CN105608703A - Current transformer oil level detection method of intelligent substation inspection robot - Google Patents

Current transformer oil level detection method of intelligent substation inspection robot Download PDF

Info

Publication number
CN105608703A
CN105608703A CN201511002514.1A CN201511002514A CN105608703A CN 105608703 A CN105608703 A CN 105608703A CN 201511002514 A CN201511002514 A CN 201511002514A CN 105608703 A CN105608703 A CN 105608703A
Authority
CN
China
Prior art keywords
oil level
prime
image
edge
modeling
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
Application number
CN201511002514.1A
Other languages
Chinese (zh)
Inventor
章海兵
陶熠昆
庞文尧
王培建
黄鸿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Guozi Robot Technology Co Ltd
Original Assignee
Zhejiang Guozi Robot Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Guozi Robot Technology Co Ltd filed Critical Zhejiang Guozi Robot Technology Co Ltd
Priority to CN201511002514.1A priority Critical patent/CN105608703A/en
Publication of CN105608703A publication Critical patent/CN105608703A/en
Pending legal-status Critical Current

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
    • G06T7/0006—Industrial image inspection using a design-rule based approach
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The present invention discloses a current transformer oil level detection method of an intelligent substation inspection robot, mainly relating to the field of machine vision. The method comprises the steps of modeling, oil level detection and the like and concretely comprises the steps of meter positioning modeling, metering area selection, parameter setting and adjustment, positioning model information storage, metering reading identification modeling, oil level area setting, upper and lower limit setting, caliper adding, pointer edge mode setting, width parameter setting, filtering parameter setting and the like. According to the method, a check error caused by same color interference in an oil level meter area can be effectively avoided, the robustness is high, the correct rate of detection is high, thus the manual intervention is few, and the labor intensity of the staff is reduced greatly.

Description

A kind of Oil of Current Transformer position detecting method of robot used for intelligent substation patrol
Technical field
The Oil of Current Transformer position detecting method that the present invention relates to a kind of robot used for intelligent substation patrol, mainly relates toAnd field of machine vision.
Background technology
The inspection of current transformer oil level is the Daily Round Check task of transformer station, checks that whether oil level is normal, has or not leakageOil phenomenon is necessary check item, and this inspection occurs that to prevention great power equipment accident is significant.
But current transformer oil level gauge meter is positioned at the higher region of transformer station, and manual detection is generally passed through telescopeObserve, record oil level, for the transformer station with a hundreds of current transformer oil level gauge, this hand inspection pairStaff has higher labour intensity, especially in the severe situations such as summer high temperature.
Along with the proposition of intelligent substation theory, more and more intelligent inspection robots replace staff to becomePower station everyday devices is patrolled and examined. By location and navigation technology, robot is independent navigation in station, and patrolling of settingCautious time-out, adopts the instrumentation location based on machine vision, the reading that recognition methods realizes various table metersDetect. Wherein, current transformer oil level meter detection method generally adopts color to know method for distinguishing, refers to by oil levelThe color of pin identifies, and then distinguishes with background. But, when background in oil level region exists part and pointer, be easy to mistake identification when in the identical region of color. And, adopt color to know method for distinguishing and be also easy to be subject to illuminationImpact, robustness is poor, detects accuracy barely satisfactory. Therefore, need a kind of new current transformer oil levelDetection method, and can ensure higher accuracy.
Summary of the invention
The object of the present invention is to provide a kind of current transformer oil level of robot used for intelligent substation patrol to detectMethod, can improve the problem that prior art exists, and solves existing general method poor robustness, accuracy lowDefect.
The present invention is achieved through the following technical solutions:
An Oil of Current Transformer position detecting method for robot used for intelligent substation patrol, comprises the following steps:
S1: modeling: comprise the following steps:
S1-1 table meter location modeling: comprise the following steps:
S1-1-1: table meter region is chosen: by artificial judgment table meter scope, take whole table meter;
S1-1-2: parameter setting, adjustment: minimum, maximum-contrast are set, rotation, dimensional variation and everyParameter; Set and can test, adjust parameter according to test result, make it adapt to various light condition;
S1-1-3: preserve location model information: preserve above-mentioned parameters value;
S1-2 meter reading identification modeling: comprise the following steps:
S1-2-1: oil level region is set: with region, the fuel-displaced position of rectangle circle, record position, the rectangle frame upper left corner(xlt,ylt) and position, the lower right corner (xrd,yrd)；
S1-2-2: bound is set: draw from the bottom up straight line, straight-line lower end is oil level indicator lower limit end is straightLine upper end is oil level indicator upper limit end;
S1-2-3: add slide calliper rule: slide calliper rule are made up of multiple parallelogram, point-blank arrange, canChange length and width, slide calliper rule number is set;
S1-2-4: pointer edge pattern, width parameter are set: according to actual conditions arrange background to pointer, refer toPin is to the situation of change at edge, background place; And utilize kind of calliper edge to width; In the present invention, contrast,Filtering threshold adopts default parameters to be respectively 6 and 2;
S2: oil level detection: comprise the following steps:
S2-1 table meter location algorithm: comprise the following steps:
S2-1-1: filtering parameter: minimum, the maximum-contrast value of preserving while importing modeling, rotation, scale-valueAnd parameters;
S2-1-2: image pyramid algorithm: according to the filtering parameter importing, by template and image to be positioned differenceCarries out image matching algorithm, obtains respectively the image sequence that resolution ratio reduces by half continuously, and at high-definition picturePixel in the region of middle 2*2 is combined into a pixel in lower one deck low-resolution image; The image gold of templateWord tower is followed successively by from top to bottom: Il、Il-1...I2、I1; The image pyramid of image to be positioned is complied with from top to bottomInferiorly be: I 'l、I′l-1...I′2、I′1；
S2-1-3: calculation template Gradient Features: adopt edge detection algorithm to obtain template IlEdge feature, bagContaining each discrete point gradient, amplitude information;
S2-1-4: template matches: by the feature in S2-1-3 image I to be identified 'lIn from left to right, from upperCarry out characteristic similarity calculating to lower traversal:
s = 1 n Σ i = 1 n d i ′ T e q + p ′ | | d i ′ | | | | e q + p ′ | | = 1 n Σ i = 1 n t i ′ v r + r i ′ , c + c i ′ + u i ′ w r + r i ′ , c + c i ′ t i ′ 2 + u i ′ 2 v 2 r + r i ′ , c + c i ′ + w 2 r + r i ′ , c + c i ′ - - - ( 1 )
Direction vector is normalized, and similarity can not be subject to any illumination, block and chaotic impact;
S2-1-5: obtain matching result: obtain template in when traversal each position on bitmap undetermined by Step4Similarity score, score extreme higher position is designated as to target location (x, y);
S2-1-6: determine target location: this position is mapped to I 'l-1, then use template Il-1Near (x, y)In region, carry out Step3 to Step5, until carry out the bottom of image, i.e. I '1，I′1With image to be positionedUnanimously, both must show the position of meter.
Further, for realizing better the present invention, also comprise step S2-2: oil level detection in image to be identifiedDetermining of region: obtain oil level positioning result according to step S2-1-6, the oil level region arranging in modeling is reflectedBe mapped in image to be identified, determine surveyed area.
Further, for realizing better the present invention, after step S2-2, carry out Edge Search, by modelingTime the slide calliper rule sequence that sets, carry out successively from top to bottom edge in oil level detection region to search.
Further, for realizing better the present invention, complete after Edge Search, carrying out step S2-3: determiningOil level edge, comprises the following steps:
S2-3-1: adopt affine transformation, bilinear interpolation technology to carry out image conversion to the image in each slide calliper rule,Make it to become rectangular image;
S2-3-2: each 2 dimension histogram is done to projection to y direction, obtain 1 dimension data;
S2-3-3: adopt filtering algorithm to carry out filtering to 1 dimension data, obtain multiple candidates peak of 1 dimension dataValue and low ebb;
S2-3-4: come edge calculation width, contrast, position etc. according to score computing rule and must assign to waitingSelect peak value, low ebb to screen, taking the highest peak value of score, low ebb as definite oil level edge.
Further, for realizing better the present invention, according to step S2-3-4 detect the oil level position that obtains andThe bound of oil level when modeling in step S1, calculates the ratio of oil level.
The present invention compared with prior art, has following beneficial effect: the present invention can effectively avoid due to oil levelHomochromy interference in meter region causes checking mistake, and has stronger robustness, detects accuracy high, makesObtain the labour intensity that manual intervention is few, greatly reduced staff.
Brief description of the drawings
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, below will be to required use in embodimentAccompanying drawing be briefly described, should be appreciated that the following drawings only shows some embodiment of the present invention, thereforeShould not be counted as the restriction to scope, for those of ordinary skill in the art, not pay creative laborUnder moving prerequisite, can also obtain other relevant accompanying drawings according to these accompanying drawings.
Fig. 1 is step S2-3-4 method schematic diagram of the present invention.
Detailed description of the invention
Below in conjunction with specific embodiment, the present invention is described in further detail, but embodiments of the present invention are notBe limited to this.
The inspection of current transformer oil level is the Daily Round Check task of transformer station, checks that whether oil level is normal, has or not leakageOil phenomenon is necessary check item, and this inspection occurs that to prevention great power equipment accident is significant.Because current transformer oil level gauge is positioned at the upper zone of transformer station, people is not easy to observe oil level, one on groundAs by telescope. Therefore, for the transformer station with a hundreds of current transformer oil level gauge, this artificial inspectionCheck staff and there is higher labour intensity, especially in the severe situations such as summer high temperature.
In the present invention, robot navigation to a certain patrol and examine a little after, call cradle head preset positions, by little table locate,Amplify, clap and get after large chart picture, utilize large table Template Location to large table position. According to template parameter, obtain oilThe liquid level region of bit table meter, a string rectangle frame that utilizes upper and lower both sides to be parallel to liquid level bar carries out from top to bottomCut-away view picture, carries out the 2 dimension histograms of affine transformation to designated shape to every a string rectangle frame, to each row phaseAdduction is averaged and is obtained 1 dimension data. Then, carry out 1 dimension data filtering, utilize contrast threshold, edge mouldThe condition such as formula, border width is carried out marginal point to determining to filtered data, is finally instead pushed into liquid level in former figurePosition, thus calculate level readings.
Embodiment 1:
As shown in Figure 1, a kind of Oil of Current Transformer position detecting method of robot used for intelligent substation patrol, comprisesFollowing steps:
S1: modeling: comprise the following steps:
S1-1 table meter location modeling: comprise the following steps:
S1-1-1: table meter region is chosen: by artificial judgment table meter scope, take whole table meter;
S1-1-2: parameter setting, adjustment: minimum, maximum-contrast are set, rotation, dimensional variation and everyParameter; Set and can test, adjust parameter according to test result, make it adapt to various light condition;
S1-1-3: preserve location model information: preserve above-mentioned parameters value;
S1-2 meter reading identification modeling: comprise the following steps:
S1-2-1: oil level region is set: with region, the fuel-displaced position of rectangle circle, record position, the rectangle frame upper left corner(xlt,ylt) and position, the lower right corner (xrd,yrd)；
S1-2-2: bound is set: draw from the bottom up straight line, straight-line lower end is oil level indicator lower limit end is straightLine upper end is oil level indicator upper limit end;
S1-2-3: add slide calliper rule: slide calliper rule are made up of multiple parallelogram, point-blank arrange, canChange length and width, slide calliper rule number is set;
S1-2-4: pointer edge pattern, width parameter are set: according to actual conditions arrange background to pointer, refer toPin is to the situation of change at edge, background place; And utilize kind of calliper edge to width; In the present invention, contrast,Filtering threshold adopts default parameters to be respectively 6 and 2;
S2: oil level detection: comprise the following steps:
S2-1 table meter location algorithm: comprise the following steps:
S2-1-1: filtering parameter: minimum, the maximum-contrast value of preserving while importing modeling, rotation, scale-valueAnd parameters;
S2-1-2: image pyramid algorithm: according to the filtering parameter importing, by template and image to be positioned differenceCarries out image matching algorithm, obtains respectively the image sequence that resolution ratio reduces by half continuously, and at high-definition picturePixel in the region of middle 2*2 is combined into a pixel in lower one deck low-resolution image; The image gold of templateWord tower is followed successively by from top to bottom: Il、Il-1...I2、I1; The image pyramid of image to be positioned is complied with from top to bottomInferiorly be: I 'l、I′l-1...I′2、I′1；
S2-1-3: calculation template Gradient Features: adopt edge detection algorithm to obtain template IlEdge feature, bagContaining each discrete point gradient, amplitude information;
S2-1-4: template matches: by the feature in S2-1-3 image I to be identified 'lIn from left to right, from upperCarry out characteristic similarity calculating to lower traversal:
s = 1 n Σ i = 1 n d i ′ T e q + p ′ | | d i ′ | | | | e q + p ′ | | = 1 n Σ i = 1 n t i ′ v r + r i ′ , c + c i ′ + u i ′ w r + r i ′ , c + c i ′ t i ′ 2 + u i ′ 2 v 2 r + r i ′ , c + c i ′ + w 2 r + r i ′ , c + c i ′ - - - ( 1 )
Direction vector is normalized, and similarity can not be subject to any illumination, block and chaotic impact;
S2-1-5: obtain matching result: obtain template in when traversal each position on bitmap undetermined by Step4Similarity score, score extreme higher position is designated as to target location (x, y);
S2-1-6: determine target location: this position is mapped to I 'l-1, then use template Il-1Near (x, y)In region, carry out Step3 to Step5, until carry out the bottom of image, i.e. I '1，I′1With image to be positionedUnanimously, both must show the position of meter.
The present invention increases current transformer oil level measuring ability in the instrument recognition system of intelligent inspection robot.Patrol and examine behind place when robot arrives to specify, call cradle head preset positions, clap and get image by high definition camera, pass throughLocating template and location algorithm find oil level gauge and navigate to oil level region, utilize oil level detection algorithm to carry out liquidPosition is detected, and obtains result and value is returned to client for staff's inquiry, confirmation. The method can effectively be kept awayExempt from because the homochromy interference in oil level indicator region causes checking mistake, and there is stronger robustness, just detectingReally rate is high, makes the labour intensity that manual intervention is few, greatly reduced staff.
Embodiment 2:
The present embodiment, on the basis of embodiment 1, also comprises step S2-2: oil level detection district in image to be identifiedDetermining of territory: obtain oil level positioning result according to step S2-1-6, by the oil level region mapping arranging in modelingIn image to be identified, determine surveyed area.
Further preferably, after step S2-2, carry out Edge Search, the slide calliper rule order setting during by modelingRow, carry out edge from top to bottom successively to search in oil level detection region.
Further preferably, complete after Edge Search, carrying out step S2-3: determine oil level edge, comprise withLower step:
S2-3-1: adopt affine transformation, bilinear interpolation technology to carry out image conversion to the image in each slide calliper rule,Make it to become rectangular image;
S2-3-2: each 2 dimension histogram is done to projection to y direction, obtain 1 dimension data;
S2-3-3: adopt filtering algorithm to carry out filtering to 1 dimension data, obtain multiple candidates peak of 1 dimension dataValue and low ebb;
S2-3-4: come edge calculation width, contrast, position etc. according to score computing rule and must assign to waitingSelect peak value, low ebb to screen, taking the highest peak value of score, low ebb as definite oil level edge.
Further preferably, oil while detecting in the oil level position that obtains and step S1 modeling according to step S2-3-4The bound of position, calculates the ratio of oil level.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for this areaTechnical staff, the present invention can have various modifications and variations. It is within the spirit and principles in the present invention all,Any amendment of doing, be equal to replacement, improvement etc., within protection scope of the present invention all should be included in.

Claims (5)

1. an Oil of Current Transformer position detecting method for robot used for intelligent substation patrol, is characterized in that: bagDraw together following steps:
S1: modeling: comprise the following steps:
S1-1 table meter location modeling: comprise the following steps:
S1-1-1: table meter region is chosen: by artificial judgment table meter scope, take whole table meter;
S1-1-2: parameter setting, adjustment: minimum, maximum-contrast are set, rotation, dimensional variation and everyParameter; Set and can test, adjust parameter according to test result, make it adapt to various light condition;
S1-1-3: preserve location model information: preserve above-mentioned parameters value;
S1-2 meter reading identification modeling: comprise the following steps:
S1-2-1: oil level region is set: with region, the fuel-displaced position of rectangle circle, record position, the rectangle frame upper left corner(xlt,ylt) and position, the lower right corner (xrd,yrd)；
S1-2-2: bound is set: draw from the bottom up straight line, straight-line lower end is oil level indicator lower limit end is straightLine upper end is oil level indicator upper limit end;
S1-2-3: add slide calliper rule: slide calliper rule are made up of multiple parallelogram, point-blank arrange, canChange length and width, slide calliper rule number is set;
S1-2-4: pointer edge pattern, width parameter are set: according to actual conditions arrange background to pointer, refer toPin is to the situation of change at edge, background place; And utilize kind of calliper edge to width;
S2: oil level detection: comprise the following steps:
S2-1 table meter location algorithm: comprise the following steps:
S2-1-1: filtering parameter: minimum, the maximum-contrast value of preserving while importing modeling, rotation, scale-valueAnd parameters;
S2-1-2: image pyramid algorithm: according to the filtering parameter importing, by template and image to be positioned differenceCarries out image matching algorithm, obtains respectively the image sequence that resolution ratio reduces by half continuously, and at high-definition picturePixel in the region of middle 2*2 is combined into a pixel in lower one deck low-resolution image; The image gold of templateWord tower is followed successively by from top to bottom: Il、Il-1...I2、I1; The image pyramid of image to be positioned is complied with from top to bottomInferiorly be: I 'l、I′l-1...I′2、I′1；
S2-1-3: calculation template Gradient Features: adopt edge detection algorithm to obtain template IlEdge feature, bagContaining each discrete point gradient, amplitude information;
S2-1-4: template matches: by the feature in S2-1-3 image I to be identified 'lIn from left to right, from upperCarry out characteristic similarity calculating to lower traversal:
s = 1 n Σ i = 1 n d i ′ T e q + p ′ | | d i ′ | | | | e q + p ′ | | = 1 n Σ i = 1 n t i ′ v r + r i ′ , c + c i ′ + u i ′ w r + r i ′ , c + c i ′ t i ′ 2 + u i ′ 2 v 2 r + r i ′ , c + c i ′ + w 2 r + r i ′ , c + c i ′ - - - ( 1 )
Direction vector is normalized, and similarity can not be subject to any illumination, block and chaotic impact;
S2-1-5: obtain matching result: obtain template in when traversal each position on bitmap undetermined by Step4Similarity score, score extreme higher position is designated as to target location (x, y);
S2-1-6: determine target location: this position is mapped to I 'l-1, then use template Il-1Near (x, y)In region, carry out Step3 to Step5, until carry out the bottom of image, i.e. I '1，I′1With image to be positionedUnanimously, both must show the position of meter.
2. the current transformer oil level of a kind of robot used for intelligent substation patrol according to claim 1 inspectionSurvey method, is characterized in that: also comprise step S2-2: in image to be identified, oil level detection region is definite:Obtain oil level positioning result according to step S2-1-6, the oil level region arranging in modeling is mapped to figure to be identifiedIn picture, determine surveyed area.
3. the current transformer oil level of a kind of robot used for intelligent substation patrol according to claim 2 inspectionSurvey method, is characterized in that: after step S2-2, carry out Edge Search, the card setting during by modelingChi sequence, carries out edge from top to bottom successively to search in oil level detection region.
4. the current transformer oil level of a kind of robot used for intelligent substation patrol according to claim 3 inspectionSurvey method, is characterized in that: complete after Edge Search, carry out step S2-3: determine oil level edge, bagDraw together following steps:
S2-3-1: adopt affine transformation, bilinear interpolation technology to carry out image conversion to the image in each slide calliper rule,Make it to become rectangular image;
S2-3-2: each 2 dimension histogram is done to projection to y direction, obtain 1 dimension data;
S2-3-3: adopt filtering algorithm to carry out filtering to 1 dimension data, obtain multiple candidates peak of 1 dimension dataValue and low ebb;
S2-3-4: come edge calculation width, contrast, position etc. according to score computing rule and must assign to waitingSelect peak value, low ebb to screen, taking the highest peak value of score, low ebb as definite oil level edge.
5. the current transformer oil level of a kind of robot used for intelligent substation patrol according to claim 4 inspectionSurvey method, is characterized in that: while detecting in the oil level position that obtains and step S1 modeling according to step S2-3-4The bound of oil level, calculates the ratio of oil level.
CN201511002514.1A 2015-12-28 2015-12-28 Current transformer oil level detection method of intelligent substation inspection robot Pending CN105608703A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201511002514.1A CN105608703A (en) 2015-12-28 2015-12-28 Current transformer oil level detection method of intelligent substation inspection robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201511002514.1A CN105608703A (en) 2015-12-28 2015-12-28 Current transformer oil level detection method of intelligent substation inspection robot

Publications (1)

Publication Number Publication Date
CN105608703A true CN105608703A (en) 2016-05-25

Family

ID=55988619

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201511002514.1A Pending CN105608703A (en) 2015-12-28 2015-12-28 Current transformer oil level detection method of intelligent substation inspection robot

Country Status (1)

Country Link
CN (1) CN105608703A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105825204A (en) * 2016-04-08 2016-08-03 国家电网公司 Method for identifying power equipment meter at night through intelligent camera
CN106778889A (en) * 2016-12-28 2017-05-31 天津普达软件技术有限公司 A kind of template matching method based on gradient intensity and direction
CN107610128A (en) * 2017-09-26 2018-01-19 山东鲁能智能技术有限公司 The method for inspecting and device of a kind of oil level indicator
CN109166096A (en) * 2018-07-16 2019-01-08 歌尔股份有限公司 A kind of image processing method, device and electronic equipment
CN112801087A (en) * 2019-11-13 2021-05-14 广东技术师范大学 Method for recognizing characters on surface of smart card based on adaptive parameter adjustment
CN113052823A (en) * 2021-03-26 2021-06-29 东莞市科研世智能科技有限公司 Oil level and oil color detection method and device, electronic equipment and storage medium
CN113139626A (en) * 2021-06-21 2021-07-20 浙江华睿科技有限公司 Template matching method and device, electronic equipment and computer-readable storage medium
CN113295910A (en) * 2021-05-14 2021-08-24 马鞍山电力规划勘察设计院有限责任公司 Split type clamp type current transformer and transformer substation line surveying and mapping method
CN113537197A (en) * 2021-01-26 2021-10-22 浙江国自机器人技术股份有限公司 Meter automatic modeling method based on machine vision

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1581209A (en) * 2004-05-21 2005-02-16 清华大学 Converting station circular/ellipsoid/square instrument monitoring method based object profile
US8249387B2 (en) * 2008-03-31 2012-08-21 Sungkyunkwan University Foundation For Corporate Collaboration Image processing method and apparatus for detecting lines of images and start and end points of lines
CN103927507A (en) * 2013-01-12 2014-07-16 山东鲁能智能技术有限公司 Improved multi-instrument reading identification method of transformer station inspection robot
CN104318198A (en) * 2014-02-28 2015-01-28 郑州金惠计算机系统工程有限公司 Identification method and device suitable for substation robot patrolling

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1581209A (en) * 2004-05-21 2005-02-16 清华大学 Converting station circular/ellipsoid/square instrument monitoring method based object profile
US8249387B2 (en) * 2008-03-31 2012-08-21 Sungkyunkwan University Foundation For Corporate Collaboration Image processing method and apparatus for detecting lines of images and start and end points of lines
CN103927507A (en) * 2013-01-12 2014-07-16 山东鲁能智能技术有限公司 Improved multi-instrument reading identification method of transformer station inspection robot
CN104318198A (en) * 2014-02-28 2015-01-28 郑州金惠计算机系统工程有限公司 Identification method and device suitable for substation robot patrolling

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105825204A (en) * 2016-04-08 2016-08-03 国家电网公司 Method for identifying power equipment meter at night through intelligent camera
CN106778889A (en) * 2016-12-28 2017-05-31 天津普达软件技术有限公司 A kind of template matching method based on gradient intensity and direction
CN107610128A (en) * 2017-09-26 2018-01-19 山东鲁能智能技术有限公司 The method for inspecting and device of a kind of oil level indicator
CN109166096A (en) * 2018-07-16 2019-01-08 歌尔股份有限公司 A kind of image processing method, device and electronic equipment
CN112801087A (en) * 2019-11-13 2021-05-14 广东技术师范大学 Method for recognizing characters on surface of smart card based on adaptive parameter adjustment
CN113537197A (en) * 2021-01-26 2021-10-22 浙江国自机器人技术股份有限公司 Meter automatic modeling method based on machine vision
CN113537197B (en) * 2021-01-26 2024-05-14 浙江国自机器人技术股份有限公司 Meter automatic modeling method based on machine vision
CN113052823A (en) * 2021-03-26 2021-06-29 东莞市科研世智能科技有限公司 Oil level and oil color detection method and device, electronic equipment and storage medium
CN113295910A (en) * 2021-05-14 2021-08-24 马鞍山电力规划勘察设计院有限责任公司 Split type clamp type current transformer and transformer substation line surveying and mapping method
CN113295910B (en) * 2021-05-14 2022-06-03 国网安徽省电力有限公司马鞍山供电公司 Split type clamp type current transformer and transformer substation line surveying and mapping method
CN113139626A (en) * 2021-06-21 2021-07-20 浙江华睿科技有限公司 Template matching method and device, electronic equipment and computer-readable storage medium
CN113139626B (en) * 2021-06-21 2021-10-15 浙江华睿科技股份有限公司 Template matching method and device, electronic equipment and computer-readable storage medium

Similar Documents

Publication Publication Date Title
CN105608703A (en) Current transformer oil level detection method of intelligent substation inspection robot
CN112906694B (en) Reading correction system and method for transformer substation inclined pointer instrument image
CN104200086B (en) Wide-baseline visible light camera pose estimation method
CN103148881B (en) Method and device for automatically reading pointer instrument by video frequency
CN100494886C (en) Three-dimensional scanning system circular index point detection method
CN109583324A (en) A kind of pointer meters reading automatic identifying method based on the more box detectors of single-point
CN106361345A (en) System and method for measuring height of human body in video image based on camera calibration
CN103927507A (en) Improved multi-instrument reading identification method of transformer station inspection robot
CN105286871A (en) Video processing-based body height measurement method
CN107833203A (en) A kind of horizontal plane identification and water level method for real-time measurement based on image procossing
CN107264570B (en) Steel rail light band distribution detecting device and method
CN107507174A (en) Power plant's instrument equipment drawing based on hand-held intelligent inspection is as recognition methods and system
CN107462174B (en) The method and device of the proportion of utilization factor and frame difference measurements contact net geometric parameter
CN105938554B (en) The tongue telescopic displacement monitoring method and system read based on image automatic judging
CN106295512A (en) Many correction line indoor vision data base construction method based on mark and indoor orientation method
CN107729853A (en) A kind of automatic identifying method suitable for the narrow tuning drive gear formula instrument of transformer station
CN106530271A (en) Infrared image significance detection method
CN107631782A (en) A kind of level testing methods based on Harris Corner Detections
CN108053416A (en) A kind of maximum oil reserve extraction system based on single width satellite image
CN109389165A (en) Oil level gauge for transformer recognition methods based on crusing robot
CN113688817A (en) Instrument identification method and system for automatic inspection
CN105423975B (en) The calibration system and method for a kind of large-scale workpiece
CN103389041B (en) A kind of method of measuring grid line width
CN108320799A (en) Image analysis and recognition method for lateral flow paper strip disease diagnosis
CN105893938A (en) Oil temperature gauge reading method and system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20160525