CN116051497A

CN116051497A - Intelligent analysis method for power transmission and transformation images of power grid based on data processing

Info

Publication number: CN116051497A
Application number: CN202310015554.8A
Authority: CN
Inventors: 于木丰; 王伟; 张广款
Original assignee: Hangzhou Qitai Information Technology Co ltd
Current assignee: Hangzhou Qitai Information Technology Co ltd
Priority date: 2023-01-04
Filing date: 2023-01-04
Publication date: 2023-05-02
Anticipated expiration: 2043-01-04
Also published as: CN116051497B

Abstract

The invention provides an intelligent analysis method for a power transmission and transformation image of a power grid based on data processing, which comprises the following steps: performing binarization processing on the first infrared image to obtain an infrared binarized image; counting first coordinate information of all white binarized pixel points to obtain a first coordinate set; extracting second coordinate information of a target pixel point in the first white light image to obtain a second coordinate set; if the first coordinate information in the first coordinate set completely corresponds to the second coordinate information in the second coordinate set, outputting a first intelligent analysis result; if the first coordinate information in the first coordinate set does not completely correspond to the second coordinate information in the second coordinate set, comparing the first coordinate set with the second coordinate set to obtain a difference coordinate set; and positioning the pixel points in the first white light image according to the difference coordinate set to obtain difference pixel points, and analyzing according to the pixel values of the difference pixel points to obtain a second intelligent analysis result.

Description

Intelligent analysis method for power transmission and transformation images of power grid based on data processing

Technical Field

The invention relates to a data processing technology, in particular to an intelligent analysis method for a power transmission and transformation image of a power grid based on data processing.

Background

With the development of the age and the progress of social economy, the electric power occupies more and more important places in people's life, and the electric network transmission and transformation circuit is taken as a very important component part of the electric power system, so that the reliability and the safety of the electric power system are directly influenced. In order to ensure that the power transmission and transformation line of the power grid can stably and safely run, the power supply enterprises are required to pay enough attention to the power transmission and transformation line of the power grid, and a series of measures are taken to improve the management level, so that accidents of the power transmission and transformation line of the power grid are prevented as much as possible.

In a power transmission and transformation line of a power grid, a power transmission cable is often wound by hanging objects such as branches, and the power transmission cable is broken when serious, so that the stability of power transmission is affected. In the prior art, when the power transmission cable is pressed by a hanging object such as a branch, the power transmission cable can be started to rescue after the power transmission cable is broken, and the current state of the power transmission cable can not be perceived in real time and dynamically by combining power transmission and transformation images of a power grid.

Disclosure of Invention

The embodiment of the invention provides an intelligent analysis method for a power transmission and transformation image of a power grid based on data processing, which is used for dynamically sensing the current state of a power transmission cable in real time by combining the processing of the power transmission and transformation image of the power grid, so that the stable operation of the power transmission and transformation system of the power grid is ensured.

A first aspect of an embodiment of the present invention provides an intelligent analysis method for a power transmission and transformation image of a power grid based on data processing, including:

s1, carrying out image acquisition on power transmission and transformation equipment of a power grid based on a white light image acquisition device and an infrared image acquisition device to obtain a first white light image and a first infrared image, and carrying out binarization processing on the first infrared image to obtain an infrared binarization image, wherein the infrared binarization image comprises white pixel points and black pixel points;

s2, carrying out coordinate processing on the infrared binarized image to obtain coordinate information of each binarized pixel point, and counting first coordinate information of all white binarized pixel points to obtain a first coordinate set;

s3, carrying out coordinate processing on the first white light image to obtain coordinate information of each white light pixel point, and extracting second coordinate information of a target pixel point in the first white light image to obtain a second coordinate set, wherein the target pixel point is a pixel point in a pixel region of interest corresponding to power transmission and transformation equipment of a power grid;

s4, if the first coordinate information in the first coordinate set completely corresponds to the second coordinate information in the second coordinate set, outputting a first intelligent analysis result;

S5, if the first coordinate information in the first coordinate set and the second coordinate information in the second coordinate set do not completely correspond, comparing according to the first coordinate set and the second coordinate set to obtain a difference coordinate set;

s6, positioning pixel points in the first white light image according to the difference coordinate set to obtain difference pixel points, and analyzing according to pixel values of the difference pixel points to obtain a second intelligent analysis result.

Optionally, the S1 includes:

and calling a preset binarization range interval, extracting all pixel points in the binarization range interval in the first infrared image as white pixel points in the infrared binarization image, and extracting all pixel points not in the binarization range interval in the first infrared image as black pixel points in the infrared binarization image.

Optionally, the S2 includes:

the center point of the infrared binarization image is used as an origin to carry out coordinate processing on the infrared binarization image to obtain coordinate information of each binarization pixel point;

counting the first coordinate information of all the white binarized pixel points to obtain a first coordinate set, and determining the first quantity of the first coordinate information with the same X axis in the first coordinate set and the second quantity of the first coordinate information with the same Y axis in the first coordinate set;

If the first quantity is larger than or equal to the second quantity, the X-axis coordinate is used as a target coordinate, and if the first quantity is smaller than the second quantity, the Y-axis coordinate is used as a target coordinate;

and counting the quantity of the first coordinate information corresponding to all the different target coordinates to obtain a first quantity corresponding relation, wherein the first quantity corresponding relation has the first coordinate quantity corresponding to each target coordinate.

Optionally, the S3 includes:

the center point of the first white light image is used as an origin to carry out coordinate processing on the first white light image to obtain coordinate information of each white light pixel point;

determining a corresponding pixel set of interest according to the type of power transmission and transformation equipment of a power grid, wherein at least one pixel interval of interest exists in the pixel set of interest, and taking a pixel point positioned in the pixel interval of interest in a first white light image as a target pixel point;

and extracting second coordinate information of the target pixel points in the first white light image to obtain a second coordinate set, and counting the quantity of the second coordinate information corresponding to all different target coordinates to obtain a second quantity corresponding relation, wherein the second quantity corresponding relation has the second coordinate quantity corresponding to each target coordinate.

Optionally, the S4 includes:

if the first coordinate number of the first coordinate information and the second coordinate number of the second coordinate information of the same target coordinate are the same, judging that the first coordinate information and the second coordinate information of the same coordinate correspond;

if all the first coordinate information and the second coordinate information of the same target coordinate are corresponding, judging that the first coordinate information in the first coordinate set is completely corresponding to the second coordinate information in the second coordinate set, and outputting a first intelligent analysis result.

Optionally, the S5 includes:

if the first coordinate number of the first coordinate information and the second coordinate number of the second coordinate information of the same target coordinate are different, judging that the first coordinate information and the second coordinate information of the same coordinate are not corresponding;

and extracting all the second coordinate information which does not correspond to the second coordinate information to obtain a difference coordinate set.

Optionally, the S6 includes:

positioning pixel points in the first white light image according to all second coordinate information in the difference coordinate set to obtain difference pixel points, and classifying all the difference pixel points according to the second coordinate information to obtain at least one difference pixel subset;

determining the number of difference pixel points in each difference pixel subset, and deleting the difference pixel subsets with the number of the difference pixel points smaller than the preset number;

Extracting a difference pixel value corresponding to a difference pixel point in the rest difference pixel sub-set, and analyzing according to the difference pixel value, a contour formed by the difference pixel point and current time information to obtain a first abnormal shielding result;

and performing de-duplication processing on the first abnormal shielding results of all the difference pixel subsets to obtain second abnormal shielding results, and taking all the second abnormal shielding results as second intelligent analysis results.

Optionally, extracting a difference pixel value corresponding to a difference pixel point in the remaining difference pixel subset, and analyzing according to the difference pixel value, a contour formed by the difference pixel point, and current time information to obtain a first abnormal shielding result, where the first abnormal shielding result includes:

comparing the difference pixel value with a preset pixel value, and determining a shielding object corresponding to the corresponding preset pixel value;

if the number of the corresponding shielding objects is multiple, determining all edge pixel points corresponding to the difference pixel subsets, and forming a current contour corresponding to the difference pixel subsets according to the edge pixel points;

calling preset contours of different determined shielding objects, and taking the shielding object corresponding to the preset contours as the shielding object to be verified if the preset contours corresponding to the current contours exist;

Acquiring current time information, and if judging that the to-be-verified shielding object corresponds to the current time information, taking the to-be-verified shielding object as a final first abnormal shielding result;

if the number of the corresponding shielding objects is 1, adding a first label to the 1 shielding objects, and generating a final first abnormal shielding result according to the 1 shielding objects and the first label;

if the preset contour corresponding to the current contour does not exist or the to-be-verified shielding object does not correspond to the current time information, adding a second label to the plurality of shielding objects, and generating a final first abnormal shielding result according to the plurality of shielding objects and the second label.

Optionally, the calling the preset contour of the different determined obscurants, if there is a preset contour corresponding to the current contour, taking the obscurant corresponding to the preset contour as the obscurant to be verified, including:

calculating according to the maximum X-axis coordinate value, the minimum X-axis coordinate value, the maximum Y-axis coordinate value and the minimum Y-axis coordinate value in the difference pixel subset to obtain a drawn center coordinate point;

determining a maximum X-axis coordinate point, a minimum X-axis coordinate point, a maximum Y-axis coordinate point and a minimum Y-axis coordinate point in the difference pixel subset through a maximum X-axis coordinate value, a minimum X-axis coordinate value, a maximum Y-axis coordinate value and a minimum Y-axis coordinate value;

Calculating according to the drawn center coordinate point, the maximum X-axis coordinate point, the minimum X-axis coordinate point, the maximum Y-axis coordinate point and the minimum Y-axis coordinate point to obtain a first X-axis current distance, a second X-axis current distance, a first Y-axis current distance and a second Y-axis current distance;

calculating the proportions among the first X-axis current distance, the second X-axis current distance, the first Y-axis current distance and the second Y-axis current distance to obtain a current proportion set corresponding to the current profile, wherein the current proportion set comprises a first current coefficient, a second current coefficient, a third current coefficient and a fourth current coefficient;

and acquiring a preset proportion set corresponding to the preset contour, comparing the current proportion set with the preset proportion set, and determining the preset contour corresponding to the current contour.

Optionally, the obtaining a preset proportion set corresponding to the preset contour, comparing the current proportion set with the preset proportion set, and determining the preset contour corresponding to the current contour includes:

acquiring a preset proportion set corresponding to a preset contour, wherein the preset proportion set comprises a first preset coefficient, a second preset coefficient, a third preset coefficient and a fourth preset coefficient;

Calculating according to preset logic to obtain a plurality of current difference values among the first current coefficient, the second current coefficient, the third current coefficient and the fourth current coefficient, and a plurality of preset difference values among the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient;

and if the current difference value corresponds to the preset difference value, determining that a preset contour corresponding to the current contour exists.

Optionally, the calculating according to the preset logic to obtain a plurality of current differences among the first current coefficient, the second current coefficient, the third current coefficient, and the fourth current coefficient, and a plurality of preset differences among the first preset coefficient, the second preset coefficient, the third preset coefficient, and the fourth preset coefficient includes:

randomly selecting one of the first current coefficient, the second current coefficient, the third current coefficient and the fourth current coefficient as a first comparison coefficient, and selecting the unselected one as a second comparison coefficient;

calculating the difference value between the first comparison coefficient and each second comparison coefficient to obtain a plurality of current difference values;

selecting a third comparison coefficient corresponding to the first comparison coefficient from the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient, and taking the unselected comparison coefficient as the fourth comparison coefficient;

And calculating the difference value between the third comparison coefficient and each fourth comparison coefficient to obtain a plurality of preset difference values.

Optionally, if the current difference value corresponds to the preset difference value, determining that a preset contour corresponding to the current contour exists includes:

classifying the current difference value and the preset difference value according to the corresponding relation between the first comparison coefficient and the second comparison coefficient and the corresponding relation between the third comparison coefficient and the fourth comparison coefficient;

calculating comparison differences between the classified current differences and preset differences, and judging that all the current differences correspond to the preset differences if all the comparison differences are smaller than the threshold differences respectively;

it is determined that there is a preset contour corresponding to the current contour.

The beneficial effects are that:

1. the method and the device can conduct intelligent comparison analysis on the collected white light image and infrared image, firstly determine the areas of the white light image and the infrared image corresponding to the power transmission and transformation equipment of the power grid, then determine whether difference pixel points exist between the white light image and the infrared image or not by taking the infrared image as a reference, if not, indicate that everything is normal, and if so, indicate that abnormal phenomenon exists, the method and the device can conduct further analysis on the difference pixel points to obtain the reason for generating the abnormal phenomenon. According to the scheme, the current state of the power transmission cable is perceived dynamically in real time by combining the processing of the power transmission and transformation image of the power grid, and when an abnormal phenomenon exists, the abnormal reason is timely reminded, and the staff is assisted in quick processing, so that the stable operation of the power transmission and transformation system of the power grid is ensured.

2. In the scheme, in the process of processing a white light image and an infrared image, binarization and coordinate processing are carried out on the infrared image to obtain a coordinate set of a pixel point corresponding to power transmission and transformation equipment of a power grid, meanwhile, the scheme carries out coordinate processing on the white light image, a pixel region of interest is used for determining the coordinate set of the pixel point corresponding to the power transmission and transformation equipment of the power grid, and then the two coordinate sets are compared to obtain a comparison result; when the comparison is carried out, the method can determine the target coordinates with larger number based on the first coordinate set, then the number of pixel points corresponding to the power transmission and transformation equipment of the power grid with the same target coordinate dimension is compared, whether the first coordinate information and the second coordinate information of the same coordinate correspond to each other or not is judged according to the number dimension, and accuracy of the comparison result can be ensured while data processing amount is reduced.

3. In the process of analyzing the difference pixel points, the method determines the outline formed by the difference pixel points, and compares the outline with a preset outline to determine what object is a shielding object; the coordinate points in the differential pixel subsets are processed to obtain the proportion among the first X-axis current distance, the second X-axis current distance, the first Y-axis current distance and the second Y-axis current distance, so that the proportion of the contours corresponding to the differential pixel subsets is determined, and then the proportion is compared with the preset proportion of the preset contours.

Drawings

Fig. 1 is a schematic flow chart of an intelligent analysis method for a power transmission and transformation image of a power grid based on data processing according to an embodiment of the invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of 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, and it is apparent that the described embodiments are only some embodiments of the present invention, 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.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein.

It should be understood that, in various embodiments of the present invention, the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in the present invention, "plurality" means two or more. "and/or" is merely an association relationship describing an association object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "comprising A, B and C", "comprising A, B, C" means that all three of A, B, C comprise, "comprising A, B or C" means that one of the three comprises A, B, C, and "comprising A, B and/or C" means that any 1 or any 2 or 3 of the three comprises A, B, C.

It should be understood that in the present invention, "B corresponding to a", "a corresponding to B", or "B corresponding to a" means that B is associated with a, from which B can be determined. Determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information. The matching of A and B is that the similarity of A and B is larger than or equal to a preset threshold value.

As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection" depending on the context.

The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.

Referring to fig. 1, a flow chart of an intelligent analysis method for a power transmission and transformation image of a power grid based on data processing according to an embodiment of the present invention is provided, where the intelligent analysis method for the power transmission and transformation image of the power grid based on data processing includes S1-S6:

s1, performing image acquisition on power transmission and transformation equipment of a power grid based on a white light image acquisition device and an infrared image acquisition device to obtain a first white light image and a first infrared image, and performing binarization processing on the first infrared image to obtain an infrared binarization image, wherein the infrared binarization image comprises white pixel points and black pixel points.

The white light image acquisition device can be a white light camera, the infrared image acquisition device can be an infrared camera, the white light image acquisition device can be used for acquiring white light images of the power grid power transmission and transformation equipment, and the infrared image acquisition device is used for acquiring infrared images of the power grid power transmission and transformation equipment. It is understood that the white light image may collect a surface image of the power grid power transmission and transformation device, and the infrared image may collect an operating temperature of the power grid power transmission and transformation device based on heat generated by the power grid power transmission and transformation device during operation. For example, for a cable, if a portion of the cable passes through the tree, then the power image acquired by the white light image is disconnected; but due to the temperature of the cable, the infrared image can take a full picture of the cable.

After the first infrared image is acquired, the first infrared image is subjected to binarization processing to obtain an infrared binarization image, so that the infrared binarization image only comprises white pixel points and black pixel points.

In some embodiments, the S1 comprises:

The binarization range section is preset in the scheme, and it can be understood that the red region (region with temperature) exists in the infrared image. According to the scheme, all pixel points in the first infrared image, which are located in the binarization range interval, are extracted to serve as white pixel points in the infrared binarization image, and all pixel points in the first infrared image, which are not located in the binarization range interval, are extracted to serve as black pixel points in the infrared binarization image. The method and the device realize binarization processing of the infrared image by adopting the mode, wherein the pixel point corresponding to the white pixel point is the pixel point corresponding to the region with the temperature, and the pixel point corresponding to the region without the temperature.

S2, carrying out coordinate processing on the infrared binarized image to obtain coordinate information of each binarized pixel point, and counting first coordinate information of all white binarized pixel points to obtain a first coordinate set.

After the infrared binarization image is obtained, the infrared binarization image is subjected to coordinate processing to obtain the coordinate information of each binarization pixel point, and then the first coordinate information of all white binarization pixel points is counted to obtain a first coordinate set.

It is understood that the first coordinate set is a set of pixels corresponding to temperatures in the power grid power transmission and transformation device.

In some embodiments, the S2 comprises S21-S24:

s21, carrying out coordinate processing on the infrared binarization image by taking the central point of the infrared binarization image as an origin to obtain coordinate information of each binarization pixel point.

The method can determine the central point of the infrared binarized image as the origin, and then coordinate the infrared binarized image to obtain the coordinate information of each binarized pixel point.

S22, counting the first coordinate information of all the white binarized pixel points to obtain a first coordinate set, and determining the first quantity of the first coordinate information with the same X axis in the first coordinate set and the second quantity of the first coordinate information with the same Y axis in the first coordinate set.

Then, the first coordinate information of all white binarized pixel points is counted to obtain a first coordinate set, wherein the first coordinate set is a pixel point set with temperature in corresponding power grid power transmission and transformation equipment.

After the first coordinate set is obtained, the scheme determines a first amount of first coordinate information having the same X axis in the first coordinate set and a second amount of first coordinate information having the same Y axis in the first coordinate set.

For example, the present solution may extract the number of different X coordinates in the first coordinate set, for example, X coordinates in the first coordinate set are respectively-5, -4, -3, -2, -1, 0, 1, 2, 3, 4,5, then the first number of the first coordinate information having the same X axis in the first coordinate set is 11; for example, the Y coordinates in the first set of coordinates are-4, -3, -2, -1, 0, 1, 2, 3, 4, respectively, then the second number of second coordinate information having the same Y axis in the first set of coordinates is 9.

S23, if the first number is larger than or equal to the second number, the X-axis coordinate is taken as the target coordinate, and if the first number is smaller than the second number, the Y-axis coordinate is taken as the target coordinate.

The method compares the first quantity with the second quantity, and if the first quantity is larger than or equal to the second quantity, the X-axis coordinate is used as a target coordinate; if the first number is smaller than the second number, which indicates that the number of Y-axes is larger, the scheme takes the Y-axis coordinate as the target coordinate.

It should be noted that, in the scheme, a larger number of coordinate axes can be determined from the X-axis dimension and the Y-axis dimension, and subsequent comparison operation is performed by the dimension corresponding to the coordinate axis, so that the accuracy of comparison can be improved.

S24, counting the quantity of all the first coordinate information corresponding to different target coordinates to obtain a first quantity corresponding relation, wherein the first quantity corresponding relation has the first coordinate quantity corresponding to each target coordinate.

For example, the comparison operation is performed on the X-axis, and the method counts the number of the first coordinate information corresponding to all the different target coordinates (X-axis coordinates) to obtain a first number corresponding relationship, where the first number corresponding relationship has the first coordinate number corresponding to each target coordinate. For example, when the X-axis coordinate is-5, the corresponding first coordinate number is 1000, when the X-axis coordinate is-4, the corresponding first coordinate number is 800, and so on, the scheme can obtain the corresponding first coordinate number of each target coordinate, and a first number corresponding relation is formed.

And S3, carrying out coordinate processing on the first white light image to obtain coordinate information of each white light pixel point, and extracting second coordinate information of a target pixel point in the first white light image to obtain a second coordinate set, wherein the target pixel point is a pixel point in a pixel region of interest corresponding to power transmission and transformation equipment of the power grid.

It will be appreciated that step S2 is the processing of an infrared image and step S3 is the processing of a white light image.

When the first white light image is processed, the method performs coordinate processing on the first white light image to obtain coordinate information of each white light pixel point, then extracts second coordinate information of a target pixel point in the first white light image to obtain a second coordinate set, wherein the target pixel point is a pixel point in an interested pixel section corresponding to the power grid power transmission and transformation equipment, and the meaning of the interested pixel section is explained in step S32.

In some embodiments, the S3 comprises S31-S33:

s31, the first white light image is subjected to coordinate processing by taking the central point of the first white light image as an origin to obtain the coordinate information of each white light pixel point.

The method comprises the steps of determining a center point of a first white light image, and carrying out coordinate processing on the first white light image by taking the center point of the first white light image as an origin to obtain coordinate information of each white light pixel point.

S32, determining a corresponding pixel set of interest according to the type of the power transmission and transformation equipment of the power grid, wherein at least one pixel region of interest exists in the pixel set of interest, and taking a pixel point positioned in the pixel region of interest in the first white light image as a target pixel point.

It can be understood that the types of the power transmission and transformation devices of the power grid are different, and the corresponding colors are also different, so that the corresponding pixel regions of interest are also different. Taking the cable as an example, when the cable A is yellow, the corresponding pixel region of interest is yellow; when the cable B is black, the corresponding pixel region of interest is black.

According to the scheme, a corresponding pixel set of interest is determined according to the type of the power transmission and transformation equipment of the power grid, at least one pixel region of interest exists in the pixel set of interest, and then a pixel point located in the pixel region of interest in the first white light image is used as a target pixel point. It is understood that the target pixel point is a pixel point corresponding to the grid power transmission and transformation device.

S33, extracting second coordinate information of the target pixel points in the first white light image to obtain a second coordinate set, and counting the quantity of the second coordinate information corresponding to all different target coordinates to obtain a second quantity corresponding relation, wherein the second quantity corresponding relation has the second coordinate quantity corresponding to each target coordinate.

Since the target pixel point is a pixel point corresponding to the grid power transmission and transformation device, the second coordinate set is also a pixel point set corresponding to the pixel point of the grid power transmission and transformation device.

The method includes counting the number of the second coordinate information corresponding to different target coordinates (for example, the X-axis coordinates determined in step S2), and obtaining a second number corresponding relation, wherein the second number corresponding relation has the second coordinate number corresponding to each target coordinate. For example, when the X-axis coordinate is-5, the corresponding second coordinate number is 1000, when the X-axis coordinate is-4, the corresponding second coordinate number is 500, and so on, the scheme can obtain the corresponding second coordinate number of each target coordinate in the second coordinate set, so as to form a second number corresponding relation.

And S4, if the first coordinate information in the first coordinate set completely corresponds to the second coordinate information in the second coordinate set, outputting a first intelligent analysis result.

It can be understood that the first coordinate information in the first coordinate set and the second coordinate information in the second coordinate set are compared, and if the first coordinate information in the first coordinate set and the second coordinate information in the second coordinate set completely correspond, a first intelligent analysis result is output.

The step S4 comprises S41-S42:

s41, if the first coordinate number of the first coordinate information and the second coordinate number of the second coordinate information of the same target coordinate are the same, judging that the first coordinate information and the second coordinate information of the same coordinate correspond.

When the comparison is carried out, the scheme can take the same target coordinates as a reference for comparison, and if the first coordinate information of the same target coordinates and the first coordinate number and the second coordinate number of the second coordinate information are the same, the scheme can determine that the first coordinate information and the second coordinate information of the same coordinates correspond.

It should be noted that, unlike the prior art, in the prior art, all pixels of an image are compared, which results in a larger comparison amount and a larger data processing amount. According to the comparison method, the large-number target coordinates are determined based on the first coordinate set, then the number of pixel points corresponding to the power grid power transmission and transformation equipment with the same target coordinate dimension is compared, whether the first coordinate information and the second coordinate information with the same coordinates are corresponding or not is judged according to the number dimension, and accuracy of comparison results can be ensured while data processing amount is reduced.

And S42, if all the first coordinate information and the second coordinate information of the same target coordinate are corresponding, judging that the first coordinate information in the first coordinate set is completely corresponding to the second coordinate information in the second coordinate set, and outputting a first intelligent analysis result.

The first coordinate information and the second coordinate information of all the same target coordinates in the dimension can be compared, if all the first coordinate information and the second coordinate information of all the same target coordinates are corresponding, the scheme can determine that the first coordinate information in the first coordinate set is completely corresponding to the second coordinate information in the second coordinate set, and at the moment, the scheme can output a first intelligent analysis result. It is understood that the first intelligent analysis result refers to a result that the power grid power transmission and transformation equipment is in a normal state, i.e. no cover or hanging object exists on the power grid power transmission and transformation equipment.

And S5, if the first coordinate information in the first coordinate set and the second coordinate information in the second coordinate set do not completely correspond, comparing according to the first coordinate set and the second coordinate set to obtain a difference coordinate set.

When the first coordinate information in the first coordinate set and the second coordinate information in the second coordinate set do not completely correspond, it is indicated that differences exist between the white light image and the infrared image, and abnormal situations occur.

In some embodiments, the S5 includes S51-S52:

s51, if the first coordinate number of the first coordinate information and the second coordinate number of the second coordinate information of the same target coordinate are different, judging that the first coordinate information and the second coordinate information of the same coordinate do not correspond.

For example, when the same target coordinate is X-axis coordinate and-5, the corresponding first coordinate number is 1000, and the second coordinate number is 500, and at this time, the first coordinate information and the second coordinate information of the same target coordinate are different in the first coordinate number and the second coordinate number, and the first coordinate information and the second coordinate information of the same coordinate are determined not to correspond in this scheme.

It should be noted that, according to the scheme, through comparing the first coordinate number and the second coordinate number, whether the first coordinate information and the second coordinate information of the same coordinate correspond or not can be rapidly judged.

S52, extracting all the second coordinate information which does not correspond to the second coordinate information to obtain a difference coordinate set.

After the comparison is completed, the scheme can extract all the second coordinate information which does not correspond to the second coordinate information to obtain a difference coordinate set. It should be noted that, the pixel points corresponding to the difference coordinate set are abnormal pixel points, but it is not yet possible to determine what the cause of the abnormality is, and the solution further determines the difference coordinate set through step S6 to determine the cause of the abnormality.

According to the scheme, pixel points of the difference coordinate set are positioned in the first white light image, corresponding difference pixel points are determined, and then the pixel values of the difference pixel points are analyzed to obtain a second intelligent analysis result.

In some embodiments, the S6 includes S61-S64:

and S61, positioning pixel points in the first white light image according to all the second coordinate information in the differential coordinate set to obtain differential pixel points, and classifying all the differential pixel points according to the second coordinate information to obtain at least one differential pixel subset.

According to the scheme, pixel points in the first white light image are positioned according to all second coordinate information in the difference coordinate set, so that difference pixel points corresponding to the difference coordinate set are obtained, and then all the difference pixel points are classified by utilizing the second coordinate information, so that at least one difference pixel subset is obtained.

The method comprises the steps of classifying all the difference pixel points by using second coordinate information to obtain at least one difference pixel subset, wherein adjacent pixel points can be determined according to the coordinate information, and then classifying the adjacent pixel points into one set.

S62, determining the number of difference pixel points in each difference pixel subset, and deleting the difference pixel subsets with the number of the difference pixel points smaller than the preset number.

After a plurality of difference pixel subsets are obtained, the number of difference pixel points in each difference pixel subset is determined, and then the difference pixel subsets with the number of the difference pixel points smaller than the preset number are deleted.

It will be appreciated that the smaller number of differential pixel subsets may be due to interference caused by imaging problems or other problems, and that this step may remove the smaller number of differential pixel subsets to implement denoising.

And S63, extracting the difference pixel values corresponding to the difference pixel points in the rest difference pixel subsets, and analyzing according to the difference pixel values, the outline formed by the difference pixel points and the current time information to obtain a first abnormal shielding result.

After denoising, the scheme extracts the difference pixel value corresponding to the difference pixel point in the rest difference pixel sub-set, and then analyzes the difference pixel value, the outline formed by the difference pixel point and the current time information to obtain a first abnormal shielding result.

In some embodiments, the step S63 (extracting the difference pixel value corresponding to the difference pixel point in the remaining difference pixel subset, and analyzing according to the difference pixel value, the contour formed by the difference pixel point, and the current time information to obtain the first abnormal shielding result) includes step S631-step S636:

S631, comparing the difference pixel value with a preset pixel value, and determining a shielding object corresponding to the corresponding preset pixel value.

The method is provided with preset pixel values, and then the difference pixel values are compared with the preset pixel values to determine the shielding object corresponding to the corresponding preset pixel values. For example, the color corresponding to the preset pixel value is green corresponding to the leaf, and when the difference pixel value corresponds to the preset pixel value, the scheme determines that the shielding object corresponding to the corresponding preset pixel value is the leaf.

S632, if the number of the corresponding shielding objects is multiple, determining all edge pixel points corresponding to the difference pixel sub-set, and forming a current contour corresponding to the difference pixel sub-set according to the edge pixel points.

If a plurality of corresponding shielding objects are provided, the scheme can further determine the shielding objects, firstly, all edge pixel points corresponding to the difference pixel sub-set are determined, and then the edge pixel points are utilized to form the current contour corresponding to the difference pixel sub-set.

When determining the edge pixel point, the pixel value can be used for judging, and it can be understood that the pixel value of the pixel point of the area where the shielding object is located is different from the pixel values of the pixel points of other adjacent areas.

S633, calling the preset outline of the different determined shielding objects, and if the preset outline corresponding to the current outline exists, taking the shielding object corresponding to the preset outline as the shielding object to be verified.

The scheme is provided with preset contours, after the current contours are obtained, the current contours are compared with a plurality of preset contours, and if the preset contours corresponding to the current contours exist, a shielding object corresponding to the preset contours is used as a shielding object to be verified.

In some embodiments, S633 (the retrieving the preset outline of the determined different occlusion object, if there is a preset outline corresponding to the current outline, taking the occlusion object corresponding to the preset outline as the occlusion object to be verified) includes S6331-S6335:

s6331, calculating according to the maximum X-axis coordinate value, the minimum X-axis coordinate value, the maximum Y-axis coordinate value and the minimum Y-axis coordinate value in the difference pixel subset to obtain the drawn center coordinate point.

Wherein the X-axis coordinate of the simulated center coordinate point is the sum of the maximum X-axis coordinate value and the minimum X-axis coordinate value divided by 2, and the Y-axis coordinate of the simulated center coordinate point is the sum of the maximum Y-axis coordinate value and the minimum Y-axis coordinate value divided by 2.

S6332, determining a maximum X-axis coordinate point, a minimum X-axis coordinate point, a maximum Y-axis coordinate point and a minimum Y-axis coordinate point in the difference pixel subset through a maximum X-axis coordinate value, a minimum X-axis coordinate value, a maximum Y-axis coordinate value and a minimum Y-axis coordinate value.

The scheme can determine the maximum X-axis coordinate point, the minimum X-axis coordinate point, the maximum Y-axis coordinate point and the minimum Y-axis coordinate point in the difference pixel subset through the maximum X-axis coordinate value, the minimum X-axis coordinate value, the maximum Y-axis coordinate value and the minimum Y-axis coordinate value. The maximum X-axis coordinate point is a coordinate point corresponding to a maximum X-axis coordinate value, the minimum X-axis coordinate point is a coordinate point corresponding to a minimum X-axis coordinate value, the maximum Y-axis coordinate point is a coordinate point corresponding to a maximum Y-axis coordinate value, and the minimum Y-axis coordinate point is a coordinate point corresponding to a minimum Y-axis coordinate value. In some cases, there may be a partial overlap between the maximum X-axis coordinate point, the minimum X-axis coordinate point, the maximum Y-axis coordinate point, and the minimum Y-axis coordinate point.

And S6333, calculating according to the drawn center coordinate point, the maximum X-axis coordinate point, the minimum X-axis coordinate point, the maximum Y-axis coordinate point and the minimum Y-axis coordinate point to obtain a first X-axis current distance, a second X-axis current distance, a first Y-axis current distance and a second Y-axis current distance.

The method comprises the steps of calculating the distance between a planned center coordinate point and a maximum X-axis coordinate point, a minimum X-axis coordinate point, a maximum Y-axis coordinate point and a minimum Y-axis coordinate point respectively to obtain a first X-axis current distance, a second X-axis current distance, a first Y-axis current distance and a second Y-axis current distance.

In some cases, when the maximum X-axis coordinate point, the minimum X-axis coordinate point, the maximum Y-axis coordinate point and the minimum Y-axis coordinate point overlap, the calculated first X-axis current distance, the second X-axis current distance, the first Y-axis current distance and the second Y-axis current distance will be equal, but this solution does not affect the calculation of the ratio, for example, when the first X-axis current distance is equal to the second Y-axis current distance, the ratio between the first X-axis current distance and the second Y-axis current distance is 1:1.

S6334, calculating the ratio among the first X-axis current distance, the second X-axis current distance, the first Y-axis current distance and the second Y-axis current distance to obtain a current ratio set corresponding to the current profile, wherein the current ratio set comprises a first current coefficient, a second current coefficient, a third current coefficient and a fourth current coefficient.

After calculating the first X-axis current distance, the second X-axis current distance, the first Y-axis current distance, and the second Y-axis current distance, the present solution calculates a ratio between the first X-axis current distance, the second X-axis current distance, the first Y-axis current distance, and the second Y-axis current distance, where the ratio is, for example, A1: a2: a3: a4, the current proportion set is { A1, A2, A3, A4}, wherein the first current coefficient is A1, the second current coefficient is A2, the third current coefficient is A3, and the fourth current coefficient is A4.

S6335, obtaining a preset proportion set corresponding to the preset contour, comparing the current proportion set with the preset proportion set, and determining the preset contour corresponding to the current contour.

The preset proportion corresponding to the preset profile can be B1: b2: b3: b4, the preset proportion set is { B1, B2, B3, B4}, and the scheme can compare the current proportion set with the preset proportion set to determine the preset contour corresponding to the current contour.

In some embodiments, S6335 (the obtaining a preset proportion set corresponding to the preset contour, comparing the current proportion set with the preset proportion set, and determining the preset contour corresponding to the current contour) includes S63351-S63353:

s63351, obtaining a preset proportion set corresponding to a preset contour, wherein the preset proportion set comprises a first preset coefficient, a second preset coefficient, a third preset coefficient and a fourth preset coefficient.

For example, the preset proportion set is { B1, B2, B3, B4}, the first preset coefficient is B1, the second preset coefficient is B2, the third preset coefficient is B3, and the fourth preset coefficient is B4.

S63352, calculating according to preset logic to obtain a plurality of current differences among a first current coefficient, a second current coefficient, a third current coefficient and a fourth current coefficient, and a plurality of preset differences among the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient;

The scheme is provided with preset logic, and calculation is performed according to the preset logic to obtain a plurality of current differences among the first current coefficient, the second current coefficient, the third current coefficient and the fourth current coefficient, and a plurality of preset differences among the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient.

Wherein S63352 (the calculating according to the preset logic to obtain a plurality of current differences among the first current coefficient, the second current coefficient, the third current coefficient, and the fourth current coefficient, and a plurality of preset differences among the first preset coefficient, the second preset coefficient, the third preset coefficient, and the fourth preset coefficient) includes S633521-S633524:

s633521, randomly selecting one of the first current coefficient, the second current coefficient, the third current coefficient and the fourth current coefficient as a first comparison coefficient, and selecting the unselected one as a second comparison coefficient.

For example, the first comparison coefficient randomly selected from the first current coefficient, the second current coefficient, the third current coefficient and the fourth current coefficient may be a first current coefficient A1, then the second current coefficient is A2, the third current coefficient is A3, and the fourth current coefficient is A4 and is a second comparison coefficient.

S633522, calculating the difference value between the first comparison coefficient and each second comparison coefficient to obtain a plurality of current difference values.

For example, the scheme may calculate the difference between the first current coefficient A1 and the second current coefficient A2, the third current coefficient is A3, and the fourth current coefficient is A4, so as to obtain a plurality of current differences.

S633523, selecting a third comparison coefficient corresponding to the first comparison coefficient from the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient, and taking the unselected comparison coefficient as the fourth comparison coefficient.

In the scheme, a third comparison coefficient corresponding to the first comparison coefficient is selected from the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient, wherein the third comparison coefficient is, for example, the first preset coefficient corresponding to the first current coefficient A1 is B1, then the unselected second preset coefficient is B2, the third preset coefficient is B3, and the fourth preset coefficient is B4 as the fourth comparison coefficient.

S633524, calculating the difference value between the third comparison coefficient and each fourth comparison coefficient to obtain a plurality of preset difference values.

The difference between the third comparison coefficient (the first preset coefficient is B1) and each fourth comparison coefficient (the second preset coefficient is B2, the third preset coefficient is B3, and the fourth preset coefficient is B4) is calculated respectively, so as to obtain a plurality of preset differences.

And S63353, if the current difference value corresponds to the preset difference value, determining that a preset contour corresponding to the current contour exists.

It will be appreciated that if the current difference corresponds to a preset difference, the present solution determines that there is a preset profile corresponding to the current profile.

By means of the scheme, the profiles can be different in size, but the profiles can be compared uniformly when the scales are the same, and the situation that the profiles cannot be compared when the sizes of the profiles are different due to shooting distance and the like is avoided.

In some embodiments, S63353 (said determining that there is a preset contour corresponding to the current contour if the current difference value corresponds to the preset difference value) includes S633531-S633532:

s633531, classifying the current difference and the preset difference according to the corresponding relation between the first comparison coefficient and the second comparison coefficient and the corresponding relation between the third comparison coefficient and the fourth comparison coefficient.

For example, the present scheme classifies the current difference between the first current coefficient A1 and the first current coefficient A2, and the preset difference between the first preset coefficient B1 and the first preset coefficient B2 into a class, and may be in one-to-one correspondence when the calculation is performed subsequently.

S633532, calculating comparison differences between the classified current differences and preset differences, and if all the comparison differences are smaller than the threshold differences respectively, judging that all the current differences correspond to the preset differences, determining that a preset contour corresponding to the current contour exists.

In addition, the scheme is also provided with a threshold value difference value, and if all the comparison difference values are respectively smaller than the threshold value difference value, the error is indicated to be in a certain range, and the scheme can judge that all the current difference values correspond to the preset difference value. At this time, the scheme can determine that a preset contour corresponding to the current contour exists.

S634, acquiring current time information, and if the to-be-verified shielding object is judged to correspond to the current time information, taking the to-be-verified shielding object as a final first abnormal shielding result.

The scheme can be combined with the current time information to further verify the shielding object, for example, the current time information is summer, the shielding object to be verified is ice-on, and then the shielding object to be verified does not correspond to the current time information, and the situation that the shielding object to be verified is wrong is possibly judged; for another example, in winter, the current time information is that the to-be-verified shielding object is ice-on, and then the to-be-verified shielding object corresponds to the current time information.

And S635, if the number of the corresponding shielding objects is 1, adding a first label to the 1 shielding objects, and generating a final first abnormal shielding result according to the 1 shielding objects and the first label.

If the number of the corresponding shielding objects is 1, the shielding objects can be determined according to the scheme, at this time, a first label is added to the 1 shielding objects, and a final first abnormal shielding result is generated according to the 1 shielding objects and the first label. It will be appreciated that the first anomalous occlusion result described above may determine what occlusion is in particular.

S636, if the preset contour corresponding to the current contour does not exist, or the to-be-verified shielding object does not correspond to the current time information, adding a second label to the plurality of shielding objects, and generating a final first abnormal shielding result according to the plurality of shielding objects and the second label.

Different from the above steps, if the preset contour corresponding to the current contour does not exist or the to-be-verified shielding object does not correspond to the current time information, it is indicated that the shielding object cannot be determined specifically what shielding object is by the scheme, at this time, the scheme adds second labels to the plurality of shielding objects, and then generates a final first abnormal shielding result according to the plurality of shielding objects and the second labels. It will be appreciated that the first abnormal occlusion result described above does not determine what occlusion is in particular.

S64, performing de-duplication processing on the first abnormal shielding results of all the difference pixel subsets to obtain second abnormal shielding results, and taking all the second abnormal shielding results as second intelligent analysis results.

In some cases, the shielding objects may be the same, for example, a plurality of leaves are shielded, so that the first abnormal shielding results obtained by comparing the schemes may be repeated, at this time, the schemes can perform de-duplication processing on the first abnormal shielding results of all the difference pixel subsets to obtain second abnormal shielding results, and finally, all the second abnormal shielding results are used as second intelligent analysis results.

The present invention also provides a storage medium having stored therein a computer program for implementing the methods provided by the various embodiments described above when executed by a processor.

The storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). In addition, the ASIC may reside in a user device. The processor and the storage medium may reside as discrete components in a communication device. The storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc.

The present invention also provides a program product comprising execution instructions stored in a storage medium. The at least one processor of the device may read the execution instructions from the storage medium, the execution instructions being executed by the at least one processor to cause the device to implement the methods provided by the various embodiments described above.

In the above embodiments of the terminal or the server, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the 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 scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims

1. The intelligent analysis method for the power transmission and transformation image of the power grid based on data processing is characterized by comprising the following steps of:

2. The intelligent analysis method for the power transmission and transformation image of the power grid based on the data processing according to claim 1, wherein,

the S1 comprises the following steps:

3. The intelligent analysis method for the power transmission and transformation image of the power grid based on the data processing according to claim 2, wherein,

the step S2 comprises the following steps:

4. The intelligent analysis method for the power transmission and transformation image of the power grid based on the data processing according to claim 3, wherein,

the step S3 comprises the following steps:

5. The intelligent analysis method for the power transmission and transformation image of the power grid based on the data processing according to claim 4, wherein,

the step S4 comprises the following steps:

6. The intelligent analysis method for the power transmission and transformation image based on the data processing according to claim 5, wherein,

the step S5 comprises the following steps:

7. The intelligent analysis method for the power transmission and transformation image of the power grid based on the data processing according to claim 6, wherein,

the step S6 comprises the following steps:

8. The intelligent analysis method for the power transmission and transformation image based on the data processing according to claim 7, wherein,

Extracting a difference pixel value corresponding to a difference pixel point in the rest difference pixel sub-set, analyzing according to the difference pixel value, a contour formed by the difference pixel point and current time information to obtain a first abnormal shielding result, wherein the method comprises the following steps of:

9. The intelligent analysis method for the power transmission and transformation image based on the data processing according to claim 8, wherein,

and if the preset contour corresponding to the current contour exists, taking the shielding object corresponding to the preset contour as the shielding object to be verified, wherein the method comprises the following steps of:

10. The intelligent analysis method for the power transmission and transformation image based on the data processing according to claim 9, wherein,

the obtaining the preset proportion set corresponding to the preset outline, comparing the current proportion set with the preset proportion set, and determining the preset outline corresponding to the current outline comprises the following steps:

calculating according to preset logic to obtain a plurality of current differences among the first current coefficient, the second current coefficient, the third current coefficient and the fourth current coefficient, and a plurality of preset differences among the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient, wherein the method comprises the following steps:

randomly selecting one of the first current coefficient, the second current coefficient, the third current coefficient and the fourth current coefficient as a first comparison coefficient, selecting the unselected one as a second comparison coefficient,

Calculating the difference value between the first comparison coefficient and each second comparison coefficient to obtain a plurality of current difference values,

selecting a third comparison coefficient corresponding to the first comparison coefficient from the first preset coefficient, the second preset coefficient, the third preset coefficient and the fourth preset coefficient, taking the unselected comparison coefficient as the fourth comparison coefficient,

calculating the difference value between the third comparison coefficient and each fourth comparison coefficient to obtain a plurality of preset difference values;