CN106296694B - Shaft tower tilts intelligent image and recognizes measurement method - Google Patents
Shaft tower tilts intelligent image and recognizes measurement method Download PDFInfo
- Publication number
- CN106296694B CN106296694B CN201610661227.XA CN201610661227A CN106296694B CN 106296694 B CN106296694 B CN 106296694B CN 201610661227 A CN201610661227 A CN 201610661227A CN 106296694 B CN106296694 B CN 106296694B
- Authority
- CN
- China
- Prior art keywords
- shaft tower
- image
- information
- angle
- inclination
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The present invention proposes a kind of shaft tower inclination intelligent image identification measurement method, belongs to intelligent power grid technology field.First, shaft tower video or image information and horizontally or vertically information are acquired, and is calculated both horizontally and vertically；Then, angle correction both horizontally and vertically is carried out to shaft tower video or image information according to calculated, then is pre-processed；It picks out the shaft tower in image and extracts shaft tower geological information, analyzing processing obtains the profile information of shaft tower, and then determine the geometric center lines of shaft tower profile, angle of inclination of the shaft tower geometric center lines in video image is calculated, the angle of inclination of shaft tower is can be obtained using triangulation method.The present invention corrects image using image processing method combination horizontal vertical orientation measurement sensor, make to be influenced by shooting angle in image procossing and calculating process and lead to generating for error, measurement accuracy is improved, the inclination measurement of electric power line pole tower is can be widely applied to.
Description
Technical field
The present invention relates to a kind of shaft towers to tilt intelligent image identification measurement method, belongs to intelligent power grid technology field.
Background technology
With the rapid development of the national economy, electric power has become production indispensable in daily life and industrial production
Product, the influence of the stability of power transmission to social development are also increasing.Transmission tower is important as electrical power transmission system
Component part plays a crucial role the stability of power transmission.Due to being destroyed by external force, ice disaster destroy,
Column foot soil stone loose damage, shaft tower are easy to happen tower body inclination.If operation maintenance personnel cannot have found in time, it will cause shaft tower
Topple over, destroy the stability of power transmission, seriously affect the development of social economy, therefore, it is necessary to incline to electric power line pole tower
Ramp-like condition is measured in real time.
Currently, shaft tower inclination measurement mainly uses the method that obliquity sensor measures, the shaft tower inclination measurement based on image
Method is few, Chinese patent " a method of the inclination of transmission line tower based on video variance measures "（Application number：
201110157735.1）It proposes the image collected and background image subtraction obtaining shaft tower target image, then after being handled
Calculate shaft tower angle of inclination.But it is very difficult due to obtaining clean background image, and background be also always in variation,
So that this method is difficult to realize；And this method does not carry out angle correction to the image collected, can not correct image
Image rotation caused by collecting device installation deviation, therefore, measurement error is big, and accuracy of measurement is low.
Invention content
For overcome the deficiencies in the prior art, intelligent image identification is tilted the object of the present invention is to provide a kind of shaft tower to measure
Method measures shaft tower with the method identification of image procossing and tilts, of low cost, simple in structure, convenient for installation and maintenance；Utilize image
Processing combines horizontal vertical orientation measurement sensor to carry out shaft tower inclination measurement, makes to be clapped in image procossing and calculating process
It takes the photograph angle influence and leads to the generation of error, effectively improve computational accuracy, improve the accuracy rate of measurement.
To solve the above problems, the technical solution adopted in the present invention is：
The shaft tower tilts intelligent image and recognizes measurement method, is realized using following steps：
1）Acquire the video or image information in shaft tower fair line road and horizontal path direction respectively with video image acquisition equipment；
DV and camera generally may be used in video image acquisition equipment, can completely acquire monitored shaft tower video or image
Information；
2）Horizontally or vertically information is acquired in real time with horizontal vertical orientation measurement sensor, is calculated accordingly horizontal and vertical
Direction；When horizontal vertical orientation measurement sensor acquires horizontal information, vertical information can be calculated in the picture, works as level
When vertical direction measurement sensor acquires vertical information, horizontal information can be calculated in the picture；
3）According to calculated horizontal and vertical information to the collected shaft tower video of video image acquisition equipment or image
Information carries out angle correction；
4）Image information after correction is pre-processed, including image filtering denoising, image enhancement processing, is reduced
Interference of the complex environment background to system image procossing accurately identifies shaft tower image information, improves the accurate of shaft tower inclination measurement
Property；Image filtering denoising can reduce the noise generated in image acquisition process, keep picture quality more preferable, filtering and noise reduction can be used
Median filtering method, because mainly salt-pepper noise, the median filtering method that are generated in image acquisition process can effectively inhibit green pepper
Salt noise, and can preferably retain the edge details in image；
5）Analyzing processing is carried out to pretreated image information, the shaft tower in image and accurate positionin is recognized accurately,
Then the shaft tower information in image is extracted；
6）Analyzing processing, including image gray processing processing, image binaryzation processing, side are carried out to the shaft tower information extracted
Edge detection process, the processing of Hough straight-line detection, obtain the outer profile information of shaft tower, so that it is determined that the geometric center of shaft tower outer profile
Line calculates the angle of inclination in video image of shaft tower geometric center lines, shaft tower is calculated further according to triangulation methods
Actual angle of inclination.Otsu methods may be used into row threshold division in image binaryzation, and Otsu methods can be very good to carry on the back
Scape and target object are split；Canny edge detection methods may be used in edge detection, and Canny edge detection methods are recognized
For the edge detection method for being optimal so far；Hough straight-line detections use improved Hough straight-line detections, traditional
Straight line angle threshold is set on the basis of Hough straight-line detections, the influence of background and transmission line of electricity to detection can be eliminated in this way, into
The geometric center lines that can calculate shaft tower outer profile of one step obtain geometric center lines inclining in the picture by mathematical computations
The angle of inclination of rake angle namely shaft tower.
Step 3 in the method）,4）,5）,6）Following step replacement can be used, have the effect of equivalent：
3）Collected shaft tower video image information is pre-processed, including image filtering denoising, image enhancement
Processing reduces interference of the complex environment background to system image procossing, accurately identifies shaft tower image information, improves shaft tower and tilts survey
The accuracy of amount；
4）Analyzing processing is carried out to pretreated image information, the shaft tower in image and accurate positionin is recognized accurately,
Then the shaft tower information in image is extracted；
5）Analyzing processing, including image gray processing processing, image binaryzation processing, side are carried out to the shaft tower information extracted
Edge detection process, the processing of Hough straight-line detection, obtain the outer profile information of shaft tower, so that it is determined that the geometric center of shaft tower outer profile
Line；
6）Calculated horizontal or vertical direction information is combined with geometric center lines, calculates shaft tower inclining in the picture
Rake angle calculates the actual angle of inclination of shaft tower further according to triangulation methods.
In the method, angle correction is that the horizontally or vertically information acquired according to horizontal vertical orientation measurement sensor is repaiied
Image tilts just caused by video image acquisition equipment installation deviation.
In the method, analyzing processing is carried out to pretreated image information, to accurately identify shaft tower region, at analysis
Reason method is template matching method, and shaft tower and locating rod tower position are accurately identified by template image.
In the method, analyzing processing is carried out to pretreated image information, to accurately identify shaft tower region, at analysis
Reason method can also be corner detection approach, and shaft tower is angle point Dense objects, and the most intensive region of angle point, that is, shaft tower region is used
Angle point intensive nature identifies shaft tower and locating rod tower position.
In the method, geometric center lines refer to the line of shaft tower outer profile top center and bottom wheel point in image.
In the method, computational geometry center line angle of inclination in video imageθIf two endpoints of geometric center lines areP 1、P 2,P 3、P 4Coordinate be respectively (x 1, y 1)、(x 2, y 2), then angle of inclinationθFor：
θ=arctan(y 2 -y 1)/(x 2 -x 1)。
In the method, the principle of shaft tower actual angle of inclination is measured using triangulation method is：Known shaft tower geometric center
Line angle of inclination is in the directional image of fair line roadα 1, the angle of inclination in horizontal path directional image isα 2, then shaft tower is practical
Angle of inclination。
Method provided by the present invention has the beneficial effect that：
Shaft tower angle of inclination is calculated using the method identification that intelligent image is handled, there is of low cost, simple in structure, installation
The advantages that easy to maintain.
The horizontally or vertically information acquired in conjunction with horizontal vertical orientation measurement sensor carries out angle correction to image, makes figure
As that will not be influenced by shooting angle in processing and calculating process and lead to generating for error, substantially increases shaft tower and tilt identification meter
The accuracy of calculation.
Angle of bank measurement calculating is carried out in such a way that shaft tower contours extract determines geometric center lines, it is easy to accomplish, and
It can effectively improve measurement accuracy.
Description of the drawings
Fig. 1：Shaft tower tilts intelligent image and recognizes measuring method flow chart.
Fig. 2：Triangulation methods schematic diagram.
Specific implementation mode
The present invention is described in further detail for embodiment below in conjunction with the accompanying drawings.
As shown in Figure 1, the implementation process that shaft tower tilts intelligent image identification measurement method is：
First, shaft tower fair line road and horizontal path direction video are acquired respectively with video image acquisition equipment or image is believed
Breath.Video image acquisition equipment is generally common DV and camera, can acquire regarding for monitored shaft tower in real time
Frequency image information；
Horizontally or vertically information is acquired in real time with horizontal vertical orientation measurement sensor, calculates horizontal and vertical side accordingly
To.Gravity accelerometer, gyroscope or level meter may be used in horizontal vertical orientation measurement sensor, can measure in real time
Shaft tower vertically or horizontally information；It, can be in image when horizontal vertical orientation measurement sensor acquires horizontal information
In calculate vertical information, when horizontal vertical orientation measurement sensor acquire vertical information when, water outlet can be calculated in the picture
Ordinary mail ceases.
Then, according to calculated horizontal and vertical information to the collected shaft tower video of video image acquisition equipment or figure
As information carries out angle correction.Angle correction can be tilted with image caused by modifying factor video image acquisition equipment installation deviation,
Improve the accuracy of shaft tower inclination measurement.
Further, the image information after correction is pre-processed, pretreatment includes image filtering denoising, image
Enhancing is handled, and is reduced interference of the complex environment background to system image procossing, is accurately identified shaft tower image information, is improved shaft tower and is inclined
The accuracy tiltedly measured.Image filtering denoising can reduce the noise in image, improve the quality of image；Image enhancement can dash forward
The edge details for going out shaft tower in image are conducive to that shaft tower is identified and positions.
Further, analyzing processing is carried out to pretreated image information, the shaft tower in image and standard is recognized accurately
It determines position, then extracts the shaft tower information in image；Template matching method can be used by identifying and positioning shaft tower, by template image standard
Really identification shaft tower and locating rod tower position；It is angle point Dense objects that corner detection approach, shaft tower, which can also be used, and angle point is most intensive
Region, that is, shaft tower region identifies shaft tower and locating rod tower position with angle point intensive nature.
Further, analyzing processing, including image gray processing processing, image two-value are carried out to the shaft tower information extracted
Change processing, edge detection process, the processing of Hough straight-line detections, obtain the outer profile information of shaft tower, so that it is determined that shaft tower outer profile
Geometric center lines.Target object and background can be split by image binaryzation, and edge detection and Hough straight-line detections can
To obtain the outer profile of shaft tower.The cluster center line of shaft tower outer profile is shaft tower outer profile top center and bottom midpoint in image
Line.
Finally, the angle of inclination in video image for calculating shaft tower geometric center lines, further according to triangulation methods
Calculate shaft tower actual angle of inclination.Geometric center lines angle of inclination in video imageθFollowing formula may be used to carry out
It calculates, if two endpoints of geometric center lines areP 1、P 2,P 3、P 4Coordinate be respectively (x 1, y 1)、(x 2, y 2), then angle of inclinationθ
For：θ=arctan(y 2 -y 1)/(x 2 -x 1)。
As shown in Fig. 2, using triangulation methods, the principle that Vector operation obtains the actual angle of inclination of shaft tower is carried out
It is：Assuming that being X-direction along line direction, horizontal path direction is Y direction.Projection of the shaft tower geometric center lines on the faces XOY
ForL,LIn being projected as X-directionL x , being projected as in the Y-axis directionL y ,L 2=L x 2 +L y 2 , then shaft tower geometric center lines are in fair line
The cotangent cot at the inclination angle projected on the direction of roadθ 1=L y /H, the cotangent cot at the inclination angle projected on horizontal path directionθ 2=L x /H
, and the cotangent at the practical inclination angle of shaft tower is cotθ=L/H, therefore the inclination angle of shaft tower can be obtained。
The foregoing is merely the preferable embodiments of the present invention, are not intended to limit the invention, all spirit in the present invention
Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Claims (5)
1. shaft tower tilts intelligent image and recognizes measurement method, it is characterised in that：
1) video or image information in shaft tower fair line road and horizontal path direction are acquired respectively with video image acquisition equipment；
2) the horizontally or vertically information for acquiring video image acquisition equipment in real time with horizontal vertical orientation measurement sensor, is counted accordingly
It calculates both horizontally and vertically；
3) according to calculated both horizontally and vertically to the collected shaft tower video of video image acquisition equipment or image information
Carry out angle correction；
4) image information after correction is pre-processed, including image filtering denoising, image enhancement processing；
5) analyzing processing is carried out to pretreated image information, picks out the shaft tower in image and accurate positionin, then extracts
Shaft tower information in image；
6) analyzing processing, including image gray processing, image binaryzation, edge detection, Hough are carried out to the shaft tower information extracted
Straight-line detection obtains the outer profile information of shaft tower, so that it is determined that the geometric center lines of shaft tower outer profile, calculate in shaft tower geometry
Angle of inclination of the heart line in video image calculates the actual angle of inclination of shaft tower further according to triangulation methods.
2. shaft tower according to claim 1 tilts intelligent image and recognizes measurement method, it is characterised in that：The angle is rectified
Exactly according to the horizontally or vertically Information revision of horizontal vertical orientation measurement sensor acquisition because video image acquisition equipment is installed
Image caused by deviation tilts.
3. shaft tower according to claim 1 tilts intelligent image and recognizes measurement method, it is characterised in that：It is described to locating in advance
Image information after reason carries out analyzing processing, and method is template matching method, accurately identifies shaft tower by template image and positions shaft tower
Position.
4. shaft tower according to claim 1 tilts intelligent image and recognizes measurement method, it is characterised in that：It is described to locating in advance
Image information after reason carries out analyzing processing, and method is corner detection approach, and shaft tower is angle point Dense objects, the most intensive area of angle point
Domain, that is, shaft tower region identifies shaft tower and locating rod tower position with angle point intensive nature.
5. shaft tower according to claim 1 tilts intelligent image and recognizes measurement method, it is characterised in that：In the geometry
Heart line refers to the line at head of mast profile midpoint and bottom profile midpoint in image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610661227.XA CN106296694B (en) | 2016-08-13 | 2016-08-13 | Shaft tower tilts intelligent image and recognizes measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610661227.XA CN106296694B (en) | 2016-08-13 | 2016-08-13 | Shaft tower tilts intelligent image and recognizes measurement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106296694A CN106296694A (en) | 2017-01-04 |
| CN106296694B true CN106296694B (en) | 2018-11-09 |
Family
ID=57668686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610661227.XA Expired - Fee Related CN106296694B (en) | 2016-08-13 | 2016-08-13 | Shaft tower tilts intelligent image and recognizes measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106296694B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107221006A (en) * | 2017-05-11 | 2017-09-29 | 南京邮电大学 | A kind of communication single pipe tower slant detection method based on unmanned plane imaging platform |
| CN109959335B (en) * | 2017-12-22 | 2021-09-21 | 北京金风科创风电设备有限公司 | Method, device and system for measuring displacement of tower top |
| CN108387215A (en) * | 2018-02-10 | 2018-08-10 | 杭州后博科技有限公司 | A kind of Iron tower incline angle computation method and system based on satellite positioning |
| KR102134396B1 (en) * | 2018-11-15 | 2020-07-15 | 한국과학기술연구원 | Portable image acquisition apparatus for plants |
| CN111024041A (en) * | 2019-12-03 | 2020-04-17 | 国网新疆电力有限公司电力科学研究院 | Device and method for measuring wind deflection motion attitude of insulator string of power transmission line |
| CN111738259A (en) * | 2020-06-29 | 2020-10-02 | 广东电网有限责任公司 | Tower state detection method and device |
| CN112082530B (en) * | 2020-08-11 | 2021-10-08 | 风脉能源（武汉）股份有限公司 | Method, device and equipment for measuring inclination of tower drum foundation ring based on marked machine vision |
| CN112037275A (en) * | 2020-08-21 | 2020-12-04 | 广东电网有限责任公司 | Method, device and system for measuring inclination of power transmission line tower |
| CN112949644B (en) * | 2021-02-25 | 2022-03-08 | 哈尔滨市科佳通用机电股份有限公司 | Fault image identification method for lower pull rod of truck |
| CN114898221A (en) * | 2022-07-14 | 2022-08-12 | 灵图数据(杭州)有限公司 | Tower inclination detection method and device, electronic equipment and medium |
| CN117636176A (en) * | 2024-01-26 | 2024-03-01 | 内蒙古工业大学 | Deep learning-based telegraph pole verticality detection method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289676A (en) * | 2011-07-30 | 2011-12-21 | 山东鲁能智能技术有限公司 | Method for identifying mode of switch of substation based on infrared detection |
| CN102353355A (en) * | 2011-06-14 | 2012-02-15 | 西安工程大学 | Method for measuring power transmission line pole and tower inclination based on video differences |
| CN102611822A (en) * | 2012-03-14 | 2012-07-25 | 海信集团有限公司 | Projector and projection image rectifying method thereof |
| CN103063166A (en) * | 2013-01-05 | 2013-04-24 | 山西省电力公司大同供电分公司 | Detection method and device for wind deflection angle of suspension type composite insulator chain |
| CN105761219A (en) * | 2016-02-03 | 2016-07-13 | 北京云江科技有限公司 | Inclination correction method and system of text image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9123113B2 (en) * | 2013-03-08 | 2015-09-01 | Raven Industries, Inc. | Row guidance parameterization with Hough transform |
-
2016
- 2016-08-13 CN CN201610661227.XA patent/CN106296694B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102353355A (en) * | 2011-06-14 | 2012-02-15 | 西安工程大学 | Method for measuring power transmission line pole and tower inclination based on video differences |
| CN102289676A (en) * | 2011-07-30 | 2011-12-21 | 山东鲁能智能技术有限公司 | Method for identifying mode of switch of substation based on infrared detection |
| CN102611822A (en) * | 2012-03-14 | 2012-07-25 | 海信集团有限公司 | Projector and projection image rectifying method thereof |
| CN103063166A (en) * | 2013-01-05 | 2013-04-24 | 山西省电力公司大同供电分公司 | Detection method and device for wind deflection angle of suspension type composite insulator chain |
| CN105761219A (en) * | 2016-02-03 | 2016-07-13 | 北京云江科技有限公司 | Inclination correction method and system of text image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106296694A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106296694B (en) | Shaft tower tilts intelligent image and recognizes measurement method | |
| CN104236462B (en) | A kind of method of object height and distance in extraction video image | |
| CN106530281B (en) | Unmanned plane image fuzzy Judgment method and system based on edge feature | |
| CN107578400A (en) | A kind of contact net device parameter detection method of BIM and three-dimensional point cloud fusion | |
| CN106485699B (en) | One kind is based on the matched reference mark localization method of point | |
| CN106352800A (en) | Power transmission line sag intelligent image recognition measuring method | |
| CN108564575A (en) | A kind of contactless catenary's parameters detection method based on three dimensional point cloud | |
| CN103557788A (en) | High-speed rail catenary geometric parameter detection non-contact compensation and Kalman filtering correction method | |
| CN106327536B (en) | A kind of collar measurement method based on section point cloud | |
| CN108088414A (en) | A kind of monocular distance measuring method | |
| CN101839690A (en) | Visual inspection method for chip electronic component position error based on edge fitting | |
| CN106989683A (en) | A kind of shield tail clearance of shield machine vision measuring method | |
| CN107478176A (en) | A kind of pantograph loss detection method and system | |
| CN103295232A (en) | SAR (specific absorption rate) image registration method based on straight lines and area | |
| CN109493385A (en) | Autonomic positioning method in a kind of mobile robot room of combination scene point line feature | |
| CN106682674B (en) | A kind of pointer instrument automatic reading method based on intelligent inspection robot | |
| CN104764407A (en) | Method for measuring thickness of cable protecting bush accurately | |
| CN108280401A (en) | A kind of pavement detection method, apparatus, cloud server and computer program product | |
| CN109712190A (en) | The outer ginseng scaling method of three-dimensional laser scanner and three-dimensional laser radar | |
| CN103438834A (en) | Hierarchy-type rapid three-dimensional measuring device and method based on structured light projection | |
| CN106570877B (en) | Based on coal-winning machine virtual prototype the coal-winning machine pose alignment system and method registering with true picture | |
| CN109359537A (en) | Human face posture angle detecting method neural network based and system | |
| CN110009678A (en) | Correction bending of arch edgewise detection method and system | |
| CN109064448A (en) | Medium-and low-speed maglev F rail rail gap detection method | |
| CN109883396A (en) | A kind of air level line width measurement method based on image processing techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181109 Termination date: 20200813 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |