentation identifies and positions method | |
| CN116030396B (en) | Accurate segmentation method for video structured extraction | |
| CN113516105B (en) | Lane detection method and device and computer readable storage medium | |
| CN116704177B (en) | Gear box fault detection method based on image data | |
| CN105869174A (en) | Sky scene image segmentation method | |
| CN108734731B (en) | Machine vision-based quasi-circular particle target counting method | |
| CN107369162B (en) | Method and system for generating insulator candidate target area | |
| CN110443142B (en) | Deep learning vehicle counting method based on road surface extraction and segmentation | |
| CN102496146B (en) | Image segmentation method based on visual symbiosis | |
| CN112258552A (en) | Pedestrian multi-target tracking method under community monitoring scene | |
| Li et al. | A multi-stage approach for automatic classification of environmental microorganisms | |
| CN110853058A (en) | High-resolution remote sensing image road extraction method based on visual saliency detection | |
| CN111582251B (en) | Method for detecting passenger crowding degree of urban rail transit based on convolutional neural network |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161005 Termination date: 20211220 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |