CN113342061A - Meter image identification dynamic correction method for transformer substation inspection robot - Google Patents
Meter image identification dynamic correction method for transformer substation inspection robot Download PDFInfo
- Publication number
- CN113342061A CN113342061A CN202110438626.0A CN202110438626A CN113342061A CN 113342061 A CN113342061 A CN 113342061A CN 202110438626 A CN202110438626 A CN 202110438626A CN 113342061 A CN113342061 A CN 113342061A
- Authority
- CN
- China
- Prior art keywords
- axis
- shooting
- shot
- instrument
- camera
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000007689 inspection Methods 0.000 title claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000003384 imaging method Methods 0.000 abstract description 17
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/12—Control of position or direction using feedback
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a substation inspection robot meter image identification dynamic correction method, which comprises the steps of establishing a coordinate system in a shooting range of a shooting cloud platform, calculating variable values of an initial position of a meter to be shot and an x axis and a y axis of the coordinate system, carrying out secondary fine adjustment on the shooting cloud platform by using a private motor according to the variable values, and correcting the position of a camera cloud platform so that the meter to be shot is positioned at the central point of the shooting range of the shooting cloud platform. When the transformer substation patrols and examines, the imaging effect of the camera shooting holder can be better through the method, and the accuracy rate of converting the meter picture into the display numerical value after the vector processing of the image recognition tool is higher.
Description
Technical Field
The invention relates to the technical field of robot image processing, in particular to a meter image identification dynamic correction method for a transformer substation inspection robot.
Background
The transformer substation is one of power equipment, and particularly relates to a place for converting voltage and current, receiving electric energy and distributing electric energy in a power system. In order to ensure the safe use of the transformer substation, the transformer substation needs to be regularly patrolled and examined, manual patrol and examine is the traditional operation mode of transformer substation patrol and examine, and patrol and examine personnel sometimes cause missing examination, wrong examination very easily because of factors such as work fatigue and boring, according to the statistics of China's electric academy of sciences and shows that the direct economic loss that each year causes because missing examination and wrong examination all exceeds 26 hundred million yuan, and visible manual patrol and examine and be difficult to guarantee the safe and reliable of electric power system. Along with the development of science and technology, use and patrol and examine the robot and accomplish the task of patrolling and examining, can improve the reliability of transformer substation's operation, become a development trend.
The existing inspection robot mostly adopts an automatic guide trolley to cooperate with a camera cloud platform to perform substation inspection work on equipment instruments of a substation. However, there are the following problems: when the automatic guide trolley travels to a shooting position and stops, the trolley body can generate an inclination angle under the influence of factors such as inertia and the like until part or all of an instrument to be shot exceeds the shooting range of a camera holder; secondly, the camera shooting tripod head is limited by the maximum upward lifting angle between the camera shooting tripod head and the automatic guide trolley, and the automatic guide trolley can only move to a position far away from the equipment of the transformer substation for shooting, so that the instrument to be shot deviates from the shooting range as long as the camera shooting tripod head horizontally rotates by a small angle.
Disclosure of Invention
In order to solve the problems, the invention provides a dynamic image identification and correction method for a meter of a transformer substation inspection robot.
The technical scheme adopted by the invention is as follows:
a transformer substation inspection robot meter image identification dynamic correction method comprises the following steps that firstly, a camera shooting cloud platform is started, the camera shooting cloud platform is moved, the position of a meter to be shot is identified, and the meter to be shot is enabled to be completely in the shooting range of the camera shooting cloud platform; establishing a coordinate system, establishing an x-axis and y-axis coordinate system by taking the central point of the shooting range of the camera holder as an origin, and recording the initial position of the instrument to be shot in the shooting range coordinate system; adjusting the position of three x axes, calculating the variable value of the x axis by the camera head according to the initial position of the instrument to be shot in the shooting range coordinate system, rotating an x axis servo motor for fine adjustment according to the variable value of the x axis, and correcting the instrument to be shot to the x axis of the shooting range coordinate system; adjusting the position of four y axes, calculating the variable value of the y axis by the camera head according to the initial position of the instrument to be shot in the shooting range coordinate system, rotating a y axis servo motor for fine adjustment according to the variable value of the y axis, and correcting the instrument to be shot to the y axis of the shooting range coordinate system; and fifthly, shooting, adjusting the focal length of the camera shooting holder, shooting the instrument to be shot after focusing, carrying out vector processing, and converting the picture subjected to vector processing into a display numerical value through an image recognition tool.
Preferably, the camera head calculates a value of a variable from the x-axis according to Δ x ═ f [ (x') - (x) ].
Preferably, the camera head calculates a value of a variable from the x-axis according to Δ y ═ f [ (y') - (y) ].
Preferably, the sequence of the third step and the fourth step can be interchanged.
The invention has the beneficial effects that:
according to the invention, a coordinate system is established in the shooting range of the camera shooting holder, the variable numerical values of the initial position of the instrument to be shot and the x axis and the y axis of the coordinate system are calculated, the camera shooting holder is finely adjusted for the second time by using a private servo motor according to the variable numerical values, and the position of the camera shooting holder is corrected, so that the instrument to be shot is positioned at the central point of the shooting range of the camera shooting holder. When the transformer substation patrols and examines, the imaging effect of the camera shooting holder can be better through the method, and the accuracy rate of converting the picture after vector processing into the display numerical value through the image recognition tool is higher.
Drawings
Fig. 1 and 2 are schematic imaging diagrams of a conventional camera head in use;
FIG. 3 is a schematic structural diagram of the present invention
FIG. 4 is a schematic flow chart of the dynamic image recognition correction according to the present invention;
FIG. 5 is a diagram illustrating dynamic modification according to a first embodiment of the present invention;
fig. 6 is a schematic diagram of dynamic correction according to the first embodiment of the present invention.
In fig. 3, 1-camera pan-tilt, 2-vertical rotation servo motor, 3-horizontal rotation servo motor.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
When the existing camera shooting cloud platform is used, as shown in fig. 1, if an instrument to be shot is located in a shooting range of the camera shooting cloud platform and is located at a central point of an imaging range of the camera shooting cloud platform, after the camera shooting cloud platform images, an image recognition tool inside the camera shooting cloud platform can be effectively converted according to a deviation angle between a pointer on an imaged picture and a zero point position, so that a display numerical value is formed. As shown in fig. 2, if the instrument to be photographed is in the photographing range of the camera head but not at the central point of the imaging range of the camera head, the image recognition tool inside the camera head cannot be effectively converted, and a display numerical value cannot be formed.
As shown in fig. 3, the present invention adds a vertical rotation servo motor 2 and a horizontal rotation servo motor 3 on the basis of the hardware of the existing camera head 1, so that the camera head 1 can rotate vertically by the vertical rotation servo motor 2 and can rotate horizontally by the horizontal rotation servo motor 3. Since the servo motor can control the control speed and the position precision very accurately, the camera head 1 can realize micro adjustment. It should be noted that the above-mentioned effects can be achieved by using other mechanical mechanisms in addition to the servo motor.
When the image recognition dynamic correction is performed, as shown in fig. 4, the camera head is started, and the camera head is moved to recognize the position of the instrument to be photographed, so that all the instruments to be photographed appear in the photographing range of the camera head. And then establishing a coordinate system, establishing an x-axis and y-axis coordinate system by taking the central point of the shooting range of the camera head as an original point, and recording the initial position of the instrument to be shot in the coordinate system of the shooting range by the camera head through an internal storage system. And then, adjusting the position of the x axis, calculating the variable value of the x axis by the camera head according to the initial position of the instrument to be shot in the imaging range coordinate system, rotating the x axis servo motor according to the variable value of the x axis for fine adjustment, and correcting the instrument to be shot to the x axis of the imaging range coordinate system. And then, adjusting the position of the y axis, calculating the variable value of the y axis by the camera head according to the initial position of the instrument to be shot in the imaging range coordinate system, rotating a y axis servo motor according to the variable value of the y axis for fine adjustment, and correcting the instrument to be shot to the y axis of the imaging range coordinate system, wherein the instrument to be shot is positioned at the central point of the shooting range of the camera head. And finally, carrying out photographing treatment, adjusting the focal length by the camera shooting holder, shooting the instrument to be shot after focusing, and converting the shot instrument and meter picture into a display numerical value after vector treatment by an image recognition tool.
In order to specifically describe the image recognition dynamic correction method, the invention provides two embodiments. First embodiment as shown in fig. 5, after the camera head is started and movedThe position of the meter to be photographed appears within the photographing range of the camera head. And after an x-axis and y-axis coordinate system is established by taking the central point of the shooting range of the camera head as an origin, the initial position of the instrument to be shot is positioned between J and K of the x axis and 3 of the y axis. At this time, the camera head records the initial position of the instrument to be photographed in the photographing range coordinate system through the internal storage system, that is, | x ═ K, J, and y ═ 3. Then, adjusting the position of an x axis, wherein the initial position x 'of the camera holder in the imaging range coordinate system according to the instrument to be shot is (K, J), and the initial position y' is 3; by the formula Δ x ═ f [ (x') - (x)]In the formula, x represents the x-axis origin position, i.e., x is (F, G). The value of the variable with the x-axis is calculated, i.e. Δ x ═ F [ (K-F), (J-G)]Based on the x-axis variable value Deltax, the horizontal rotation servo motor rotating the x-axis moves DeltaxAnAnd (5) fine adjustment is carried out on the unit, and the instrument to be shot is corrected to the x axis of the imaging range coordinate system. Then, adjusting the position of the y axis, wherein the initial position x 'of the camera shooting holder in the imaging range coordinate system is (K, J), and the y' is 3; f [ (y') - (y) by the formula Δ y]In the formula, y represents the origin position of the y axis, i.e., y is 0. The value of the variable with the y-axis is calculated, i.e. Δ y ═ f [ (3-0)]Based on the y-axis variable value Δ y, the vertical rotary servomotor for rotating the y-axis moves by Δ yAnAnd (5) fine adjustment is carried out on the unit, and the instrument to be shot is corrected to the y axis of the imaging range coordinate system. At the moment, the instrument to be shot is located at the central point of the shooting range of the camera shooting holder, and then the shooting process can be carried out. And adjusting the focal length of the camera shooting holder, shooting the instrument to be shot after focusing, recognizing the deflection angle between the pointer and the zero position after the shot instrument picture is processed by the image recognition tool vector, and displaying the corresponding numerical value in proportion.
In a second embodiment, as shown in fig. 6, after the camera head is started and moved, the position of the instrument to be photographed appears in the photographing range of the camera head. And establishing an x-axis and y-axis coordinate system by taking the central point of the shooting range of the camera head as an origin, wherein the initial position of the instrument to be shot is positioned on the x axis and 3 positions of the y axis. At this time, the camera head records the initial position of the instrument to be photographed in the photographing range coordinate system through the internal storage system, namely x ═ F, G, and y ═ 3. Then directly skip xAdjusting the axis position, namely directly adjusting the y-axis position, wherein the position x 'of the camera holder in the imaging range coordinate system is (F, G), and the position y' is 3 according to the instrument to be shot; f [ (y') - (y) by the formula Δ y]In the formula, y represents the origin position of the y axis, i.e., y is 0. The value of the variable with the y-axis is calculated, i.e. Δ y ═ f [ (3-0)]Vertical rotation servomotor movement Δ y to rotate y-axis according to y-axis variable value Δ yAnAnd (5) fine adjustment is carried out on the unit, and the instrument to be shot is corrected to the y axis of the imaging range coordinate system. The instrument to be shot is located at the center of the shooting range of the camera shooting holder, the camera shooting holder adjusts the focal length, the instrument to be shot is shot after being focused, vector processing is carried out, the image after the vector processing identifies that the deflection angle between the pointer and the zero position is 90 degrees through the image identification tool, and the image is converted into a display numerical value of 1.5.
It should be noted that if the initial position of the instrument to be photographed is located on the y-axis, the camera head calculates the variable value of the x-axis according to the position of the instrument to be photographed in the imaging range coordinate system, and rotates the x-axis servo motor to perform fine adjustment according to the variable value of the x-axis, and after the instrument to be photographed is corrected to the x-axis of the imaging range coordinate system, the instrument to be photographed is located at the center point of the shooting range of the camera head, so that the y-axis position adjustment can be skipped. In addition, the sequence of the x-axis position adjustment and the y-axis position adjustment can be interchanged, and after the sequence is interchanged, the correction result is not influenced.
Claims (4)
1. A transformer substation inspection robot meter image identification dynamic correction method is characterized in that: comprises the following steps of (a) carrying out,
the method comprises the steps that firstly, a camera shooting cloud platform is started, the camera shooting cloud platform is moved, the position of an instrument to be shot is identified, and the instrument to be shot is enabled to be completely in the shooting range of the camera shooting cloud platform;
establishing a coordinate system, establishing an x-axis and y-axis coordinate system by taking the central point of the shooting range of the camera holder as an origin, and recording the initial position of the instrument to be shot in the shooting range coordinate system;
adjusting the position of three x axes, calculating the variable value of the x axis by the camera head according to the initial position of the instrument to be shot in the shooting range coordinate system, rotating an x axis servo motor for fine adjustment according to the variable value of the x axis, and correcting the instrument to be shot to the x axis of the shooting range coordinate system;
adjusting the position of four y axes, calculating the variable value of the y axis by the camera head according to the initial position of the instrument to be shot in the shooting range coordinate system, rotating a y axis servo motor for fine adjustment according to the variable value of the y axis, and correcting the instrument to be shot to the y axis of the shooting range coordinate system; and fifthly, shooting, adjusting the focal length of the camera shooting holder, shooting the instrument to be shot after focusing, carrying out vector processing, and converting the shot instrument picture into a display numerical value after the vector processing by an image recognition tool.
2. The image recognition dynamic correction method of claim 1, wherein: the camera tripod head calculates a variable value with the x axis according to the delta x ═ f [ (x') - (x) ].
3. The image recognition dynamic correction method of claim 1, wherein: the camera tripod head calculates a variable value with the x axis according to the delta y ═ f [ (y') - (y) ].
4. The image recognition dynamic correction method of claim 1, wherein: the sequence of the third step and the fourth step can be interchanged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110438626.0A CN113342061A (en) | 2021-04-22 | 2021-04-22 | Meter image identification dynamic correction method for transformer substation inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110438626.0A CN113342061A (en) | 2021-04-22 | 2021-04-22 | Meter image identification dynamic correction method for transformer substation inspection robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113342061A true CN113342061A (en) | 2021-09-03 |
Family
ID=77468384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110438626.0A Pending CN113342061A (en) | 2021-04-22 | 2021-04-22 | Meter image identification dynamic correction method for transformer substation inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113342061A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615147A (en) * | 2015-02-13 | 2015-05-13 | 中国北方车辆研究所 | Method and system for accurately positioning polling target of transformer substation |
| CN110503144A (en) * | 2019-08-15 | 2019-11-26 | 南京天创电子技术有限公司 | A kind of pointer instrument recognition methods for crusing robot |
| CN111814919A (en) * | 2020-08-31 | 2020-10-23 | 江西小马机器人有限公司 | Instrument positioning and identifying system based on deep learning |
| CN112183369A (en) * | 2020-09-29 | 2021-01-05 | 国网上海市电力公司 | Pointer instrument reading identification method for transformer substation unmanned inspection |
| CN112476461A (en) * | 2020-11-26 | 2021-03-12 | 云南电网有限责任公司昆明供电局 | Transformer substation inspection robot carrying unmanned aerial vehicle and inspection method |
| CN112561986A (en) * | 2020-12-02 | 2021-03-26 | 南方电网电力科技股份有限公司 | Secondary alignment method, device, equipment and storage medium for inspection robot holder |
-
2021
- 2021-04-22 CN CN202110438626.0A patent/CN113342061A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615147A (en) * | 2015-02-13 | 2015-05-13 | 中国北方车辆研究所 | Method and system for accurately positioning polling target of transformer substation |
| CN110503144A (en) * | 2019-08-15 | 2019-11-26 | 南京天创电子技术有限公司 | A kind of pointer instrument recognition methods for crusing robot |
| CN111814919A (en) * | 2020-08-31 | 2020-10-23 | 江西小马机器人有限公司 | Instrument positioning and identifying system based on deep learning |
| CN112183369A (en) * | 2020-09-29 | 2021-01-05 | 国网上海市电力公司 | Pointer instrument reading identification method for transformer substation unmanned inspection |
| CN112476461A (en) * | 2020-11-26 | 2021-03-12 | 云南电网有限责任公司昆明供电局 | Transformer substation inspection robot carrying unmanned aerial vehicle and inspection method |
| CN112561986A (en) * | 2020-12-02 | 2021-03-26 | 南方电网电力科技股份有限公司 | Secondary alignment method, device, equipment and storage medium for inspection robot holder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106125744B (en) | The Intelligent Mobile Robot cloud platform control method of view-based access control model servo | |
| CN109739239B (en) | Planning method for uninterrupted instrument recognition of inspection robot | |
| CN109940603B (en) | Point-of-arrival error compensation control method for inspection robot | |
| CN111161446A (en) | Image acquisition method of inspection robot | |
| WO2022037633A1 (en) | Calibration method and apparatus for binocular camera, image correction method and apparatus for binocular camera, storage medium, terminal and intelligent device | |
| CN112949478A (en) | Target detection method based on holder camera | |
| CN111912381A (en) | Airplane control surface angle measuring method based on binocular vision principle | |
| CN113724337B (en) | Camera dynamic external parameter calibration method and device without depending on tripod head angle | |
| CN112658643B (en) | Connector assembly method | |
| CN111759463A (en) | Method for improving positioning precision of surgical mechanical arm | |
| WO2020063058A1 (en) | Calibration method for multi-degree-of-freedom movable vision system | |
| CN113111715A (en) | Unmanned aerial vehicle target tracking and information acquisition system and method | |
| CN113155084A (en) | Binocular vision distance measuring device and method based on laser cross standard line assistance | |
| CN111408861A (en) | Five-axis laser equipment RTCP calibration equipment and method | |
| CN114820761A (en) | XY-direction included angle measuring and motion compensating method based on image micro-scanning platform | |
| CN113177918A (en) | Intelligent and accurate inspection method and system for electric power tower by unmanned aerial vehicle | |
| CN108227753A (en) | For the not parking method for inspecting of power equipment | |
| Hao et al. | Image-based visual servoing for position alignment with orthogonal binocular vision | |
| CN113192121B (en) | Light spot center sliding weighted centroid positioning method under atmospheric turbulence | |
| CN113342061A (en) | Meter image identification dynamic correction method for transformer substation inspection robot | |
| CN110702423B (en) | Dynamic stability analysis method and device for metro vehicle door system | |
| CN116931248A (en) | Microscope automatic focusing method and system based on image definition evaluation | |
| CN114815211B (en) | Microscope automatic focusing method based on image processing | |
| CN105812669A (en) | Curved automatic imaging focusing method and system | |
| CN109318235A (en) | A kind of quick focusing method of Visual Servoing System |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210903 |