CN109242880A - A kind of power line extraction method based on image procossing - Google Patents
A kind of power line extraction method based on image procossing Download PDFInfo
- Publication number
- CN109242880A CN109242880A CN201810972259.0A CN201810972259A CN109242880A CN 109242880 A CN109242880 A CN 109242880A CN 201810972259 A CN201810972259 A CN 201810972259A CN 109242880 A CN109242880 A CN 109242880A
- Authority
- CN
- China
- Prior art keywords
- straightway
- image
- power line
- distance
- dis
- 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.)
- Pending
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 22
- 239000000284 extract Substances 0.000 claims abstract description 16
- 229910052704 radon Inorganic materials 0.000 claims abstract description 14
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims abstract description 14
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 4
- 230000009977 dual effect Effects 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000007689 inspection Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Abstract
The invention discloses a kind of power line extraction methods based on image procossing, it includes: step 1, and the image of acquisition is carried out histogram equalization, forms image one;Step 2, the image border of image one is extracted, image two is formed;Step 3, it is based on image two, the power line in image two is extracted in conjunction with Radon transformation and Hough transform;Step 4, the straightway of redundancy is rejected;Step 5, connection is fitted to the straightway after step 4 rejecting screening according to the estimation method of statistics feature, to extract the power line with complete length.There is continuity, integrality by the power line that the extracting method extracts, but also there is preferable noise robustness and stronger robust performance.
Description
Technical field
The present invention relates to field of image processing more particularly to a kind of power line extraction methods based on image procossing.
Background technique
In recent years, with cities and towns expanding economy, infrastructure it is perfect, life and industry power demand increasingly
Greatly.Transmission line of electricity has the characteristics that route distance, wide coverage, highly-safe, and is usually set up in wilderness field, once
Inspection is safeguarded not in time, and power line short circuit caused by interfering because of ambient enviroment occurs often and trips, raw to resident living, industry
Production brings great puzzlement.Therefore, particularly significant to the inspection of transmission line of electricity.
The generation of power grid safety accident in order to prevent, China will put into every year a large amount of human and material resources, financial resources carry out it is defeated
The inspection of electric line is safeguarded.Conventional routine inspection mode mainly has manpower and helicopter routing inspection at present, but its labor force is big, environment
Hardships, to the personal safety of patrol officer, there is also risks, in this case, unmanned plane are applied to the inspection of transmission line of electricity
It is possibly realized.Working strength is not only reduced, labor efficiency is improved, also saves a large amount of human cost, and ensured work
Make the safety of personnel.
Currently, researcher extracts line feature often through phase-grouping method, Hough transform, Radon transformation etc..Phase
Although marshalling method high resolution, due to gradient calculate and be grouped when be not it is very clear, error can be introduced, integrality is poor, mentions
The power line taken is mostly discontinuous, and there are certain missing inspections, erroneous detection;Hough transform noise resisting ability is good, but since it is calculated again
Miscellaneous, long operational time, required amount of storage is big, and efficiency is not high;Radon transformation calculations amount is small, and runing time is short, global performance
It is good, there are certain noise immunity, but its position to power line starting point, width and length information can not all determine, thus cannot
It is accurate to extract power line.Traditional extraction power line is carried out by a certain method, and image can not be preferably extracted
Information.Therefore, how completely, efficiently extract power line be at this stage urgent need to resolve the problem of one of.
Summary of the invention
The present invention provides a kind of power line extraction methods based on image procossing, and which overcome described in background technology
The deficiencies in the prior art.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of power line extraction method based on image procossing, it includes:
Step 1, the image of acquisition is subjected to histogram equalization, forms image one;
Step 2, the image border of image one is extracted, image two is formed;
Step 3, it is based on image two, extracts the power line in image two in conjunction with Radon transformation and Hough transform, it is specific to walk
Suddenly include:
Step 31, formula is utilizedAt section [0,2 π] to figure
As carrying out Radon transformation, the wherein distance of γ indicates coordinate origin (0,0) straightway into image space, α indicate the distance with
Angle between x-axis, D indicate the plane of whole image two, and g (x, y) indicates the gray value of pixel (x, y) in image, in turn
Obtain the subpoint of parameter space;
Step 32, according to Radon reconstructed formulaRoot
The slope of straightway, intercept in image space are determined according to each subpoint of parameter space, further restore straight line in image space
The position of section;
Step 33, the gray value of straightway pixel after reduction is compared with the gray threshold of setting, if more than this
The pixel is set to 1, is otherwise set to 0 by gray threshold, to preferably highlight straightway feature, obtains image three;
Step 34, Hough transform is carried out to image three, further extracts electric power straightway;
Step 4, the straightway of redundancy is rejected;
Step 5, company is fitted to the straightway after step 4 rejecting screening according to the estimation method of statistics feature
It connects, to extract the power line with complete length.
Among one embodiment: in the step 2, the image border of image one is extracted using canny algorithm;Extraction step packet
It includes:
Step 21, denoising is carried out to image one using Gaussian Blur;
Step 22, amplitude and the direction of gradient are calculated using sobel operator;
Step 23, edge is refined by non-maxima suppression, and then image border is extracted by dual threshold.
Among one embodiment: the Low threshold and high threshold of the dual threshold are set to 30% and 100%.
Among one embodiment: in the step 4, rejecting redundancy straightway, method according to the slope characteristics of straightway are as follows:
The slope k of all straightways is calculated firstn(n=1,2,3...) counts the frequency of occurrences of each slope, it is maximum to choose the frequency of occurrences
Slope as leading slope kmIf tolerance is kdIf | km-kn|≥kd, the corresponding straightway of exception slope is deleted, instead
It, then retain.
Among one embodiment: the step 4 rejects redundancy straightway, method also according to the color characteristic of straightway are as follows:
The center pixel for extracting every straightway obtains sample set O, and image is transformed into CIELAB color space, utilizes
Color characteristic calculates the otherness d between straightway two-by-twoij,
Wherein, i, j are the corresponding two different straightways of the pixel in sample set O, if threshold value is Threshij,
Threshij=| li-lj|+|ai-aj|+|bi-bj|;
Since one straightway i, is traversed respectively to two sides, calculate the otherness d of the straightway Yu remaining each straight linein(n
≠ i, n=1,2...), if din> Threshin, then the straight line traversed is considered as the removal of redundancy straightway, if din≤
Threshin, then retain the straightway.
Among one embodiment: in the step 5, the method for being fitted connection to the straightway after de-redundancy includes:
It step 51, is k to slope in imagenStraightway, acquire corresponding intercept t respectivelyn, obtain straightway collection Ln: knx-y+
tn=0 (n=1,2 ...), extract the two sides endpoint (a of every straightwaynl, bnl), (anr, bnr) (n=1,2 ...), obtain sample
This point set M., with straightway LiLeft end point (ail, bil) arrive straight line LjDistance dis of the distance as two straight linesij, with image upper left
Angle straightway L1Left end point A1l(a1l, b1l) it is starting point, the range formula for a little arriving plane and straight line is obtained,
Step 52, from starting point A1l(a1l, b1l) rise, from left to right, straightway is traversed from top to bottom, calculate separately out point
A1l(a1l, b1l) arrive each straightway distance, as straightway L1The distance between remaining each straightway { dis12, dis13,
dis14..., take s1=min { dis12, dis13, dis14..., then being s with straightway distance1That direct line of sight be with
Straightway L1It is the edge of same power line in the picture, the two is connected;
Step 53, remaining minimum range between straightway two-by-two is calculated, two straightways with minimum range are regarded
Calculating is no longer participate in by the straightway that connection is completed labeled as processed state for same power line edge;
Step 54, work as disijWhen=0, two straightways can be considered in the same horizontal line, extract two endpoint respectively
{Ail(ail, bil)、Air(air, bir), { Ajl(ajl, bjl)、Ajr(ajr, bjr), according to plane distance between two points formula, calculate
Point A outil、AjlThe distance betweenSimilarly calculate Dil-jr、Dir-jl、Dir-jr, compare
Dil-jl、Dil-jr、Dir-jl、Dir-jrMinimum range opposite ends point is connected, recovers complete power line by size.
Among one embodiment: further including step 6, reject interference power line using length characteristic, method includes: to calculate warp
Each complete power line length s that step 5 recoversn(n=1,2,3...), takes sm=median { s1、s2、s3..., if sn<
smedian, then the power line is rejected, otherwise is retained.
Among one embodiment: described image is obtained by the camera module on unmanned plane.
The technical program compared with the background art, it has the following advantages:
(1) by Radon transformation and Hough transform in conjunction with to extract power line, not only can ensure that the power line that extracts has
There are continuity, integrality, but also there is preferable noise robustness and stronger robust performance.
(2) slope, color characteristic are utilized, redundant power lines can be effectively rejected, improve the accuracy of the electric power extracted.
(3) it when being fitted connection to straightway, can effectively solve to extract using the estimation method of statistics feature
Power line occur fracture, overlapping the problem of.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is the step flow chart of the power line extraction method based on image procossing described in the present embodiment.
Fig. 2 is the image change schematic diagram before and after electric power line drawing.
Specific embodiment
Fig. 1 and Fig. 2 are please referred to, a kind of power line extraction method based on image procossing, it includes:
Step 1, the image of acquisition is subjected to histogram equalization, forms image one;
Step 2, the image border of image one is extracted, image two is formed;
Step 3, it is based on image two, the power line in image two is extracted in conjunction with Radon transformation and Hough transform;
Step 4, the straightway of redundancy is rejected;
Step 5, company is fitted to the straightway after step 4 rejecting screening according to the estimation method of statistics feature
It connects, to extract the power line with complete length.
In the step 2, the image border of image one is extracted using canny algorithm;Extraction step includes:
Step 21, denoising is carried out to image one using Gaussian Blur;The Gaussian Blur radius of the present embodiment takes 5;
Step 22, amplitude and the direction of gradient are calculated using sobel operator;
Step 23, edge is refined by non-maxima suppression, and then image border is extracted by dual threshold.This
In embodiment, the Low threshold and high threshold of the dual threshold are set to 30% and 100%.
In the step 3, the specific steps packet of the power line in image two is extracted in conjunction with Radon transformation and Hough transform
It includes:
Step 31, formula is utilizedAt section [0,2 π] to figure
As carrying out Radon transformation, the wherein distance of γ indicates coordinate origin (0,0) straightway into image space, α indicate the distance with
Angle between x-axis, D indicate the plane of whole image two, and g (x, y) indicates the gray value of pixel (x, y) in image, in turn
Obtain the subpoint of parameter space;
Step 32, according to Radon reconstructed formulaRoot
The slope of straightway, intercept in image space are determined according to each subpoint of parameter space, further restore straight line in image space
The position of section;
Step 33, the gray value of straightway pixel after reduction is compared with the gray threshold of setting, if more than this
The pixel is set to 1, is otherwise set to 0 by gray threshold, to preferably highlight straightway feature, obtains image three;
Step 34, Hough transform is carried out to image three, further extracts electric power straightway.
In the step 4, redundancy straightway, method are rejected according to the slope characteristics of straightway are as follows: are calculated first all
The slope k of straightwayn(n=1,2,3...) counts the frequency of occurrences of each slope, chooses the maximum slope of the frequency of occurrences as master
Lead slope kmIf tolerance is kdIf | km-kn|≥kd, the corresponding straightway of exception slope is deleted, conversely, then retaining.
Preferably, in the present embodiment, the step 4 rejects redundancy straightway, side also according to the color characteristic of straightway
Method are as follows:
The center pixel for extracting every straightway obtains sample set O, and image is transformed into CIELAB color space, utilizes
Color characteristic calculates the otherness d between straightway two-by-twoij,
Wherein, i, j are the corresponding two different straightways of the pixel in sample set O, if threshold value is Threshij,
Threshij=| li-lj|+|ai-aj|+|bi-bj|
Since one straightway i, is traversed respectively to two sides, calculate the otherness d of the straightway Yu remaining each straightwayin
(n ≠ i, n=1,2...), if din> Threshin, illustrate the color difference of the current straightway traversed and straightway i compared with
Greatly, it is not belonging to power line, therefore the straight line traversed is considered as the removal of redundancy straightway, if din≤Threshin, then retain
The straightway.Straightway i, which has determined that, herein belongs to power line.
In the step 5, the method for being fitted connection to the straightway after de-redundancy includes:
It step 51, is k to slope in imagenStraightway, acquire corresponding intercept t respectivelyn, obtain straightway collection Ln: knx-y+
tn=0 (n=1,2 ...), extract the two sides endpoint (a of every straightwaynl, bnl), (anr, bnr) (n=1,2 ...), obtain sample
Point set M., with straightway LiLeft end point (ail, bil) arrive straight line LjDistance dis of the distance as two straight linesij, straight with the image upper left corner
Line segment L1Left end point A1l(a1l, b1l) it is starting point, the range formula for a little arriving plane and straight line is obtained,
Step 52, from starting point A1l(a1l, b1l) rise, from left to right, straightway is traversed from top to bottom, calculate separately out point
A1l(a1l, b1l) arrive each straightway distance, as straightway L1The distance between remaining each straightway { dis12, dis13,
dis14..., take s1=min { dis12, dis13, dis14..., then being s with straightway distance1That direct line of sight be with
Straightway L1It is the edge of same power line in the picture, the two is connected;
Step 53, remaining minimum range between straightway two-by-two is calculated, two straightways with minimum range are regarded
Calculating is no longer participate in by the straightway that connection is completed labeled as processed state for same power line edge;
Step 54, work as disijWhen=0, two straightways can be considered in the same horizontal line, extract two endpoint respectively
{Ail(ail, bil)、Air(air, bir), { Ajl(ajl, bjl)、Ajr(ajr, bjr), according to plane distance between two points formula, calculate
Point A outil、AjlThe distance betweenSimilarly calculate Dil-jr、Dir-jl、Dir-jr, compare
Dil-jl、Dil-jr、Dir-jl、Dir-jrMinimum range opposite ends point is connected, recovers complete power line by size.
Preferably, further include step 6, reject interference power line using length characteristic, method includes: to calculate through step 5
Each complete power line length s recoveredn(n=1,2,3...), takes sm=median { s1、s2、s3..., if sn< smedian,
The power line is then rejected, otherwise is retained.
In the present embodiment, described image is obtained by the camera module on unmanned plane.
The above is only the preferred embodiment of the present invention, the range implemented of the present invention that therefore, it cannot be limited according to, i.e., according to
Equivalent changes and modifications made by the invention patent range and description, should still be within the scope of the present invention.
Claims (8)
1. a kind of power line extraction method based on image procossing, it is characterised in that: include:
Step 1, the image of acquisition is subjected to histogram equalization, forms image one;
Step 2, the image border of image one is extracted, image two is formed;
Step 3, it is based on image two, extracts the power line in image two, specific steps packet in conjunction with Radon transformation and Hough transform
It includes:
Step 31, formula is utilizedSection [0,2 π] to image into
Row Radon transformation, wherein the distance of γ indicates coordinate origin (0,0) straightway into image space, α indicate the distance and x-axis
Between angle, D indicates the plane of whole image two, and g (x, y) indicates the gray value of pixel (x, y) in image, and then obtains
The subpoint of parameter space;
Step 32, according to Radon reconstructed formulaAccording to ginseng
Each subpoint of number space determines the slope of straightway, intercept in image space, further restores straightway in image space
Position;
Step 33, the gray value of straightway pixel after reduction is compared with the gray threshold of setting, if more than the gray scale
The pixel is set to 1, is otherwise set to 0 by threshold value, to preferably highlight straightway feature, obtains image three;
Step 34, Hough transform is carried out to image three, further extracts electric power straightway;
Step 4, the straightway of redundancy is rejected;
Step 5, connection is fitted to the straightway after step 4 rejecting screening according to the estimation method of statistics feature, with
Extract the power line with complete length.
2. a kind of power line extraction method based on image procossing according to claim 1, it is characterised in that: the step
In 2, the image border of image one is extracted using canny algorithm;Extraction step includes:
Step 21, denoising is carried out to image one using Gaussian Blur;
Step 22, amplitude and the direction of gradient are calculated using sobel operator;
Step 23, edge is refined by non-maxima suppression, and then image border is extracted by dual threshold.
3. a kind of power line extraction method based on image procossing according to claim 2, it is characterised in that: the dual threashold
The Low threshold and high threshold of value are set to 30% and 100%.
4. a kind of power line extraction method based on image procossing according to claim 1, it is characterised in that: the step
In 4, redundancy straightway, method are as follows: calculate the slope k of all straightways first are rejected according to the slope characteristics of straightwayn(n
=1,2,3...) frequency of occurrences of each slope, is counted, chooses the maximum slope of the frequency of occurrences as leading slope kmIf tolerance
Degree is kdIf | km-kn|≥kd, the corresponding straightway of exception slope is deleted, conversely, then retaining.
5. a kind of power line extraction method based on image procossing according to claim 4, it is characterised in that: the step
4, redundancy straightway, method are rejected also according to the color characteristic of straightway are as follows:
The center pixel for extracting every straightway obtains sample set O, and image is transformed into CIELAB color space, utilizes color
The feature calculation otherness d between straightway two-by-twoij,
Wherein, i, j are the corresponding two different straightways of the pixel in sample set O, if threshold value is Threshij,
Threshij=| li-lj|+|ai-aj|+|bi-bj|;
Since one straightway i, is traversed respectively to two sides, calculate the otherness d of the straightway Yu remaining each straight linein(n ≠ i,
N=1,2...), if din> Threshin, then the straight line traversed is considered as the removal of redundancy straightway, if din≤Threshin,
Then retain the straightway.
6. a kind of power line extraction method based on image procossing according to claim 1, it is characterised in that: the step
In 5, the method for being fitted connection to the straightway after de-redundancy includes:
It step 51, is k to slope in imagenStraightway, acquire corresponding intercept t respectivelyn, obtain straightway collection Ln: knx-y+tn=0
(n=1,2 ...), extract the two sides endpoint (a of every straightwaynl, bnl), (anr, bnr) (n=1,2 ...), obtain sample point
Collect M., with straightway LiLeft end point (ail, bil) arrive straight line LjDistance dis of the distance as two straight linesij, straight with the image upper left corner
Line segment L1Left end point A1l(a1l, b1l) it is starting point, the range formula for a little arriving plane and straight line is obtained,
Step 52, from starting point A1l(a1l, b1l) rise, from left to right, straightway is traversed from top to bottom, calculate separately out point A1l
(a1l, b1l) arrive each straightway distance, as straightway L1The distance between remaining each straightway { dis12, dis13,
dis14..., take s1=min { dis12, dis13, dis14..., then being s with straightway distance1That direct line of sight be with
Straightway L1It is the edge of same power line in the picture, the two is connected;
Step 53, remaining minimum range between straightway two-by-two is calculated, two straightways with minimum range are considered as together
One power line edge is no longer participate in calculating by the straightway that connection is completed labeled as processed state;
Step 54, work as disijWhen=0, two straightways can be considered in the same horizontal line, extract two endpoint { A respectivelyil
(ail, bil)、Air(air, bir), { Ajl(ajl, bjl)、Ajr(ajr, bjr), according to plane distance between two points formula, calculate
Point Ail、AjlThe distance betweenSimilarly calculate Dil-jr、Dir-jl、Dir-jr, compare
Dil-jl、Dil-jr、Dir-jl、Dir-jrMinimum range opposite ends point is connected, recovers complete power line by size.
7. a kind of power line extraction method based on image procossing according to claim 1, it is characterised in that: further include step
Rapid 6, interference power line is rejected using length characteristic, method includes: each complete power line length for calculating and recovering through step 5
sn(n=1,2,3...), takes sm=median { s1、s2、s3..., if sn< smedian, then the power line is rejected, otherwise is retained.
8. a kind of power line extraction method based on image procossing according to any one of claim 1 to 7, feature exist
In: described image is obtained by the camera module on unmanned plane.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810972259.0A CN109242880A (en) | 2018-08-24 | 2018-08-24 | A kind of power line extraction method based on image procossing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810972259.0A CN109242880A (en) | 2018-08-24 | 2018-08-24 | A kind of power line extraction method based on image procossing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109242880A true CN109242880A (en) | 2019-01-18 |
Family
ID=65067956
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810972259.0A Pending CN109242880A (en) | 2018-08-24 | 2018-08-24 | A kind of power line extraction method based on image procossing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109242880A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110189344A (en) * | 2019-04-24 | 2019-08-30 | 河海大学常州校区 | A kind of line segment extraction method in power knife switch image |
CN110501384A (en) * | 2019-08-15 | 2019-11-26 | 东南大学 | A kind of bead wire curtain defect detecting device and detection method based on heat radiation visual pattern |
CN111739042A (en) * | 2020-06-04 | 2020-10-02 | 中南大学 | Complex background power line extraction method based on digital image features |
CN112364874A (en) * | 2020-09-15 | 2021-02-12 | 广东电网有限责任公司 | Extraction method of power transmission line |
CN112408153A (en) * | 2020-10-10 | 2021-02-26 | 上海市特种设备监督检验技术研究院 | Method for monitoring movement amount of steel wire rope in elevator braking process |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090238433A1 (en) * | 2008-03-21 | 2009-09-24 | Shenzhen Mindray Bio-Medical Electronics Co., Ltd. | Method and device for automatically detecting collimation edges |
CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
CN102930535A (en) * | 2012-10-16 | 2013-02-13 | 余杭供电局 | Power line contour extraction method for detecting online foreign object intrusion |
CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
CN104966065A (en) * | 2015-06-23 | 2015-10-07 | 电子科技大学 | Target recognition method and device |
CN106056619A (en) * | 2016-06-13 | 2016-10-26 | 长安大学 | Unmanned aerial vehicle vision wire patrol method based on gradient constraint Radon transform |
-
2018
- 2018-08-24 CN CN201810972259.0A patent/CN109242880A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090238433A1 (en) * | 2008-03-21 | 2009-09-24 | Shenzhen Mindray Bio-Medical Electronics Co., Ltd. | Method and device for automatically detecting collimation edges |
CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
CN102930535A (en) * | 2012-10-16 | 2013-02-13 | 余杭供电局 | Power line contour extraction method for detecting online foreign object intrusion |
CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
CN104966065A (en) * | 2015-06-23 | 2015-10-07 | 电子科技大学 | Target recognition method and device |
CN106056619A (en) * | 2016-06-13 | 2016-10-26 | 长安大学 | Unmanned aerial vehicle vision wire patrol method based on gradient constraint Radon transform |
Non-Patent Citations (3)
Title |
---|
李彩林 等: "复杂地物背景下的电力线提取方法", 《计算机工程与应用》 * |
王飞: "低空影像中道路信息检测研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
黄婷婷: "无人机自动巡线方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110189344A (en) * | 2019-04-24 | 2019-08-30 | 河海大学常州校区 | A kind of line segment extraction method in power knife switch image |
CN110189344B (en) * | 2019-04-24 | 2022-09-13 | 河海大学常州校区 | Method for extracting straight line segment in electric power disconnecting link image |
CN110501384A (en) * | 2019-08-15 | 2019-11-26 | 东南大学 | A kind of bead wire curtain defect detecting device and detection method based on heat radiation visual pattern |
CN111739042A (en) * | 2020-06-04 | 2020-10-02 | 中南大学 | Complex background power line extraction method based on digital image features |
CN111739042B (en) * | 2020-06-04 | 2023-06-09 | 中南大学 | Complex background power line extraction method based on digital image features |
CN112364874A (en) * | 2020-09-15 | 2021-02-12 | 广东电网有限责任公司 | Extraction method of power transmission line |
CN112408153A (en) * | 2020-10-10 | 2021-02-26 | 上海市特种设备监督检验技术研究院 | Method for monitoring movement amount of steel wire rope in elevator braking process |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109242880A (en) | A kind of power line extraction method based on image procossing | |
CN111126184B (en) | Post-earthquake building damage detection method based on unmanned aerial vehicle video | |
CN103528534B (en) | A kind of electric power line ice-covering thickness detection method based on image monitoring | |
CN103727930A (en) | Edge-matching-based relative pose calibration method of laser range finder and camera | |
Huang et al. | A top-down strategy for buildings extraction from complex urban scenes using airborne LiDAR point clouds | |
CN106886988B (en) | Linear target detection method and system based on unmanned aerial vehicle remote sensing | |
CN109859246B (en) | Low-altitude slow unmanned aerial vehicle tracking method combining correlation filtering and visual saliency | |
CN103810462A (en) | High voltage transmission line detection method based on linear targets | |
CN111275040A (en) | Positioning method and device, electronic equipment and computer readable storage medium | |
CN109829459B (en) | Visual positioning method based on improved RANSAC | |
CN115331000A (en) | ORB algorithm-based bow net running state detection method | |
Zhao et al. | MSANet: efficient detection of tire defects in radiographic images | |
CN117197700B (en) | Intelligent unmanned inspection contact net defect identification system | |
CN113807184A (en) | Obstacle detection method and device, electronic equipment and automatic driving vehicle | |
CN105844614B (en) | It is a kind of that northern method is referred to based on the vision for proofreading robot angle | |
Zhou et al. | Segmentation algorithm for 3D LiDAR point cloud based on region clustering | |
Guangyun et al. | An improved ORB feature extraction and matching algorithm | |
Li et al. | Research on transmission conductor extraction method based on mainline projection LSD algorithm | |
Chang et al. | On-line detection of pantograph offset based on deep learning | |
CN111340833B (en) | Power transmission line extraction method for least square interference-free random Hough transformation | |
CN112016610B (en) | Image feature matching method and system | |
CN113378918B (en) | Insulator binding wire state detection method based on metric learning | |
CN109410186A (en) | A kind of contact net positioner wire clamp image detecting method | |
CN115273044B (en) | Vehicle door damage fault identification and detection method based on improved graph convolution network | |
CN115953589B (en) | Engine cylinder block aperture size measurement method based on depth camera |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190118 |
|
WD01 | Invention patent application deemed withdrawn after publication |