CN117830589A - Distribution transformer specified contour line length measurement system and method - Google Patents
Distribution transformer specified contour line length measurement system and method Download PDFInfo
- Publication number
- CN117830589A CN117830589A CN202410242435.0A CN202410242435A CN117830589A CN 117830589 A CN117830589 A CN 117830589A CN 202410242435 A CN202410242435 A CN 202410242435A CN 117830589 A CN117830589 A CN 117830589A
- Authority
- CN
- China
- Prior art keywords
- distribution transformer
- binocular camera
- contour line
- distance
- data
- 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.)
- Granted
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 109
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims description 39
- 230000000007 visual effect Effects 0.000 claims description 31
- 238000007781 pre-processing Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000003384 imaging method Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000000691 measurement method Methods 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 229910000808 amorphous metal alloy Inorganic materials 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a system and a method for measuring the length of a specified contour line of a distribution transformer, and relates to the technical field of distribution transformer detection. In order to solve the problems that in the prior art, the length of a specified contour line is obtained based on the symmetry of a distribution transformer, the contour line of the transformer may change, and the length of the specified contour line is inconsistent with the actual measured length; a distribution transformer stipulates the length measurement system of the outline, including data acquisition unit, outline withdraw unit and length measurement unit; the shape and the direction of the contour line can be determined by measuring the angle of the straight line where the characteristic points are located and combining the distance measurement data, the method is suitable for contour line measurement of various shapes, and the contour line length of the distribution transformer can be rapidly and accurately measured by determining the measurement distance data of the distribution transformer and the shape and the direction of the contour line, so that the measurement accuracy and efficiency are improved, the automation degree is high, and the influence of human factors on the measurement result is reduced.
Description
Technical Field
The invention relates to the technical field of distribution transformer detection, in particular to a distribution transformer specified contour line length measurement system and method.
Background
Distribution transformers are static electric appliances used in distribution systems for transmitting alternating current electric energy by converting alternating current voltage and current according to the law of electromagnetic induction. The main stream energy-saving distribution transformers mainly comprise an energy-saving oil immersed transformer and an amorphous alloy transformer. In an electrical power system, a distribution transformer is an important device responsible for converting a voltage from a lower level to a higher level. Concerning the contour line length measurement of transformers, there are related patents; for example, chinese patent publication No. CN115839690a discloses a method and a system for measuring the length of a specified contour line of an oil immersed distribution transformer, which includes obtaining the size information of the distribution transformer and the surrounding heat sinks according to the model information of the distribution transformer; according to the position of the specified contour line to be solved, the position of a measuring point is drawn, and the intercept from the measuring point to the distribution transformer is measured; the predetermined contour line length is obtained from the dimensional information and the intercept by combining the symmetry of the distribution transformer. The length of the specified contour line can be obtained through calculation, compared with the existing method for measuring the length of the specified contour line by adopting a ground paying-off method, the method has the advantages of one-time measurement completion, high repeatability, particularly outstanding advantages in comparison tests among laboratories, shortened measurement time, time and labor saving, rapidness and accuracy.
The above patent, although giving a prescribed contour length, still has the following problems:
in the prior art, the length of the specified contour line is obtained based on the symmetry of the distribution transformer, however, the contour line of the transformer may change with the passage of time, so that the condition that the length of the specified contour line is not consistent with the actual measured length is caused, and the measurement error is large;
the change of the contour line easily causes the working efficiency of the transformer to be reduced, even brings potential safety hazards, the transformer cannot be evaluated and analyzed according to the measurement data, the use of the transformer is affected, and the potential safety hazards cannot be found in time.
Disclosure of Invention
The invention aims to provide a distribution transformer specified contour line length measuring system and method, which can rapidly and accurately measure the contour line length of a distribution transformer by determining the measurement distance data of the distribution transformer and the shape and direction of the contour line, improve the measurement accuracy and efficiency, have high automation degree and reduce the influence of human factors on the measurement result so as to solve the problems in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a distribution transformer prescribed contour length measurement system, comprising:
the data acquisition unit is used for:
image data acquisition is carried out based on an image acquisition terminal, wherein the number of the image acquisition terminal is not less than one image acquisition point, and a two-dimensional characteristic image, under a plurality of view angles, of the distribution transformer to be measured, acquired by the image acquisition terminal is acquired;
performing image preprocessing on the two-dimensional characteristic images under the plurality of view angles, extracting depth information in the preprocessed two-dimensional characteristic images, and obtaining three-dimensional image data of the surface of the distribution transformer;
a contour line extraction unit configured to:
acquiring three-dimensional image data actively uploaded by the data acquisition unit, optimizing an image, determining the appearance characteristics of the distribution transformer based on the optimized three-dimensional image data, and identifying all endpoints of the contour line based on the appearance characteristics;
determining the distance between the endpoints based on each endpoint of the contour line, extracting the characteristic parameters of the contour line, and performing smoothing on the extracted characteristic parameters of the contour line to obtain a complete distribution transformer contour line;
a length measurement unit for:
matching corresponding distribution transformer models based on characteristic parameters of the distribution transformers, and calculating the lengths of the distribution transformer contour lines according to all endpoints of the contour lines;
and obtaining a measurement result, comparing the measurement data with historical measurement data, evaluating the change trend of the distribution transformer, and displaying the measurement result.
Further, the data acquisition unit includes:
the sensor acquisition module is used for acquiring image data of the distribution transformer to be measured by adopting a binocular camera to acquire two-dimensional images of the distribution transformer to be measured at two visual angles;
the image preprocessing module is used for carrying out center correction on the acquired image based on a sensor in the binocular camera, extracting the appearance of the distribution transformer from the corrected image and generating three-dimensional image data of the distribution transformer;
the data transmission module is used for establishing a data transmission channel, and transmitting the three-dimensional image data of the distribution transformer to the central processing platform based on the data transmission channel for data processing and length measurement.
Further, the sensor acquisition module includes:
the first distance information extraction module is used for extracting the baseline distance of the binocular camera;
the second distance information extraction module is used for extracting the linear distance between the installation position of the binocular camera and the distribution transformer;
the distance parameter acquisition module is used for acquiring the distance parameter of the binocular camera by utilizing the baseline distance of the binocular camera and the linear distance between the mounting position of the binocular camera and the distribution transformer; the distance parameter of the binocular camera is obtained through the following formula:
wherein S represents the binocular cameraA distance parameter of the head; sqrt represents an open root number operation; l (L) x Representing a baseline distance of the binocular camera; l (L) y Representing a linear distance between the distribution transformers; s is S 0 Representing a preset distance parameter reference value of the binocular camera; e represents a constant; x represents a preset multiple reference threshold value for evaluating a multiple relationship between a linear distance between the distribution transformers and the baseline distance;
and the parameter setting module is used for determining the visual angle of the binocular camera and the depth between the two lenses of the binocular camera by utilizing the distance parameter of the binocular camera.
Further, the parameter setting module includes:
the first parameter extraction module is used for extracting the baseline distance of the binocular camera and the linear distance between the mounting position of the binocular camera and the distribution transformer;
the second parameter extraction module is used for extracting the distance parameters of the binocular camera;
the visual angle parameter setting module is used for obtaining the visual angle of the binocular camera by utilizing the baseline distance of the binocular camera, the linear distance between the mounting position of the binocular camera and the distribution transformer and the distance parameter of the binocular camera, wherein the visual angle of the binocular camera is obtained by the following formula:
wherein F represents the visual angle of the binocular camera; d represents the diagonal dimension of the imaging screen of the binocular camera; f represents the focal length parameter of the binocular camera; s represents the distance parameter of the binocular camera; s is S 0 Representing a preset distance parameter reference value of the binocular camera;
the third parameter extraction module is used for extracting the focal length parameters of the binocular camera;
a fourth parameter extraction module, configured to extract parallax parameters of the binocular camera;
the depth parameter setting module is used for obtaining the depth of the binocular camera by utilizing the baseline distance of the binocular camera, the linear distance between the mounting position of the binocular camera and the distribution transformer, the focal length parameter and the parallax parameter of the binocular camera, and the distance parameter of the binocular camera, wherein the depth of the binocular camera is obtained by the following formula:
wherein Z represents the depth of the binocular camera; f represents the focal length parameter of the binocular camera; l (L) x Representing a baseline distance of the binocular camera; b represents the parallax parameter of the binocular camera (i.e. the difference between the pixel positions of the same object in the images of the left and right cameras of the binocular camera); s represents the distance parameter of the binocular camera; s is S 0 And representing a preset distance parameter reference value of the binocular camera.
Further, the image preprocessing module is further configured to:
acquiring two calibration images with parallax based on two-dimensional images of the distribution transformer to be measured at two visual angles, enabling the center points of the two calibration images to coincide with the image center points of the calibration images where the two calibration images are positioned, and carrying out parameter correction;
meanwhile, based on a binocular stereo vision method, the three-dimensional coordinate data of the distribution transformer to be measured are obtained by calculating the position deviation of the corresponding characteristic points in the two images;
and establishing a coordinate system for each two-dimensional characteristic image based on the three-dimensional coordinate data of the distribution transformer to be measured, and generating three-dimensional image data of the distribution transformer to be measured based on the three-dimensional coordinate data in the same coordinate system.
Further, the contour line extraction unit includes:
the image optimization module is used for acquiring two-dimensional images of the distribution transformer to be measured at two visual angles based on the data transmission channel, and carrying out filtering denoising treatment on the two-dimensional images to obtain a clear three-dimensional image of the distribution transformer to be measured;
the measuring point determining module is used for determining the appearance characteristics of the distribution transformer based on the three-dimensional image, and determining characteristic points to be measured according to the appearance characteristic points of the distribution transformer, wherein the characteristic points comprise a starting point, an ending point and turning points of the outline;
the contour line detection module is used for extracting edge information of the contour line and calculating the length of the contour line by combining the measurement angle and the height.
Further, the smoothing processing is performed on the extracted characteristic parameters of the contour line, specifically:
extracting feature points from the edge information of the contour line to obtain feature point extraction results;
comparing feature point extraction results of edge information of contour lines in two images with parallax, and selecting target contour line feature points appearing in each image data;
and filtering and denoising the target contour line characteristic points based on the mean value filtering method, and extracting the center of the filtered and denoised distribution transformer target contour line characteristic points to obtain a complete contour line.
Further, the contour line detection module specifically includes:
determining angle measurement data of the distribution transformer by measuring the angle of the straight line where the characteristic point is located, and determining measurement distance data of the distribution transformer based on the distance between the measurement angle and the characteristic point;
and determining the shape and the direction of the contour line based on the angle of the straight line where the measurement characteristic point is located and the combined distance measurement data.
Further, the length measurement unit includes:
the model matching module is used for matching the model of the distribution transformer corresponding to the model based on the appearance characteristics of the distribution transformer and acquiring the length data of the specified contour line of the distribution transformer associated with the model;
the length measurement module is used for calculating the length of the contour line based on the distance between the measurement characteristic points and the angle measurement data and determining the length of the contour line as the length measurement data of the distribution transformer;
the data comparison module is used for comparing the length measurement data of the distribution transformer with the history measurement data corresponding to the distribution transformer and evaluating the change trend of the distribution transformer;
and the display module is used for displaying the evaluation result and the length measurement data of the distribution transformer in real time, and simultaneously highlighting abnormal data in the change trend of the distribution transformer.
The invention provides another technical scheme, namely a distribution transformer specified contour line length measurement method, which comprises the following steps:
step one: acquiring a multi-view two-dimensional characteristic image of the distribution transformer by using an image acquisition terminal, and performing image preprocessing to acquire three-dimensional image data of the surface of the distribution transformer;
step two: carrying out optimization processing and feature point extraction on the three-dimensional image data through a contour line extraction unit to obtain a contour line image of the distribution transformer, and identifying each endpoint of the contour line;
step three: and calculating the length of each contour line of the distribution transformer according to each endpoint of the contour line, evaluating the change trend of the distribution transformer, and displaying the measurement result and the evaluation result of the distribution transformer in real time.
Compared with the prior art, the invention has the beneficial effects that:
1. the method comprises the steps of preprocessing an obtained original image, repairing a basic image, providing a good basis for subsequent edge detection, highlighting the contour features of a distribution transformer in the image, extracting the contour lines of the distribution transformer from the preprocessed image based on an edge detection algorithm in the prior art, forming a preliminary edge image, analyzing and extracting the features, further identifying each endpoint of the contour lines, and carrying out smoothing treatment on the feature parameters of the extracted contour lines, thereby obtaining the complete contour lines of the distribution transformer, improving the extraction precision of the contour lines, further improving the length measurement precision and reducing the measurement errors.
2. The shape and the direction of the contour line can be determined by measuring the angle of the straight line where the characteristic points are located and combining the distance measurement data, the method is suitable for contour line measurement of various shapes, and the contour line length of the distribution transformer can be rapidly and accurately measured by determining the measurement distance data of the distribution transformer and the shape and the direction of the contour line, so that the measurement accuracy and efficiency are improved, the automation degree is high, and the influence of human factors on the measurement result is reduced.
Drawings
Fig. 1 is a block diagram of a distribution transformer prescribed contour length measurement system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the technical problem that the length of the specified contour line is inconsistent with the actual measured length due to the fact that the contour line of the transformer may change over time, referring to fig. 1, the present embodiment provides the following technical scheme:
a distribution transformer prescribed contour length measurement system, comprising:
the data acquisition unit is used for:
image data acquisition is carried out based on an image acquisition terminal, wherein the number of the image acquisition terminal is not less than one image acquisition point, and a two-dimensional characteristic image, under a plurality of view angles, of the distribution transformer to be measured, acquired by the image acquisition terminal is acquired;
performing image preprocessing on the two-dimensional characteristic images under the plurality of view angles, extracting depth information in the preprocessed two-dimensional characteristic images, and obtaining three-dimensional image data of the surface of the distribution transformer;
a contour line extraction unit configured to:
acquiring three-dimensional image data actively uploaded by the data acquisition unit, optimizing an image, determining the appearance characteristics of the distribution transformer based on the optimized three-dimensional image data, and identifying all endpoints of the contour line based on the appearance characteristics;
determining the distance between the endpoints based on each endpoint of the contour line, extracting the characteristic parameters of the contour line, and performing smoothing on the extracted characteristic parameters of the contour line to obtain a complete distribution transformer contour line;
smoothing the extracted characteristic parameters of the contour lines, specifically:
extracting feature points from the edge information of the contour line to obtain feature point extraction results;
comparing feature point extraction results of edge information of contour lines in two images with parallax, and selecting target contour line feature points appearing in each image data;
the target contour line characteristic points comprise relevant characteristics of the distribution transformer, including parameters such as round angles, diameters, positions and the like;
filtering and denoising the target contour line characteristic points based on an average filtering method, and extracting the center of the filtered and denoised distribution transformer target contour line characteristic points to obtain a complete contour line;
specifically, the obtained original image is preprocessed, noise, interference and the like in the image are removed, a basic picture is repaired, a good foundation is provided for subsequent edge detection, the contour features of a distribution transformer in the image are highlighted, the contour lines of the distribution transformer are extracted from the preprocessed image based on an edge detection algorithm in the prior art, including Sobel, canny and the like, a preliminary edge image is formed, the features of the contour lines are analyzed and extracted, all endpoints of the contour lines are further identified, the characteristic parameters of the extracted contour lines are subjected to smoothing treatment, and therefore the complete contour lines of the distribution transformer are obtained, the extraction precision of the contour lines is improved, the length measurement precision is further improved, and the measurement error is reduced;
a length measurement unit for:
matching corresponding distribution transformer models based on characteristic parameters of the distribution transformers, and calculating the lengths of the distribution transformer contour lines according to all endpoints of the contour lines;
obtaining a measurement result, comparing the measurement data with historical measurement data, evaluating the change trend of the distribution transformer, and displaying the measurement result;
a length measurement unit comprising:
the model matching module is used for matching the model of the distribution transformer corresponding to the model based on the appearance characteristics of the distribution transformer and acquiring the length data of the specified contour line of the distribution transformer associated with the model;
the length measurement module is used for calculating the length of the contour line based on the distance between the measurement characteristic points and the angle measurement data and determining the length of the contour line as the length measurement data of the distribution transformer;
the data comparison module is used for comparing the length measurement data of the distribution transformer with the history measurement data corresponding to the distribution transformer and evaluating the change trend of the distribution transformer;
and the display module is used for displaying the evaluation result and the length measurement data of the distribution transformer in real time, and simultaneously highlighting abnormal data in the change trend of the distribution transformer.
Specifically, through the analysis to the measured data, can extract other potential fault characteristics of distribution transformer, perhaps can appear some abnormal conditions, for example sensor trouble, data transmission mistake etc. provide more valuable information for the maintenance and the maintenance of transformer, through modes such as cell-phone APP or email, inform relevant technical personnel with alarm information, ensure that the problem is solved in time, and look over measuring result directly perceivedly through display module, convenient and practical.
In order to solve the technical problem that the change of the contour line easily causes the reduction of the working efficiency of the transformer and even brings potential safety hazards, the transformer cannot be evaluated and analyzed according to the measured data, the use of the transformer is affected, and the potential safety hazards cannot be found in time, please refer to fig. 1, the embodiment provides the following technical scheme:
a data acquisition unit comprising:
the sensor acquisition module is used for acquiring image data of the distribution transformer to be measured by adopting a binocular camera to acquire two-dimensional images of the distribution transformer to be measured at two visual angles;
specifically, an infrared sensor, an ultrasonic sensor, a laser range finder and the like are specifically arranged in the binocular camera according to actual requirements; the method has the characteristics of high precision, high reliability and good stability;
specifically, the sensor acquisition module includes:
the first distance information extraction module is used for extracting the baseline distance of the binocular camera;
the second distance information extraction module is used for extracting the linear distance between the installation position of the binocular camera and the distribution transformer;
the distance parameter acquisition module is used for acquiring the distance parameter of the binocular camera by utilizing the baseline distance of the binocular camera and the linear distance between the mounting position of the binocular camera and the distribution transformer; the distance parameter of the binocular camera is obtained through the following formula:
wherein S represents the distance parameter of the binocular camera; sqrt represents an open root number operation; l (L) x Representing a baseline distance of the binocular camera; l (L) y Representing a linear distance between the distribution transformers; s is S 0 Representing a preset distance parameter reference value of the binocular camera; e represents a constant; x represents a preset multiple reference threshold value for evaluating a multiple relationship between a linear distance between the distribution transformers and the baseline distance;
and the parameter setting module is used for determining the visual angle of the binocular camera and the depth between the two lenses of the binocular camera by utilizing the distance parameter of the binocular camera.
The technical effects of the technical scheme are as follows: binocular disparity based distance estimation: the distance parameter (S) of the binocular camera is calculated by extracting the baseline distance of the binocular camera and the linear distance between the camera mounting position and the distribution transformer and using a given formula. This parameter represents the distance between the binocular camera and the object.
Distance parameter automation: the system can automatically calculate the distance parameters without manually inputting the distance information, thereby improving the convenience and accuracy of the system.
Depth and viewing angle calculations: through the calculated distance parameters, the system can further calculate the visual angle of the binocular camera and the depth information between the two lenses. This helps the system achieve stereoscopic vision and depth perception to better understand the location and distance of objects in the photographed scene.
Distribution transformer distance assessment: by taking into account the relationship between the linear distance between the distribution transformers and the baseline distance, the system can assess the relative position and distance between objects, which facilitates applications in different fields, such as object detection, autopilot, safety monitoring, and the like.
In general, the technical effect of the above technical solution of the present embodiment is to provide an automated method, which can calculate the distance parameter and the related viewing angle and depth information according to the configuration and the distance information of the binocular camera, so as to improve the depth perception and the stereoscopic vision capability of the vision system.
Specifically, the parameter setting module includes:
the first parameter extraction module is used for extracting the baseline distance of the binocular camera and the linear distance between the mounting position of the binocular camera and the distribution transformer;
the second parameter extraction module is used for extracting the distance parameters of the binocular camera;
the visual angle parameter setting module is used for obtaining the visual angle of the binocular camera by utilizing the baseline distance of the binocular camera, the linear distance between the mounting position of the binocular camera and the distribution transformer and the distance parameter of the binocular camera, wherein the visual angle of the binocular camera is obtained by the following formula:
wherein F represents the visual angle of the binocular camera; d represents the diagonal dimension of the imaging screen of the binocular camera; f represents the focal length parameter of the binocular camera; s represents the distance parameter of the binocular camera; s is S 0 Representing a preset distance parameter reference value of the binocular camera;
the third parameter extraction module is used for extracting the focal length parameters of the binocular camera;
a fourth parameter extraction module, configured to extract parallax parameters of the binocular camera;
the depth parameter setting module is used for obtaining the depth of the binocular camera by utilizing the baseline distance of the binocular camera, the linear distance between the mounting position of the binocular camera and the distribution transformer, the focal length parameter and the parallax parameter of the binocular camera, and the distance parameter of the binocular camera, wherein the depth of the binocular camera is obtained by the following formula:
wherein Z represents the depth of the binocular camera; f represents the focal length parameter of the binocular camera; l (L) x Representing a baseline distance of the binocular camera; b represents the parallax parameter of the binocular camera (i.e. the difference between the pixel positions of the same object in the images of the left and right cameras of the binocular camera); s represents the distance parameter of the binocular camera; s is S 0 And representing a preset distance parameter reference value of the binocular camera.
The technical effects of the technical scheme are as follows: and (3) calculating view angle parameters: by extracting the baseline distance of the binocular camera, the linear distance between the camera mounting position and the distribution transformer and the distance parameters of the binocular camera, the system can calculate the visual angle of the binocular camera. This parameter is very important in the vision system, as it determines the range and angle that the camera can see.
Depth parameter calculation: the system can calculate depth information of the binocular cameras by extracting baseline distances of the binocular cameras, linear distances between the camera mounting positions and the distribution transformers, focal length parameters and parallax parameters. Depth information helps to understand the distance and three-dimensional structure of objects in a photographed scene.
Automatic parameter extraction: the system can automatically extract the basic parameters of the binocular camera without manually inputting the parameters, thereby improving the convenience and accuracy of the system.
Reference value and reference threshold: the system evaluates parameters of the binocular camera using preset baseline values and reference thresholds to ensure that the calculated parameters are within reasonable limits.
In general, the technical effect of the above technical solution of the present embodiment is to provide an automated method that can calculate the viewing angle, depth and other parameters of the binocular camera to improve the depth perception and stereoscopic capability of the vision system. This is of potential importance in many fields of application, such as computer vision, autopilot, object detection, etc.
The image preprocessing module is used for carrying out center correction on the acquired image based on a sensor in the binocular camera, extracting the appearance of the distribution transformer from the corrected image and generating three-dimensional image data of the distribution transformer;
the image preprocessing module is further used for:
acquiring two calibration images with parallax based on two-dimensional images of the distribution transformer to be measured at two visual angles, enabling the center points of the two calibration images to coincide with the image center points of the calibration images where the two calibration images are positioned, and carrying out parameter correction;
meanwhile, based on a binocular stereo vision method, the three-dimensional coordinate data of the distribution transformer to be measured are obtained by calculating the position deviation of the corresponding characteristic points in the two images;
establishing a coordinate system for each two-dimensional characteristic image based on three-dimensional coordinate data of the distribution transformer to be measured, and generating three-dimensional image data of the distribution transformer to be measured based on the three-dimensional coordinate data in the same coordinate system;
the data transmission module is used for establishing a data transmission channel, and transmitting the three-dimensional image data of the distribution transformer to the central processing platform based on the data transmission channel for data processing and length measurement.
Specifically, the relative positions of two image visual angles of a binocular stereo vision method are fixed, a stereo pair under the visual angle is obtained, local segmentation is carried out on each stereo image pair aiming at the stereo pair under each visual angle, three-dimensional coordinate data in each visual angle image are established, based on the prior art, the included angle between reflected light of a laser ray emitted by a sensor in the binocular camera after being reflected on an object and an imaging plane is calculated, depth information of a corresponding position point on the surface of a measured piece is obtained, and therefore the data of the two visual angles are spliced based on the three-dimensional coordinate data, three-dimensional image data of a distribution transformer to be measured are obtained, the accuracy and the definition of three-dimensional imaging are further improved, and the reduction is clearer and more complete.
A contour extraction unit comprising:
the image optimization module is used for acquiring two-dimensional images of the distribution transformer to be measured at two visual angles based on the data transmission channel, and carrying out filtering denoising treatment on the two-dimensional images to obtain a clear three-dimensional image of the distribution transformer to be measured;
the measuring point determining module is used for determining the appearance characteristics of the distribution transformer based on the three-dimensional image, and determining characteristic points to be measured according to the appearance characteristic points of the distribution transformer, wherein the characteristic points comprise a starting point, an ending point and turning points of the outline;
specifically, determining the appearance characteristics of the distribution transformer, and extracting characteristics related to the distribution transformer, so as to obtain various information of the distribution transformer, such as data of model, manufacturer, position and the like, for subsequent inquiry and data comparison; the appearance and the use state of the distribution transformer can be intuitively reflected through the appearance characteristics, a basis is provided for subsequent identification and classification, the time for matching the data of the distribution transformer with the historical data is reduced, and the situation that errors or anomalies occur in evaluation due to errors in matching is avoided;
the contour line detection module is used for extracting edge information of the contour line and calculating the length of the contour line by combining the measurement angle and the height;
the contour line detection module specifically comprises:
determining angle measurement data of the distribution transformer by measuring the angle of the straight line where the characteristic point is located, and determining measurement distance data of the distribution transformer based on the distance between the measurement angle and the characteristic point;
and determining the shape and the direction of the contour line based on the angle of the straight line where the measurement characteristic point is located and the combined distance measurement data.
Specifically, the shape and the direction of the contour line can be determined by measuring the angle of the straight line where the characteristic point is located and combining the distance measurement data, the method is suitable for contour line measurement of various shapes, and the contour line length of the distribution transformer can be rapidly and accurately measured by determining the measurement distance data of the distribution transformer and the shape and the direction of the contour line, so that the accuracy and the efficiency of measurement are improved, the degree of automation is high, and the influence of human factors on the measurement result is reduced.
In order to better reveal a measurement method of a distribution transformer specified contour length measurement system, the invention provides another distribution transformer specified contour length measurement method, which comprises the following steps:
step one: acquiring a multi-view two-dimensional characteristic image of the distribution transformer by using an image acquisition terminal, and performing image preprocessing to acquire three-dimensional image data of the surface of the distribution transformer; preprocessing the image to enable the contour of the distribution transformer to be smoother, and further optimizing the quality of the contour line;
step two: carrying out optimization processing and feature point extraction on the three-dimensional image data through a contour line extraction unit to obtain a contour line image of the distribution transformer, and identifying each endpoint of the contour line; tracking and identifying the trend and shape of the contour line by identifying texture and shape information in the image;
step three: and calculating the length of each contour line of the distribution transformer according to each endpoint of the contour line, evaluating the change trend of the distribution transformer, displaying the measurement result and the evaluation result of the distribution transformer in real time, and providing an important reference basis for the maintenance and management of a power system.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should be covered by the protection scope of the present invention by making equivalents and modifications to the technical solution and the inventive concept thereof.
Claims (10)
1. A distribution transformer prescribed contour line length measurement system characterized by: comprising the following steps:
the data acquisition unit is used for:
image data acquisition is carried out based on an image acquisition terminal, wherein the number of the image acquisition terminal is not less than one image acquisition point, and a two-dimensional characteristic image, under a plurality of view angles, of the distribution transformer to be measured, acquired by the image acquisition terminal is acquired;
performing image preprocessing on the two-dimensional characteristic images under a plurality of view angles, and extracting depth information in the preprocessed two-dimensional characteristic images to obtain three-dimensional image data of the surface of the distribution transformer;
a contour line extraction unit configured to:
acquiring three-dimensional image data actively uploaded by the data acquisition unit, optimizing an image, determining the appearance characteristics of the distribution transformer based on the optimized three-dimensional image data, and identifying all endpoints of the contour line based on the appearance characteristics;
determining the distance between the endpoints based on each endpoint of the contour line, extracting the characteristic parameters of the contour line, and performing smoothing on the extracted characteristic parameters of the contour line to obtain a complete distribution transformer contour line;
a length measurement unit for:
matching corresponding distribution transformer models based on characteristic parameters of the distribution transformers, and calculating the lengths of the distribution transformer contour lines according to all endpoints of the contour lines;
and obtaining a measurement result, comparing the measurement data with historical measurement data, evaluating the change trend of the distribution transformer, and displaying the measurement result.
2. A distribution transformer specified contour length measurement system as defined in claim 1, wherein: a data acquisition unit comprising:
the sensor acquisition module is used for acquiring image data of the distribution transformer to be measured by adopting a binocular camera to acquire two-dimensional images of the distribution transformer to be measured at two visual angles;
the image preprocessing module is used for carrying out center correction on the acquired image based on a sensor in the binocular camera, extracting the appearance of the distribution transformer from the corrected image and generating three-dimensional image data of the distribution transformer;
the data transmission module is used for establishing a data transmission channel, and transmitting the three-dimensional image data of the distribution transformer to the central processing platform based on the data transmission channel for data processing and length measurement.
3. A distribution transformer specified contour length measurement system as defined in claim 2, wherein: a sensor acquisition module comprising:
the first distance information extraction module is used for extracting the baseline distance of the binocular camera;
the second distance information extraction module is used for extracting the linear distance between the installation position of the binocular camera and the distribution transformer;
the distance parameter acquisition module is used for acquiring the distance parameter of the binocular camera by utilizing the baseline distance of the binocular camera and the linear distance between the mounting position of the binocular camera and the distribution transformer; the distance parameter of the binocular camera is obtained through the following formula:
wherein S represents the distance parameter of the binocular camera; sqrt represents an open root number operation; l (L) x Representing a baseline distance of the binocular camera; l (L) y Representing the saidA linear distance between distribution transformers; s is S 0 Representing a preset distance parameter reference value of the binocular camera; e represents a constant; x represents a preset multiple reference threshold value for evaluating a multiple relationship between a linear distance between the distribution transformers and the baseline distance;
and the parameter setting module is used for determining the visual angle of the binocular camera and the depth between the two lenses of the binocular camera by utilizing the distance parameter of the binocular camera.
4. A distribution transformer specified contour length measurement system as defined in claim 2, wherein: a parameter setting module, comprising:
the first parameter extraction module is used for extracting the baseline distance of the binocular camera and the linear distance between the mounting position of the binocular camera and the distribution transformer;
the second parameter extraction module is used for extracting the distance parameters of the binocular camera;
the visual angle parameter setting module is used for obtaining the visual angle of the binocular camera by utilizing the baseline distance of the binocular camera, the linear distance between the mounting position of the binocular camera and the distribution transformer and the distance parameter of the binocular camera, wherein the visual angle of the binocular camera is obtained by the following formula:
wherein F represents the visual angle of the binocular camera; d represents the diagonal dimension of the imaging screen of the binocular camera; f represents the focal length parameter of the binocular camera; s represents the distance parameter of the binocular camera; s is S 0 Representing a preset distance parameter reference value of the binocular camera;
the third parameter extraction module is used for extracting the focal length parameters of the binocular camera;
a fourth parameter extraction module, configured to extract parallax parameters of the binocular camera;
the depth parameter setting module is used for obtaining the depth of the binocular camera by utilizing the baseline distance of the binocular camera, the linear distance between the mounting position of the binocular camera and the distribution transformer, the focal length parameter and the parallax parameter of the binocular camera, and the distance parameter of the binocular camera, wherein the depth of the binocular camera is obtained by the following formula:
wherein Z represents the depth of the binocular camera; f represents the focal length parameter of the binocular camera; l (L) x Representing a baseline distance of the binocular camera; b represents parallax parameters of the binocular camera; s represents the distance parameter of the binocular camera; s is S 0 And representing a preset distance parameter reference value of the binocular camera.
5. A distribution transformer specified contour length measurement system as defined in claim 2, wherein: the image preprocessing module is further used for:
acquiring two calibration images with parallax based on two-dimensional images of the distribution transformer to be measured at two visual angles, enabling the center points of the two calibration images to coincide with the image center points of the calibration images where the two calibration images are positioned, and carrying out parameter correction;
meanwhile, based on a binocular stereo vision method, the three-dimensional coordinate data of the distribution transformer to be measured are obtained by calculating the position deviation of the corresponding characteristic points in the two images;
and establishing a coordinate system for each two-dimensional characteristic image based on the three-dimensional coordinate data of the distribution transformer to be measured, and generating three-dimensional image data of the distribution transformer to be measured based on the three-dimensional coordinate data in the same coordinate system.
6. A distribution transformer specified contour length measurement system as defined in claim 5, wherein: a contour extraction unit comprising:
the image optimization module is used for acquiring two-dimensional images of the distribution transformer to be measured at two visual angles based on the data transmission channel, and carrying out filtering denoising treatment on the two-dimensional images to obtain a clear three-dimensional image of the distribution transformer to be measured;
the measuring point determining module is used for determining the appearance characteristics of the distribution transformer based on the three-dimensional image, and determining characteristic points to be measured according to the appearance characteristic points of the distribution transformer, wherein the characteristic points comprise a starting point, an ending point and turning points of the outline;
the contour line detection module is used for extracting edge information of the contour line and calculating the length of the contour line by combining the measurement angle and the height.
7. A distribution transformer specified contour length measurement system as defined in claim 6, wherein: smoothing the extracted characteristic parameters of the contour lines, specifically:
extracting feature points from the edge information of the contour line to obtain feature point extraction results;
comparing feature point extraction results of edge information of contour lines in two images with parallax, and selecting target contour line feature points appearing in each image data;
and filtering and denoising the target contour line characteristic points based on the mean value filtering method, and extracting the center of the filtered and denoised distribution transformer target contour line characteristic points to obtain a complete contour line.
8. A distribution transformer specified contour length measurement system as defined in claim 7, wherein: the contour line detection module specifically comprises:
determining angle measurement data of the distribution transformer by measuring the angle of the straight line where the characteristic point is located, and determining measurement distance data of the distribution transformer based on the distance between the measurement angle and the characteristic point;
and determining the shape and the direction of the contour line based on the angle of the straight line where the measurement characteristic point is located and the combined distance measurement data.
9. A distribution transformer specified contour length measurement system as defined in claim 8, wherein: a length measurement unit comprising:
the model matching module is used for matching the model of the distribution transformer corresponding to the model based on the appearance characteristics of the distribution transformer and acquiring the length data of the specified contour line of the distribution transformer associated with the model;
the length measurement module is used for calculating the length of the contour line based on the distance between the measurement characteristic points and the angle measurement data and determining the length of the contour line as the length measurement data of the distribution transformer;
the data comparison module is used for comparing the length measurement data of the distribution transformer with the history measurement data corresponding to the distribution transformer and evaluating the change trend of the distribution transformer;
and the display module is used for displaying the evaluation result and the length measurement data of the distribution transformer in real time, and simultaneously highlighting abnormal data in the change trend of the distribution transformer.
10. A distribution transformer specified contour length measurement method, implemented based on the distribution transformer specified contour length measurement system according to any of claims 1-9, characterized in that: the method comprises the following steps:
step one: acquiring a multi-view two-dimensional characteristic image of the distribution transformer by using an image acquisition terminal, and performing image preprocessing to acquire three-dimensional image data of the surface of the distribution transformer;
step two: carrying out optimization processing and feature point extraction on the three-dimensional image data through a contour line extraction unit to obtain a contour line image of the distribution transformer, and identifying each endpoint of the contour line;
step three: and calculating the length of each contour line of the distribution transformer according to each endpoint of the contour line, evaluating the change trend of the distribution transformer, and displaying the measurement result and the evaluation result of the distribution transformer in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410242435.0A CN117830589B (en) | 2024-03-04 | 2024-03-04 | Distribution transformer specified contour line length measurement system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410242435.0A CN117830589B (en) | 2024-03-04 | 2024-03-04 | Distribution transformer specified contour line length measurement system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117830589A true CN117830589A (en) | 2024-04-05 |
| CN117830589B CN117830589B (en) | 2024-05-24 |
Family
ID=90508073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410242435.0A Active CN117830589B (en) | 2024-03-04 | 2024-03-04 | Distribution transformer specified contour line length measurement system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117830589B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101555233B1 (en) * | 2014-10-31 | 2015-09-25 | 영남대학교 산학협력단 | Broadband sensor for detecting partial discharge of pole transformer |
| CN109926817A (en) * | 2018-12-20 | 2019-06-25 | 南京理工大学 | Transformer automatic assembly method based on machine vision |
| CN110824317A (en) * | 2019-12-06 | 2020-02-21 | 国网天津市电力公司 | Transformer partial discharge source rapid positioning system based on thermal imaging technology |
| US20200166333A1 (en) * | 2016-12-07 | 2020-05-28 | Ki 'an Chishine Optoelectronics Technology Co., Ltd. | Hybrid light measurement method for measuring three-dimensional profile |
| CN114120097A (en) * | 2021-10-21 | 2022-03-01 | 中国电力科学研究院有限公司 | Distribution network engineering on-site transformer detection method and system based on machine vision |
-
2024
- 2024-03-04 CN CN202410242435.0A patent/CN117830589B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101555233B1 (en) * | 2014-10-31 | 2015-09-25 | 영남대학교 산학협력단 | Broadband sensor for detecting partial discharge of pole transformer |
| US20200166333A1 (en) * | 2016-12-07 | 2020-05-28 | Ki 'an Chishine Optoelectronics Technology Co., Ltd. | Hybrid light measurement method for measuring three-dimensional profile |
| CN109926817A (en) * | 2018-12-20 | 2019-06-25 | 南京理工大学 | Transformer automatic assembly method based on machine vision |
| CN110824317A (en) * | 2019-12-06 | 2020-02-21 | 国网天津市电力公司 | Transformer partial discharge source rapid positioning system based on thermal imaging technology |
| CN114120097A (en) * | 2021-10-21 | 2022-03-01 | 中国电力科学研究院有限公司 | Distribution network engineering on-site transformer detection method and system based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 任舒琪: "基于多特征不变量融合的高频变压器尺寸视觉测量方法研究", 《中国优秀硕士学位论文全文数据库(信息科技辑)》, 15 January 2020 (2020-01-15), pages 8 - 47 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117830589B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109300161B (en) | Positioning method and device based on binocular vision | |
| CN110119680B (en) | Automatic error checking system of regulator cubicle wiring based on image recognition | |
| CN109974582B (en) | Device and method for non-contact visual detection of core wire size of automobile wire harness | |
| US7221805B1 (en) | Method for generating a focused image of an object | |
| CN111412842B (en) | Method, device and system for measuring cross-sectional dimension of wall surface | |
| CN109839384B (en) | Visual detector and detection method for detecting defects of micro vibration motor | |
| CN104634242A (en) | Point adding system and method of probe | |
| CN110425996A (en) | Workpiece size measurement method based on binocular stereo vision | |
| CN104483331A (en) | Three-dimensional detection method, three-dimensional detection device and three-dimensional detection system for connector contact pin | |
| CN109990711A (en) | A kind of appearance quality detection method of punched nickel-plated steel band | |
| Itami et al. | A simple calibration procedure for a 2D LiDAR with respect to a camera | |
| CN115330712A (en) | Intelligent quality inspection method and system for prefabricated components of fabricated building based on virtual-real fusion | |
| CN114596301A (en) | Coating roller surface defect detection system adopting 3D line laser profile technology | |
| CN117830589B (en) | Distribution transformer specified contour line length measurement system and method | |
| CN110851978A (en) | Camera position optimization method based on visibility | |
| CN108180871A (en) | A kind of method of quantitative assessment surface of composite insulator dusting roughness | |
| CN107202680B (en) | Module detection equipment and detection method | |
| CN116596987A (en) | Workpiece three-dimensional size high-precision measurement method based on binocular vision | |
| CN111475016A (en) | Assembly process geometric parameter self-adaptive measurement system and method based on computer vision | |
| Kochi et al. | 3D modeling of architecture by edge-matching and integrating the point clouds of laser scanner and those of digital camera | |
| CN112102473A (en) | Operation scene modeling method and system for distribution network live working robot | |
| Wang et al. | Detection of HF-ERW process by 3D bead shape measurement with line-structured laser vision | |
| CN112734840A (en) | Power transmission line safety distance measuring method | |
| Belhaoua et al. | Estimation of 3D reconstruction errors in a stereo-vision system | |
| CN114332069A (en) | Machine vision-based connector detection method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |