CN114114314A - Power transmission line inspection detection system and detection method based on laser point cloud - Google Patents
Power transmission line inspection detection system and detection method based on laser point cloud Download PDFInfo
- Publication number
- CN114114314A CN114114314A CN202111316891.8A CN202111316891A CN114114314A CN 114114314 A CN114114314 A CN 114114314A CN 202111316891 A CN202111316891 A CN 202111316891A CN 114114314 A CN114114314 A CN 114114314A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- point cloud
- line
- classification
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
Abstract
The invention discloses a power transmission line inspection detection method based on laser point cloud, which comprises the following steps: step 100: carrying a laser radar system on an unmanned aerial vehicle, flying the unmanned aerial vehicle along a power transmission line to obtain data of a power line corridor, obtaining account data of the power line corridor through post settlement processing and analysis, carrying out vectorization classification management on the power line corridor, and establishing a three-dimensional model of the power line corridor according to the data; step 200: analyzing the established three-dimensional model of the line corridor, and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data, wherein the high-precision point cloud tower model data comprise wire classification data and tower classification data; step 300: and generating high-precision point cloud tower model data according to classification, planning a route and autonomously flying, and realizing automatic and accurate shooting selection of the tower body for fine inspection by means of a deep learning algorithm to form a flying track connecting all shooting points.
Description
Technical Field
The invention relates to the technical field of electrical equipment and electrical engineering, in particular to a power transmission line inspection detection system and a power transmission line inspection detection method based on laser point cloud.
Background
Detection equipment such as a high-resolution visible light camera (video camera), a high-precision thermal infrared imager, a three-dimensional laser radar scanning device and the like enriches the operation and detection means of the power transmission line, particularly, in recent years, the policy of the navigation field of China is gradually released, the unmanned aerial vehicle technology is rapidly advanced, the unmanned aerial vehicle carries a special sensor load, the power transmission line is rapidly developed, and the line inspection is promoted to be changed from a traditional manual inspection mode to an unmanned aerial vehicle inspection mode. The unmanned aerial vehicle system is applied to power grid construction such as power engineering infrastructure planning, topographic survey and line inspection, overcomes the defects of complicated examination and approval and high use and maintenance cost of an unmanned aerial vehicle airspace, avoids the occurrence of an inspection missing event of manual inspection, reduces the working strength of inspection personnel, improves the line inspection efficiency, and is a traditional Chinese medicine means for developing the power transmission line management to a safer, efficient, fine and economic direction.
However, the current unmanned aerial vehicle control technology is not popular, the unmanned aerial vehicle is applied to the daily power transmission line patrol maintenance, the unmanned aerial vehicle needs to fly to control the long-time flight control operation of hands, the patrol maintenance of the power transmission line can be influenced by regions, landforms and various natural severe weathers, and the unmanned aerial vehicle is not a simple technology for skillfully controlling the patrol maintenance of the power transmission line for general line patrol personnel. The patent with the publication number of CN106774392A discloses a dynamic planning method for a flight path in a power line inspection process, and particularly discloses that laser point cloud data of a power line corridor in an aircraft track planning area are obtained, an initial flight route is generated after track points of the planned flight route are determined, space coordinates and a range of an obstacle on a flight channel are obtained, the track points of the obstacle are calculated according to the space coordinates and the range of the obstacle, and the optimal flight route of the aircraft obstacle avoidance and the regression planned flight route is calculated by using a route planning algorithm. The patent with publication number CN106157361A discloses a full-automatic three-dimensional reconstruction method of a multi-bundle conductor based on LiDAR point cloud, and particularly discloses a method for preliminarily extracting power line point cloud based on an elevation histogram and point cloud frequency by using the spatial distribution characteristics of a power transmission line; then, automatically extracting a coordinate center of the tower through the point cloud elevation histogram, and taking the coordinate center as a basis for conducting wire segmentation; secondly, identifying and extracting the point clouds of the single-stranded power lines by adopting an Euclidean space clustering algorithm, then performing local projection on each strand of split conductor, and performing space combination on the projection clustering; and finally, a method for finely modeling the split conductor is completed by using a catenary model and a least square fitting method, but the patent mainly aims at fine reconstruction of a multi-split conductor, and does not consider the spatial distribution condition after the conductor is broken.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention provides a power transmission line inspection detection method and a power transmission line inspection detection system based on laser point cloud.
The technical scheme of the invention is as follows:
the invention discloses a power transmission line inspection detection method based on laser point cloud, which comprises the following steps:
step 100: carrying a laser radar system on an unmanned aerial vehicle, flying the unmanned aerial vehicle along a power transmission line to obtain data of a power line corridor, obtaining account data of the power line corridor through post settlement processing and analysis, carrying out vectorization classification management on the power line corridor, and establishing a three-dimensional model of the power line corridor according to the data;
step 200: analyzing the established three-dimensional model of the line corridor, and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data;
step 300: and generating high-precision point cloud tower model data according to classification, planning a route and autonomously flying, and realizing automatic and accurate shooting selection of the tower body for fine inspection by means of a deep learning algorithm to form a flying track connecting all shooting points.
Further, the specific steps of analyzing and classifying the established three-dimensional model of the line corridor in the step 200 are as follows:
step 210: when the established three-dimensional model of the line corridor is analyzed, the laser point cloud data collected by inspection is processed into a standard digital elevation model, then the classified point cloud is combined to realize further three-dimensional digitization of the power line, the lower part of the line is classified according to the types of common ground objects in a line channel, and the ground surface form and the ground surface attachments along the power line are recovered;
step 220: automatically measuring and classifying the clearance distance of the cross spanning object, automatically analyzing the hidden defect danger and automatically generating a report;
step 230: reconstructing the power line by adopting a gradual dimension reduction mode;
step 240: and based on the spatial topological relation between the wires and the towers, the rapid automatic synchronous classification of the wires and the towers is realized by applying Hough transformation and a Kmeans clustering method.
Further, the specific steps of reconstructing the power line in step 230 by using a step-by-step dimensionality reduction method are as follows:
step 231: filtering repeated data influencing the calculation efficiency in the point cloud data, and removing the repeated data points;
step 232: according to the distribution characteristics of the conducting wires in a linear manner on the horizontal plane, linear fitting of an X-Y two-dimensional plane is carried out, and first dimension reduction is realized;
step 233: according to the distribution characteristic that the conducting wire presents a parabola on a vertical horizontal plane, performing curve fitting on an X-Z two-dimensional plane to realize secondary dimensionality reduction;
step 234: and after the secondary dimensionality reduction is completed, fitting of the whole three-dimensional space is realized, and distribution of the three-dimensional whole space of the lead is obtained.
Further, the step 240 is based on the spatial topological relation between the wires and the towers, and the specific steps of implementing the fast and automatic synchronous classification between the wires and the towers by applying the Hough transformation and the Kmeans clustering method are as follows:
step 241: through interpersonal interactive operation, the preliminary filtering of a target wire is realized, the line trend is judged, the maximum value in the horizontal direction and the minimum value in the vertical direction and corresponding coordinates are searched in a two-dimensional plane, and the line trend slope is calculated;
step 242: generating two line trend overlooking image pictures according to the line trend slope, and judging and calculating the span value between parallel lines according to the obtained line trend by utilizing the generated two-dimensional image;
step 243: canny edge detection is carried out on the generated two-dimensional image, Hough transformation is carried out to obtain a straight line segment, Kmeans clustering is carried out on the obtained straight line segment according to the slope of the straight line, two cluster types obtained through clustering respectively represent two types of the slope of the straight line, the two types of the cluster types are respectively compared with the trend slope of the line, and point cloud data corresponding to the cluster types with the same trend slope are wire data;
step 244: and (4) performing Kmeans clustering again on the data which are remained after the comparison and screening in the step 243, clustering the remained straight line segments according to the starting points of the line segments to obtain independent tower classification data, and further realizing the rapid automatic synchronous classification of the lead and the tower.
The invention also discloses a power transmission line inspection detection system based on the laser point cloud for implementing the method, which comprises a three-dimensional model modeling module, a classification module and a flight planning module; the three-dimensional model modeling module is used for carrying a laser radar system on the unmanned aerial vehicle, flying along the power transmission line, acquiring data of the power line corridor, and establishing a three-dimensional model of the line corridor according to the data subjected to post-analysis processing; the classification module is used for analyzing the established three-dimensional model of the line corridor and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data; and the flight planning module is used for generating high-precision point cloud tower model data according to classification and carrying out air route planning and autonomous flight.
Further, the classification module comprises a basic point cloud data management module, a laser point cloud space measurement module, a gradual dimension reduction module and a wire and tower classification module; the basic point cloud data management module is used for processing the laser point cloud data collected by inspection into a standard digital elevation model, combining the classified point clouds, classifying the lower part of the line according to the types of common ground objects in a line channel, and recovering the ground surface form and ground surface attachments along the power line; the laser point cloud space measurement module is used for automatically measuring and classifying the clearance distance of the cross spanning object, automatically analyzing the hidden defect danger and automatically generating a report; the step-by-step dimensionality reduction module is used for reconstructing the power line in a step-by-step dimensionality reduction mode; the wire and tower classification module is used for realizing the rapid automatic synchronous classification of the wires and the towers by applying Hough transformation and a Kmeans clustering method based on the spatial topological relation of the wires and the towers.
Further, the step-by-step dimensionality reduction module comprises a repeated point removing module, a plane straight line fitting module, a two-dimensional curve fitting module and a three-dimensional space fitting module; the repeated point removing module is used for filtering repeated data influencing the calculation efficiency in the electric fish data; the plane straight line fitting module is used for performing first dimension reduction of straight line fitting of a two-dimensional plane; the two-dimensional curve fitting module is used for performing two-dimensional curve fitting to realize a second dimension reduction wire; and the three-dimensional space fitting module is used for fitting the distribution of the three-dimensional overall space of the conducting wire after the secondary dimensionality reduction.
Furthermore, the wire and tower classification module comprises a slope calculation module, a span value calculation module, a wire data judgment module and a tower classification data module; the slope calculation module is used for judging the line trend of the target lead and calculating the line trend slope; the span value calculation module generates a two-dimensional image based on the line trend slope obtained by the slope calculation module, and judges and calculates the span value between parallel lines; the wire data judgment module carries out detection, transformation, cluster analysis and comparison on the basis of the two-dimensional image generated by the span value calculation module to obtain wire classification data; and the tower classification data module is used for carrying out clustering analysis on the data left after the screening of the wire data judgment module again to obtain independent tower classification data.
Compared with the prior art, the invention has the following beneficial effects:
1. the power transmission line inspection detection method and the power transmission line inspection detection system based on the laser point cloud can achieve autonomous planning and autonomous generation of the air line of the unmanned aerial vehicle, the unmanned aerial vehicle achieves full autonomous flight operation according to the air line planning, the operation threshold of the unmanned aerial vehicle is reduced, the influence of personnel experience on inspection work of the power transmission line is reduced, inspection operation efficiency is improved, unmanned inspection operation flight in the whole process of the unmanned aerial vehicle is achieved, potential risks of a power grid are reduced, power supply reliability is improved, and safe operation and driving protection of the power grid line are achieved.
2. According to the power transmission line inspection detection method and the power transmission line inspection detection system based on the laser point cloud, the steps of analyzing the established three-dimensional model of the line corridor and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data are set, so that the problems that the acquired power transmission line point cloud data are not dense enough, the point cloud spatial distribution interval is large, even the line is broken and the like due to the influence of environmental factors such as terrain, landform and the like when an unmanned aerial vehicle is used for carrying a laser radar to inspect the power transmission line in the prior art are solved; the power line is reconstructed in a mode of gradually reducing dimensions, straight lines and curves are respectively fitted on different planes in the process of calculation each time, the effect of reducing the dimensions for multiple times is achieved, and due to the fact that the dimensions are reduced each time, the calculation efficiency is greatly improved, therefore, the real-time fitting and real-time recovery of the wires can be achieved, the wires can be timely repaired, the original spatial distribution of the wires is recovered, and accurate and efficient course planning and safe and stable autonomous flight are achieved on the basis.
Drawings
FIG. 1 is a flow chart of a power transmission line inspection detection method based on laser point cloud;
fig. 2 is a schematic structural diagram of the power transmission line inspection detection system based on the laser point cloud.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments.
Example 1
Referring to fig. 1, the inspection method for the power transmission line based on the laser point cloud in the embodiment specifically includes the following steps:
step 100: carrying a laser radar system on an unmanned aerial vehicle, flying the unmanned aerial vehicle along a power transmission line to obtain data of a power line corridor, obtaining account data of the power line corridor through post settlement processing and analysis, carrying out vectorization classification management on the power line corridor, and establishing a three-dimensional model of the power line corridor according to the data;
the working principle of the laser radar is that the laser ranging principle is utilized to obtain the slant distance between a laser transmitter and a ground point, the laser point cloud is positioned and oriented according to the synchronously carried GPS and inertial measurement unit data, and the three-dimensional space coordinate of the point cloud is recovered, so that the system has the characteristics of initiative, non-contact property, non-penetrability, high precision, high density and the like;
step 200: analyzing the established three-dimensional model of the line corridor, and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data;
step 300: and generating high-precision point cloud tower model data according to classification, planning a route and autonomously flying, and realizing automatic and accurate shooting selection of the tower body for fine inspection by means of a deep learning algorithm to form a flying track connecting all shooting points.
Further, the specific steps of analyzing and classifying the established three-dimensional model of the line corridor in the step 200 are as follows:
step 210: processing laser point cloud data acquired by inspection into a standard digital elevation model when analyzing the established three-dimensional model of the line corridor, combining the digital elevation model and a point cloud classification result to realize further three-dimensional digitization after establishing the standard digital elevation model, acquiring point cloud classification information and three-dimensional model information after fusion to realize the fusion of the point cloud data and the elevation data, classifying the lower part of the line according to the types of common ground objects in a line channel, and recovering the surface morphology and surface attachments along the power line; the classified point cloud specifically refers to a result of point cloud classification realized by a conventional manual classification method or an automatic classification method, such as an SVM classification algorithm and the like; the classified point cloud comprises a classified result of identifying laser point cloud data, such as a power transmission line point cloud tower point cloud and the like;
step 220: automatically measuring and classifying the clearance distance of the cross spanning object, automatically analyzing the hidden defect danger and automatically generating a report; firstly, measuring by using the crossing clearance, and then comprehensively according to the measurement result, the point cloud classification result, the ground object classification result and the defect hidden danger (generally, the defect hidden danger exists when the difference between the distances from the point cloud of the power transmission line to the point cloud of the ground object is lower than the standard)
Step 230: reconstructing the power line by adopting a gradual dimension reduction mode;
step 240: and based on the spatial topological relation between the wires and the towers, the rapid automatic synchronous classification of the wires and the towers is realized by applying Hough transformation and a Kmeans clustering method.
Further, the specific steps of reconstructing the power line in step 230 by using a step-by-step dimensionality reduction method are as follows:
step 231: filtering repeated data influencing the calculation efficiency in the point cloud data, and removing the repeated data points;
step 232: according to the distribution characteristics of the conducting wires in a linear manner on the horizontal plane, linear fitting of an X-Y two-dimensional plane is carried out, and first dimension reduction is realized;
step 233: according to the distribution characteristic that the conducting wire presents a parabola on a vertical horizontal plane, performing curve fitting on an X-Z two-dimensional plane to realize secondary dimensionality reduction;
step 234: and after the secondary dimensionality reduction is completed, fitting of the whole three-dimensional space is realized, and distribution of the three-dimensional whole space of the lead is obtained.
Further, the step 240 is based on the spatial topological relation between the wires and the towers, and the specific steps of implementing the fast and automatic synchronous classification between the wires and the towers by applying the Hough transformation and the Kmeans clustering method are as follows:
step 241: the method comprises the steps of achieving preliminary filtering of a target wire through interpersonal interactive operation, judging the line trend, searching a maximum value (xmax) in the horizontal x direction and a minimum value (ymin) in the vertical y direction in a two-dimensional plane, and respectively corresponding y coordinates [ y (xmax) ], x coordinates [ x (ymin) ], and calculating a line trend slope k, wherein k is (y (xmax) -ymin)/(xmax-x (ymin));
step 242: generating two line trend overhead image maps according to the line trend slope k, and judging and calculating a span value between parallel lines according to the obtained line trend by using the generated two-dimensional image;
step 243: canny edge detection is carried out on the generated two-dimensional image, Hough transformation is carried out to obtain a straight line segment, Kmeans clustering is carried out on the obtained straight line segment according to the slope of the straight line, two cluster types obtained through clustering respectively represent two types of the slope of the straight line, the two types of the cluster types are respectively compared with the trend slope of the line, and point cloud data corresponding to the cluster types with the same trend slope are wire data;
step 244: and (4) performing Kmeans clustering again on the data which are remained after the comparison and screening in the step 243, clustering the remained straight line segments according to the starting points of the line segments to obtain independent tower classification data, and further realizing the rapid automatic synchronous classification of the lead and the tower.
Example 2
Referring to fig. 2, the present embodiment is a power transmission line inspection detection system based on laser point cloud, including a three-dimensional model modeling module, a classification module, and a flight planning module; the three-dimensional model modeling module is used for carrying a laser radar system on the unmanned aerial vehicle, flying along the power transmission line, acquiring data of the power line corridor, and establishing a three-dimensional model of the line corridor according to the data subjected to post-analysis processing; the classification module is used for analyzing the established three-dimensional model of the line corridor and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data; and the flight planning module is used for generating high-precision point cloud tower model data according to classification and carrying out air route planning and autonomous flight.
Further, the classification module comprises a basic point cloud data management module, a laser point cloud space measurement module, a gradual dimension reduction module and a wire and tower classification module; the basic point cloud data management module is used for processing the laser point cloud data collected by inspection into a standard digital elevation model, combining the classified point clouds, classifying the lower part of the line according to the types of common ground objects in a line channel, and recovering the ground surface form and ground surface attachments along the power line; the laser point cloud space measurement module is used for automatically measuring and classifying the clearance distance of the cross spanning object, automatically analyzing the hidden defect danger and automatically generating a report; the step-by-step dimensionality reduction module is used for reconstructing the power line in a step-by-step dimensionality reduction mode; the wire and tower classification module is used for realizing the rapid automatic synchronous classification of the wires and the towers by applying Hough transformation and a Kmeans clustering method based on the spatial topological relation of the wires and the towers.
Further, the step-by-step dimensionality reduction module comprises a repeated point removing module, a plane straight line fitting module, a two-dimensional curve fitting module and a three-dimensional space fitting module; the repeated point removing module is used for filtering repeated data influencing the calculation efficiency in the electric fish data; the plane straight line fitting module is used for performing first dimension reduction of straight line fitting of a two-dimensional plane; the two-dimensional curve fitting module is used for performing two-dimensional curve fitting to realize a second dimension reduction wire; and the three-dimensional space fitting module is used for fitting the distribution of the three-dimensional overall space of the conducting wire after the secondary dimensionality reduction.
Furthermore, the wire and tower classification module comprises a slope calculation module, a span value calculation module, a wire data judgment module and a tower classification data module; the slope calculation module is used for judging the line trend of the target lead and calculating the line trend slope; the span value calculation module generates a two-dimensional image based on the line trend slope obtained by the slope calculation module, and judges and calculates the span value between parallel lines; the wire data judgment module carries out detection, transformation, cluster analysis and comparison on the basis of the two-dimensional image generated by the span value calculation module to obtain wire classification data; and the tower classification data module is used for carrying out clustering analysis on the data left after the screening of the wire data judgment module again to obtain independent tower classification data.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (9)
1. The power transmission line inspection detection method based on the laser point cloud is characterized by comprising the following steps:
step 100: carrying a laser radar system on an unmanned aerial vehicle, flying the unmanned aerial vehicle along a power transmission line to obtain data of a power line corridor, obtaining account data of the power line corridor through post settlement processing and analysis, carrying out vectorization classification management on the power line corridor, and establishing a three-dimensional model of the power line corridor according to the data;
step 200: analyzing the established three-dimensional model of the line corridor, and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data, wherein the high-precision point cloud tower model data comprise wire classification data and tower classification data;
step 300: and generating high-precision point cloud tower model data according to classification, planning a route and autonomously flying, and realizing automatic and accurate shooting selection of the tower body for fine inspection by means of a deep learning algorithm to form a flying track connecting all shooting points.
2. The power transmission line inspection detection method based on the laser point cloud of claim 1, characterized in that: the data of the power line corridor acquired in the step 100 comprise laser point cloud data, image data, camera data, infrared and ultraviolet data and environment variable parameters; the ledger data of the power line corridor comprises characteristic data of a line planing surface diagram, a section diagram, a span and an arc sag.
3. The power transmission line inspection detection method based on the laser point cloud of claim 1, characterized in that: the specific steps of analyzing and classifying the established three-dimensional model of the line corridor in the step 200 are as follows:
step 210: when the established three-dimensional model of the line corridor is analyzed, the laser point cloud data collected by inspection is processed into a standard digital elevation model, then the classified point cloud is combined to realize further three-dimensional digitization of the power line, the lower part of the line is classified according to the types of common ground objects in a line channel, and the ground surface form and the ground surface attachments along the power line are recovered;
step 220: automatically measuring and classifying the clearance distance of the cross spanning object, automatically analyzing the hidden defect danger and automatically generating a report;
step 230: reconstructing the power line by adopting a gradual dimension reduction mode;
step 240: and based on the spatial topological relation between the wires and the towers, the rapid automatic synchronous classification of the wires and the towers is realized by applying Hough transformation and a Kmeans clustering method.
4. The power transmission line inspection detection method based on the laser point cloud of claim 3, characterized in that: the specific steps of reconstructing the power line in step 230 by using a step-by-step dimensionality reduction method are as follows:
step 231: filtering repeated data influencing the calculation efficiency in the point cloud data, and removing the repeated data points;
step 232: according to the distribution characteristics of the conducting wires in a linear manner on the horizontal plane, linear fitting of an X-Y two-dimensional plane is carried out, and first dimension reduction is realized;
step 233: according to the distribution characteristic that the conducting wire presents a parabola on a vertical horizontal plane, performing curve fitting on an X-Z two-dimensional plane to realize secondary dimensionality reduction;
step 234: and after the secondary dimensionality reduction is completed, fitting of the whole three-dimensional space is realized, and distribution of the three-dimensional whole space of the lead is obtained.
5. The power transmission line inspection detection method based on the laser point cloud of claim 3, characterized in that: the step 240 is implemented by applying Hough transformation and Kmeans clustering methods to realize rapid automatic synchronous classification of the wires and the towers based on the spatial topological relation of the wires and the towers, and comprises the following specific steps:
step 241: through interpersonal interactive operation, the preliminary filtering of a target wire is realized, the line trend is judged, the maximum value in the horizontal direction and the minimum value in the vertical direction and corresponding coordinates are searched in a two-dimensional plane, and the line trend slope is calculated;
step 242: generating two line trend overlooking image pictures according to the line trend slope, and judging and calculating the span value between parallel lines according to the obtained line trend by utilizing the generated two-dimensional image;
step 243: canny edge detection is carried out on the generated two-dimensional image, Hough transformation is carried out to obtain a straight line segment, Kmeans clustering is carried out on the obtained straight line segment according to the slope of the straight line, two cluster types obtained through clustering respectively represent two categories of the slope of the straight line, the two categories are respectively compared with the trend slope of the line, and point cloud data corresponding to the cluster types with the same trend slope are wire classification data;
step 244: and (4) performing Kmeans clustering again on the data which are remained after the comparison and screening in the step 243, clustering the remained straight line segments according to the starting points of the line segments to obtain independent tower classification data, and further realizing the rapid automatic synchronous classification of the lead and the tower.
6. Transmission line inspection detecting system based on laser point cloud, its characterized in that: the system comprises a three-dimensional model modeling module, a classification module and a flight planning module; the three-dimensional model modeling module is used for carrying a laser radar system on the unmanned aerial vehicle, flying along the power transmission line, acquiring data of the power line corridor, and establishing a three-dimensional model of the line corridor according to the data subjected to post-analysis processing; the classification module is used for analyzing the established three-dimensional model of the line corridor and classifying the established three-dimensional model of the line corridor to generate high-precision point cloud tower model data; and the flight planning module is used for generating high-precision point cloud tower model data according to classification and carrying out air route planning and autonomous flight.
7. The power transmission line inspection detection system based on the laser point cloud of claim 6, wherein: the classification module comprises a basic point cloud data management module, a laser point cloud space measurement module, a gradual dimension reduction module and a wire and tower classification module; the basic point cloud data management module is used for processing the laser point cloud data collected by inspection into a standard digital elevation model, combining the classified point clouds, classifying the lower part of the line according to the types of common ground objects in a line channel, and recovering the ground surface form and ground surface attachments along the power line; the laser point cloud space measurement module is used for automatically measuring and classifying the clearance distance of the cross spanning object, automatically analyzing the hidden defect danger and automatically generating a report; the step-by-step dimensionality reduction module is used for reconstructing the power line in a step-by-step dimensionality reduction mode; the wire and tower classification module is used for realizing the rapid automatic synchronous classification of the wires and the towers by applying Hough transformation and a Kmeans clustering method based on the spatial topological relation of the wires and the towers.
8. The power transmission line inspection detection system based on the laser point cloud of claim 7, wherein: the step-by-step dimensionality reduction module comprises a repeated point removing module, a plane straight line fitting module, a two-dimensional curve fitting module and a three-dimensional space fitting module; the repeated point removing module is used for filtering repeated data influencing the calculation efficiency in the electric fish data; the plane straight line fitting module is used for performing first dimension reduction of straight line fitting of a two-dimensional plane; the two-dimensional curve fitting module is used for performing two-dimensional curve fitting to realize a second dimension reduction wire; and the three-dimensional space fitting module is used for fitting the distribution of the three-dimensional overall space of the conducting wire after the secondary dimensionality reduction.
9. The power transmission line inspection detection system based on the laser point cloud of claim 7, wherein: the wire and tower classification module comprises a slope calculation module, a span value calculation module, a wire data judgment module and a tower classification data module; the slope calculation module is used for judging the line trend of the target lead and calculating the line trend slope; the span value calculation module generates a two-dimensional image based on the line trend slope obtained by the slope calculation module, and judges and calculates the span value between parallel lines; the wire data judgment module carries out detection, transformation, cluster analysis and comparison on the basis of the two-dimensional image generated by the span value calculation module to obtain wire classification data; and the tower classification data module is used for carrying out clustering analysis on the data left after the screening of the wire data judgment module again to obtain independent tower classification data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111316891.8A CN114114314A (en) | 2021-11-08 | 2021-11-08 | Power transmission line inspection detection system and detection method based on laser point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111316891.8A CN114114314A (en) | 2021-11-08 | 2021-11-08 | Power transmission line inspection detection system and detection method based on laser point cloud |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114114314A true CN114114314A (en) | 2022-03-01 |
Family
ID=80377605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111316891.8A Pending CN114114314A (en) | 2021-11-08 | 2021-11-08 | Power transmission line inspection detection system and detection method based on laser point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114114314A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639024A (en) * | 2022-03-03 | 2022-06-17 | 江苏方天电力技术有限公司 | Automatic laser point cloud classification method for power transmission line |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN115187648A (en) * | 2022-09-08 | 2022-10-14 | 安徽继远软件有限公司 | Reverse modeling method and device for power transmission line body, electronic equipment and storage medium |
| CN115240093A (en) * | 2022-09-22 | 2022-10-25 | 山东大学 | Automatic power transmission channel inspection method based on visible light and laser radar point cloud fusion |
| CN116843909A (en) * | 2023-05-12 | 2023-10-03 | 国家电网有限公司华东分部 | Power line extraction method and device, storage medium and computer equipment |
| CN116858195A (en) * | 2023-06-08 | 2023-10-10 | 中铁第四勘察设计院集团有限公司 | Existing railway measurement method based on unmanned aerial vehicle laser radar technology |
| CN117406778A (en) * | 2023-11-16 | 2024-01-16 | 广东工贸职业技术学院 | Unmanned plane laser radar ground-imitating flight method based on geospatial data |
-
2021
- 2021-11-08 CN CN202111316891.8A patent/CN114114314A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639024A (en) * | 2022-03-03 | 2022-06-17 | 江苏方天电力技术有限公司 | Automatic laser point cloud classification method for power transmission line |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN114782947B (en) * | 2022-06-22 | 2022-10-04 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN115187648A (en) * | 2022-09-08 | 2022-10-14 | 安徽继远软件有限公司 | Reverse modeling method and device for power transmission line body, electronic equipment and storage medium |
| CN115240093A (en) * | 2022-09-22 | 2022-10-25 | 山东大学 | Automatic power transmission channel inspection method based on visible light and laser radar point cloud fusion |
| CN115240093B (en) * | 2022-09-22 | 2022-12-23 | 山东大学 | Automatic power transmission channel inspection method based on visible light and laser radar point cloud fusion |
| CN116843909A (en) * | 2023-05-12 | 2023-10-03 | 国家电网有限公司华东分部 | Power line extraction method and device, storage medium and computer equipment |
| CN116843909B (en) * | 2023-05-12 | 2024-03-08 | 国家电网有限公司华东分部 | Power line extraction method and device, storage medium and computer equipment |
| CN116858195A (en) * | 2023-06-08 | 2023-10-10 | 中铁第四勘察设计院集团有限公司 | Existing railway measurement method based on unmanned aerial vehicle laser radar technology |
| CN116858195B (en) * | 2023-06-08 | 2024-04-02 | 中铁第四勘察设计院集团有限公司 | Existing railway measurement method based on unmanned aerial vehicle laser radar technology |
| CN117406778A (en) * | 2023-11-16 | 2024-01-16 | 广东工贸职业技术学院 | Unmanned plane laser radar ground-imitating flight method based on geospatial data |
| CN117406778B (en) * | 2023-11-16 | 2024-03-12 | 广东工贸职业技术学院 | Unmanned plane laser radar ground-imitating flight method based on geospatial data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114114314A (en) | Power transmission line inspection detection system and detection method based on laser point cloud | |
| CN110780681B (en) | Unmanned aerial vehicle autonomous routing inspection insulator path planning method based on laser point cloud | |
| Guan et al. | UAV-lidar aids automatic intelligent powerline inspection | |
| CN109829199B (en) | Power line rapid layered extraction method based on LiDAR point cloud | |
| CN112884931B (en) | Unmanned aerial vehicle inspection method and system for transformer substation | |
| CN112033414A (en) | Unmanned aerial vehicle inspection route generation method, device, equipment and medium | |
| Sohn et al. | Automatic powerline scene classification and reconstruction using airborne lidar data | |
| CA2839165C (en) | Method and system for processing image data | |
| CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
| CN112414309B (en) | High-speed rail contact line height-guiding and pull-out value inspection method based on airborne laser radar | |
| CN113963276A (en) | Unmanned aerial vehicle autonomous inspection method and system for power transmission line | |
| CN114862901A (en) | Road-end multi-source sensor fusion target sensing method and system for surface mine | |
| CN110579771A (en) | Airplane berth guiding method based on laser point cloud | |
| CN113205116A (en) | Automatic extraction and flight path planning method for unmanned aerial vehicle inspection shooting target point of power transmission line | |
| Nardinocchi et al. | Fully automatic point cloud analysis for powerline corridor mapping | |
| CN112767352A (en) | High-voltage line tower automatic fine extraction method for airborne LiDAR power inspection | |
| Ariyachandra et al. | Digital twinning of railway overhead line equipment from airborne lidar data | |
| Chen et al. | Environment perception technologies for power transmission line inspection robots | |
| CN115825984A (en) | Power transmission line inspection system and inspection method based on laser point cloud | |
| CN114187297A (en) | Power transmission line wind deflection checking method and checking system | |
| JP2022119973A (en) | Method, system and apparatus for planning forced landing route of flight vehicle based on image identification | |
| Neubert et al. | Extraction of railroad objects from very high resolution helicopter-borne LiDAR and ortho-image data | |
| CN116893685A (en) | Unmanned aerial vehicle route planning method and system | |
| CN116309828A (en) | Three-dimensional laser point cloud data-based power pole information extraction method | |
| CN116520881A (en) | Unmanned plane continuous tower foundation three-dimensional inspection path planning method based on laser point cloud |
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 |