CN115294145B - Method and system for measuring sag of power transmission line - Google Patents
Method and system for measuring sag of power transmission line Download PDFInfo
- Publication number
- CN115294145B CN115294145B CN202211231249.4A CN202211231249A CN115294145B CN 115294145 B CN115294145 B CN 115294145B CN 202211231249 A CN202211231249 A CN 202211231249A CN 115294145 B CN115294145 B CN 115294145B
- Authority
- CN
- China
- Prior art keywords
- target
- transmission line
- power transmission
- image data
- sag
- 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.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 161
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005259 measurement Methods 0.000 claims abstract description 51
- 239000011159 matrix material Substances 0.000 claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 239000000725 suspension Substances 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 230000009467 reduction Effects 0.000 claims description 41
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 5
- 238000000691 measurement method Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 description 30
- 238000004422 calculation algorithm Methods 0.000 description 14
- 238000001514 detection method Methods 0.000 description 12
- 238000007619 statistical method Methods 0.000 description 8
- 238000007796 conventional method Methods 0.000 description 6
- 230000000877 morphologic effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02G—INSTALLATION OF ELECTRIC CABLES OR LINES, OR OF COMBINED OPTICAL AND ELECTRIC CABLES OR LINES
- H02G1/00—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines
- H02G1/02—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines for overhead lines or cables
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Power Engineering (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Mathematical Physics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method and a system for measuring sag of a power transmission line, which respond to a received sag measurement request, acquire target image data corresponding to a target power transmission line through a preset binocular vision sensor and perform preprocessing to obtain corresponding preprocessed image data; performing feature extraction on the preprocessed image data through a preset selected area to obtain a plurality of target image features; selecting a plurality of target clusters according to the co-occurrence matrix matching result of the characteristics of the plurality of target images, and performing epipolar constraint to obtain an intermediate matching point pair; performing curve fitting on the intermediate matching point pairs on a two-dimensional plane to determine the lowest point coordinate corresponding to the target power transmission line; determining a sag value by adopting the coordinates of the suspension point and the coordinates of the lowest point; the method solves the technical problems that the arc sag of the power transmission line is measured usually through manual inspection observation in the existing method for measuring the arc sag of the power transmission line, but the arc sag efficiency of the power transmission line is low through the measurement mode, and the arc sag of the power transmission line cannot be accurately measured.
Description
Technical Field
The invention relates to the technical field of sag measurement, in particular to a method and a system for measuring sag of a power transmission line.
Background
The sag of the transmission line determines the tightness degree of the transmission line and the height of a transmission tower, and is an important index for the design and operation of the transmission line. The size of the arc sag of the power transmission line directly influences the safe and stable operation of the power transmission line. And the change of the operating load of the power transmission line and the change of the surrounding environment can cause the change of the sag of the power transmission line, so that potential safety hazards are easy to appear. Therefore, it needs to be monitored and maintained continuously to ensure the safe operation of the transmission line.
The existing method for measuring the sag of the power transmission line generally measures the power transmission line through manual inspection observation, but the measurement method for measuring the sag of the power transmission line is low in efficiency and cannot accurately measure the sag of the power transmission line.
Disclosure of Invention
The invention provides a method and a system for measuring sag of a power transmission line, which solve the technical problems that the sag of the power transmission line is measured by manual inspection observation in the conventional method for measuring the sag of the power transmission line, but the measurement efficiency of the sag of the power transmission line is low and the sag of the power transmission line cannot be accurately measured by the measurement mode.
The invention provides a method for measuring sag of a power transmission line, which comprises the following steps:
responding to the received sag measurement request, and acquiring target image data corresponding to the target power transmission line through a preset binocular vision sensor;
preprocessing the target image data to obtain corresponding preprocessed image data;
performing feature extraction on the preprocessed image data through a preset selected area to obtain a plurality of target image features;
selecting a plurality of target clusters according to the co-occurrence matrix matching result of the target image characteristics, and performing epipolar constraint to obtain an intermediate matching point pair;
performing curve fitting on the intermediate matching point pairs on a two-dimensional plane, and determining the lowest point coordinate corresponding to the target power transmission line;
and determining the sag value corresponding to the target power transmission line by adopting the hanging point coordinate corresponding to the target power transmission line and the lowest point coordinate.
Optionally, the method further includes, before the step of responding to the received sag measurement request and acquiring target image data corresponding to the target power transmission line through a preset binocular vision sensor, a binocular vision sensor and a calibration plate arranged at a front end of the binocular vision sensor, the method further includes:
acquiring a left calibration image and a right calibration image corresponding to the calibration plate through the binocular vision sensor;
detecting the corresponding mark points of the left and right calibration images, and calculating corresponding coordinate data;
and calibrating an internal reference matrix, a distortion coefficient and a binocular baseline corresponding to the binocular vision sensor by adopting the coordinate data.
Optionally, the step of preprocessing the target image data to obtain corresponding preprocessed image data includes:
acquiring target pixel points corresponding to the target image data, and performing convolution calculation on pixel values corresponding to the target pixel points to obtain corresponding noise reduction image data;
acquiring the pixel number, the gray value and the total number of the gray values corresponding to the noise reduction image data;
calculating the gray value frequency corresponding to each noise reduction image data by adopting the total number of the gray values and the number of pixels, and determining a binarization threshold value by combining the gray values;
carrying out binarization on the noise reduction image data by adopting the binarization threshold value to obtain binarization image data;
and corroding and expanding the binary image data to obtain corresponding preprocessed image data.
Optionally, the step of obtaining a target pixel point corresponding to the target image data, and performing convolution calculation on a pixel value corresponding to the target pixel point to obtain corresponding noise reduction image data includes:
exposing the grating corresponding to the target image data to obtain corresponding exposure charges;
carrying out light-shielding storage on the exposure charges, and capturing corresponding target pixel points;
and performing convolution calculation on the pixel value corresponding to the target pixel point to obtain corresponding noise reduction image data.
Optionally, the step of calculating a gray value frequency corresponding to each of the noise-reduced image data by using the total number of gray values and the number of pixels, and determining a binarization threshold by combining the gray value includes:
calculating a first ratio between the total number of the gray values and the number of pixels to obtain the corresponding gray value frequency;
and determining a binarization threshold value by adopting the gray value frequency and the gray value.
Optionally, the step of performing feature extraction on the preprocessed image data through a preset selected region to obtain a plurality of target image features includes:
rotating the preprocessed image data through a preset selected area, and calculating a pixel point LBP value corresponding to the preset selected area;
and sequencing the LBP values of the pixel points according to the anticlockwise rotating sequence, and converting the sequencing result into a decimal system to obtain a plurality of target image characteristics.
Optionally, the step of selecting a plurality of target clusters according to the co-occurrence matrix matching result of the plurality of target image features, and performing epipolar constraint to obtain an intermediate matching point pair includes:
carrying out mean value clustering on the plurality of target image characteristics to obtain a plurality of target clusters;
acquiring the common occurrence frequency corresponding to each target cluster, and calculating the target symbiosis probability corresponding to each target cluster;
matching the plurality of target clusters according to the target symbiosis probability to obtain an initial matching point pair;
and carrying out polar line constraint on the initial matching point pair to obtain a middle matching point pair.
Optionally, the step of performing curve fitting on the intermediate matching point pair on a two-dimensional plane to determine a lowest point coordinate corresponding to the target power transmission line includes:
obtaining a target space point pair corresponding to the intermediate matching point pair;
projecting the target space point pair to a two-dimensional plane to obtain a two-dimensional space point pair;
and performing curve fitting on the two-dimensional space point pairs by adopting a least square method, and determining the lowest point coordinate corresponding to the target power transmission line.
Optionally, the step of determining the sag value corresponding to the target power transmission line by using the hanging point coordinate corresponding to the target power transmission line and the lowest point coordinate includes:
calculating an absolute value of a first difference value between an abscissa corresponding to the coordinates of the suspension point and an abscissa corresponding to the coordinates of the lowest point to obtain a first target absolute value;
calculating an absolute value of a second difference value between a vertical coordinate corresponding to the coordinates of the hanging point and a vertical coordinate corresponding to the coordinates of the lowest point to obtain a second target absolute value;
determining a sag value corresponding to the target power transmission line by adopting the first target absolute value and the second target absolute value;
the calculation formula of the first target absolute value is as follows:
wherein,representing the absolute value of the first target,represents the abscissa corresponding to the coordinates of the suspension point,representing an abscissa corresponding to the lowest point coordinate;
the calculation formula of the second target absolute value is as follows:
wherein,representing the absolute value of the second target,represents the ordinate corresponding to the coordinates of the suspension point,representing a vertical coordinate corresponding to the lowest point coordinate;
the calculation formula of the sag value is as follows:
The invention provides a measuring system for sag of a power transmission line in a second aspect, which comprises:
the response module is used for responding to the received sag measurement request and acquiring target image data corresponding to the target power transmission line through a preset binocular vision sensor;
the preprocessing module is used for preprocessing the target image data to obtain corresponding preprocessed image data;
the feature extraction module is used for extracting features of the preprocessed image data through a preset selected area to obtain a plurality of target image features;
the matching module is used for selecting a plurality of target clusters according to the co-occurrence matrix matching result of the target image characteristics and carrying out epipolar constraint to obtain an intermediate matching point pair;
the fitting module is used for performing curve fitting on the intermediate matching point pairs on a two-dimensional plane and determining the lowest point coordinate corresponding to the target power transmission line;
and the sag value acquisition module is used for determining a sag value corresponding to the target power transmission line by adopting the suspension point coordinate and the lowest point coordinate corresponding to the target power transmission line.
According to the technical scheme, the invention has the following advantages:
when a sag measurement request sent by any measuring person is received, the sag measurement request is read, the position of a corresponding target power transmission line is obtained, target image data corresponding to the target power transmission line is obtained through a preset binocular vision sensor, noise reduction processing, binarization processing and morphological processing are carried out on the target image data, corresponding preprocessed image data are obtained, when feature extraction is carried out through a circular LBP operator, a detection window is provided with a circular area with the radius of r, feature extraction is carried out on the preprocessed image data, a plurality of target image features are obtained, a plurality of target clusters are obtained after K-means algorithm processing is carried out according to the plurality of target image features, then co-occurrence times of each target cluster in the preprocessed image data are solved through solving a co-occurrence matrix, the co-occurrence probability of each target cluster is solved through a gray level co-occurrence matrix statistical method, polar line constraint is carried out on the target clusters, intermediate matching is obtained, intermediate matching point pairs are projected to a two-dimensional plane and curve fitting is carried out, the lowest point corresponding to the target power transmission line coordinates are determined, and the hanging sag value corresponding to the sag value of the target power transmission line is calculated according to the obtained coordinates; the technical problems that the sag of the power transmission line is low in efficiency and cannot be accurately measured by the measuring method of the sag of the power transmission line in the conventional method for measuring the sag of the power transmission line, which is usually measured by manual inspection observation; according to the invention, the noise reduction processing is carried out on the target image data through the filter, the image noise can be effectively filtered, and meanwhile, the circular LBP operator and the co-occurrence matrix matching algorithm are adopted, so that the required target image characteristics can be accurately extracted and matched, and the sag measurement accuracy is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating steps of a method for measuring sag of a power transmission line according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of a method for measuring sag of a power transmission line according to a second embodiment of the present invention;
fig. 3 is a block diagram of a power transmission line sag measurement system according to a third embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method and a system for measuring sag of a power transmission line, which are used for solving the technical problems that the sag of the power transmission line is measured usually by manual inspection observation in the conventional method for measuring the sag of the power transmission line, but the measurement of the sag of the power transmission line by the measuring method is low in efficiency and cannot be accurately measured.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating steps of a method for measuring sag of a power transmission line according to an embodiment of the present invention.
The invention provides a method for measuring sag of a power transmission line, which comprises the following steps:
The transmission line is realized by using a transformer to boost the electric energy generated by the generator and then connecting the electric energy to the transmission line through control equipment such as a breaker and the like. The transmission lines are divided into overhead transmission lines and cable lines.
The sag measurement request refers to a sag measurement request which is sent by a measurer and is used for measuring sag of a target power transmission line, and the sag measurement request comprises a corresponding area, a corresponding serial number and/or a corresponding position of the target power transmission line.
A binocular vision sensor is carrier equipment applying a binocular vision technology, images of a light bar are shot by two cameras at the same time, positions of all pixel points on the light bar in the two images are obtained through matching of the two images, and the positions and depth information of the pixel points can be calculated by using parallax.
The binocular vision technology is based on the parallax of two paths of videos, namely the difference of image pixel points formed by the left eye and the right eye relative to the same target, and the difference of the pixel points passes through a base line, namely the distance relation between two cameras.
The binocular vision sensor is used for acquiring target image data corresponding to the target power transmission line.
The target image data is image data of the target power transmission line acquired through the binocular vision sensor, and is important data for acquiring the lowest point coordinate corresponding to the target power transmission line.
In the embodiment of the invention, when the sag measurement request sent by any measuring person is received, the sag measurement request is read, the position of the corresponding target power transmission line is obtained, and therefore, the target image data corresponding to the target power transmission line is obtained through the preset binocular vision sensor.
And 102, preprocessing the target image data to obtain corresponding preprocessed image data.
And preprocessing, including noise reduction processing, binarization processing and morphology processing.
The preprocessed image data refers to image data obtained by performing noise reduction processing, binarization processing, and morphological processing on target image data.
In the embodiment of the invention, image noise is filtered by a filter, and the filter comprises a plurality of two-dimensional filter matrixes, light-shielding storage units and at least one CMOS sensor array.
In the embodiment of the invention, the target image data is subjected to noise reduction processing, binarization processing and morphology processing to obtain corresponding preprocessed image data.
And 103, extracting the features of the preprocessed image data through a preset selected area to obtain a plurality of target image features.
The preset selected region is a circular region with the radius r of the detection window when the circular LBP operator is used for feature extraction.
And feature extraction, namely performing feature extraction on the preprocessed image data by using a circular LBP operator.
The target image feature refers to a target image feature obtained by performing feature extraction on the preprocessed image data through a circular LBP operator.
LBP (Local Binary Patterns) is used for extracting Local features as a basis for distinguishing, is an effective texture description operator, measures and extracts Local texture information of an image, has the remarkable advantages of rotation invariance, gray scale invariance and the like, and has invariance to illumination.
In the embodiment of the invention, when the circular LBP operator is used for feature extraction, a circular area with the radius of r is arranged on a detection window, and the feature extraction is carried out on the preprocessed image data to obtain a plurality of target image features.
And 104, selecting a plurality of target clusters according to the co-occurrence matrix matching result of the characteristics of the plurality of target images, and performing epipolar constraint to obtain an intermediate matching point pair.
And (3) symbiotic matrix matching, namely performing K-means algorithm processing according to the characteristics of a plurality of target images to obtain a plurality of target clusters, then solving the times of the common occurrence of each target cluster in the preprocessed image data by solving a symbiotic matrix, and solving the symbiotic probability of each target cluster by adopting a gray level symbiotic matrix statistical method to complete initial matching.
The K-means algorithm is a K-means clustering algorithm, which is an iterative solution clustering analysis algorithm and comprises the steps of dividing data into K groups in advance, randomly selecting K objects as initial clustering centers, calculating the distance between each object and each seed clustering center, and allocating each object to the nearest clustering center. The cluster centers and the objects assigned to them represent a cluster.
The co-occurrence matrix is a result obtained by counting that a single pixel on the pre-processed image data has a certain gray level, and the gray level co-occurrence matrix is obtained by counting that two pixels at a certain distance on the image respectively have a certain gray level.
The gray level co-occurrence matrix statistical method is to solve the co-occurrence probability of each target cluster based on the times of the co-occurrence of the target clusters in the preprocessed image data obtained by solving the co-occurrence matrix.
The epipolar constraint means that the epipolar constraint is a point-to-straight constraint, that is, knowing one imaging point, the corresponding point of the imaging point is found on the other image.
In the embodiment of the invention, a plurality of target clusters are obtained after K-means algorithm processing is carried out according to the characteristics of a plurality of target images, then the co-occurrence frequency of each target cluster in the preprocessed image data is solved by solving the co-occurrence matrix, the co-occurrence probability of each target cluster is solved by adopting a gray level co-occurrence matrix statistical method, epipolar constraint is carried out on the target clusters, and an intermediate matching point pair is obtained.
And 105, performing curve fitting on the intermediate matching point pairs on the two-dimensional plane, and determining the lowest point coordinate corresponding to the target power transmission line.
The curve fitting refers to selecting a proper curve type to fit observation data, and analyzing the relationship between two variables by using a fitted curve equation.
In the embodiment of the invention, the intermediate matching point pairs are projected to a two-dimensional plane and subjected to curve fitting, then the lowest point of the curve is solved, and the lowest point coordinate corresponding to the target power transmission line is determined.
And 106, determining a sag value corresponding to the target power transmission line by adopting the coordinates of the suspension point corresponding to the target power transmission line and the coordinates of the lowest point.
The suspension point coordinates refer to position coordinates of the suspension points of the overhead line.
In the embodiment of the invention, the sag value corresponding to the target power transmission line is calculated according to the obtained coordinates of the suspension point and the lowest point.
In the embodiment of the invention, when a sag measurement request sent by any measuring person is received, the sag measurement request is read, the position of a corresponding target power transmission line is obtained, so that target image data corresponding to the target power transmission line is obtained through a preset binocular vision sensor, noise reduction, binarization and morphological processing are carried out on the target image data to obtain corresponding preprocessed image data, when feature extraction is carried out by utilizing a circular LBP operator, a circular area with the radius of r is arranged on a detection window, feature extraction is carried out on the preprocessed image data to obtain a plurality of target image features, K-means algorithm processing is carried out according to the plurality of target image features to obtain a plurality of target clusters, then the number of times of co-occurrence of each target cluster in the preprocessed image data is solved through solving a co-occurrence matrix, the co-occurrence probability of each target cluster is solved through a gray level co-occurrence matrix statistical method, polar point pair constraint is carried out on the target clusters to obtain intermediate matching point pairs, the intermediate matching point pairs are projected to a two-dimensional plane, the lowest point curve is determined, and the coordinate of the hanging point corresponding to the sag value of the power transmission line is calculated according to the obtained coordinate of the hanging point and the lowest point; the technical problems that the sag of the power transmission line is low in efficiency and cannot be accurately measured by the measuring method of the sag of the power transmission line in the conventional method for measuring the sag of the power transmission line, which is usually measured by manual inspection observation; according to the invention, the noise reduction processing is carried out on the target image data through the filter, the image noise can be effectively filtered, and meanwhile, the circular LBP operator and the symbiotic matrix matching algorithm are adopted, so that the required target image characteristics can be accurately extracted and matched, and the sag measurement accuracy is improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating steps of a method for measuring sag of a power transmission line according to a second embodiment of the present invention.
The invention provides a method for measuring sag of a power transmission line, which relates to a binocular vision sensor and a calibration plate arranged at the front end of the binocular vision sensor, and comprises the following steps:
In the embodiment of the invention, the left and right calibration images of the calibration plate arranged at the front end of the binocular vision sensor are acquired through the binocular vision sensor.
5363A Zhang Zhengyou calibration method is a 2D plane target-based camera calibration, which can be used for calculating the corresponding relation between world coordinates and pixel coordinates by shooting pictures of a plurality of calibration plates and corresponding a plurality of actual points (world coordinates) to points (pixel coordinates) on the pictures.
The coordinate data refers to world coordinates and pixel coordinates.
In the embodiment of the invention, the corresponding mark points of the left and right calibration images are detected, and the corresponding coordinate data is calculated by a Zhang Zhengyou calibration method.
And 203, calibrating an internal reference matrix, a distortion coefficient and a binocular baseline corresponding to the binocular vision sensor by using the coordinate data.
In the embodiment of the invention, the coordinate data is adopted to calibrate the internal reference matrix, the distortion coefficient and the binocular baseline corresponding to the binocular vision sensor, so as to complete calibration.
And 204, responding to the received sag measurement request, and acquiring target image data corresponding to the target power transmission line through a preset binocular vision sensor.
In the embodiment of the present invention, the specific implementation process of step 204 is similar to that of step 101, and is not described herein again.
In another example of the present invention, the power transmission lines may be further divided according to areas where the power transmission lines are located, all the power transmission lines in each area are numbered, each power transmission line has a unique entry, the entry is used for storing the location and the number of the power transmission line, when a sag measurement request sent by any detection person is received, the sag measurement request is read, the area, the number and the location of the target power transmission line corresponding to the sag measurement request are obtained, and whether the location and the number of the power transmission line in the entry are consistent with the number and the location of the power transmission line in the sag measurement request is checked, and if the location and the number of the power transmission line in the entry are consistent with the number and the location of the sag measurement request, sag measurement is performed on the power transmission line.
In another example of the present invention, all power transmission lines are divided into regions, all power transmission lines in each region are numbered, each power transmission line has a unique entry, the entry is used for storing the position and the number of the power transmission line, when a sag measurement request sent by any detection person is received, the sag measurement request is read, the region and the number of the target power transmission line corresponding to the sag measurement request are obtained, whether the number of the power transmission line in the entry is consistent with the number of the sag measurement request is checked, and if so, sag measurement is performed on the power transmission lines.
In another example of the present invention, all power transmission lines are divided into areas, all power transmission lines in each area are numbered, each power transmission line has a unique entry, the entry is used for storing the location and the number of the power transmission line, when a sag measurement request sent by any detection person is received, the sag measurement request is read, the area and the location of a target power transmission line corresponding to the sag measurement request are obtained, whether the location of the power transmission line in the entry is consistent with the location in the sag measurement request is checked, and if so, sag measurement is performed on the power transmission line.
Further, step 205 may comprise the sub-steps of:
and S11, acquiring target pixel points corresponding to the target image data, and performing convolution calculation on pixel values corresponding to the target pixel points to obtain corresponding noise reduction image data.
Further, step S11 may comprise the following sub-steps:
and step S111, exposing the raster corresponding to the target image data to obtain corresponding exposure charges.
In an embodiment of the present invention, at least N rows of rasters of target image data are exposed through a CMOS sensor array, thereby generating a sufficient amount of exposure charge.
And S112, carrying out light-shielding storage on the exposure charges, and capturing corresponding target pixel points.
In the embodiment of the invention, the exposure charges generated by exposure are transferred to the light-shielding storage unit at t so as to capture the target pixel points of the M pixel regions in the target image data.
And step S113, performing convolution calculation on the pixel value corresponding to the target pixel point to obtain corresponding noise reduction image data.
In the embodiment of the invention, the pixel value of the target pixel point is convolved through the two-dimensional filter matrix, so that the noise reduction processing is completed, and the noise reduction image data is obtained.
And S12, acquiring the pixel number, the gray value and the total gray value corresponding to the noise reduction image data.
In the embodiment of the invention, the pixel number, the gray value and the total number of the gray values corresponding to the noise reduction image data are obtained.
And S13, calculating the gray value frequency corresponding to each noise reduction image data by adopting the total number of the gray values and the number of pixels, and determining a binarization threshold value by combining the gray values.
Further, step S13 may comprise the following sub-steps:
step S131, calculating a first ratio between the total number of the gray values and the number of pixels to obtain corresponding gray value frequencies.
The calculation formula of the gray value frequency is as follows:
in the formula,indicating each gray-level value in the noise-reduced image data is at the secondThe frequency of the grey values that occur in a pixel,representing the total number of gray values in the noise-reduced image data,indicating the number of pixels.
In the embodiment of the present invention, a first ratio between the total number of gray-scale values and the number of pixels is calculated to obtain a corresponding frequency of the gray-scale values, and preferably, the noise-reduced image data is a gray-scale histogram.
And step S132, determining a binarization threshold value by adopting the gray value frequency and the gray value.
The calculation formula of the binarization threshold value is as follows:
in the formula,a binary threshold value is represented, and the threshold value is represented,is shown asA gray value.
In the embodiment of the invention, the frequency and the gray value of the gray value are adopted to calculate the binary threshold value.
And S14, carrying out binarization on the noise reduction image data by adopting a binarization threshold value to obtain binarization image data.
In the embodiment of the invention, the binarization processing is carried out on the noise reduction image data according to the binarization threshold value to obtain the binarization image data.
And S15, corroding and expanding the binary image data to obtain corresponding preprocessed image data.
Image corrosion, after the image is corroded, noise is removed, but the image is compressed;
and (4) image expansion, namely, the corroded image is subjected to expansion processing, so that noise can be removed, and the original shape can be kept.
In the embodiment of the invention, the binary image data is corroded and expanded, so that the original shape can be kept while noise is removed, and the preprocessed image data is obtained.
And step 206, performing feature extraction on the preprocessed image data through a preset selected area to obtain a plurality of target image features.
Further, step 206 may include the following sub-steps:
and S21, rotating the preprocessed image data through the preset selected area, and calculating a pixel point LBP value corresponding to the preset selected area.
The preset selected area is a circular area with the radius r of the detection window.
In the embodiment of the invention, the detection window is set into a circular area with the radius of r, the circular area is continuously rotated, and the LBP value of the central pixel point of the detection window is calculated.
The calculation formula of the LBP value of the pixel point is as follows:
in the formula,the expression function is to find the minimum value,express a function ofAnd (4) performing bit translation, namely moving the highest bit to the lowest bit.
And S22, sequencing the LBP values of the pixel points according to the anticlockwise rotating sequence, and converting the sequencing result into a decimal system to obtain a plurality of target image characteristics.
In the embodiment of the invention, the obtained LBP values are sequentially arranged according to the sequence of anticlockwise rotation, and the arrangement result is converted into decimal, so that the extracted target image characteristics are obtained.
And step 207, selecting a plurality of target clusters according to the co-occurrence matrix matching result of the characteristics of the plurality of target images, and performing epipolar constraint to obtain an intermediate matching point pair.
Further, step 207 may comprise the following sub-steps:
and S31, carrying out mean value clustering on the characteristics of the plurality of target images to obtain a plurality of target clusters.
In the embodiment of the invention, the features are quantized into K target cluster classes through a K-means algorithm.
And S32, acquiring the co-occurrence frequency corresponding to each target cluster, and calculating the target symbiosis probability corresponding to each target cluster.
In the embodiment of the invention, the frequency of common occurrence of each target cluster pair in the preprocessed image data is counted by solving the co-occurrence matrix.
And S33, matching the plurality of target clusters according to the target symbiosis probability to obtain an initial matching point pair.
In the embodiment of the invention, the gray level co-occurrence matrix statistical method is adopted to solve the co-occurrence probability of each cluster class, and the initial matching is completed.
And S34, performing epipolar constraint on the initial matching point pairs to obtain intermediate matching point pairs.
In the embodiment of the invention, after the initial matching is completed, epipolar constraint is carried out on the initial matching point pair to obtain a middle matching point pair.
And 208, performing curve fitting on the intermediate matching point pairs on the two-dimensional plane to determine the lowest point coordinate corresponding to the target power transmission line.
Further, step 208 may include the following sub-steps:
and S41, acquiring a target space point pair corresponding to the intermediate matching point pair.
In the embodiment of the invention, the target spatial point pair corresponding to the intermediate matching point pair is obtained.
And S42, projecting the target space point pair to a two-dimensional plane to obtain a two-dimensional space point pair.
In the embodiment of the invention, the target space point pair is projected onto a two-dimensional plane to obtain the two-dimensional space point pair.
And S43, performing curve fitting on the two-dimensional space point pairs by adopting a least square method, and determining the lowest point coordinate corresponding to the target power transmission line.
The least square formula refers to a mathematical formula, which is mathematically called curve fitting, and includes not only a linear regression equation but also a least square method of a matrix.
The least square method is a mathematical tool widely applied in the fields of various disciplines of data processing such as error estimation, uncertainty, system identification and prediction, forecast and the like.
In the embodiment of the invention, a least square method is adopted to perform curve fitting on the two-dimensional space point pairs, and the coordinate of the lowest point of the curve is solved.
And 209, determining a sag value corresponding to the target power transmission line by adopting the coordinates of the suspension point and the coordinates of the lowest point corresponding to the target power transmission line.
Further, step 209 may comprise the following sub-steps:
and S51, calculating the absolute value of a first difference value between the abscissa corresponding to the coordinates of the suspension point and the abscissa corresponding to the coordinates of the lowest point to obtain a first target absolute value.
And S52, calculating the absolute value of a second difference value between the vertical coordinate corresponding to the coordinates of the suspension points and the vertical coordinate corresponding to the coordinate of the lowest point to obtain a second target absolute value.
And S53, determining a sag value corresponding to the target power transmission line by adopting the first target absolute value and the second target absolute value.
The first target absolute value is calculated by the formula:
wherein,representing the absolute value of the first target,represents the abscissa corresponding to the coordinates of the suspension point,representing an abscissa corresponding to the lowest point coordinate;
the calculation formula of the second target absolute value is:
wherein,represents the absolute value of the second target,represents the ordinate corresponding to the coordinates of the suspension point,representing a vertical coordinate corresponding to the lowest point coordinate;
the sag value is calculated by the following formula:
In the embodiment of the invention, to simplify the formula, let,Combining the trigonometric function to calculate the sag value,as a coordinate of the suspension point,is the lowest point coordinate.
In the embodiment of the invention, when a sag measurement request sent by any measuring person is received, the sag measurement request is read, the position of a corresponding target power transmission line is obtained, so that target image data corresponding to the target power transmission line is obtained through a preset binocular vision sensor, noise reduction, binarization and morphological processing are carried out on the target image data to obtain corresponding preprocessed image data, when feature extraction is carried out by utilizing a circular LBP operator, a circular area with the radius of r is arranged on a detection window, feature extraction is carried out on the preprocessed image data to obtain a plurality of target image features, K-means algorithm processing is carried out according to the plurality of target image features to obtain a plurality of target clusters, then the number of times of co-occurrence of each target cluster in the preprocessed image data is solved through solving a co-occurrence matrix, the co-occurrence probability of each target cluster is solved through a gray level co-occurrence matrix statistical method, polar point pair constraint is carried out on the target clusters to obtain intermediate matching point pairs, the intermediate matching point pairs are projected to a two-dimensional plane, the lowest point curve is determined, and the coordinate of the hanging point corresponding to the sag value of the power transmission line is calculated according to the obtained coordinate of the hanging point and the lowest point; the technical problems that the sag of the power transmission line is low in efficiency and cannot be accurately measured by the measuring method of the sag of the power transmission line in the conventional method for measuring the sag of the power transmission line, which is usually measured by manual inspection observation; according to the invention, the noise reduction processing is carried out on the target image data through the filter, the image noise can be effectively filtered, and meanwhile, the circular LBP operator and the symbiotic matrix matching algorithm are adopted, so that the required target image characteristics can be accurately extracted and matched, and the sag measurement accuracy is improved.
Referring to fig. 3, fig. 3 is a block diagram of a sag measurement system of a power transmission line according to a third embodiment of the present invention.
The invention provides a measuring system for sag of a power transmission line, which comprises:
the response module 301 is configured to, in response to the received sag measurement request, obtain target image data corresponding to the target power transmission line through a preset binocular vision sensor.
The preprocessing module 302 is configured to preprocess the target image data to obtain corresponding preprocessed image data.
A feature extraction module 303, configured to perform feature extraction on the preprocessed image data through a preset selected region to obtain multiple target image features.
And the matching module 304 is configured to select a plurality of target clusters according to the co-occurrence matrix matching result of the plurality of target image features, and perform epipolar constraint to obtain an intermediate matching point pair.
A fitting module 305, configured to perform curve fitting on the intermediate matching point pairs on a two-dimensional plane, and determine a lowest point coordinate corresponding to the target power transmission line.
And the sag value acquisition module 306 is configured to determine a sag value corresponding to the target power transmission line by using the suspension point coordinate and the lowest point coordinate corresponding to the target power transmission line.
Further, relate to binocular vision sensor and set up at the calibration board of binocular vision sensor front end still includes:
and the left and right calibration image acquisition module is used for acquiring left and right calibration images corresponding to the calibration plate through the binocular vision sensor.
And the coordinate data acquisition module is used for detecting the mark points corresponding to the left and right calibration images and calculating corresponding coordinate data.
And the calibration module is used for calibrating the internal reference matrix, the distortion coefficient and the binocular baseline corresponding to the binocular vision sensor by adopting the coordinate data.
Further, the preprocessing module 302 includes:
and the noise reduction image data acquisition submodule is used for acquiring target pixel points corresponding to the target image data and carrying out convolution calculation on pixel values corresponding to the target pixel points to obtain corresponding noise reduction image data.
And the gray data acquisition submodule is used for acquiring the number of pixels, the gray value and the total number of the gray values corresponding to the noise reduction image data.
And the binarization threshold value obtaining submodule is used for calculating the corresponding grey value frequency of each noise reduction image data by adopting the total number of the grey values and the pixel number, and determining the binarization threshold value by combining the grey values.
And the binarization image data acquisition submodule is used for carrying out binarization on the noise reduction image data by adopting the binarization threshold value to obtain binarization image data.
And the preprocessing image data acquisition submodule is used for corroding and expanding the binaryzation image data to obtain corresponding preprocessing image data.
Further, the noise reduction image data acquisition sub-module includes:
and the exposure charge acquisition unit is used for exposing the grating corresponding to the target image data to obtain corresponding exposure charge.
And the target pixel point acquisition unit is used for carrying out light shielding storage on the exposure charges and capturing the corresponding target pixel points.
And the noise reduction image data acquisition unit is used for performing convolution calculation on the pixel value corresponding to the target pixel point to obtain corresponding noise reduction image data.
Further, the binarization threshold value obtaining sub-module comprises:
and the gray value frequency acquisition unit is used for calculating a first ratio between the total number of the gray values and the number of pixels to obtain the corresponding gray value frequency.
And the binarization threshold value acquisition unit is used for determining a binarization threshold value by adopting the gray value frequency and the gray value.
Further, the feature extraction module 303 includes:
and the pixel point LBP value acquisition submodule is used for rotating the preprocessed image data through a preset selected area and calculating a pixel point LBP value corresponding to the preset selected area.
And the target image characteristic obtaining submodule is used for sequencing the LBP values of the pixel points according to the anticlockwise rotating sequence and converting the sequencing result into a decimal system to obtain a plurality of target image characteristics.
Further, the matching module 304 includes:
and the target cluster obtaining submodule is used for carrying out mean value clustering on the characteristics of the plurality of target images to obtain a plurality of target clusters.
And the target symbiosis probability obtaining submodule is used for obtaining the common occurrence times corresponding to the target clusters and calculating the target symbiosis probability corresponding to the target clusters.
And the initial matching point acquisition submodule is used for matching the target clusters according to the target symbiosis probability to obtain an initial matching point pair.
And the intermediate matching point pair obtaining submodule is used for carrying out polar line constraint on the initial matching point pair to obtain an intermediate matching point pair.
Further, the fitting module 305 includes:
and the target space acquisition submodule is used for acquiring the target space point pair corresponding to the intermediate matching point pair.
And the two-dimensional space point pair obtaining submodule is used for projecting the target space point pair to a two-dimensional plane to obtain a two-dimensional space point pair.
And the lowest point coordinate acquisition submodule is used for performing curve fitting on the two-dimensional space point pairs by adopting a least square method and determining the lowest point coordinate corresponding to the target power transmission line.
Further, the sag value obtaining module 306 includes:
and the first target absolute value acquisition submodule is used for calculating the absolute value of a first difference value between the abscissa corresponding to the coordinates of the suspension point and the abscissa corresponding to the coordinates of the lowest point to obtain a first target absolute value.
And the second target absolute value acquisition submodule is used for calculating the absolute value of a second difference value between the vertical coordinate corresponding to the hanging point coordinate and the vertical coordinate corresponding to the lowest point coordinate to obtain a second target absolute value.
And the sag value acquisition submodule is used for determining a sag value corresponding to the target power transmission line by adopting the first target absolute value and the second target absolute value.
In the embodiment of the invention, when a sag measurement request sent by any measuring person is received, the sag measurement request is read, the position of a corresponding target power transmission line is obtained, so that target image data corresponding to the target power transmission line is obtained through a preset binocular vision sensor, noise reduction, binarization and morphological processing are carried out on the target image data to obtain corresponding preprocessed image data, when feature extraction is carried out by utilizing a circular LBP operator, a circular area with the radius of r is arranged on a detection window, feature extraction is carried out on the preprocessed image data to obtain a plurality of target image features, K-means algorithm processing is carried out according to the plurality of target image features to obtain a plurality of target clusters, then the number of times of co-occurrence of each target cluster in the preprocessed image data is solved through solving a co-occurrence matrix, the co-occurrence probability of each target cluster is solved through a gray level co-occurrence matrix statistical method, polar point pair constraint is carried out on the target clusters to obtain intermediate matching point pairs, the intermediate matching point pairs are projected to a two-dimensional plane, the lowest point curve is determined, and the coordinate of the hanging point corresponding to the sag value of the power transmission line is calculated according to the obtained coordinate of the hanging point and the lowest point; the technical problems that the sag of the power transmission line is low in efficiency and cannot be accurately measured by the measuring method of the sag of the power transmission line in the conventional method for measuring the sag of the power transmission line, which is usually measured by manual inspection observation; according to the invention, the noise reduction processing is carried out on the target image data through the filter, the image noise can be effectively filtered, and meanwhile, the circular LBP operator and the symbiotic matrix matching algorithm are adopted, so that the required target image characteristics can be accurately extracted and matched, and the sag measurement accuracy is improved.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for measuring sag of a power transmission line is characterized by comprising the following steps:
responding to the received sag measurement request, and acquiring target image data corresponding to the target power transmission line through a preset binocular vision sensor;
preprocessing the target image data to obtain corresponding preprocessed image data;
performing feature extraction on the preprocessed image data through a preset selected area to obtain a plurality of target image features corresponding to the target power transmission line;
selecting a plurality of target clusters according to the co-occurrence matrix matching result of the target image characteristics, and performing epipolar constraint to obtain a middle matching point pair;
the step of selecting a plurality of target clusters according to the co-occurrence matrix matching result of the target image characteristics and carrying out epipolar constraint to obtain a middle matching point pair comprises the following steps:
carrying out mean value clustering on the plurality of target image characteristics to obtain a plurality of target clusters;
acquiring the common occurrence frequency corresponding to each target cluster, and calculating the target symbiosis probability corresponding to each target cluster;
matching the plurality of target clusters according to the target symbiosis probability to obtain an initial matching point pair;
carrying out polar line constraint on the initial matching point pair to obtain a middle matching point pair;
performing curve fitting on the intermediate matching point pairs on a two-dimensional plane, and determining the lowest point coordinate corresponding to the target power transmission line;
and determining the sag value corresponding to the target power transmission line by adopting the hanging point coordinate corresponding to the target power transmission line and the lowest point coordinate.
2. The sag measurement method for the power transmission line according to claim 1, wherein the sag measurement method involves a binocular vision sensor and a calibration plate arranged at the front end of the binocular vision sensor, and before the step of acquiring target image data corresponding to a target power transmission line by a preset binocular vision sensor in response to a received sag measurement request, the sag measurement method further comprises:
acquiring a left calibration image and a right calibration image corresponding to the calibration plate through the binocular vision sensor;
detecting the corresponding mark points of the left and right calibration images, and calculating corresponding coordinate data;
and calibrating the internal reference matrix, the distortion coefficient and the binocular baseline corresponding to the binocular vision sensor by adopting the coordinate data.
3. The method for measuring sag of an electric transmission line according to claim 1, wherein the step of preprocessing the target image data to obtain corresponding preprocessed image data comprises:
acquiring target pixel points corresponding to the target image data, and performing convolution calculation on pixel values corresponding to the target pixel points to obtain corresponding noise reduction image data;
acquiring the pixel number, the gray value and the total number of the gray values corresponding to the noise reduction image data;
calculating the gray value frequency corresponding to each noise reduction image data by adopting the total number of the gray values and the number of pixels, and determining a binarization threshold value by combining the gray values;
carrying out binarization on the noise reduction image data by adopting the binarization threshold value to obtain binarization image data;
and corroding and expanding the binary image data to obtain corresponding preprocessed image data.
4. The method according to claim 3, wherein the step of obtaining target pixel points corresponding to the target image data and performing convolution calculation on pixel values corresponding to the target pixel points to obtain corresponding noise reduction image data comprises:
exposing the grating corresponding to the target image data to obtain corresponding exposure charges;
carrying out light-shielding storage on the exposure charges, and capturing corresponding target pixel points;
and performing convolution calculation on the pixel value corresponding to the target pixel point to obtain corresponding noise reduction image data.
5. The method for measuring the sag of the power transmission line according to claim 3, wherein the step of calculating the gray value frequency corresponding to each noise reduction image data by using the total number of the gray values and the number of pixels and determining the binarization threshold value by combining the gray values comprises the following steps:
calculating a first ratio between the total number of the gray values and the number of pixels to obtain the corresponding gray value frequency;
and determining a binarization threshold value by adopting the gray value frequency and the gray value.
6. The method for measuring the sag of the power transmission line according to claim 1, wherein the step of performing feature extraction on the preprocessed image data through a preset selected area to obtain a plurality of target image features corresponding to the target power transmission line comprises:
rotating the preprocessed image data through a preset selected area, and calculating a pixel point LBP value corresponding to the preset selected area;
and sequencing the LBP values of the pixel points according to a counterclockwise rotation sequence, and converting a sequencing result into a decimal system to obtain a plurality of target image characteristics corresponding to the target power transmission line.
7. The method for measuring sag of an electric transmission line according to claim 1, wherein the step of performing curve fitting on the intermediate matching point pairs on a two-dimensional plane to determine the lowest point coordinate corresponding to the target electric transmission line comprises:
obtaining a target space point pair corresponding to the intermediate matching point pair;
projecting the target space point pair to a two-dimensional plane to obtain a two-dimensional space point pair;
and performing curve fitting on the two-dimensional space point pairs by adopting a least square method, and determining the lowest point coordinate corresponding to the target power transmission line.
8. The method for measuring the sag of the power transmission line according to claim 1, wherein the step of determining the sag value corresponding to the target power transmission line by using the coordinates of the suspension point corresponding to the target power transmission line and the coordinates of the lowest point comprises the steps of:
calculating an absolute value of a first difference value between an abscissa corresponding to the coordinates of the hanging point and an abscissa corresponding to the coordinates of the lowest point to obtain a first target absolute value;
calculating an absolute value of a second difference value between a vertical coordinate corresponding to the coordinates of the hanging point and a vertical coordinate corresponding to the coordinates of the lowest point to obtain a second target absolute value;
determining a sag value corresponding to the target power transmission line by adopting the first target absolute value and the second target absolute value;
the calculation formula of the first target absolute value is as follows:
wherein,representing the absolute value of the first target,represents the abscissa corresponding to the coordinates of the suspension point,representing an abscissa corresponding to the lowest point coordinate;
the calculation formula of the second target absolute value is as follows:
wherein,represents the absolute value of the second target,represents a vertical coordinate corresponding to the coordinates of the suspension point,a vertical coordinate corresponding to the lowest point coordinate is represented;
the calculation formula of the sag value is as follows:
9. The utility model provides a measurement system of transmission line arc is hung down which characterized in that includes:
the response module is used for responding to the received sag measurement request and acquiring target image data corresponding to the target power transmission line through a preset binocular vision sensor;
the preprocessing module is used for preprocessing the target image data to obtain corresponding preprocessed image data;
the feature extraction module is used for extracting features of the preprocessed image data through a preset selected area to obtain a plurality of target image features corresponding to the target power transmission line;
the matching module is used for selecting a plurality of target clusters according to the co-occurrence matrix matching result of the target image characteristics and carrying out epipolar constraint to obtain an intermediate matching point pair;
the matching module includes:
the target cluster obtaining submodule is used for carrying out mean value clustering on the characteristics of the plurality of target images to obtain a plurality of target clusters;
the target symbiosis probability obtaining submodule is used for obtaining the common occurrence times corresponding to the target clusters and calculating the target symbiosis probability corresponding to the target clusters;
an initial matching point obtaining sub-module, configured to match the plurality of target clusters according to the target symbiotic probability to obtain an initial matching point pair;
the intermediate matching point pair obtaining submodule is used for carrying out polar line constraint on the initial matching point pair to obtain an intermediate matching point pair;
the fitting module is used for performing curve fitting on the intermediate matching point pairs on a two-dimensional plane and determining the lowest point coordinate corresponding to the target power transmission line;
and the sag value acquisition module is used for determining a sag value corresponding to the target power transmission line by adopting the suspension point coordinate and the lowest point coordinate corresponding to the target power transmission line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211231249.4A CN115294145B (en) | 2022-10-10 | 2022-10-10 | Method and system for measuring sag of power transmission line |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211231249.4A CN115294145B (en) | 2022-10-10 | 2022-10-10 | Method and system for measuring sag of power transmission line |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115294145A CN115294145A (en) | 2022-11-04 |
CN115294145B true CN115294145B (en) | 2023-01-24 |
Family
ID=83819352
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211231249.4A Active CN115294145B (en) | 2022-10-10 | 2022-10-10 | Method and system for measuring sag of power transmission line |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115294145B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116295031B (en) * | 2023-02-24 | 2024-03-12 | 中国测绘科学研究院 | Sag measurement method, sag measurement device, computer equipment and storage medium |
CN116819229A (en) * | 2023-06-26 | 2023-09-29 | 广东电网有限责任公司 | Distance measurement method, device, equipment and storage medium for power transmission line |
CN116718122B (en) * | 2023-08-09 | 2023-10-20 | 南方电网数字电网研究院有限公司 | Sag measurement method and device based on image parallax depth and computer equipment |
CN117830676B (en) * | 2024-03-06 | 2024-06-04 | 国网湖北省电力有限公司 | Unmanned aerial vehicle-based power transmission line construction risk identification method and system |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10229347B2 (en) * | 2017-05-14 | 2019-03-12 | International Business Machines Corporation | Systems and methods for identifying a target object in an image |
CN107314762B (en) * | 2017-07-06 | 2020-05-08 | 广东电网有限责任公司电力科学研究院 | Method for detecting ground object distance below power line based on monocular sequence images of unmanned aerial vehicle |
CN109084687A (en) * | 2018-08-29 | 2018-12-25 | 广东电网有限责任公司 | Sag computing method and device thereof based on unmanned plane lidar measurement technology |
CN111121645B (en) * | 2019-12-31 | 2021-03-19 | 内蒙古蒙能建设工程监理有限责任公司 | High-precision overhead transmission conductor sag detection method |
CN112419284A (en) * | 2020-11-27 | 2021-02-26 | 金华八达集团有限公司监理分公司 | Sag measurement method based on partial images of power transmission line |
CN112697083A (en) * | 2020-12-11 | 2021-04-23 | 广东电网能源发展有限公司 | Sag measurement method, device, equipment and medium based on smooth curve fitting |
CN112686938B (en) * | 2020-12-29 | 2024-03-15 | 重庆大学 | Power transmission line clear distance calculation and safety alarm method based on binocular image ranging |
-
2022
- 2022-10-10 CN CN202211231249.4A patent/CN115294145B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115294145A (en) | 2022-11-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115294145B (en) | Method and system for measuring sag of power transmission line | |
WO2021000524A1 (en) | Hole protection cap detection method and apparatus, computer device and storage medium | |
CN109919975B (en) | Wide-area monitoring moving target association method based on coordinate calibration | |
CN104363815A (en) | Image processing device, image processing method, and image processing program | |
CN107085728B (en) | Method and system for effectively scoring probe in image by using vision system | |
CN110490924B (en) | Light field image feature point detection method based on multi-scale Harris | |
CN110197185B (en) | Method and system for monitoring space under bridge based on scale invariant feature transform algorithm | |
WO2022206161A1 (en) | Feature point recognition-based block movement real-time detection method | |
CN110189341B (en) | Image segmentation model training method, image segmentation method and device | |
CN116228780B (en) | Silicon wafer defect detection method and system based on computer vision | |
US11651581B2 (en) | System and method for correspondence map determination | |
CN113628261B (en) | Infrared and visible light image registration method in electric power inspection scene | |
CN110634137A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
CN112560837A (en) | Reading method, device, equipment and storage medium of pointer instrument | |
CN112001880B (en) | Method and device for detecting characteristic parameters of planar member | |
CN112561986A (en) | Secondary alignment method, device, equipment and storage medium for inspection robot holder | |
CN113592839A (en) | Distribution network line typical defect diagnosis method and system based on improved fast RCNN | |
CN114862973A (en) | Space positioning method, device and equipment based on fixed point location and storage medium | |
CN116129195A (en) | Image quality evaluation device, image quality evaluation method, electronic device, and storage medium | |
JP2016526182A (en) | Method and apparatus for immediate adjustment of lens mounting flatness | |
Zhao et al. | Binocular vision measurement for large-scale weakly textured ship hull plates using feature points encoding method | |
CN117314986A (en) | Unmanned aerial vehicle cross-mode power distribution equipment inspection image registration method based on semantic segmentation | |
CN117520581A (en) | Land mapping information management method, system, equipment and medium | |
CN112924037A (en) | Infrared body temperature detection system and detection method based on image registration | |
CN115855961B (en) | Distribution box fault detection method used in operation |
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 |