CN116912273B - Three-dimensional GIS-based transmission line crossing construction scheme visualization method - Google Patents

Three-dimensional GIS-based transmission line crossing construction scheme visualization method Download PDF

Info

Publication number
CN116912273B
CN116912273B CN202311174811.9A CN202311174811A CN116912273B CN 116912273 B CN116912273 B CN 116912273B CN 202311174811 A CN202311174811 A CN 202311174811A CN 116912273 B CN116912273 B CN 116912273B
Authority
CN
China
Prior art keywords
edge
deviation
transmission line
dimensional
power transmission
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311174811.9A
Other languages
Chinese (zh)
Other versions
CN116912273A (en
Inventor
赵信华
张建民
谭冲
裴秀高
李保生
张建平
亓鹏
程远
赵勇
张洪帅
张国奎
刘均鹏
贾会永
李英
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Laiwu Power Supply Co of State Grid Shandong Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Laiwu Power Supply Co of State Grid Shandong Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Laiwu Power Supply Co of State Grid Shandong Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202311174811.9A priority Critical patent/CN116912273B/en
Publication of CN116912273A publication Critical patent/CN116912273A/en
Application granted granted Critical
Publication of CN116912273B publication Critical patent/CN116912273B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Graphics (AREA)
  • Human Resources & Organizations (AREA)
  • Geometry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to the technical field of image data processing, in particular to a three-dimensional GIS-based transmission line crossing construction scheme visualization method, which comprises the following steps: by combining the three-dimensional power transmission line image and the power transmission line edge image under different angles, after fitting the edge line segments by utilizing a plurality of deviation parameters, obtaining the edge confidence degree according to the difference relation between the fitted straight line segments, obtaining the confidence edge line segments corresponding to the power transmission line according to the magnitude of the edge confidence degree, and further utilizing the area of the centroid edge line segments to complete the power transmission line crossing construction scheme visualization of the three-dimensional GIS. The method and the device improve the accurate extraction of the position information of the power transmission line in the three-dimensional power transmission line image, and improve the visualization effect of the power transmission line by carrying out image enhancement on the region where the obtained confidence edge line segment is located.

Description

Three-dimensional GIS-based transmission line crossing construction scheme visualization method
Technical Field
The invention relates to the technical field of image data processing, in particular to a three-dimensional GIS-based transmission line crossing construction scheme visualization method.
Background
The vehicle-mounted movable crossing frame of the power transmission line is a necessary operation tool for crossing obstacles such as highways, railways, power lines and the like in construction operation, can quickly reach various operation areas, meets the requirement of quick construction, and effectively saves construction time and construction cost.
In a complex and changeable construction scene, how to guarantee the data accuracy of a visualized construction scheme constructed by a three-dimensional GIS according to the specific power transmission line distribution condition and the building distribution characteristics of the construction scene is a key step of the power transmission line crossing construction scheme visualization operation based on the three-dimensional GIS, wherein the key step is to accurately extract the regional form information of the power transmission line, the three-dimensional image of the power transmission line region in the construction scene is often influenced by the view angle limitation in the process of using a binocular camera, so that certain errors exist between the edge of the power transmission line region in the constructed three-dimensional image and the actual power transmission line edge, namely, the three-dimensional image reconstructed by the edge region in multiple dimensions is fluctuated in a small range due to the single view angle limitation, so that a plurality of edge line segments are formed, and the accurate edge information of the power transmission line is difficult to be effectively identified only by means of a conventional edge detection algorithm.
Because the transmission line has morphological characteristics in a conventional state, the regional morphology of the transmission line in a three-dimensional image can be obtained by utilizing linear fitting, and the linear fitting process of a revolving door algorithm is generally utilized to perform linear fitting on edge line segments in the transmission line image under multiple angles so as to rapidly extract the regional morphological characteristics of the edge line segments, but the linear fitting effect of the conventional revolving door algorithm is easily influenced by deviation parameters of the revolving door algorithm, so that the fitting result has a local area of an enhanced image, the deviation of which cannot be better, and the visual result of the three-dimensional GIS construction scheme is not ideal.
Disclosure of Invention
The invention provides a three-dimensional GIS-based transmission line crossing construction scheme visualization method, which aims to solve the existing problems: the three-dimensional image reconstructed in the edge area under the multi-dimension condition is subject to small-range fluctuation due to the limitation of a single visual angle, a plurality of edge line segments are formed, accurate edge information of a power transmission line is difficult to effectively identify only by means of a conventional edge detection algorithm, and the straight line fitting effect of the conventional revolving door algorithm is easily influenced by deviation parameters of the revolving door algorithm, so that the fitting result has a local area of the enhanced image, the deviation of which cannot be better, and the visual result of the three-dimensional GIS construction scheme is not ideal.
The three-dimensional GIS-based transmission line crossing construction scheme visualization method provided by the invention adopts the following technical scheme:
the embodiment of the invention provides a three-dimensional GIS-based transmission line crossing construction scheme visualization method, which comprises the following steps of:
acquiring a three-dimensional power transmission line image and a three-dimensional edge line, and acquiring power transmission line edge images under different angles according to mapping results of the three-dimensional power transmission line image under different angles in a three-dimensional coordinate system;
constructing a search window with a preset size, traversing edge lines in an edge image of any power transmission line to obtain edge line segments, dividing the edge line segments containing branches into a plurality of new edge line segments, and performing straight line fitting on the new edge line segments in the edge image of the power transmission line under any angle by utilizing preset deviation parameters with different sizes to obtain a plurality of fitted straight line segments; obtaining the linear fitting degree of the new edge line segment according to the slope difference of the fitting linear segment;
Obtaining a plurality of overlapping points corresponding to the edge pixel points according to the coordinates of the edge pixel points of the new edge line segment in the three-dimensional power transmission line image, and obtaining the confidence weight of the new edge line segment according to the number of the overlapping points; recording the confidence weight, the slope of the new edge line segment under a plurality of different deviation parameters and the fusion result of the linear fitting degree as the deviation sensitivity degree of the new edge line segment, and obtaining the edge confidence degree of the new edge line segment according to a deviation space formed by the deviation sensitivity degree;
and completing visualization of the transmission line crossing construction scheme of the three-dimensional GIS by using the edge confidence.
Further, the method for obtaining the three-dimensional power transmission line image and the three-dimensional edge line, according to the mapping result of the three-dimensional power transmission line image under different angles in the three-dimensional coordinate system, obtains the power transmission line edge image under different angles, includes the following specific steps:
firstly, acquiring images of different visual angles of a vehicle-mounted movable spanning frame of a power transmission line in a construction operation scene by using a stereoscopic vision technology and combining an MVS algorithm to construct a three-dimensional image of a power transmission line region, and recording the three-dimensional image as a three-dimensional power transmission line image; acquiring an edge line in a three-dimensional power transmission line image by using a three-dimensional Canny operator, marking the edge line as a three-dimensional edge line, wherein the three-dimensional edge line is formed by a plurality of voxels, and marking the voxels in the three-dimensional edge line as edge voxels;
Then, the three-dimensional transmission line image is placed on a power gridIn a three-dimensional rectangular coordinate system formed by three coordinate axes, a three-dimensional image is acquired inThe two-dimensional images mapped in the directions corresponding to the three coordinate axes are recorded as images to be measured of the power transmission line, and the images to be measured of the power transmission line under multiple angles are obtained; denoising and graying the image to be measured of the power transmission line to obtain a gray image to be measured of the power transmission line;
and finally, carrying out edge detection on the gray level image to be detected of the power transmission line under multiple angles by using a Canny edge detection algorithm, obtaining a plurality of edge images corresponding to the multiple angles, and marking the edge images as the power transmission line edge images.
Further, the method for constructing the search window with the preset size to traverse the edge line in the edge image of any power transmission line to obtain the edge line segment comprises the following specific steps:
constructing a preset size ofTraversing any power transmission line edge image, taking edge pixel points in the power transmission line edge image as center points of the search window, if any edge pixel points are 8 neighborhood pixel points of the center points of the search window, the center points of the search window and the corresponding 8 neighborhood pixel points belong to the same edge line, and marking the same edge line formed by a plurality of edge pixel points as an edge line segment to obtain a plurality of edge line segments; wherein, Is a preset super parameter.
Further, the method for dividing the edge line segment containing the branches into a plurality of new edge line segments comprises the following specific steps:
the method comprises the steps of obtaining a center point of at least three edge pixel points in 8 neighborhood pixel points of a search window, marking the center point as a breakpoint of an edge line segment, setting a gray value of the edge pixel point corresponding to the breakpoint as 0, dividing the edge line segment where the breakpoint is located into a plurality of edge line segments without branches by utilizing the breakpoint, and marking the edge line segment obtained after division as a new edge line segment.
Further, the new edge line segments in the power transmission line edge image under any angle are subjected to straight line fitting by utilizing preset deviation parameters with different sizes, so that a plurality of fitted straight line segments are obtained; the method for obtaining the linear fitting degree of the new edge line segment according to the slope difference of the fitting linear segment comprises the following specific steps:
firstly, presetting deviation parameters of a plurality of revolving door algorithms, and performing straight line fitting on any new edge line segment by using the revolving door algorithm to obtain a plurality of fitted straight line segments corresponding to the new edge line segment under any deviation parameters;
then, acquiring slopes corresponding to all fitting straight-line segments of a new edge line segment under any deviation parameter, and recording differences of slopes corresponding to any two adjacent fitting straight-line segments as slope differences to acquire a plurality of slope differences;
And finally, marking the accumulated sum of all slope differences of any new edge line segment as a first numerical value, and marking the product of the first numerical value and the number of the corresponding fitting straight line segments of the new edge line segment as the straight line fitting degree of the new edge line segment.
Further, the method for obtaining a plurality of overlapping points corresponding to the edge pixel points according to the coordinates of the edge pixel points of the new edge line segment in the three-dimensional power transmission line image and obtaining the confidence weight of the new edge line segment according to the number of the overlapping points includes the following specific steps:
firstly, acquiring three-dimensional coordinates of edge pixel points in any new edge line segment in a three-dimensional power transmission line image under any angle, setting coordinate values corresponding to the dimension reduction as 0 when the power transmission line gray scale image to be tested where the new edge line segment is positioned is subjected to dimension reduction in a mapping mode, and recording coordinate values which are not set as 0 in the three-dimensional coordinates as special coordinate values of the corresponding edge pixel points; acquiring a plurality of edge voxels which are the same as the special coordinate values in the three-dimensional power transmission line image, and marking the edge voxels as overlapping points of edge pixel points corresponding to the special coordinate values to acquire a plurality of overlapping points;
and then, the accumulated value of the number of the overlapping points of all the edge pixel points in any new edge line segment in the edge image of the power transmission line under any angle is marked as a second value, the accumulated value of the number of the overlapping points of all the edge pixel points in all the new edge line segment in the edge image of the power transmission line is marked as a third value, and the ratio of the second value to the third value is marked as the confidence weight of the new edge line segment.
Further, the method for recording the fusion result of the confidence weight, the slope of the new edge line segment under a plurality of different deviation parameters and the linear fitting degree as the deviation sensitivity degree of the new edge line segment comprises the following specific steps:
firstly, obtaining the difference value of the corresponding straight line fitting degree of any new edge line segment under the deviation parameters of adjacent sizes, and marking the difference value as the straight line fitting degree difference value of the new edge line segment; acquiring the shortest Euclidean distance between any new edge line segment and other new edge line segments in the corresponding power transmission line edge image under any angle, and recording the shortest Euclidean distance as the distance characteristic of the new edge line segment; acquiring the average value of all slope differences of any new edge line segment in the corresponding power transmission line edge image under any angle, and recording the average value as the slope characteristic of the new edge line segment;
then, acquiring a minimum circumscribed rectangle of any new edge line segment in an edge image of any power transmission line, and acquiring a local range area of the new edge line segment according to the minimum circumscribed rectangle;
finally, in the corresponding power transmission line edge image under any angle, the specific calculation method of the deviation sensitivity degree of any new edge line segment comprises the following steps:
wherein,representing a new edge segment at the firstCorresponding deviation sensitivity degree under the deviation parameters; Confidence weights representing new edge line segments;an exponential function based on a natural constant;representing new edge line segments inDeviation parameter(s)Corresponding straight line fitting degree difference values under the deviation parameters;distance features representing new edge line segments;representing the number of new edge line segments contained in the local range region corresponding to the new edge line segments;is shown in the firstNew edge line segments under the deviation parameters and the corresponding local range areaDifferences in slope characteristics between the new edge segments.
Further, the local range area comprises the following specific methods:
the middle point position of the length and the width of the minimum circumscribed rectangle is kept unchanged, and the lengths of the length and the width are respectively increasedAndthe area corresponding to the increased length and width of the minimum circumscribed rectangle is recorded as the local area of the new edge line segment, whereinAndis a preset super parameter.
Further, the method for obtaining the edge confidence level of the new edge line segment according to the deviation space formed by the deviation sensitivity level comprises the following specific steps:
firstly, for the deviation sensitivity degree of any new edge line segment corresponding to all angles, forming a multidimensional space by the deviation sensitivity degree corresponding to all angles to be recorded as a deviation space, wherein the dimension number of the deviation space is the same as the number of angles corresponding to all the deviation sensitivity degrees of any new edge line segment; marking the three-dimensional sitting formed by the corresponding deviation sensitivity degree of the new edge line segment under all angles as the three-dimensional deviation coordinates of the edge pixel points in the new edge line segment;
Then constructing a pixel point with any edge as a center and a side length as a size in a deviation spaceIs denoted as a deviation cube, whereinIs a preset super parameter; when any edge pixel point is taken as the center of the deviation cube, the cosine similarity of the three-dimensional deviation coordinates between the edge pixel point and other edge pixel points is recorded as the deviation similarityThe method comprises the steps of carrying out a first treatment on the surface of the When any edge pixel point is taken as the center of the deviation cube, euclidean distance between the three-dimensional deviation coordinates of the edge pixel point and other edge pixel points is recorded as deviationA distance;
finally, the specific calculation method of the edge confidence level of the new edge line segment where any edge pixel point is located is as follows:
wherein,represent the firstThe edge confidence level of the new edge line segment where the edge pixel points are located,represent the firstWhen the edge pixel points are taken as the centers of the deviation cubes, the edge pixel points are matched with the first pixel point in the deviation cubesDeviation similarity between the edge pixel points;representing a standard one-dimensional gaussian function;represent the firstWhen the edge pixel points are taken as the centers of the deviation cubes, the edge pixel points are matched with the first pixel point in the deviation cubesDeviation distance between edge pixel points;represent the firstVectors formed by three-dimensional deviation coordinates of the edge pixel points;represent the first When the edge pixel points are taken as the centers of the deviation cubes, the third pixel point in the deviation cubesVectors formed by three-dimensional deviation coordinates of the edge pixel points;represent the firstWhen the edge pixel points are used as the centers of the deviation cubes, the number of the edge pixel points included in the deviation cubes;representing the modulus of the acquired vector.
Further, the method for completing visualization of the transmission line crossing construction scheme of the three-dimensional GIS by using the edge confidence comprises the following specific steps:
firstly, carrying out normalization processing on all edge confidence degrees by using a linear normalization method, marking a normalization result of the edge confidence degrees as normalized edge confidence degrees, marking a new edge line segment corresponding to the normalized edge confidence degrees which are larger than a preset confidence threshold value as a confidence edge line segment, and marking the position of the confidence edge line segment in a three-dimensional power transmission line image as a power transmission line region;
and then, carrying out gray scale enhancement on the power transmission line region by utilizing a piecewise linear enhancement algorithm, and carrying out visual presentation on the enhanced power transmission line region through a display.
The technical scheme of the invention has the beneficial effects that: according to the method, after the edge line segments are fitted by combining the three-dimensional power transmission line image and the power transmission line edge images under different angles through a plurality of deviation parameters, the edge confidence degree is obtained according to the difference relation between the fitted straight line segments, the confidence edge line segments corresponding to the power transmission line are obtained according to the magnitude of the edge confidence degree, the power transmission line crossing construction scheme visualization of the three-dimensional GIS is further completed through the area where the centroid edge line segments are located, the accurate extraction of the power transmission line position information is improved, and the visualization effect of the power transmission line is improved through the image enhancement of the area where the obtained confidence edge line segments are located.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of a transmission line crossing construction scheme visualization method based on a three-dimensional GIS.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a specific implementation, structure, characteristics and effects of the three-dimensional GIS-based transmission line crossing construction scheme visualization method according to the invention, which are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scheme of the three-dimensional GIS-based transmission line crossing construction scheme visualization method provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a step flow chart of a three-dimensional GIS-based transmission line crossing construction scheme visualization method according to an embodiment of the present invention is shown, where the method includes the following steps:
and S001, acquiring an image to be detected of the power transmission line under multiple angles, and performing image preprocessing operation and edge detection processing to acquire an image of the edge of the power transmission line.
Specifically, in order to implement the three-dimensional GIS-based transmission line crossing construction scheme visualization method provided by the embodiment, a transmission line gray level image to be measured under multiple angles and a transmission line edge image under corresponding multiple angles need to be acquired, and the specific process is as follows:
firstly, acquiring images of different visual angles of a vehicle-mounted movable spanning frame of a power transmission line under a construction operation scene by using a binocular camera by utilizing a stereoscopic vision technology, constructing a three-dimensional image of a power transmission line region by combining depth and texture information among a plurality of images with three-dimensional point cloud data acquired by an MVS algorithm, and recording the three-dimensional image as a three-dimensional power transmission line image; and obtaining an edge line in the three-dimensional power transmission line image by utilizing a three-dimensional Canny operator, marking the edge line as a three-dimensional edge line, wherein the three-dimensional edge line is formed by a plurality of voxels, and marking the voxels in the three-dimensional edge line as edge voxels.
It should be noted that, the chinese name of the MVS algorithm is a multi-view stereo reconstruction algorithm, the chinese name of the three-dimensional Canny operator is a three-dimensional Canny operator, and the MVS algorithm and the three-dimensional Canny operator are related technologies, so that the specific algorithm processes of the MVS algorithm and the three-dimensional Canny operator are not repeated in this embodiment.
The voxel is the smallest volume element in the three-dimensional image data, similar to the pixel in the two-dimensional image, but the voxel is represented in the three-dimensional space, and the voxel corresponds to the three-dimensional coordinates and the gradation value in the three-dimensional image data.
Then, the three-dimensional transmission line image is placed on a power gridIn a three-dimensional rectangular coordinate system formed by three coordinate axes, a three-dimensional image is acquired inMapped in the directions corresponding to the three coordinate axesThe two-dimensional image is recorded as an image to be measured of the power transmission line, and the image to be measured of the power transmission line under multiple angles is obtained; and denoising and graying the image to be measured of the power transmission line to obtain a gray image to be measured of the power transmission line.
It should be noted that the image to be measured of the transmission line under the multi-angle is thatAnd respectively mapping the three coordinate axis directions to obtain a two-dimensional image.
And finally, carrying out edge detection on the gray level image to be detected of the power transmission line under multiple angles by using a Canny edge detection algorithm, obtaining a plurality of edge images corresponding to the multiple angles, and marking the edge images as the power transmission line edge images.
It should be noted that, the chinese name of the Canny edge detection algorithm is a Canny edge detection algorithm, and the Canny edge detection algorithm is an existing algorithm, so this embodiment is not repeated.
So far, the method is used for obtaining the edge image of the power transmission line under multiple angles.
And step S002, performing linear fitting on the edge lines in the power transmission line edge image, and obtaining the linear fitting degree according to the linear fitting result.
It should be noted that, since the linear fitting of the edge line segment by the revolving door algorithm is greatly affected by the deviation parameter, the deviation parameter is an important parameter for controlling the linear fitting effect thereof, and plays a decisive role in the subsequent result of distinguishing the edge line segment types by the linear fitting degree of the edge line segment. Therefore, how to obtain the adaptive deviation parameter of each edge line segment is a key process for obtaining the linear simulation degree of the accurate edge line segment.
Therefore, the linear fitting result of the edge line segment under the processing of the deviation parameters of the multi-level revolving door algorithm shows the sensitivity degree to different deviation parameters, namely the influence of the deviation parameter variation in a certain range on the linear fitting degree of the edge line segment is small, the linear fitting result is taken as the self-changing property of the edge line segment, the directional consistency of the linear fitting segment of the edge line segment on the multi-angle image and the three-dimensional image is combined, the type distinction of the edge line segment is finally realized, and the position extraction of the power transmission line region is obtained.
Because the edge line segment of the power transmission line region is required to be subjected to the linear fitting of a revolving door algorithm, the obtained edge pixel points are required to be subjected to the linear fitting of the edge line segment on a coordinate system, and the linear fitting degree of the edge line segment is obtained according to the linear fitting result.
Specifically, first, a preset size is constructed as followsTraversing any power transmission line edge image, taking edge pixel points in the power transmission line edge image as center points of the search window, when any edge pixel point is an 8 neighborhood pixel point of the center point of the search window, the center point of the search window and the corresponding 8 neighborhood pixel point are the same edge line, and marking the same edge line formed by a plurality of edge pixel points as an edge line segment to obtain a plurality of edge line segments; wherein,is a preset super parameter.
When it is needed, the size of the search window is preset according to experienceThe present embodiment is not particularly limited, and may be adjusted according to actual conditions.
And secondly, because a plurality of branches possibly exist in a plurality of edge line segments, the analysis of the subsequent edge line segments is not facilitated, and when the edge line segments contain a plurality of branches, a plurality of edge pixel points exist in the neighborhood corresponding to the 8 edge pixel points at the positions of the branch nodes, so that the center points of the plurality of edge pixel points contained in the 8 neighborhood pixel points of the search window are obtained and marked as break points of the edge line segments, the gray value of the edge pixel points corresponding to the break points is set as 0, the edge line segments where the break points are located are divided into a plurality of edge line segments without branches by utilizing the break points, and the finally obtained edge line segments are marked as new edge line segments.
The new edge line segment includes an edge line segment obtained by breaking an edge line segment including a branch, and also includes an edge line segment not including a branch.
The gray value of the edge pixel point in the power transmission line edge image is 255, and the gray value of the non-edge pixel point is 0.
And then presetting deviation parameters of a plurality of rotation gate algorithms, performing straight line fitting on any new edge line segment by utilizing the rotation gate algorithms to obtain a plurality of fitted straight line segments corresponding to the new edge line segment under any deviation parameters, and marking line segments formed by the corresponding plurality of fitted straight line segments after fitting the new edge line segment as fitted line segments.
Because the new edge line segments in the power transmission line edge image are not straight lines in a strict sense, a plurality of fitting straight line segments connected end to end are corresponding to any new edge line segment in the fitting process.
In addition, the folding line formed by the fitting straight line segments with adjacent sections from the beginning to the end reflects the folding degree of the edge line segments, and the closer the fitting line segments are to a straight line, the more accords with the morphological characteristics of the real power transmission line in the power transmission line to-be-detected image.
It should be noted that, the deviation parameter of the revolving door algorithm is preset as an interval according to experience The integer in the range can adjust the deviation parameter value according to the actual situation, and the embodiment is not particularly limited.
It should be noted that, the revolving door algorithm is an existing algorithm, and the existing revolving door algorithm is an algorithm for performing linear fitting on a data sequence or a data curve, and can be used for data compression and linear fitting, and the algorithm can fit the data sequence or the data curve into a plurality of linear segments connected end to end during linear fitting; in this embodiment, deviation parameters of a plurality of rotation gate algorithms are preset, and any new edge line segment is linearly fitted by using the rotation gate algorithm to obtain a plurality of fitted straight line segments corresponding to the new edge line segment under any deviation parameters, and the specific process and content of the algorithm are not repeated in this embodiment.
Finally, acquiring slopes corresponding to all fitting straight-line segments of the new edge line segment under any deviation parameter, and recording differences of slopes corresponding to any two adjacent fitting straight-line segments as slope differences to acquire a plurality of slope differences; according to the straight line fitting result, the straight line fitting degree of a new edge line segment under any deviation parameter in the transmission line edge image under any angle is obtained, and the specific calculation method comprises the following steps:
Wherein,representing the linear fitting degree of the new edge line segment;representing the number of the new edge line segments corresponding to the fitted straight line segments;representing the first of the new edge line segmentsThe slope difference.
The degree of straight line fit reflects the degree of the new edge line segment's nearly straight line morphology.
The linear fitting degree reflects the approximation degree of the new edge line segment in the transmission line image approaching the linear form of the transmission line under any view angle, and the larger the linear fitting degree is, the closer the form of the new edge line segment in the transmission line image under the corresponding view angle is to the linear, namely the more likely the corresponding transmission line region is.
So far, a plurality of straight line fitting degrees corresponding to any new edge line segments in the power transmission line edge image under any view angle are obtained through the method.
Step S003: and obtaining the deviation sensitivity degree of the new edge line segment according to the linear fitting results processed by the different deviation parameters, and obtaining the edge confidence degree of the new edge line segment according to the deviation space formed by the deviation sensitivity degree.
It should be noted that, the straight line fitting degree of the new edge line segment can only primarily distinguish the type of the new edge line segment, the calculation result is greatly affected by the preset deviation parameter, and the new edge line segment in the power transmission line cannot be accurately distinguished. Therefore, the embodiment combines the change condition of the straight line fitting degree of the new edge line segment under the multi-level deviation parameter processing result and the distribution characteristic of the new edge line segment to further accurately distinguish the new edge line segment, the change degree of the straight line fitting degree is related to the shape of the new edge line segment, the closer the new edge line segment is to a straight line, the smaller the change degree of the straight line fitting degree is in the process of carrying out straight line fitting by utilizing a revolving door algorithm under a plurality of different deviation parameters, and the smaller the influence of the deviation parameters on the new edge line segment is, so that the embodiment obtains the deviation sensitivity degree of the new edge line segment according to the straight line fitting result under a plurality of different deviation parameters.
The deviation sensitivity degree of the new edge line segment reflects the confidence degree that the new edge line segment belongs to the power transmission line region, the larger the deviation sensitivity degree is, the higher the linear stability degree of the new edge line segment under the corresponding deviation parameter is, but for the deviation sensitivity degree of the new edge line segment under different dimensions, the problem of overlapping of edge pixel points on the new edge line segment may exist in the three-dimensional space, but due to the limitation of the view angle under a single dimension, the confidence weight is obtained according to the overlapping degree of the edge pixel points on the new edge line segment, so that the confidence degree of the new edge line segment reconstructed in the subsequent acquired multiple dimensions is distinguished more.
In addition, in this embodiment, the overlapping degree of the edge pixel points under the single view angle on the three-dimensional space is used to represent the confidence weight of the new edge line segment, where the overlapping degree represents the number of the pixel points overlapping on the edge pixel point position on the new edge line segment, and the ratio of the number of the pixel points in the whole two-dimensional image under the single view angle; the confidence weight is associated with the morphological structure of the power transmission line under different visual angles, and when the overlapping part of the edge pixel points of the power transmission line is fewer, the confidence degree of the deviation sensitivity degree of the new edge line segment is higher.
Specifically, in the step (1), the deviation sensitivity degree of the new edge line segment is obtained according to the straight line fitting results processed by a plurality of different deviation parameters.
In the embodiment, the deviation sensitivity degree of the new edge line segment is represented by using the difference value of the straight line fitting degree between the layers and the consistent change quantity of the direction of the edge line segment of the region.
Firstly, obtaining the difference value of the corresponding straight line fitting degree of any new edge line segment under the deviation parameters of adjacent sizes, and marking the difference value as the straight line fitting degree difference value of the new edge line segment; and acquiring the shortest Euclidean distance between any new edge line segment and other new edge line segments in the corresponding power line edge image under any angle, and recording the shortest Euclidean distance as the distance characteristic of the new edge line segment.
Then, obtaining the average value of all slope differences of any new edge line segment in the corresponding power transmission line edge image under any angle, and marking the average value as the slope characteristic of the new edge line segment; acquiring the minimum circumscribed rectangle of any new edge line segment in any power transmission line edge image, keeping the midpoint position of the length and width of the minimum circumscribed rectangle unchanged, and respectively increasing the length of the length and the widthAndthe area corresponding to the increased length and width of the minimum circumscribed rectangle is recorded as the local area of the new edge line segment, wherein Andis a preset super parameter.
The closer the slope of the fitted straight line segment of the new edge line segment is to the other new edge line segments in the corresponding local range area, the greater the deviation sensitivity of the new edge line segment is.
It should be noted that the super parameters are preset according to experienceAnd150 and 10, respectively, may be adjusted empirically, and the present embodiment is not particularly limited.
Secondly, acquiring three-dimensional coordinates of edge pixel points in any new edge line segment in a three-dimensional power transmission line image under any angle, setting coordinate values corresponding to the dimension reduction as 0 when the power transmission line gray scale image to be tested where the new edge line segment is positioned is subjected to dimension reduction in a mapping mode, and recording coordinate values which are not set as 0 in the three-dimensional coordinates as special coordinate values of the corresponding edge pixel points; and acquiring a plurality of edge voxels which are the same as the special coordinate values in the three-dimensional power transmission line image, and marking the edge voxels as overlapping points of the edge pixel points corresponding to the special coordinate values to acquire a plurality of overlapping points.
For example, there is a pixel atThe two-dimensional coordinates mapped in the coordinate axis direction areThe corresponding three-dimensional coordinates of the pixel point in three dimensions are according to the three-dimensional coordinate acquisition method。
Finally, in the corresponding power transmission line edge image under any angle, the specific calculation method of the deviation sensitivity degree of any new edge line segment comprises the following steps:
Wherein,representing a new edge segment at the firstCorresponding deviation sensitivity degree under the deviation parameters;confidence weights representing new edge line segments;an exponential function based on a natural constant;representing new edge line segments inDeviation parameter(s)Corresponding straight line fitting degree difference values under the deviation parameters;distance features representing new edge line segments;representing the number of new edge line segments contained in the local range region corresponding to the new edge line segments;is shown in the firstNew edge line segments under the deviation parameters and the corresponding local range areaDifferences in slope characteristics between the new edge segments;representing the number of edge pixel points on the new edge line segment;representing the first on a new edge line segmentThe number of overlapping points of the edge pixels;representing the number of new edge line segments in the power line edge image where the new edge line segments are located;representing the first of the transmission line edge imagesThe first of the new edge line segmentsThe number of overlapping points of the individual edge pixels.
The deviation sensitivity reflects the variation stability of the new edge line segment to the straight line fitting result in the multi-level deviation parameter processing process, so that the type of the region to which the edge line segment belongs can be further distinguished according to the straight line fitting result reflecting the shape of the edge line segment.
And (2) dividing the real edge line segments of the power transmission line in the three-dimensional power transmission line image can not be ensured only by the deviation sensitivity degree of the new edge line segments under the multi-view angle, so that the embodiment obtains the edge confidence degree of the edge pixel points by utilizing the position relation of the three-dimensional point cloud data in the three-dimensional space.
Firstly, obtaining the corresponding deviation sensitivity degree of any new edge line segment under all angles according to an obtaining method of the deviation sensitivity degree, and forming a multidimensional space serving as a deviation space by the corresponding deviation sensitivity degree under all angles, wherein the number of dimensions of the deviation space is the same as the number of angles corresponding to all the deviation sensitivity degrees of any new edge line segment; marking a three-dimensional sitting mark formed by the corresponding deviation sensitivity degree of the new edge line segment under all angles as a three-dimensional deviation coordinate; and taking the three-dimensional deviation coordinates of the new edge line segment as the three-dimensional deviation coordinates of the edge pixel points in the new edge line segment.
In the present embodiment, the three-dimensional coordinate system is selected，Andthe deviation sensitivity degree of the new edge line segment is acquired in the directions of three coordinate axes and is respectively recorded as a first deviation coordinateSecond deviation coordinates Third deviation coordinatesThen from the first deviation coordinatesSecond deviation coordinatesThird deviation coordinatesForming three-dimensional deviation coordinates corresponding to new edge line segments。
The greater the deviation sensitivity degree of the edge pixel points under a plurality of angles, and the closer the Euclidean distance of the edge pixel points with similar magnitude to other deviation sensitivity degrees in a deviation space, the greater the edge confidence degree of the new edge line segment where the edge pixel points are located.
Then constructing a pixel point with any edge as a center and a side length as a size in a deviation spaceIs denoted as a deviation cube, whereinIs a preset super parameter; when any edge pixel point is taken as the center of the deviation cube, the three-dimensional deviation between the pixel point and other edge pixel points is obtainedCosine similarity of the difference coordinates, denoted as bias similarityThe method comprises the steps of carrying out a first treatment on the surface of the When any edge pixel point is taken as the center of the deviation cube, euclidean distance of three-dimensional deviation coordinates between the edge pixel point and other edge pixel points is recorded as the deviation distance.
It should be noted that the super parameters are preset according to experience21, which can be adjusted according to practical situations, the present embodiment is not particularly limited.
Finally, the specific calculation method of the edge confidence level of the new edge line segment where any edge pixel point is located is as follows:
Wherein,represent the firstThe edge confidence level of the new edge line segment where the edge pixel points are located,represent the firstWhen the edge pixel points are taken as the centers of the deviation cubes, the edge pixel points are matched with the first pixel point in the deviation cubesDeviation similarity between the edge pixel points;representing a standard one-dimensional gaussian function;represent the firstWhen the edge pixel points are taken as the centers of the deviation cubes, the edge pixel points are matched with the first pixel point in the deviation cubesDeviation distance between edge pixel points;represent the firstVectors formed by three-dimensional deviation coordinates of the edge pixel points;represent the firstWhen the edge pixel points are taken as the centers of the deviation cubes, the third pixel point in the deviation cubesVectors formed by three-dimensional deviation coordinates of the edge pixel points;represent the firstWhen the edge pixel points are used as the centers of the deviation cubes, the number of the edge pixel points included in the deviation cubes;representing the modulus of the acquired vector.
So far, the edge confidence level is obtained through the method.
Step S004: and completing visualization of the transmission line crossing construction scheme of the three-dimensional GIS by using the edge confidence.
It should be noted that, because the edge confidence level of the edge pixel point reflects the possibility that the edge pixel point in the deviation space belongs to the actual power transmission line area, the edge confidence level of the edge pixel point is primarily screened through a preset confidence threshold value to obtain all confidence edge line segments, and the adjacent head-to-tail connection reliability judgment in the straight line fitting direction of the confidence edge line segments is performed, the power transmission line should extend from one side of the image to the other side of the image, and parallel edge line segments with adjacent positions in the normal direction of the extending direction exist, so that the edge line segments belonging to the power transmission line area are judged, and the power transmission line area position information extraction is obtained according to the coordinate position information.
Specifically, firstly, performing normalization processing on all edge confidence degrees by using a linear normalization method, marking a normalization result of the edge confidence degrees as normalized edge confidence degrees, marking a new edge line segment corresponding to the normalized edge confidence degrees which are larger than a preset confidence threshold value as a confidence edge line segment, and marking the position of the confidence edge line segment in a three-dimensional power transmission line image as a power transmission line region.
And then, carrying out gray scale enhancement on the power transmission line region by utilizing a piecewise linear enhancement algorithm, and carrying out visual presentation on the enhanced power transmission line region through a display.
It should be noted that, the piecewise linear enhancement algorithm is an existing image enhancement algorithm, so this implementation is not repeated.
This embodiment is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (4)

1. The three-dimensional GIS-based transmission line crossing construction scheme visualization method is characterized by comprising the following steps of:
acquiring a three-dimensional power transmission line image and a three-dimensional edge line, and acquiring power transmission line edge images under different angles according to mapping results of the three-dimensional power transmission line image under different angles in a three-dimensional coordinate system;
Constructing a search window with a preset size, traversing edge lines in an edge image of any power transmission line to obtain edge line segments, dividing the edge line segments containing branches into a plurality of new edge line segments, and performing straight line fitting on the new edge line segments in the edge image of the power transmission line under any angle by utilizing preset deviation parameters with different sizes to obtain a plurality of fitted straight line segments; obtaining the linear fitting degree of the new edge line segment according to the slope difference of the fitting linear segment;
obtaining a plurality of overlapping points corresponding to the edge pixel points according to the coordinates of the edge pixel points of the new edge line segment in the three-dimensional power transmission line image, and obtaining the confidence weight of the new edge line segment according to the number of the overlapping points; recording the confidence weight, the slope of the new edge line segment under a plurality of different deviation parameters and the fusion result of the linear fitting degree as the deviation sensitivity degree of the new edge line segment, and obtaining the edge confidence degree of the new edge line segment according to a deviation space formed by the deviation sensitivity degree;
the visualization of the transmission line crossing construction scheme of the three-dimensional GIS is completed by utilizing the edge confidence;
the method for acquiring the three-dimensional power transmission line image and the three-dimensional edge line, and acquiring the power transmission line edge image under different angles according to the mapping results of the three-dimensional power transmission line image under different angles in a three-dimensional coordinate system, comprises the following specific steps:
Firstly, acquiring images of different visual angles of a vehicle-mounted movable spanning frame of a power transmission line in a construction operation scene by using a stereoscopic vision technology and combining an MVS algorithm to construct a three-dimensional image of a power transmission line region, and recording the three-dimensional image as a three-dimensional power transmission line image; acquiring an edge line in a three-dimensional power transmission line image by using a three-dimensional Canny operator, marking the edge line as a three-dimensional edge line, wherein the three-dimensional edge line is formed by a plurality of voxels, and marking the voxels in the three-dimensional edge line as edge voxels;
then, the three-dimensional transmission line image is placed on a power gridIn a three-dimensional rectangular coordinate system formed by three coordinate axes, a three-dimensional image is acquired in +.>The three coordinate axes are oppositeThe dimension-reduced two-dimensional image mapped in the direction is recorded as an image to be measured of the power transmission line, and the image to be measured of the power transmission line under multiple angles is obtained; denoising and graying the image to be measured of the power transmission line to obtain a gray image to be measured of the power transmission line;
finally, carrying out edge detection on the gray level image to be detected of the power transmission line under multiple angles by using a Canny edge detection algorithm to obtain edge images corresponding to the multiple angles, and marking the edge images as the power transmission line edge images;
performing straight line fitting on new edge line segments in the power transmission line edge image under any angle by utilizing preset deviation parameters with different sizes to obtain a plurality of fitted straight line segments; the method for obtaining the linear fitting degree of the new edge line segment according to the slope difference of the fitting linear segment comprises the following specific steps:
Firstly, presetting deviation parameters of a plurality of revolving door algorithms, and performing straight line fitting on any new edge line segment by using the revolving door algorithm to obtain a plurality of fitted straight line segments corresponding to the new edge line segment under any deviation parameters;
then, acquiring slopes corresponding to all fitting straight-line segments of a new edge line segment under any deviation parameter, and recording differences of slopes corresponding to any two adjacent fitting straight-line segments as slope differences to acquire a plurality of slope differences;
finally, the accumulated sum of all slope differences of the new edge line segment under any deviation parameter is recorded as a first numerical value, and the product of the first numerical value and the number of the straight line segments correspondingly fitted to the new edge line segment is recorded as the straight line fitting degree of the new edge line segment under any deviation parameter;
the method for obtaining the confidence weight of the new edge line segment according to the number of the overlapping points comprises the following specific steps:
firstly, acquiring three-dimensional coordinates of edge pixel points in any new edge line segment in a three-dimensional power transmission line image under any angle, setting coordinate values corresponding to the dimension reduction as 0 when the power transmission line gray scale image to be tested where the new edge line segment is positioned is subjected to dimension reduction in a mapping mode, and recording coordinate values which are not set as 0 in the three-dimensional coordinates as special coordinate values of the corresponding edge pixel points; acquiring a plurality of edge voxels which are the same as the special coordinate values in the three-dimensional power transmission line image, and marking the edge voxels as overlapping points of edge pixel points corresponding to the special coordinate values to acquire a plurality of overlapping points;
Then, the accumulated value of the number of the overlapping points of all the edge pixel points in any new edge line segment in the edge image of the power transmission line under any angle is marked as a second value, the accumulated value of the number of the overlapping points of all the edge pixel points in all the new edge line segment in the edge image of the power transmission line is marked as a third value, and the ratio of the second value to the third value is marked as the confidence weight of the new edge line segment;
the fusion result of the confidence weight, the slope of the new edge line segment under a plurality of different deviation parameters and the linear fitting degree is recorded as the deviation sensitivity degree of the new edge line segment, and the specific method comprises the following steps:
firstly, obtaining the difference value of the corresponding straight line fitting degree of any new edge line segment under the deviation parameters of adjacent sizes, and marking the difference value as the straight line fitting degree difference value of the new edge line segment; acquiring the shortest Euclidean distance between any new edge line segment and other new edge line segments in the corresponding power transmission line edge image under any angle, and recording the shortest Euclidean distance as the distance characteristic of the new edge line segment; acquiring the average value of all slope differences of any new edge line segment in the corresponding power transmission line edge image under any angle, and recording the average value as the slope characteristic of the new edge line segment;
then, acquiring a minimum circumscribed rectangle of any new edge line segment in an edge image of any power transmission line, and acquiring a local range area of the new edge line segment according to the minimum circumscribed rectangle;
Finally, in the corresponding power transmission line edge image under any angle, the specific calculation method of the deviation sensitivity degree of any new edge line segment comprises the following steps:
wherein,representing a new edge segment at +.>Corresponding deviation sensitivity degree under the deviation parameters; />Confidence weights representing new edge line segments; />An exponential function based on a natural constant; />Representing a new edge segment at->Deviation parameter and->Corresponding straight line fitting degree difference values under the deviation parameters; />Distance features representing new edge line segments; />Representing the number of new edge line segments contained in the local range region corresponding to the new edge line segments; />Is indicated at +.>New edge line segment under the deviation parameter, and the corresponding local area is +.>Differences in slope characteristics between the new edge segments;
the local range area comprises the following specific methods:
the middle point position of the length and the width of the minimum circumscribed rectangle is kept unchanged, and the lengths of the length and the width are respectively increasedAnd->The area corresponding to the increased length and width of the minimum bounding rectangle is recorded as the local area of the new edge line segment, wherein +.>And->Is a preset super parameter;
the method for obtaining the edge confidence level of the new edge line segment according to the deviation space formed by the deviation sensitivity level comprises the following specific steps:
Firstly, for the deviation sensitivity degree of any new edge line segment corresponding to all angles, forming a multidimensional space by the deviation sensitivity degree corresponding to all angles to be recorded as a deviation space, wherein the dimension number of the deviation space is the same as the number of angles corresponding to all the deviation sensitivity degrees of any new edge line segment; marking the three-dimensional sitting formed by the corresponding deviation sensitivity degree of the new edge line segment under all angles as the three-dimensional deviation coordinates of the edge pixel points in the new edge line segment;
then constructing a pixel point with any edge as a center and a side length as a size in a deviation spaceIs denoted as deviation cube, wherein +.>Is a preset super parameter; when any edge pixel point is taken as the center of the deviation cube, the pixel point is matched with other edgesCosine similarity of three-dimensional deviation coordinates between edge pixel points is denoted as deviation similarity +.>The method comprises the steps of carrying out a first treatment on the surface of the When any edge pixel point is taken as the center of the deviation cube, euclidean distance of three-dimensional deviation coordinates between the edge pixel point and other edge pixel points is recorded as deviation distance;
finally, the specific calculation method of the edge confidence level of the new edge line segment where the edge pixel point is located is as follows:
wherein,indicate->Edge confidence level of new edge line segment where each edge pixel point is located, +. >Indicate->When the edge pixel point is used as the center of the deviation cube, the edge pixel point is the first +.>Deviation similarity between the edge pixel points; />Representing a standard one-dimensional gaussian function; />Indicate->When the edge pixel point is used as the center of the deviation cube, the edge pixel point is the first +.>Deviation distance between edge pixel points; />Indicate->Vectors formed by three-dimensional deviation coordinates of the edge pixel points; />Indicate->When the edge pixel point is used as the center of the deviation cube, the first +.>Vectors formed by three-dimensional deviation coordinates of the edge pixel points; />Indicate->When the edge pixel points are used as the centers of the deviation cubes, the number of the edge pixel points included in the deviation cubes; />Representing the modulus of the acquired vector.
2. The three-dimensional GIS-based transmission line crossing construction scheme visualization method according to claim 1, wherein the construction of the search window with a preset size is performed to traverse edge lines in any transmission line edge image to obtain edge line segments, and the specific method comprises the following steps:
build size ofTraversing any power transmission line edge image, taking edge pixel points in the power transmission line edge image as center points of the search window, if any edge pixel points are 8 neighborhood pixel points of the center points of the search window, the center points of the search window and the corresponding 8 neighborhood pixel points belong to the same edge line, and marking the same edge line formed by a plurality of edge pixel points as an edge line segment to obtain a plurality of edge line segments; wherein (1) >Is a preset super parameter.
3. The three-dimensional GIS-based transmission line crossing construction scheme visualization method according to claim 1, wherein the dividing the edge line segment containing the branches into a plurality of new edge line segments comprises the following specific steps:
the method comprises the steps of obtaining a center point of at least three edge pixel points in 8 neighborhood pixel points of a search window, marking the center point as a breakpoint of an edge line segment, setting a gray value of the edge pixel point corresponding to the breakpoint as 0, dividing the edge line segment where the breakpoint is located into a plurality of edge line segments without branches by utilizing the breakpoint, and marking the edge line segment obtained after division as a new edge line segment.
4. The three-dimensional GIS-based transmission line crossing construction scheme visualization method according to claim 1, wherein the transmission line crossing construction scheme visualization of the three-dimensional GIS is completed by utilizing edge confidence, and the method comprises the following specific steps:
firstly, carrying out normalization processing on all edge confidence degrees by using a linear normalization method, marking a normalization result of the edge confidence degrees as normalized edge confidence degrees, marking a new edge line segment corresponding to the normalized edge confidence degrees which are larger than a preset confidence threshold value as a confidence edge line segment, and marking the position of the confidence edge line segment in a three-dimensional power transmission line image as a power transmission line region;
And then, carrying out gray scale enhancement on the power transmission line region by utilizing a piecewise linear enhancement algorithm, and carrying out visual presentation on the enhanced power transmission line region through a display.
CN202311174811.9A 2023-09-13 2023-09-13 Three-dimensional GIS-based transmission line crossing construction scheme visualization method Active CN116912273B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311174811.9A CN116912273B (en) 2023-09-13 2023-09-13 Three-dimensional GIS-based transmission line crossing construction scheme visualization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311174811.9A CN116912273B (en) 2023-09-13 2023-09-13 Three-dimensional GIS-based transmission line crossing construction scheme visualization method

Publications (2)

Publication Number Publication Date
CN116912273A CN116912273A (en) 2023-10-20
CN116912273B true CN116912273B (en) 2023-12-12

Family

ID=88363393

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311174811.9A Active CN116912273B (en) 2023-09-13 2023-09-13 Three-dimensional GIS-based transmission line crossing construction scheme visualization method

Country Status (1)

Country Link
CN (1) CN116912273B (en)

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH113421A (en) * 1997-06-11 1999-01-06 Meidensha Corp Method for detecting line segment
KR20090017209A (en) * 2007-08-14 2009-02-18 한국전자통신연구원 Method and apparatus for detecting line segment by incremental pixel extension in an image
CN106056619A (en) * 2016-06-13 2016-10-26 长安大学 Unmanned aerial vehicle vision wire patrol method based on gradient constraint Radon transform
KR101677875B1 (en) * 2016-04-12 2016-11-18 숭실대학교산학협력단 Apparatus and method for line segment detection
CN109215020A (en) * 2018-08-30 2019-01-15 国网黑龙江省电力有限公司佳木斯供电公司 Ultra-high-tension power transmission line fault recognition method based on computer vision
CN109325935A (en) * 2018-07-24 2019-02-12 国网浙江省电力有限公司杭州供电公司 A kind of transmission line faultlocating method based on unmanned plane image
CN109801302A (en) * 2018-12-14 2019-05-24 华南理工大学 A kind of ultra-high-tension power transmission line foreign matter detecting method based on binocular vision
CN110189344A (en) * 2019-04-24 2019-08-30 河海大学常州校区 A kind of line segment extraction method in power knife switch image
WO2020181870A1 (en) * 2019-03-12 2020-09-17 Zhejiang Dahua Technology Co., Ltd. Systems and methods for lane detection
CN112464789A (en) * 2020-11-25 2021-03-09 河海大学常州校区 Power transmission line extraction method based on line characteristics
CN112991283A (en) * 2021-03-04 2021-06-18 华南理工大学 Flexible IC substrate line width detection method based on super-pixels, medium and equipment
CN114972575A (en) * 2022-04-08 2022-08-30 湖南科技大学 Linear fitting algorithm based on contour edge
WO2023279966A1 (en) * 2021-07-08 2023-01-12 中移(上海)信息通信科技有限公司 Multi-lane-line detection method and apparatus, and detection device
WO2023070593A1 (en) * 2021-10-29 2023-05-04 京东方科技集团股份有限公司 Line width measurement method and apparatus, computing processing device, computer program, and computer readable medium
CN116363157A (en) * 2023-03-29 2023-06-30 上海大学 Overhead transmission line edge positioning method, system, electronic equipment and medium
CN116580032A (en) * 2023-07-14 2023-08-11 青岛西海岸城市建设集团有限公司 Quality monitoring method for road construction

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH113421A (en) * 1997-06-11 1999-01-06 Meidensha Corp Method for detecting line segment
KR20090017209A (en) * 2007-08-14 2009-02-18 한국전자통신연구원 Method and apparatus for detecting line segment by incremental pixel extension in an image
KR101677875B1 (en) * 2016-04-12 2016-11-18 숭실대학교산학협력단 Apparatus and method for line segment detection
CN106056619A (en) * 2016-06-13 2016-10-26 长安大学 Unmanned aerial vehicle vision wire patrol method based on gradient constraint Radon transform
CN109325935A (en) * 2018-07-24 2019-02-12 国网浙江省电力有限公司杭州供电公司 A kind of transmission line faultlocating method based on unmanned plane image
CN109215020A (en) * 2018-08-30 2019-01-15 国网黑龙江省电力有限公司佳木斯供电公司 Ultra-high-tension power transmission line fault recognition method based on computer vision
CN109801302A (en) * 2018-12-14 2019-05-24 华南理工大学 A kind of ultra-high-tension power transmission line foreign matter detecting method based on binocular vision
WO2020181870A1 (en) * 2019-03-12 2020-09-17 Zhejiang Dahua Technology Co., Ltd. Systems and methods for lane detection
CN110189344A (en) * 2019-04-24 2019-08-30 河海大学常州校区 A kind of line segment extraction method in power knife switch image
CN112464789A (en) * 2020-11-25 2021-03-09 河海大学常州校区 Power transmission line extraction method based on line characteristics
CN112991283A (en) * 2021-03-04 2021-06-18 华南理工大学 Flexible IC substrate line width detection method based on super-pixels, medium and equipment
WO2023279966A1 (en) * 2021-07-08 2023-01-12 中移(上海)信息通信科技有限公司 Multi-lane-line detection method and apparatus, and detection device
WO2023070593A1 (en) * 2021-10-29 2023-05-04 京东方科技集团股份有限公司 Line width measurement method and apparatus, computing processing device, computer program, and computer readable medium
CN114972575A (en) * 2022-04-08 2022-08-30 湖南科技大学 Linear fitting algorithm based on contour edge
CN116363157A (en) * 2023-03-29 2023-06-30 上海大学 Overhead transmission line edge positioning method, system, electronic equipment and medium
CN116580032A (en) * 2023-07-14 2023-08-11 青岛西海岸城市建设集团有限公司 Quality monitoring method for road construction

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
Detecting Wires in Cluttered Urban Scenes Using a Gaussian Model 等.Detecting Wires in Cluttered Urban Scenes Using a Gaussian Model.《2010 20th International Conference on Pattern Recognition》.2010,全文. *
Shang-Che Huang 等.Point-of-Regard Measurement via Iris Contour with One Eye from Single Image.《2010 IEEE International Symposium on Multimedia》.2011,全文. *
刘思雨 ; 吕开云 ; 刘盈 ; .基于LSD算法的航拍影像电力线提取.江西科学.2019,(06),全文. *
夏斌 等.基于无人机图像的输电线自动提取技术.《电子器件》.2021,全文. *
牛明花 等.基于机器视觉的车道线识别算法.《天津职业技术师范大学学报》.2015,全文. *

Also Published As

Publication number Publication date
CN116912273A (en) 2023-10-20

Similar Documents

Publication Publication Date Title
CN109029381B (en) Tunnel crack detection method and system and terminal equipment
CN107248159A (en) A kind of metal works defect inspection method based on binocular vision
CN110349207B (en) Visual positioning method in complex environment
Awrangjeb et al. Automatic detection of residential buildings using LIDAR data and multispectral imagery
CN104484648B (en) Robot variable visual angle obstacle detection method based on outline identification
Lari et al. An adaptive approach for the segmentation and extraction of planar and linear/cylindrical features from laser scanning data
CN103247045B (en) A kind of method obtaining artificial scene principal direction and image border from multi views
CN111460922A (en) System for recognizing whether parking is reasonable or not by sharing three-dimensional model image of vehicle parking area
CN104091324A (en) Quick checkerboard image feature matching algorithm based on connected domain segmentation
CN108596975A (en) A kind of Stereo Matching Algorithm for weak texture region
CN110310331B (en) Pose estimation method based on combination of linear features and point cloud features
CN104851089A (en) Static scene foreground segmentation method and device based on three-dimensional light field
CN111105452B (en) Binocular vision-based high-low resolution fusion stereo matching method
CN107301649B (en) Regional merged SAR image coastline detection algorithm based on superpixels
CN111126116A (en) Unmanned ship river channel garbage identification method and system
CN113887624A (en) Improved feature stereo matching method based on binocular vision
Ecins et al. Seeing behind the scene: Using symmetry to reason about objects in cluttered environments
Jiao et al. Color image-guided boundary-inconsistent region refinement for stereo matching
CN106709432A (en) Binocular stereoscopic vision based head detecting and counting method
CN116912273B (en) Three-dimensional GIS-based transmission line crossing construction scheme visualization method
Shen et al. Knowledge-based road extraction from high resolution remotely sensed imagery
CN114937211B (en) Remote sensing image change detection method based on invariant object
CN113340201B (en) Three-dimensional measurement method based on RGBD camera
Lindblad et al. Exact linear time euclidean distance transforms of grid line sampled shapes
CN107153823B (en) Lane line feature extraction method based on visual correlation double spaces

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant