CN116295031B

CN116295031B - Sag measurement method, sag measurement device, computer equipment and storage medium

Info

Publication number: CN116295031B
Application number: CN202310190733.5A
Authority: CN
Inventors: 李永荣; 宋江; 刘正军; 钱建国; 陈一铭; 周佳慧
Original assignee: Chinese Academy of Surveying and Mapping
Current assignee: Chinese Academy of Surveying and Mapping
Priority date: 2023-02-24
Filing date: 2023-02-24
Publication date: 2024-03-12
Anticipated expiration: 2043-02-24
Also published as: CN116295031A

Abstract

The present application relates to a sag measurement method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: image acquisition is carried out on a target power transmission line to obtain a corresponding sequence image, wherein at least one preset target is deployed on the target power transmission line; carrying out semantic segmentation processing on the sequence image to obtain each semantic segmentation graph comprising the target power line and the preset target; determining a curve relation of the target power transmission line on a ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power transmission line and the internal and external azimuth elements of the semantic segmentation map; and determining sag of the target power transmission line according to the curve relation of the target power transmission line on the ground measurement coordinate system. The measuring efficiency of sag can be improved to this scheme.

Description

Sag measurement method, sag measurement device, computer equipment and storage medium

Technical Field

The present disclosure relates to the field of measurement technologies, and in particular, to a sag measurement method, apparatus, computer device, and storage medium.

Background

With the development of the measuring technology, a sag measuring technology appears, and the sag measuring technology can measure sag of the power transmission line to obtain sag of the power transmission line.

In the traditional sag measurement technology, when the power transmission line is manually and locally inspected, the sag of the power transmission line is manually and locally measured.

However, in the current sag measurement technology, a great deal of manpower is input, and sag measurement efficiency is low.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a sag measurement method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve sag measurement efficiency.

In a first aspect, the present application provides a method of measuring sag. The method comprises the following steps:

image acquisition is carried out on a target power transmission line to obtain a corresponding sequence image, wherein at least one preset target is deployed on the target power transmission line;

carrying out semantic segmentation processing on the sequence image to obtain each semantic segmentation graph comprising the target power line and the preset target;

determining a curve relation of the target power transmission line on a ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power transmission line and the internal and external azimuth elements of the semantic segmentation map; aiming at any preset target, the first image coordinate set corresponding to the preset target comprises first coordinate information corresponding to the preset target in each semantic segmentation graph; for any hanging point, the second image coordinate set corresponding to the hanging point comprises second coordinate information corresponding to the hanging point in each semantic segmentation graph;

And determining sag of the target power transmission line according to the curve relation of the target power transmission line on the ground measurement coordinate system.

In one embodiment, the performing semantic segmentation processing on the sequence image to obtain each semantic segmentation graph including the target power line and the preset target includes:

performing semantic segmentation processing on any sequence image to obtain an initial semantic segmentation graph corresponding to the sequence image;

determining each first semantic segmentation graph comprising the target power line and the preset target from each initial semantic segmentation graph;

and aiming at any one of the first semantic segmentation graphs, acquiring first target coordinate information corresponding to each preset target in the first semantic segmentation graph and second target coordinate information of the target power transmission line, and correcting the first semantic segmentation graph according to the first target coordinate information and the second target coordinate information to obtain a corresponding semantic segmentation graph.

In one embodiment, the performing semantic segmentation processing on the sequence image to obtain an initial semantic segmentation map corresponding to the sequence image includes:

For any sequence image, carrying out blocking processing on the sequence image to obtain each sequence sub-image corresponding to the sequence image;

performing semantic segmentation processing on any sequence sub-image to obtain an initial semantic segmentation sub-image corresponding to the sequence sub-image;

and performing stitching processing on the initial semantic segmentation subgraphs of the sequence sub-images corresponding to any sequence image to obtain the initial semantic segmentation graph corresponding to the sequence image.

In one embodiment, the first target coordinate information includes a center coordinate of the preset target in the first semantic segmentation map; the second target coordinate information comprises coordinate information of each pixel point of the target power line in the first semantic segmentation graph; the correcting the first semantic segmentation map according to the first target coordinate information and the second target coordinate information to obtain a corresponding semantic segmentation map includes:

and aiming at any preset target, determining a correction reference area corresponding to the preset target according to the center coordinates and the preset radius of the preset target, and deleting classification labels of all pixel points corresponding to the preset target in the first semantic segmentation map under the condition that the number of the pixel points of a target power line positioned in the correction reference area is smaller than a preset threshold value to obtain a semantic segmentation map.

In one embodiment, the semantic segmentation map includes a reference match map and an associated match map; the correcting the first semantic segmentation map according to the first target coordinate information and the second target coordinate information to obtain a corresponding semantic segmentation map includes:

according to the first target coordinate information and the second target coordinate information, correcting the first semantic segmentation map to obtain a corresponding second semantic segmentation map;

taking the second semantic segmentation graphs with the number of the suspension points of the target power line meeting the preset number as an initial matching graph;

and determining the number of the preset targets in each initial matching graph, taking the initial matching graph with the largest number of the preset targets as the reference matching graph, and determining an associated matching graph associated with the reference matching graph from the initial matching graph.

In one embodiment, after determining the associated matching graph associated with the reference matching graph, the method further comprises:

determining a reference matching graph from each semantic segmentation graph, and determining corresponding reference coordinate information of each target object in the reference matching graph; the target object comprises the preset target or the hanging point;

According to the reference coordinate information of each target object and a preset matching strategy, matching to obtain coordinate information associated with each reference coordinate information from the rest of semantic segmentation graphs; the coordinate information comprises first coordinate information or second coordinate information;

for any target object, constructing an image coordinate set corresponding to the target object according to the reference coordinate information corresponding to the target object and the coordinate information associated with the reference coordinate information; the image coordinate set includes a first image coordinate set or a second image coordinate set.

In one embodiment, the determining a curve relation of the target power transmission line on the ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power transmission line, and the internal and external azimuth elements of the semantic segmentation map includes:

determining a first ground coordinate set of the preset target on a ground measurement coordinate system and a second ground coordinate set of the suspension point on the ground measurement coordinate system according to the first image coordinate set corresponding to each preset target, the second image coordinate set corresponding to each suspension point of the target power line and the internal and external azimuth elements of the semantic segmentation map; the first ground coordinate set comprises first ground coordinates of at least one preset target on the ground measurement coordinate system; the second ground coordinate set comprises second ground coordinates of at least two suspension points on the ground measurement coordinate system;

And fitting to obtain a curve relation of the target power transmission line on the ground measurement coordinate system based on the first ground coordinate set and the second ground coordinate set. In a second aspect, the present application also provides a sag measurement device. The device comprises:

the acquisition module is used for acquiring images of a target power transmission line to obtain corresponding sequence images, and at least one preset target is deployed on the target power transmission line;

the semantic segmentation module is used for carrying out semantic segmentation processing on the sequence image to obtain each semantic segmentation graph comprising the target power line and the preset target;

the first determining module is used for determining a curve relation of the target power transmission line on a ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power transmission line and the internal and external azimuth elements of the semantic segmentation map; aiming at any preset target, the first image coordinate set corresponding to the preset target comprises first coordinate information corresponding to the preset target in each semantic segmentation graph; for any hanging point, the second image coordinate set corresponding to the hanging point comprises second coordinate information corresponding to the hanging point in each semantic segmentation graph;

And the second determining module is used for determining sag of the target power transmission line according to the curve relation of the target power transmission line on the ground measurement coordinate system.

In one embodiment, the semantic segmentation module is specifically configured to:

In one embodiment, the first target coordinate information includes a center coordinate of the preset target in the first semantic segmentation map; the second target coordinate information comprises coordinate information of each pixel point of the target power line in the first semantic segmentation graph; the semantic segmentation module is specifically configured to:

In one embodiment, the semantic segmentation map includes a reference match map and an associated match map; the semantic segmentation module is specifically configured to:

In one embodiment, the sag measurement device further comprises:

a fourth determining module, configured to determine a reference matching graph from each of the semantic segmentation graphs, and determine reference coordinate information corresponding to each target object in the reference matching graph; the target object comprises the preset target or the hanging point;

the matching module is used for matching and obtaining coordinate information associated with each piece of reference coordinate information from the rest of semantic segmentation graphs according to the reference coordinate information of each piece of target object and a preset matching strategy; the coordinate information comprises first coordinate information or second coordinate information;

The construction module is used for constructing an image coordinate set corresponding to any target object according to the reference coordinate information corresponding to the target object and the coordinate information associated with the reference coordinate information; the image coordinate set includes a first image coordinate set or a second image coordinate set.

In one embodiment, the first determining module is specifically configured to:

and fitting to obtain a curve relation of the target power transmission line on the ground measurement coordinate system based on the first ground coordinate set and the second ground coordinate set.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the first aspect when the processor executes the computer program.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, realizes the steps as described in the first aspect.

In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps as described in the first aspect.

The sag measurement method, the sag measurement device, the computer equipment, the storage medium and the computer program product are used for acquiring images of a target power transmission line to obtain corresponding sequence images, and at least one preset target is deployed on the target power transmission line; carrying out semantic segmentation processing on the sequence image to obtain each semantic segmentation graph comprising a target power line and a preset target; determining a curve relation of the target power transmission line on a ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power transmission line and the internal and external azimuth elements of the semantic segmentation map; aiming at any preset target, a first image coordinate set corresponding to the preset target comprises first coordinate information corresponding to the preset target in each semantic segmentation graph; for any hanging point, the second image coordinate set corresponding to the hanging point comprises second coordinate information corresponding to the hanging point in each semantic segmentation graph; and determining sag of the target power transmission line according to a curve relation of the target power transmission line on the ground measurement coordinate system. According to the method, a first image coordinate set corresponding to each preset target on a target power transmission line and a second image coordinate set corresponding to each suspension point of the power transmission line are determined according to each sequence image of the target power transmission line, and further, a curve relation of the target power transmission line on a ground measurement coordinate system is determined according to each first image coordinate set, each second image coordinate set and the internal and external azimuth elements of the semantic segmentation map, so that sag of the target power transmission line is determined. Therefore, the sag of the target power transmission line can be determined according to the sequence image of the power transmission line and the internal and external azimuth elements of the semantic segmentation map, the target power transmission line is not required to be manually inspected in the field, and the sag of the target power transmission line is not required to be manually measured in the field, namely, the input of manpower is reduced, and further the sag measurement efficiency and measurement accuracy are improved.

Drawings

FIG. 1 is a flow chart of a method for measuring sag in one embodiment;

FIG. 2 is a flow diagram of a method of determining a semantic segmentation map in one embodiment;

FIG. 3 is a flow chart of a method for determining a semantic segmentation map according to another embodiment;

FIG. 4 is a flow chart of a method of constructing an image coordinate set in one embodiment;

FIG. 5 is a schematic diagram of an auxiliary plane rectangular coordinate system in one embodiment;

FIG. 6 is a block diagram of a measuring device for sag in one embodiment;

fig. 7 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

In one embodiment, as shown in fig. 1, a sag measurement method is provided, where the method is applied to a terminal to illustrate the sag measurement method, it is understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:

And 102, acquiring images of the target power transmission line to obtain corresponding sequence images.

At least one preset target is deployed on the target power transmission line.

In the embodiment of the application, the terminal shoots the target power transmission line through the image acquisition equipment, and acquires the sequence image of the target power transmission line. The image acquisition equipment shoots the target power line, obtains a patrol video of the target power line and sends the patrol video to the terminal. And the terminal performs frame extraction processing on the inspection video of the target power transmission line to obtain a sequence image of the target power transmission line. The number of frames of the sequence image of the target power line may be preset. The image capturing device is a device with a shooting function, and in one embodiment, the image capturing device is an unmanned aerial vehicle.

And 104, carrying out semantic segmentation processing on the sequence image to obtain each semantic segmentation graph comprising the target power line and a preset target.

In the embodiment of the application, for any sequence image, the terminal performs semantic segmentation processing on the sequence image to obtain a semantic segmentation graph corresponding to the sequence image. The terminal performs semantic segmentation processing on the sequence image based on the semantic segmentation model to obtain a semantic segmentation graph corresponding to the sequence image. In one embodiment, the semantic segmentation model may be a Mask RCNN model. The classification category of the semantic segmentation processing comprises a target power line and a preset target. In one embodiment, the preset target category includes a spacer. And acquiring each semantic segmentation graph comprising the target power line and a preset target from each semantic segmentation graph by the terminal. The number of semantic segmentation graphs comprising the target power line and the preset target is at least two.

And 106, determining a curve relation of the target power transmission line on a ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power transmission line and the internal and external azimuth elements of the semantic segmentation map.

The first image coordinate set corresponding to the preset target comprises first coordinate information corresponding to the preset target in each semantic segmentation graph aiming at any preset target. For any hanging point, the second image coordinate set corresponding to the hanging point comprises second coordinate information corresponding to the hanging point in each semantic segmentation graph.

In the embodiment of the application, for any preset target, the terminal respectively acquires first coordinate information corresponding to the preset target in each semantic segmentation graph, and constructs a first image coordinate set corresponding to the preset target based on the first coordinate information corresponding to the preset target in each semantic segmentation graph. And aiming at any hanging point in the target power line, the terminal respectively acquires second coordinate information corresponding to the hanging point in each semantic segmentation graph, and constructs a second image coordinate set corresponding to the hanging point based on the second coordinate information corresponding to the hanging point in each semantic segmentation graph. And the terminal calculates to obtain a first ground coordinate of at least one preset target on a ground measurement coordinate system and a second ground coordinate of at least two suspension points on the ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power line and the internal and external azimuth elements of the semantic segmentation map.

Wherein, the internal azimuth element of the semantic segmentation graph is prestored in the terminal. The external orientation element of the semantic segmentation map is obtained by calculating the external orientation element of the sequence image by the terminal based on each sequence image of the target power line and a beam adjustment method, and taking the external orientation element of the sequence image as the external orientation element of the semantic segmentation map corresponding to the sequence image. The terminal calculates a first ground coordinate of at least one preset target on a ground measurement coordinate system and a second ground coordinate of at least two suspension points on the ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power line, the internal and external azimuth elements of the semantic segmentation map and a space front intersection method. And the terminal performs curve fitting processing based on a first ground coordinate of at least one preset target on the ground measurement coordinate system and a second ground coordinate of at least two suspension points on the ground measurement coordinate system to obtain a curve relation of the target power transmission line on the ground measurement coordinate system. In one embodiment, the method of curve fitting is a least squares method. The beam adjustment method is to use each beam (photo) as basic adjustment unit, the collineation equation of central projection as basic equation of adjustment, uniformly carrying out adjustment in the whole area, calculating out the external orientation element of each sequence image, and calculating out the ground coordinates of the encryption point according to the intersection of multiple front sides. Specifically, the processing procedure of the space front intersection method is to acquire the image coordinates of at least one pixel point of the image pair for the terminal respectively. Exemplary, assume that the image pair includes graphs A and B, where P _A The dots are pixels in the diagram APoint, P _A The coordinates of the point on the graph a are (x ₁ ，y ₁ )，P _B The dots are pixel dots in the diagram B, and are P _B And P _A Is a homonymous image point, P _B The coordinates of the image of the point on the graph B are (x ₂ ，y ₂ ). The terminal will P _A Image coordinates of points (x ₁ ，t ₁ ) Mapping to an image space auxiliary coordinate system A-uvw corresponding to the image A to obtain P _A The image space auxiliary coordinates (u) of the point on the image space auxiliary coordinate system a-uvw ₁ ，v ₁ ，w ₁ ) The method comprises the steps of carrying out a first treatment on the surface of the Will P _B Image coordinates of points (x ₂ ，y ₂ ) Mapping to an image space auxiliary coordinate system B-uvw corresponding to the graph B to obtain P _B The image space auxiliary coordinates (u) of the point on the image space auxiliary coordinate system B-uvw ₂ ，v ₂ ，w ₂ ). Terminal according to (u) ₁ ，v ₁ ，w ₁ ) Sum (u) ₂ ，v ₂ ，w ₂ ) Coordinate information of the photographing base line, the external orientation element of the graph A and the external orientation element of the graph B are obtained through calculation. Then, the terminal sets P according to the external azimuth element of the diagram A, the external azimuth element of the diagram B and the preset stored internal azimuth element _A Image space auxiliary coordinates of points (u ₁ ，v ₁ ，w ₁ ) Converting to the ground measurement coordinate system D-XYZ to obtain P _A Ground coordinates (x) of points on the ground measurement coordinate system D-XYZ _a ，y _a ，z _a ) Will P _B Image space auxiliary coordinates of points (u ₂ ，v ₂ ，w ₂ ) Converting to the ground measurement coordinate system D-XYZ to obtain P _B Ground coordinates (x) of points on the ground measurement coordinate system D-XYZ _b ，y _b ，z _b )。

And step 108, determining sag of the target power transmission line according to a curve relation of the target power transmission line on the ground measurement coordinate system.

In the embodiment of the application, the terminal calculates the sag of the target power transmission line according to the curve relation of the target power transmission line on the ground measurement coordinate system. The terminal calculates the extreme point of the curve relation of the target power transmission line on the ground measurement coordinate system, and calculates the vertical distance between the extreme point and the suspension point to obtain the sag of the target power transmission line. Wherein the curve relation is a polynomial equation of a plurality of times. In one embodiment, the curve relationship is a quadratic polynomial equation, specifically as shown in equation (3) below.

y＝a ₀ +a ₁ ·x+a ₂ ·x ² (3)

Wherein y is the ordinate of the pixel point on the target power line on the ground measurement coordinate system, x is the abscissa of the pixel point on the target power line on the ground measurement coordinate system, and a ₀ 、a ₁ And a ₂ Is a parameter obtained after curve fitting treatment.

In the sag measurement method, according to each sequence image of the target power transmission line, a first image coordinate set corresponding to each preset target on the target power transmission line and a second image coordinate set corresponding to each suspension point of the power transmission line are determined, and further, according to each first image coordinate set, each second image coordinate set and the internal and external azimuth elements of the semantic segmentation map, a curve relation of the target power transmission line on a ground measurement coordinate system is determined, so that sag of the target power transmission line is determined. Therefore, the sag of the target power line can be determined according to the sequence image of the power line and the internal and external azimuth elements of the semantic segmentation map, the target power line is not required to be manually inspected in the field, and the sag of the target power line is not required to be manually measured in the field, namely, the input of manpower is reduced, further, the sag measurement efficiency and measurement accuracy are improved, meanwhile, the degree of automation is provided, and further, the cost is reduced.

In one embodiment, as shown in fig. 2, performing semantic segmentation processing on a sequence image to obtain each semantic segmentation graph including a target power line and a preset target, where the semantic segmentation graph includes:

step 202, for any sequence image, performing semantic segmentation processing on the sequence image to obtain an initial semantic segmentation map corresponding to the sequence image.

In the embodiment of the application, for any sequence image, the terminal performs semantic segmentation processing on the sequence image to obtain an initial semantic segmentation map corresponding to the sequence image. The terminal performs semantic segmentation processing on the sequence image based on the semantic segmentation model to obtain an initial semantic segmentation map corresponding to the sequence image. In one embodiment, the semantic segmentation model may be a Mask RCNN model.

Step 204, determining each first semantic segmentation graph comprising the target power line and a preset target from each initial semantic segmentation graph.

In the embodiment of the present application, due to the problem of image acquisition angle, the information contained in the initial semantic segmentation map corresponding to each sequence image is different, for example: the part of the initial semantic segmentation images only comprises the target power line and does not comprise the preset target, so that the terminal selects a first semantic segmentation graph comprising the target power line and the preset target from all the initial semantic segmentation graphs. Wherein the number of first semantic segmentation graphs is at least two.

Step 206, for any first semantic segmentation graph, acquiring first target coordinate information corresponding to each preset target in the first semantic segmentation graph and second target coordinate information of the target power line, and correcting the first semantic segmentation graph according to the first target coordinate information and the second target coordinate information to obtain a corresponding semantic segmentation graph.

In the embodiment of the application, for any preset target in the first semantic segmentation map, the terminal acquires first target coordinate information corresponding to the preset target in the first semantic segmentation map, and calculates the center coordinates of the preset target according to the first target coordinate information corresponding to the preset target. Aiming at any preset target in the first semantic segmentation map, the terminal determines whether the classification label of the preset target in the first semantic segmentation map needs to be corrected according to the center coordinates of the preset target and the second target coordinate information of the target power line in the first semantic segmentation map to which the preset target belongs. Aiming at any preset target in the first semantic segmentation graph, if the classification label of the preset target in the first semantic segmentation graph needs to be corrected, the terminal deletes the classification label of the preset target in the first semantic segmentation graph, or updates the classification label of the preset target in the first semantic segmentation graph into the classification label of the power line. And aiming at each preset target in the first semantic segmentation map, after the correction processing, the terminal obtains a semantic segmentation map corresponding to the first semantic segmentation map. It can be understood that, since at least one preset target is disposed on the target power line, power lines exist around the preset target, that is, whether the classification label of the preset target is correct or not can be judged by the first target coordinate information of the preset target and the second target coordinate information of the target power line, and correction processing is performed based on the judgment result.

In this embodiment, correction processing is performed on each first semantic segmentation map including the target power line and the preset target, so as to obtain each corresponding semantic segmentation map. Therefore, classification errors caused by semantic segmentation processing can be reduced, so that the classification precision of the semantic segmentation map is improved, and the measurement precision of sag measurement based on the semantic segmentation map is improved.

In one embodiment, performing semantic segmentation processing on a sequence image to obtain an initial semantic segmentation map corresponding to the sequence image, including:

for any sequence image, carrying out blocking treatment on the sequence image to obtain each sequence sub-image corresponding to the sequence image; for any sequence sub-image, carrying out semantic segmentation processing on the sequence sub-image to obtain an initial semantic segmentation sub-image corresponding to the sequence sub-image; and aiming at any sequence image, performing splicing processing on the initial semantic segmentation subgraphs of each sequence sub-image corresponding to the sequence image to obtain an initial semantic segmentation graph corresponding to the sequence image.

In the embodiment of the application, for any sequence image, the terminal performs blocking processing on the sequence image to obtain each sequence sub-image corresponding to the sequence image. Wherein the number of sequence sub-images included in each frame of sequence image is determined according to the size of the sequence image and the size of the sequence sub-image. And aiming at any sequence sub-image, the terminal performs semantic segmentation processing on the sequence sub-image to obtain an initial semantic segmentation sub-image corresponding to the sequence sub-image. The terminal performs semantic segmentation processing on the sequence sub-images based on the semantic segmentation model to obtain initial semantic segmentation subgraphs corresponding to the sequence sub-images. In one embodiment, the semantic segmentation model may be a Mask RCNN model. And aiming at any sequence image, the terminal performs splicing processing on the initial semantic segmentation subgraphs of each sequence sub-image corresponding to the sequence image to obtain an initial semantic segmentation image corresponding to the sequence image.

In this embodiment, semantic segmentation is performed on each sequence sub-image of the sequence image, so as to obtain an initial semantic segmentation sub-image of each sequence sub-image. And then, performing splicing processing based on each initial semantic segmentation sub-graph to obtain an initial semantic segmentation graph corresponding to the sequence image. It can be understood that, since the sequence sub-image is smaller than the sequence image in size, features of each pixel point can be better focused when the semantic segmentation processing is performed, and further, classification precision of the semantic segmentation processing is improved, so that measurement precision of sag measurement based on the semantic segmentation graph is improved.

In one embodiment, the first object coordinate information includes a center coordinate of the preset object in the first semantic segmentation map; the second target coordinate information comprises coordinate information of each pixel point of the target power line in the first semantic segmentation map; according to the first target coordinate information and the second target coordinate information, correcting the first semantic segmentation map to obtain a corresponding semantic segmentation map, including:

and aiming at any preset target, determining a correction reference area corresponding to the preset target according to the central coordinates and the preset radius of the preset target, and deleting classification labels of all pixel points corresponding to the preset target in the first semantic segmentation map under the condition that the number of pixel points of a target power line positioned in the correction reference area is smaller than a preset threshold value to obtain the semantic segmentation map.

In the embodiment of the application, for any preset target in the first semantic segmentation map, the terminal acquires first target coordinate information corresponding to the preset target in the first semantic segmentation map, and calculates the center coordinates of the preset target according to the first target coordinate information corresponding to the preset target. The terminal recognizes the preset target as a polygon, and calculates the center coordinates of the preset target based on a center of gravity coordinate calculation strategy of the polygon. Aiming at any preset target in the first semantic segmentation map, the terminal determines a correction reference area corresponding to the preset target in the first semantic segmentation map to which the preset target belongs according to the center coordinates and the preset radius of the preset target. The correction reference area is an image area taking the central coordinate of a preset target as a circle center and the preset radius as a radius, and the preset radius is a non-negative number. In one embodiment, the preset radius is 0. For any correction reference area, the terminal identifies whether pixel points of the target power line exist in the correction reference area, and when the number of the pixel points of the target power line in the correction reference area is smaller than a preset threshold value, the terminal deletes classification labels of the pixel points corresponding to the preset target in the first semantic segmentation map to obtain the semantic segmentation map. Wherein the preset threshold is a non-negative integer. Specifically, the barycentric coordinate calculation strategy of the polygon is shown in the following formulas (1) and (2).

Wherein C is _x Is the abscissa of the central coordinate of the preset target, C _y Is the ordinate of the central coordinate of the preset target, C _xi Is the abscissa of the gravity center point of the ith triangle of the preset target, C _yi Is the ordinate of the gravity center point of the ith triangle of the preset target, A _i Is the area of the ith triangle of the preset target, and n is the number of triangles dividing the preset target.

In one embodiment, as shown in FIG. 3, the semantic segmentation map includes a reference match map and an associated match map; according to the first target coordinate information and the second target coordinate information, correcting the first semantic segmentation map to obtain a corresponding semantic segmentation map, including:

and 302, correcting the first semantic segmentation map according to the first target coordinate information and the second target coordinate information to obtain a corresponding second semantic segmentation map.

In the embodiment of the application, for any preset target in the first semantic segmentation map, the terminal acquires first target coordinate information corresponding to the preset target in the first semantic segmentation map, and calculates the center coordinates of the preset target according to the first target coordinate information corresponding to the preset target. Aiming at any preset target in the first semantic segmentation map, the terminal determines a correction reference area corresponding to the preset target in the first semantic segmentation map to which the preset target belongs according to the center coordinates and the preset radius of the preset target. For any correction reference area, the terminal identifies whether pixel points of the target power line exist in the correction reference area, and when the number of the pixel points of the target power line in the correction reference area is smaller than a preset threshold value, the terminal deletes classification labels of the pixel points corresponding to the preset target in the first semantic segmentation map to obtain a second semantic segmentation map.

And step 304, taking the second semantic segmentation graphs with the number of hanging points of the target power line meeting the preset number as an initial matching graph.

In the embodiment of the application, in each second semantic segmentation map, the terminal acquires second semantic segmentation maps with the number of hanging points of the target power line meeting the preset number, and takes the second semantic segmentation maps with the number of hanging points of the target power line meeting the preset number as the initial matching map. Wherein the preset number is a positive integer and greater than 1. It is understood that the terminal obtains at least one initial matching graph.

Step 306, determining the number of preset targets in each initial matching graph, taking the initial matching graph with the largest number of preset targets as a reference matching graph, and determining an associated matching graph associated with the reference matching graph from the initial matching graphs.

In this embodiment of the present application, for any initial matching graph, the terminal counts the number of preset targets (for convenience of distinction, referred to as the target number) in the initial matching graph. The terminal takes the initial matching diagram with the largest target number as a reference matching diagram, and determines an associated matching diagram associated with the reference matching diagram from the initial matching diagrams. Wherein the semantic segmentation map comprises a reference matching map and an associated matching map, the reference matching map and the associated matching map associated with the reference matching map being a pair of image pairs. The terminal determines the target ordering of each initial matching image in each initial matching image according to the ordering of the sequence images corresponding to each initial matching image in each sequence image. And the terminal determines an initial matching diagram adjacent to the reference matching image according to the target sequence of the reference matching image, and obtains an associated matching diagram associated with the reference matching diagram.

In this embodiment, according to the number of preset targets in each initial matching graph, a reference matching graph is determined in each initial matching graph, and an associated matching graph associated with the reference matching graph is determined. Wherein the semantic segmentation map comprises a reference matching map and an associated matching map. Because the number of preset targets included in the reference matching graphs is the largest in each initial matching graph, the first image coordinate set determined based on the semantic segmentation graph can contain more preset targets, so that the fitting precision of curve fitting based on the first image coordinate set is improved, namely the measuring precision of sag measurement based on a curve relation obtained by curve fitting is improved.

In one embodiment, as shown in fig. 4, after determining the associated matching graph associated with the reference matching graph, the method further comprises:

step 402, determining a reference matching graph from the semantic segmentation graphs, and determining reference coordinate information corresponding to each target object in the reference matching graph.

Wherein the target object comprises a preset target or a hanging point.

In the embodiment of the application, the terminal selects one reference matching graph from the semantic segmentation graphs, and acquires the reference coordinate information corresponding to each preset target (or hanging point) in the reference matching graph.

Step 404, according to the reference coordinate information of each target object, according to a preset matching strategy, matching to obtain coordinate information associated with each reference coordinate information from the rest of the semantic segmentation graphs.

Wherein the coordinate information includes first coordinate information or second coordinate information.

In the embodiment of the application, for the reference coordinate information of any preset target (or hanging point), the terminal obtains each piece of first coordinate information (or second coordinate information) associated with the reference coordinate information from the rest of the semantic segmentation graphs in a matching manner according to a preset matching strategy. Wherein the rest of the semantic segmentation graphs refer to the semantic segmentation graphs except the reference matching graph. By way of example, assume that there are 3 semantic segmentation graphs including semantic segmentation graph 1, semantic segmentation graph 2, and semantic segmentation graph 3, where semantic segmentation graph 1 is a reference match graph; semantic segmentation fig. 1 includes a preset target a ₁ Preset target b ₁ Suspension pointAnd suspension point->Semantic segmentation FIG. 2 includes a preset target a ₂ Preset target b ₂ Suspension point->And suspension point->Semantic segmentation FIG. 3 includes a preset target a ₃ Preset target b ₃ Suspension point->And suspension point->Then, for the preset target a ₁ With a preset target a ₁ Each first coordinate information associated with the reference coordinate information of (a) includes a preset target a ₂ Is set to be a target of the preset target a ₃ Is set in the first coordinate information of the first image; for suspension point->And suspension point->Each of the second coordinate information associated with the reference coordinate information of (a) includes a suspension pointSecond coordinate information and suspension point of (2)>Is set in the database, and is set in the database.

Step 406, for any target object, constructing and obtaining an image coordinate set corresponding to the target object according to the reference coordinate information corresponding to the target object and the coordinate information associated with the reference coordinate information.

Wherein the image coordinate set comprises a first image coordinate set or a second image coordinate set.

In this embodiment of the present application, for any preset target (or hanging point), an image coordinate set corresponding to the preset target (or hanging point) is constructed according to the reference coordinate information and the first coordinate information (or the second coordinate information) associated with the reference coordinate information.

In this embodiment, a reference matching graph is determined from each semantic segmentation graph, and coordinate information associated with each reference coordinate information in the rest of the semantic segmentation graphs is determined based on the reference coordinate information of each target object in the reference matching graph, so as to construct an image coordinate set including the reference coordinate information and the coordinate information associated with the reference coordinate information. Therefore, the method can be used for constructing and obtaining the image coordinate set and providing data support for the subsequent curve fitting based on the image coordinate set.

In one embodiment, determining a curve relation of the target power transmission line on the ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power transmission line, and the inside and outside azimuth elements of the semantic segmentation map includes:

determining a first ground coordinate set of the preset target on a ground measurement coordinate system and a second ground coordinate set of the suspension point on the ground measurement coordinate system according to the first image coordinate set corresponding to each preset target, the second image coordinate set corresponding to each suspension point of the target power line and the internal and external azimuth elements of the semantic segmentation map; and fitting to obtain a curve relation of the target power transmission line on the ground measurement coordinate system based on the first ground coordinate set and the second ground coordinate set.

The first ground coordinate set of the preset target on the ground measurement coordinate system comprises at least one first ground coordinate of the preset target on the ground measurement coordinate system. The second set of ground coordinates of the suspension points on the ground measurement coordinate system comprises second ground coordinates of at least two suspension points on the ground measurement coordinate system.

In the embodiment of the application, the terminal calculates to obtain a first ground coordinate of at least one preset target on a ground measurement coordinate system and a second ground coordinate of at least two suspension points on the ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power line and the internal and external azimuth elements of the semantic segmentation map. Specifically, the terminal acquires at least one pair of image pairs from each semantic segmentation graph, and acquires each first image coordinate set corresponding to each preset target in the image pairs and each second image coordinate set corresponding to each suspension point in the target power line. For any pair of image pairs, the terminal calculates to obtain a first ground coordinate of at least one preset target on a ground measurement coordinate system and a second ground coordinate of at least two suspension points on the ground measurement coordinate system by adopting a space front intersection method according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power line and the internal and external azimuth elements of the semantic segmentation map. Wherein, the method for acquiring the image pair can refer to steps 302 to 306; the method for obtaining each first image coordinate set corresponding to each preset target in the image pair or each second image coordinate set corresponding to each suspension point in the target power line may refer to steps 402 to 406. And the terminal performs curve fitting based on the first ground coordinate set and the second ground coordinate set to obtain a curve relation of the target power transmission line on the ground measurement coordinate system.

The terminal selects two suspension points of the target power transmission line in one span from the suspension points of the target power transmission line to obtain the target suspension point. The terminal constructs an auxiliary plane rectangular coordinate system based on the two target suspension points. The origin point of the rectangular coordinate system of the construction auxiliary plane is one of the target suspension points, the horizontal axis is a ray where two target suspension points are located, and the vertical axis is a ray which is perpendicularly directed to the ground through the origin point, as shown in fig. 5. In fig. 5, points P1 and P6 represent target suspension points, points P2 to P5 represent preset targets, black arcs represent auxiliary curves corresponding to the auxiliary curve relation (i.e. the fitted target power transmission line), xoy plane rectangular coordinate system represents auxiliary plane rectangular coordinate system, and black dotted lines represent ground. The terminal maps the first ground coordinates of at least one preset target on the ground measurement coordinate system to an auxiliary plane rectangular coordinate system to obtain first auxiliary coordinates of the at least one preset target. And the terminal maps the second ground coordinates of the at least two suspension points on the ground measurement coordinate system to an auxiliary plane rectangular coordinate system to obtain second auxiliary coordinates of the at least two suspension points. It can be understood that the terminal maps the three-dimensional coordinates on the ground measurement coordinate system to the auxiliary plane rectangular coordinate system, namely, the three-dimensional coordinates are converted to the two-dimensional coordinates, so that dimension reduction is realized on the three-dimensional coordinates, and the curve fitting efficiency is improved, thereby improving the sag measurement efficiency. And the terminal fits to obtain an auxiliary curve relation of the target power transmission line on an auxiliary plane rectangular coordinate system according to the first auxiliary coordinate of at least one preset target and the second auxiliary coordinates of at least two suspension points. And the terminal calculates and obtains the sag of the target power transmission line according to an auxiliary curve relation of the target power transmission line on an auxiliary plane rectangular coordinate system. The terminal calculates an auxiliary extreme point of an auxiliary curve relation of the target power transmission line on an auxiliary plane rectangular coordinate system, and calculates an absolute value of an ordinate corresponding to the auxiliary extreme point to obtain sag of the target power transmission line. Among the absolute values of the ordinate of each point on the auxiliary curve relation, the absolute value of the ordinate of the auxiliary extremum point is the largest, that is, the auxiliary extremum point is the lowest point on the auxiliary curve corresponding to the auxiliary curve relation, and as shown in fig. 5, for example, assuming that the M point is the auxiliary extremum point, the distance from the M point to the x axis is the sag of the target power transmission line.

In this embodiment, according to the first image coordinate sets, the second image coordinate sets and the internal and external azimuth elements of the semantic segmentation map, a curve relation of the target power transmission line on the ground measurement coordinate system is obtained by fitting, so that a precondition is provided for calculating sag of the target power transmission line based on the curve relation of the target power transmission line on the ground measurement coordinate system.

In one embodiment, there is also provided an example of a method of measuring sag, the method comprising the steps of:

s1, acquiring images of a target power transmission line to obtain corresponding sequence images, wherein at least one preset target is deployed on the target power transmission line;

s2, for any sequence image, carrying out block processing on the sequence image to obtain each sequence sub-image corresponding to the sequence image;

s3, carrying out semantic segmentation processing on the sequence sub-images aiming at any sequence sub-image to obtain an initial semantic segmentation sub-image corresponding to the sequence sub-image;

s4, for any sequence image, performing stitching processing on the initial semantic segmentation sub-graphs of each sequence sub-image corresponding to the sequence image to obtain an initial semantic segmentation graph corresponding to the sequence image;

s5, determining each first semantic segmentation graph comprising a target power line and a preset target from each initial semantic segmentation graph;

S6, aiming at any first semantic segmentation graph, acquiring first target coordinate information corresponding to each preset target in the first semantic segmentation graph and second target coordinate information of a target power line;

s7, aiming at any preset target in the first semantic segmentation map, determining a correction reference area corresponding to the preset target according to the center coordinates and the preset radius of the preset target, and deleting classification labels of all pixel points corresponding to the preset target in the first semantic segmentation map under the condition that the number of the pixel points of a target power line positioned in the correction reference area is smaller than a preset threshold value to obtain a corresponding second semantic segmentation map;

s8, taking the second semantic segmentation graphs with the number of hanging points of the target power transmission line meeting the preset number as an initial matching graph;

s9, determining the number of preset targets in each initial matching graph, taking the initial matching graph with the largest number of the preset targets as a reference matching graph, and determining an associated matching graph associated with the reference matching graph from the initial matching graphs; the semantic segmentation map comprises a reference matching map and an associated matching map;

s10, determining a reference matching graph from each semantic segmentation graph, and determining corresponding reference coordinate information of each target object in the reference matching graph; the target object comprises a preset target or a hanging point;

S11, according to the reference coordinate information of each target object and a preset matching strategy, matching to obtain coordinate information associated with each reference coordinate information from the rest of the semantic segmentation graphs; the coordinate information includes first coordinate information or second coordinate information;

s12, constructing and obtaining an image coordinate set corresponding to any target object according to the reference coordinate information corresponding to the target object and the coordinate information associated with the reference coordinate information; the image coordinate set comprises a first image coordinate set or a second image coordinate set;

s13, determining a first ground coordinate set of the preset target on a ground measurement coordinate system and a second ground coordinate set of the suspension point on the ground measurement coordinate system according to the first image coordinate set corresponding to each preset target, the second image coordinate set corresponding to each suspension point of the target power line and the internal and external azimuth elements of the semantic segmentation map; the first ground coordinate set comprises first ground coordinates of at least one preset target on a ground measurement coordinate system; the second ground coordinate set comprises second ground coordinates of at least two suspension points on a ground measurement coordinate system;

and S14, fitting to obtain a curve relation of the target power transmission line on the ground measurement coordinate system based on the first ground coordinate set and the second ground coordinate set.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a sag measurement device for realizing the sag measurement method. The implementation of the solution provided by the device is similar to that described in the above method, so specific limitations in the embodiments of the measuring device for sag or sags provided below can be found in the above limitations of the measuring method for sag, and will not be repeated here.

In one embodiment, as shown in fig. 6, there is provided a sag measurement device, the device comprising:

the acquisition module 602 is configured to perform image acquisition on a target power transmission line, so as to obtain a corresponding sequence image, where at least one preset target is disposed on the target power transmission line;

the semantic segmentation module 604 is configured to perform semantic segmentation processing on the sequence image to obtain each semantic segmentation graph including a target power line and a preset target;

the first determining module 606 is configured to determine a curve relation of the target power line on the ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power line, and the inside and outside azimuth elements of the semantic segmentation map; aiming at any preset target, a first image coordinate set corresponding to the preset target comprises first coordinate information corresponding to the preset target in each semantic segmentation graph; for any hanging point, the second image coordinate set corresponding to the hanging point comprises second coordinate information corresponding to the hanging point in each semantic segmentation graph;

a second determining module 608 is configured to determine sag of the target power line according to a curve relationship of the target power line on the ground measurement coordinate system.

In one embodiment, the semantic segmentation module 604 is specifically configured to:

for any sequence image, carrying out semantic segmentation processing on the sequence image to obtain an initial semantic segmentation image corresponding to the sequence image;

determining each first semantic segmentation graph comprising a target power line and a preset target from each initial semantic segmentation graph;

and aiming at any first semantic segmentation graph, acquiring first target coordinate information corresponding to each preset target in the first semantic segmentation graph and second target coordinate information of a target power line, and correcting the first semantic segmentation graph according to the first target coordinate information and the second target coordinate information to obtain a corresponding semantic segmentation graph.

for any sequence image, carrying out blocking treatment on the sequence image to obtain each sequence sub-image corresponding to the sequence image;

for any sequence sub-image, carrying out semantic segmentation processing on the sequence sub-image to obtain an initial semantic segmentation sub-image corresponding to the sequence sub-image;

and aiming at any sequence image, performing splicing processing on the initial semantic segmentation subgraphs of each sequence sub-image corresponding to the sequence image to obtain an initial semantic segmentation graph corresponding to the sequence image.

In one embodiment, the first object coordinate information includes a center coordinate of the preset object in the first semantic segmentation map; the second target coordinate information comprises coordinate information of each pixel point of the target power line in the first semantic segmentation map; the semantic segmentation module 604 is specifically configured to:

aiming at any preset target, determining a correction reference area corresponding to the preset target according to the central coordinates and the preset radius of the preset target, and deleting classification labels of all pixel points corresponding to the preset target in the first semantic segmentation map under the condition that the number of the pixel points of the target power transmission line in the correction reference area is smaller than a preset threshold value to obtain the semantic segmentation map.

In one embodiment, the semantic segmentation map includes a reference match map and an associated match map; the semantic segmentation module 604 is specifically configured to:

taking the second semantic segmentation graphs with the number of hanging points of the target power transmission line meeting the preset number as an initial matching graph;

and determining the number of preset targets in each initial matching graph, taking the initial matching graph with the largest number of the preset targets as a reference matching graph, and determining an associated matching graph associated with the reference matching graph from the initial matching graphs.

In one embodiment, the sag measurement device further comprises:

the fourth determining module is used for determining a reference matching graph from the semantic segmentation graphs and determining reference coordinate information corresponding to each target object in the reference matching graph; the target object comprises a preset target or a hanging point;

the matching module is used for matching and obtaining coordinate information associated with each piece of reference coordinate information from the rest of semantic segmentation graphs according to the reference coordinate information of each target object and a preset matching strategy; the coordinate information includes first coordinate information or second coordinate information;

In one embodiment, the first determining module 606 is specifically configured to:

determining a first ground coordinate set of the preset target on a ground measurement coordinate system and a second ground coordinate set of the suspension point on the ground measurement coordinate system according to the first image coordinate set corresponding to each preset target, the second image coordinate set corresponding to each suspension point of the target power line and the internal and external azimuth elements of the semantic segmentation map; the first ground coordinate set comprises first ground coordinates of at least one preset target on a ground measurement coordinate system; the second ground coordinate set comprises second ground coordinates of at least two suspension points on a ground measurement coordinate system;

The modules in the sag measurement device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of measuring sag. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the relevant data need to comply with relevant laws and regulations and standards of the relevant region.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method of measuring sag, the method comprising:

2. The method according to claim 1, wherein the performing semantic segmentation processing on the sequence image to obtain each semantic segmentation map including the target power line and the preset target includes:

3. The method according to claim 2, wherein the performing semantic segmentation processing on the sequence image to obtain an initial semantic segmentation map corresponding to the sequence image includes:

4. The method according to claim 2, wherein the first target coordinate information includes a center coordinate of the preset target in the first semantic segmentation map; the second target coordinate information comprises coordinate information of each pixel point of the target power line in the first semantic segmentation graph; the correcting the first semantic segmentation map according to the first target coordinate information and the second target coordinate information to obtain a corresponding semantic segmentation map includes:

5. The method of claim 2, wherein the semantic segmentation map comprises a reference match map and an associated match map; the correcting the first semantic segmentation map according to the first target coordinate information and the second target coordinate information to obtain a corresponding semantic segmentation map includes:

6. The method of claim 5, wherein after determining an association match graph associated with the reference match graph, the method further comprises:

7. The method according to claim 1, wherein determining a curve relation of the target power line on a ground measurement coordinate system according to each first image coordinate set corresponding to each preset target, each second image coordinate set corresponding to each suspension point in the target power line, and the inside and outside azimuth element of the semantic segmentation map includes:

8. A sag measurement device, the device comprising:

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.