CN112561968A - Monocular vision-based transmission conductor galloping monitoring method and device - Google Patents

Monocular vision-based transmission conductor galloping monitoring method and device Download PDF

Info

Publication number
CN112561968A
CN112561968A CN202011531510.3A CN202011531510A CN112561968A CN 112561968 A CN112561968 A CN 112561968A CN 202011531510 A CN202011531510 A CN 202011531510A CN 112561968 A CN112561968 A CN 112561968A
Authority
CN
China
Prior art keywords
image
power transmission
spacer
galloping
frame
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.)
Granted
Application number
CN202011531510.3A
Other languages
Chinese (zh)
Other versions
CN112561968B (en
Inventor
刘焕云
蔡富东
吕昌峰
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.)
Jinan Xinxinda Electric Technology Co ltd
Original Assignee
Jinan Xinxinda Electric Technology 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 Jinan Xinxinda Electric Technology Co ltd filed Critical Jinan Xinxinda Electric Technology Co ltd
Priority to CN202011531510.3A priority Critical patent/CN112561968B/en
Publication of CN112561968A publication Critical patent/CN112561968A/en
Application granted granted Critical
Publication of CN112561968B publication Critical patent/CN112561968B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/168—Segmentation; Edge detection involving transform domain methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20048—Transform domain processing
    • G06T2207/20061—Hough transform
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance
    • 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
    • Y04S10/40—Display of information, e.g. of data or controls

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Electric Cable Installation (AREA)

Abstract

The application provides a method and a device for monitoring galloping of a transmission conductor based on monocular vision. The method comprises the following steps: controlling a monitoring device arranged on the power transmission iron tower to record a scene video image of the power transmission line based on the fact that the wind speed exceeds a preset threshold value or based on a preset time interval; extracting position information of the power transmission conductors from a first frame image in the power transmission conductor scene video image, clustering and grouping the position information, and determining the position information of each spacer on each group of power transmission conductors in the first frame image; acquiring tracking pixel position information of each spacer in each frame of image except the first frame of image in the scene video image according to the pixel information of each spacer; and determining the galloping amplitude and the galloping frequency of the power transmission conductor according to the change condition of the position information of the tracking pixel of each spacer along with time in each frame of image of the scene video image. The technical scheme can accurately monitor the conductor galloping condition in a simple measuring process and reduce the generated data volume.

Description

Monocular vision-based transmission conductor galloping monitoring method and device
Technical Field
The application relates to the technical field of electric power, in particular to a method and a device for monitoring transmission line galloping based on monocular vision.
Background
When the power transmission conductor is disturbed by wind power with transverse speed, such as the wind speed is more than 5m/s, and the included angle between the wind direction and the conductor trend is more than 45 degrees, an upward and downward acceleration motion is generated, so that the conductor is twisted under the action of aerodynamic moment. Conductor flapping occurs when the frequency of the torsional motion is synchronized with the frequency of the vertical motion. The conductor galloping is low-frequency and large-amplitude self-excited vibration, the frequency is generally between 0.1Hz and 3Hz, and the floating is 5-300 times of the diameter of the conductor.
The influence range of conductor galloping is very big, and the duration is very long, leads to the large tracts of land power failure accident easily. The conductor galloping not only can lead to short circuit tripping, long-time galloping still can lead to the shaft tower screw not hard up, intensity reduces, damage such as gold utensil, insulator, wire jumper, the wire strand breaking, the broken string of wire, the impaired tower material of tower, column foot or even tower down. Hardware defects such as looseness of tower screws, damage of hardware fittings and insulator performance and the like caused by conductor galloping are often difficult to find in a short time, and great hidden danger is caused to safe operation of the transmission conductors.
The prevention and control of the galloping of the overhead transmission line is a complex system project, in order to prevent the galloping of the line, anti-galloping devices such as an interphase spacer, a wire clamp rotary spacer, a double-pendulum anti-galloping device, a detuning pendulum, an eccentric heavy hammer and the like are generally installed, however, the anti-galloping devices have the functions of weakening the galloping degree of the line to a certain extent, and are poor in stability and anti-galloping strength, so that the real-time tracking and checking of the galloping condition of the line are particularly urgent and necessary.
One of the existing conductor galloping monitoring methods is to adopt an acceleration sensor mode, a data acquisition device must be fixed with a power transmission conductor, an inertia information acquisition device must work uninterruptedly, so that a power supply system of the data acquisition device must guarantee certain electric quantity, the installation of the sensors is very inconvenient for an erected line, and meanwhile, the overweight device is fixed on the power transmission conductor, so that the sag of the conductor is inevitably increased, and certain negative effects are brought to the power transmission conductor. The other is to adopt the camera sensor, and this kind of mounting means need not with wire direct contact, only need install on the shaft tower certain suitable fixed position can, and such equipment is more ripe in transmission wire visual system simultaneously, and usable solar energy power supply guarantees that equipment moves for a long time.
The existing main conductor galloping identification technology comprises a power transmission line galloping monitoring technology based on a displacement and acceleration sensor and a power transmission line galloping monitoring technology based on a video/image acquisition technology. The first monitoring technique requires sensors to be installed in the power conductors, and therefore the number, manner of installation of sensors in the power conductors and the selection of a suitable fitting algorithm are difficult. The more the sensors of the monitoring system are installed, the higher the monitoring and curve fitting accuracy is, but the problems of greatly increased software calculation amount and increased cost are brought, and more importantly, the installation of the sensors can cause great influence on a mathematical model of transmission conductor galloping, and even cause model distortion seriously. The second existing power transmission line detection technology, namely a conductor galloping monitoring technology based on a video/image technology, firstly needs to judge the conductor to twist and gallop by identifying the twisting direction angle of the spacer, but cannot identify the horizontal and vertical galloping of the conductor. Secondly, the distance from the measured point to the camera needs to be measured through the laser range finder, a ground observation camera needs to be specially erected each time to measure the lead, and the measuring point on the lead is not easy to confirm under the long-distance condition, so that the distance from the measuring point to the camera is difficult to obtain, and the measuring process is complex. Thirdly, a specially-made infrared camera is required to be installed on a tower to monitor a power transmission conductor in real time, field data obtained within a period of time are labeled, and a convolutional neural network is used for carrying out classification training on the labeled field data.
Disclosure of Invention
In view of the problems in the prior art, the embodiment of the application provides a monocular vision-based transmission line galloping monitoring method and device, and solves the problems that the existing conductor galloping monitoring technology cannot identify horizontal and vertical conductor galloping, the measuring process is complex, and the amount of generated monitoring data is large.
On one hand, the embodiment of the application provides a method for monitoring power transmission line galloping based on monocular vision, which comprises the following steps: controlling a monitoring device arranged on the power transmission iron tower to record a scene video image of the power transmission line based on the fact that the wind speed exceeds a preset threshold value or based on a preset time interval; extracting position information of the power transmission conductors from a first frame image in the power transmission conductor scene video image, clustering and grouping the position information, and determining the position information of each spacer on each group of power transmission conductors in the first frame image; acquiring tracking pixel position information of each spacer in each frame of image except the first frame of image in the scene video image according to the pixel position information of each spacer; and determining the galloping amplitude and the galloping frequency of the power transmission conductor according to the change condition of the position information of the tracking pixel of each spacer along with time in each frame of image of the scene video image. According to the scheme provided by the embodiment of the application, the monitoring equipment is triggered to record videos through wind power-based monitoring or time intervals, the recorded videos are processed frame by frame, the galloping amplitude and the galloping frequency of the spacers are determined by determining the positions of the spacers on each group of conductors in the video image, so that the galloping amplitude and the galloping frequency of the power transmission conductors are obtained, the conductor galloping frequency and amplitude can be quantitatively calculated, the calculation process is simpler, and the generated data volume is less.
In one embodiment, before extracting location information of the power transmission conductors and performing cluster grouping in a first frame image of the video images of the power transmission conductor scene, the method further comprises: identifying a first frame image in the power transmission line scene video image to obtain a skyline between a sky area and a ground area; fitting the skyline into a straight line through a Hough transformation straight line fitting algorithm; by theta-arctan (abs (k)1) Derive the angle of inclination of the skyline, where k1Fitting the slope of a straight line for the skyline; the inclination angle theta of the skyline is the installation inclination angle of the monitoring equipment installed on the power transmission tower, and the value range of theta is [0,45 ]]。
Since some surveillance devices, such as a camera, must be installed at an inclined angle due to the installation position, it is necessary to calculate the inclination angle thereof in order to correct the magnitude of the waving in the following. The installation angle of the monitoring equipment can be conveniently calculated by identifying the boundary line between the ground and the sky and calculating the included angle between the boundary line and the horizontal line.
In one embodiment, the determining the galloping amplitude of the power transmission conductor according to the change of the tracking result position of each spacer bar with time in each frame of image of the scene video image specifically includes: according to Scalen＝An/anObtaining a proportional scale relation between the pixel size of the pixel point on each spacer in the scene video and the actual physical size corresponding to the pixel point; wherein A represents the physical size of the spacer, a represents the pixel size of the spacer, and n represents the nth spacer on the transmission line; according to Aptitude Pixeln＝Scalen*abs(Y1-Y2) Obtaining the actual galloping amplitude of each spacer on the power transmission conductor; wherein, Y1For the maximum value, Y, of the tracking pixel position information of the nth spacer in each frame image2The minimum value of the position information of the tracking pixel of the nth spacer in each frame of image is obtained; the maximum value Apt in the actual waving amplitude of a plurality of spacing rods on the power transmission conductor is set as max (Aptitude)n) The actual galloping amplitude of the power transmission conductor in the current scene video is taken as the actual galloping amplitude; and correcting the galloping amplitude of the power transmission line in the current scene video to be Apt _ opt which is Apt/cos theta according to the inclination angle theta of the skyline.
In one embodiment, the determining the galloping frequency of the power transmission conductor according to the change of the tracking pixel position information of each spacer bar with time in each frame of image of the scene video specifically includes: according to FPSwd＝FPS/average(Fn) Obtaining the galloping frequency of the power transmission conductor; the FPS is the frame rate of the scene video and is obtained by the known parameters of the monitoring equipment; fnTwo corresponding to the spacer when the spacer is swung twice to the highest tracking pixel position informationThe number of frames that differ between frame images.
In one embodiment, the extracting, in a first frame image of the power transmission conductor scene video image, position information of power transmission conductors and performing cluster grouping specifically includes: performing edge detection on a first frame image in the power transmission conductor scene video to obtain an edge image, and detecting the linear position in the edge image through Hough transformation so as to detect the power transmission conductor position information in the first frame image of the scene video image; determining the distance between the two power transmission conductors according to the slope and intercept of the two power transmission conductors, thereby obtaining an initial distance matrix D (0) between every two power transmission conductors; selecting the minimum value of the off-diagonal elements in the initial distance matrix D (0) and marking as DpqThe minimum value d in the off-diagonal elementspqTwo corresponding power transmission conductors GpAnd GqSynthesizing a new wire class Gr＝{Gp，Gq}; determining the class G of a wirerAnd removing wire GpAnd GqThe distances of the other k power conductors, thereby obtaining a first distance matrix D (1); adding the power transmission conductor corresponding to the minimum element in the first distance matrix D (1) into the conductor class GrIn the step (c), the wire class G is circularly calculatedrObtaining a z-th distance matrix D (z) from distance matrixes of other power transmission lines, and stopping circulation until the minimum element in the matrix D (z) is larger than a preset threshold value; conducting wire G obtained after the circulation is stoppedrThe power conductors in (1) are grouped into one group, and after the classified conductors are removed, other conductors are clustered again until all conductors are grouped.
In one embodiment, the determining the position information of each spacer on each group of transmission lines in the first frame image specifically includes: extracting a group comprising two or more power transmission conductors, digging out an image area occupied by pixels occupied by each group of conductors after the pixels are expanded by m pixels outwards, and converting the image area into a gray scale image; constructing c detection template image groups based on a plurality of fixed template images of the power transmission line scene, and dividing the detection template image groups into e scales; according to
Figure BDA0002852233060000051
Matching the detection template images of each scale, wherein NCC is the matching degree of the image area and the detection template images, f (x, y) represents the gray value of a pixel point (x, y) in the image area, t (x, y) represents the gray value of the pixel point (x, y) in the detection template images, mu represents the average value of all pixel values of the image area, sigma is the standard deviation, and u represents the total number of pixels of the detection template images; and selecting a detection template image with the highest matching degree with the image area, wherein the pixel positions of a plurality of spacers in the detection template image are used as the pixel positions of a plurality of spacers on each group of transmission wires in the first frame image.
In an embodiment, the obtaining, according to the pixel information of each spacer, tracking pixel position information of each spacer in each frame of image of the scene video image except for the first frame of image specifically includes: expanding the initial pixel Size of each spacer to obtain TrackSize ═ Size × b, wherein Size is the initial pixel Size of the spacer, and b is a multiple of Size expansion; taking TrackSize as a tracking parameter of a KCF algorithm, and acquiring and storing tracking pixel position information of a plurality of spacers on a transmission conductor through the KCF algorithm for each frame image except a first frame image in the scene video image; and taking the image frame as an abscissa and the tracking pixel position information of each spacer in the vertical direction of the image as an ordinate to obtain a position change diagram of each spacer.
In one embodiment, after said determining the amplitude and frequency of galloping of the power conductor, the method further comprises: matching the galloping amplitude and the galloping frequency of the power transmission conductor with amplitudes and frequencies corresponding to different galloping types of the power transmission conductor to determine the galloping type of the power transmission conductor; wherein the waving types comprise breeze vibration, wire waving and subspan vibration; and sending the galloping type of the power transmission conductor and the corresponding scene video image to a monitoring platform.
In one embodiment, the controlling, based on the wind speed exceeding a preset threshold or based on a preset time interval, a monitoring device installed on a power transmission tower to record a video image of a scene of a power transmission line specifically includes: the monitoring equipment is triggered to record a scene video of the power transmission conducting wire by installing a wind sensor or a microclimate sensor on the monitoring equipment when the wind sensor monitors that the wind speed is higher than a second preset threshold; or when the microclimate sensor monitors that the wind speed is higher than a second preset threshold value, triggering the monitoring equipment to record a power transmission conductor scene video; or shooting the scene video of the power transmission line according to a preset time interval.
According to the embodiment of the application, the wind speed is monitored by installing the wind sensor or the microclimate sensor on the monitoring equipment, and video recording can be performed when the wind speed reaches a conductor galloping line, so that the video storage space is saved, and the generation of data is reduced.
On the other hand, this application embodiment provides a transmission line monitoring devices that waves based on monocular vision, includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to: controlling a monitoring device arranged on the power transmission iron tower to record a scene video image of the power transmission line based on the fact that the wind speed exceeds a preset threshold value or based on a preset time interval; extracting position information of the power transmission conductors from a first frame image in the power transmission conductor scene video image, clustering and grouping the position information, and determining the position information of each spacer on each group of power transmission conductors in the first frame image; acquiring tracking pixel position information of each spacer in each frame of image except the first frame of image in the scene video image according to the pixel information of each spacer; and determining the galloping amplitude and the galloping frequency of the power transmission conductor according to the change condition of the position information of the tracking pixel of each spacer along with time in each frame of image of the scene video image.
The utility model provides a pixel position through the conductor spacer on the wire is trailed to this application one side to according to the range and the frequency that the conductor waved represent the range and the frequency that the conductor waved, come to monitor the wave condition of conductor, when the conductor waved and surpassed certain range or frequency, send the video that corresponds to monitoring platform so that the staff in time overhauls, improved the maintenance efficiency of conductor greatly, reduced the loss that the conductor damaged and led to the fact. On the other hand, the video is not shot at all times, but the video shooting is carried out after the wind speed reaches a certain condition, so that unnecessary redundant data can be avoided, and the storage space is saved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic view of a transmission conductor galloping monitoring device based on monocular vision according to an embodiment of the present application;
fig. 2 is a flowchart of a method for monitoring galloping of a power transmission conductor based on monocular vision according to an embodiment of the present application;
FIG. 3 is a graph showing the results of the dancing position of a spacer;
fig. 4 is a diagram of a monitoring entity device for transmission conductor galloping based on monocular vision according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a method and a device for monitoring galloping of a transmission conductor based on monocular vision, and the technical scheme provided by the embodiment of the application is explained in detail through the attached drawings.
Fig. 1 is a schematic view of a transmission conductor galloping monitoring device based on monocular vision according to an embodiment of the present application, and as shown in fig. 1, a transmission conductor galloping monitoring device 100 based on monocular vision includes a monitoring device 110, a front-end detection device 120, and a monitoring platform 130.
Specifically, the monitoring device 110 is configured to record a power transmission conductor scene video when the wind speed exceeds a preset threshold; or recording the scene video of the transmission line at regular time based on a preset time interval. The front-end detection device 120 is configured to identify the video recorded by the monitoring device 110, identify position information of the power transmission conductors in the video image, and determine position information of spacers for fixing the conductors on each group of power transmission conductors; and is further configured to obtain pixel position information of each spacer in each frame of image of the video recorded by the monitoring device 110 through a matching algorithm and a tracking algorithm, and obtain the galloping amplitude and the galloping frequency of the spacers, so as to determine the galloping amplitude and the galloping frequency of the conductor and the galloping type. The monitoring platform 130 is configured to receive a conductor video with a waving phenomenon and a waving type of a conductor in the video, which are sent by the front-end detection device 120, so that a maintainer can conveniently determine whether to overhaul the conductor.
In one embodiment, the types of waving include breeze vibration, wire waving, and sub-span oscillation. Wherein, the breeze vibration is a high-frequency low-amplitude vibration in a standing wave mode, the vibration frequency is about between 3Hz and 150Hz, the amplitude is about between 0.1d and 3d, and d is the diameter of the wire. The conductor galloping is low-frequency self-excited vibration with large amplitude caused by the lifting force generated by wind in the horizontal direction on the line with the asymmetrical section, the vibration frequency is about 0.1 Hz-3 Hz, and the amplitude is about 5 d-300 d. The subspan oscillation generally occurs in a horizontal plane and has an elliptical trajectory with a frequency of oscillation between about 0.5Hz and about 10Hz and an amplitude of oscillation between about 3d and about 5 d.
In one example, if the conductor detected by the front-end detection device 120 has a waving frequency of 100Hz, a waving amplitude of 5cm and a conductor diameter of 2cm, the waving amplitude of the conductor is 2.5d, and thus it is known that the waving type of the conductor is a breeze vibration.
Fig. 2 is a flowchart of a method for monitoring galloping of a power transmission conductor based on monocular vision according to an embodiment of the present application.
S201, the monitoring device 110 triggers short video shooting of the power transmission line scene based on a sensor or at regular time.
Specifically, by installing a wind sensor or a microclimate sensor on the monitoring device 110, when the wind sensor monitors that the wind speed is higher than a second preset threshold, the monitoring device 110 is triggered to record a scene video of the power transmission conductor scene; or when the microclimate sensor monitors that the wind speed is higher than a second preset threshold, triggering the monitoring equipment 110 to record the scene video of the power transmission conductor; or controlling the monitoring device 110 to shoot the scene video of the transmission line according to a preset time interval.
In one example, the second preset threshold may be set to a wind speed that causes the wire to start waving, for example, when the wind speed is greater than 5m/s, the video recording function of the monitoring device 110 is triggered.
S202, the front end detection device 120 decodes each frame of image in the power transmission line scene video.
Specifically, the front-end detection device 120 decodes the power transmission line scene video recorded by the monitoring device 110 into images of one frame and one frame, so as to facilitate subsequent image processing on each frame of image.
S203, the front end detection device 120 determines whether the position of the spacer has been extracted from the short video.
Specifically, if the front-end detection device 120 has not extracted the position of the spacer in the received power transmission line scene video, it needs to extract the position of the spacer first, and then S204 is executed; if the spacer bar position has been extracted, S207 is performed.
S204, the front end detection device 120 extracts the sky boundary line and determines the installation tilt angle of the surveillance device 110.
Specifically, a first frame image in a power transmission conductor scene video image is converted into a gray image, gradient information of the gray image is extracted by using a Sobel operator, and boundary line information of the sky is extracted from the gradient information. Then each row of pixels of the image is scanned, whether the pixel belongs to a sky pixel or not is judged according to the Mahalanobis distance between each row of pixels and the real sky, and a boundary line extraction result is improved. And extracting the outermost outline of the detected sky boundary line to obtain a sky area, wherein the sky area comprises towers and wires. The boundary line between the sky area and the ground area is the skyline; and fitting the skyline into a straight line through a Hough transformation straight line fitting algorithm.
By theta-arctan (abs (k)1) Derive the angle of inclination of the skyline, where k1Fitting the slope of a straight line for the skyline; the inclination angle θ of the skyline is the installation inclination angle of the monitoring device 110 installed on the power transmission tower, and the value range of θ is [0,45 degrees ] since the installation inclination angle of the monitoring device 110 cannot exceed 45 degrees]。
S205, the front-end detection device 120 detects the position information of the conducting wires in the video image and carries out clustering grouping.
Specifically, graying a first frame image in a power transmission conductor scene video, and performing fuzzy processing on the grayscale image by using a Gaussian fuzzy function to obtain a fuzzy image. And then carrying out edge detection on the blurred image to obtain an edge image. Detecting straight line position information in the edge image through Hough transformation, so as to detect power transmission conductor position information in a first frame image of a scene video image;
the detected leads are grouped according to distance, the leads with similar distances are divided into a group, the grouping method adopts a hierarchical clustering method, and the similarity and the difference in the cluster are determined through distance measurement.
According to Gi＝{ki，biDefining a power conductor, wherein i represents the ith power conductor in the first frame image in the scene video image, kiIs the slope of the ith power conductor, biIs the intercept of the ith power conductor.
According to the distance formula dij＝sqrt((ki-kj)2+(bi-bj)2) Determining the distance between two power conductors, thereby obtaining an initial distance matrix D (0) between every two power conductors; at each timeThe strip conductors are self-forming, and Dij＝dij. Selecting the minimum value of the off-diagonal elements in the initial distance matrix D (0) and recording the minimum value as DpqD is mixingpqTwo corresponding power transmission conductors GpAnd GqSynthesizing a new wire class Gr＝{Gp，Gq}；
By passing
Figure BDA0002852233060000101
Determining the class G of a wirerAnd removing wire GpAnd GqThe distance of the k outer power conductors, resulting in a first distance matrix D (1); wherein i represents a dividing line GpAnd GqI-th of the other k power conductors, j representing conductor class GrThe jth wire in (1).
Because the minimum element in D (1) represents the wire class GrMinimum distance between the other wires, so the wire corresponding to the minimum element in D (1) is updated to wire class GrThen circularly calculating the wire class GrAnd obtaining a z-th distance matrix D (z) according to the distance between the first conducting wire and the other conducting wires, and stopping circulation until the minimum element in the matrix D (z) is larger than a preset threshold value.
For example, if the predetermined threshold is 10, the minimum element in the matrix D (5) is greater than 10, i.e. the latest wire class GrAfter a minimum distance of more than 10 from the other wires, the cycle is stopped. Then current GrThe conductor in (1) is the closest group of conductors.
Final wire class GrThe several transmission conductors in (a) are clustered into a group. Then, after the classified leads are removed, other leads are clustered again according to the method until all leads are grouped.
S206, the front-end detection device 120 extracts the position information of each spacer on the conductor in the video.
Specifically, for each group of lead groups with two or more leads, the edgemost leads in the group are expanded outwards by m pixels, the image area occupied by the expanded lead group is scratched, and the image area is converted into a gray-scale image;
because the spacers on the wires are fixedly installed, a fixed template image with the highest matching degree with a first frame image in a power transmission wire scene video can be found out from a plurality of fixed template images of a certain line, and the positions of the spacers in the fixed template images are used as the positions of the spacers in the first frame image in the power transmission wire scene video.
In one embodiment, for a plurality of fixed template images of a certain line, 3 detection template image groups are constructed, and the detection template image groups are divided into 5 scales; the NCC algorithm is used for the detection template image of each scale along the direction of the wire:
Figure BDA0002852233060000111
and matching, wherein NCC is the matching degree of the image area occupied by the expanded lead group and the detection template image of each scale, f (x, y) represents the gray value of a pixel point (x, y) in the image area, t (x, y) represents the gray value of the pixel point (x, y) in the detection template image, mu represents the average value of all pixel values in the image area, sigma is the standard deviation, and u represents the total number of pixels of the detection template image.
Selecting a detection template image with the highest matching degree with the image area, and taking the pixel position information of a plurality of spacers in the detection template image as the pixel position information of a plurality of spacers on each group of transmission lines in the first frame image, wherein the pixel position information is the pixel coordinates of the spacers in the video image.
S207, the front end detection device 120 obtains and stores tracking pixel position information of the spacer in each frame of image through a spacer tracking algorithm.
It should be noted that the tracking pixel position information of the spacer is used to indicate the pixel coordinates of the tracking position of the spacer obtained by the tracking algorithm in each frame of image except the first frame of image in the power transmission line scene video. For example, the spacer bar L1The tracking pixel position information in the second frame video image is (x)2，y2)。
Specifically, for each spacer, the initial pixel Size of the spacer is enlarged to obtain TrackSize ═ Size × b, where Size is the initial pixel Size of the spacer and b is a multiple of the Size enlargement.
And taking TrackSize as a tracking parameter of a KCF algorithm, and acquiring and storing tracking pixel position information of each spacer on the transmission wire through the KCF algorithm for each frame image except the first frame image in the scene video image.
It should be noted that the embodiment of the present application is not limited to performing target tracking on the spacer by using the KCF algorithm, and other single-target or multi-target tracking algorithms may also be used. The position of the spacer is identified by using a target tracking algorithm, so that the calculated amount can be reduced, and the identification precision is improved. If the position of the spacer for each frame is obtained by the NCC matching algorithm, the computational effort of the front-end detection device 120 is increased and the accuracy is low.
In one embodiment, FIG. 3 is a graph of the results of the dancing position of a spacer. As shown in fig. 3, the image frame is used as the abscissa, and the position of a certain spacer in each frame of image on the y-axis of the image is used as the ordinate, so as to obtain the dancing position change diagram of the certain spacer in the video.
S208, the front-end detection device 120 determines whether all the frame images in the video are calculated, if so, S209 is executed, and if not, S202 is executed.
S209, the front end detection device 120 judges the galloping amplitude and frequency of the lead according to the stored position of the spacer.
Specifically, knowing the physical size A of the spacer and the pixel size a of the spacer in the scene video image, calculating the Scale relation Scale of the pixel point at the position of the spacern＝An/anWherein n represents the nth spacer on the transmission line.
Determining the highest dancing pixel position Y from the dancing positions of the spacers recorded in FIG. 31And the lowest dancing pixel position Y2By the formula AptitudePixeln＝Scalen*abs(Y1-Y2) And obtaining the actual waving amplitude of a certain spacer on the power transmission conductor.
The maximum value Apt in the actual waving amplitude of each spacer on the transmission conductor is set as max (Aptitude)n) As the actual galloping amplitude of the power transmission conductor in the current scene video. And correcting the galloping amplitude of the power transmission line in the video of the current scene to be Apt _ opt ═ Apt/cos theta according to the installation inclination angle theta of the monitoring device 110.
According to FPSwd＝FPS/average(Fn) Obtaining the galloping frequency of the transmission conductor; wherein FPS is a frame rate of the scene video, and is obtained from known parameters of the monitoring device 110; fnThe number of frames of the difference between the two corresponding frames of images when the spacer is swung twice to the highest position information of the tracking pixel is shown in fig. 3, which is the number of frames of the difference between the x coordinates corresponding to the two peaks.
S210, the front-end detection device 120 judges the conductor galloping type according to the conductor galloping amplitude and frequency.
Specifically, the types of waving include breeze vibration, wire waving, and sub-span oscillation. Wherein, the vibration frequency of the breeze vibration is about between 3Hz and 150Hz, the amplitude is about between 0.1d and 3d, wherein d is the diameter of the wire. The vibration frequency of the conductor galloping is about 0.1 Hz-3 Hz, and the amplitude is about 5 d-300 d. The vibration frequency of the subspan oscillation is about 0.5 Hz-10 Hz, and the amplitude is about 3 d-5 d.
And matching the galloping amplitude and the galloping frequency of the wire calculated in the step S209 with the amplitudes and the frequency ranges of the three galloping types according to the diameter of the wire, and determining the galloping type of the wire.
S211, the front-end detecting device 120 sends the monitoring result to the monitoring platform 130.
In one embodiment, if the amplitude and frequency of the conductor galloping detected in a certain video segment meet the conditions of the three galloping types, the segment of video segment and the galloping type are both sent to the monitoring platform 130.
Fig. 4 is a diagram of a monitoring entity device for transmission conductor galloping based on monocular vision according to an embodiment of the present application. As shown in fig. 4, the monocular vision-based transmission conductor galloping monitoring entity apparatus includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:
controlling a monitoring device arranged on the power transmission iron tower to record a scene video image of the power transmission line based on the fact that the wind speed exceeds a preset threshold value or based on a preset time interval;
extracting position information of the power transmission conductors from a first frame image in the power transmission conductor scene video image, clustering and grouping the position information, and determining the position information of each spacer on each group of power transmission conductors in the first frame image; acquiring tracking pixel position information of each spacer in each frame of image except the first frame of image in the scene video image according to the pixel information of each spacer;
and determining the galloping amplitude and the galloping frequency of the power transmission conductor according to the change condition of the position information of the tracking pixel of each spacer along with time in each frame of image of the scene video image.
The method and the device for monitoring the galloping of the transmission conductor based on the monocular vision can automatically monitor the position of the spacer and quantize the amplitude and the frequency of the galloping of the conductor according to the position change of the spacer, a new device does not need to be installed, hardware upgrading is not needed, and data does not need to be frequently transmitted back to a monitoring center, so that a video section with abnormal frequency and abnormal amplitude of the galloping of the conductor is pushed to operation and maintenance personnel in a targeted manner, the operation and maintenance personnel can take measures in time, and the method and the device have important positive significance for the safe operation of the transmission line.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application. It should be noted that various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement and the like made without departing from the principle of the present application shall be included in the scope of the claims of the present application.

Claims (10)

1. A monocular vision-based transmission conductor galloping monitoring method is characterized by comprising the following steps:
controlling a monitoring device arranged on the power transmission iron tower to record a scene video image of the power transmission line based on the fact that the wind speed exceeds a preset threshold value or based on a preset time interval;
extracting position information of the power transmission conductors from a first frame image in the power transmission conductor scene video image, clustering and grouping the position information, and determining the position information of each spacer on each group of power transmission conductors in the first frame image; acquiring tracking pixel position information of each spacer in each frame of image except the first frame of image in the scene video image according to the pixel position information of each spacer;
and determining the galloping amplitude and the galloping frequency of the power transmission conductor according to the change condition of the position information of the tracking pixel of each spacer along with time in each frame of image of the scene video image.
2. The monocular vision-based power transmission line galloping monitoring method according to claim 1, wherein before extracting and clustering position information of power transmission lines in a first frame image of the power transmission line scene video image, the method further comprises:
identifying a first frame image in the power transmission line scene video image to obtain a skyline between a sky area and a ground area; fitting the skyline into a straight line through a Hough transformation straight line fitting algorithm;
by theta-arctan (abs (k)1) Derive the angle of inclination of the skyline, where k1Fitting the slope of a straight line for the skyline; the inclination angle theta of the skyline is the installation inclination angle of the monitoring equipment installed on the power transmission tower, and the value range of theta is [0,45 ]]。
3. The method according to claim 2, wherein the determining the transmission conductor galloping amplitude according to the variation of the tracking result position of each spacer bar in each frame of the scene video image with time specifically comprises:
according to Scalen＝An/anObtaining a proportional scale relation between the pixel size of the pixel point on each spacer in the scene video and the actual physical size corresponding to the pixel point; wherein A isnDenotes the physical size of the spacer, anThe pixel size of the spacer is shown, and n is the nth spacer on the transmission line;
according to Aptitude Pixeln＝Scalen*abs(Y1-Y2) Obtaining the actual galloping amplitude of each spacer on the power transmission conductor; wherein, Y1For the maximum value, Y, of the tracking pixel position information of the nth spacer in each frame image2The minimum value of the position information of the tracking pixel of the nth spacer in each frame of image is obtained;
the maximum value Apt in the actual waving amplitude of a plurality of spacing rods on the power transmission conductor is set as max (Aptitude)n) The actual galloping amplitude of the power transmission conductor in the current scene video is taken as the actual galloping amplitude;
and correcting the galloping amplitude of the power transmission line in the current scene video to be Apt _ opt which is Apt/cos theta according to the inclination angle theta of the skyline.
4. The method according to claim 3, wherein the determining the galloping frequency of the power transmission conductor according to the change of the tracking pixel position information of each spacer bar in each frame of image of the scene video with time specifically comprises:
according to FPSwd＝FPS/average(Fn) Obtaining the galloping frequency of the power transmission conductor; the FPS is the frame rate of the scene video and is obtained by the known parameters of the monitoring equipment; fnThe number of the difference between the two corresponding frame images when the spacer is waved twice to the highest tracking pixel position information is determined.
5. The method according to claim 1, wherein the extracting and clustering position information of the power transmission conductors in the first frame of image of the power transmission conductor scene video image specifically comprises:
performing edge detection on a first frame image in the power transmission conductor scene video to obtain an edge image, and detecting the linear position in the edge image through Hough transformation so as to detect the power transmission conductor position information in the first frame image of the scene video image;
determining the distance between the two power transmission conductors according to the slope and intercept of the two power transmission conductors, thereby obtaining an initial distance matrix D (0) between every two power transmission conductors; selecting the minimum value of the off-diagonal elements in the initial distance matrix D (0) and marking as DpqThe minimum value d in the off-diagonal elementspqTwo corresponding power transmission conductors GpAnd GqSynthesizing a new wire class Gr＝{Gp，Gq}；
Determining the class G of a wirerAnd removing wire GpAnd GqThe distances of the other k power conductors, thereby obtaining a first distance matrix D (1); adding the power transmission conductor corresponding to the minimum element in the first distance matrix D (1) into the conductor class GrIn the step (c), the wire class G is circularly calculatedrObtaining a z-th distance matrix D (z) from distance matrixes of other power transmission lines, and stopping circulation until the minimum element in the matrix D (z) is larger than a preset threshold value;
conducting wire G obtained after the circulation is stoppedrThe power conductors in (1) are grouped into one group, and after the classified conductors are removed, other conductors are clustered again until all conductors are grouped.
6. The method according to claim 5, wherein the determining the position information of the spacers on each group of transmission conductors in the first frame of image specifically comprises:
extracting a group comprising two or more power transmission conductors, digging out an image area occupied by pixels occupied by each group of conductors after the pixels are expanded by m pixels outwards, and converting the image area into a gray scale image;
constructing c detection template image groups based on a plurality of fixed template images of the power transmission line scene, and dividing the detection template image groups into e scales; according to
Figure FDA0002852233050000031
Matching the detection template images of each scale, wherein NCC is the matching degree of the image area and the detection template images, f (x, y) represents the gray value of a pixel point (x, y) in the image area, t (x, y) represents the gray value of the pixel point (x, y) in the detection template images, mu represents the average value of all pixel values of the image area, sigma is the standard deviation, and u represents the total number of pixels of the detection template images;
and selecting a detection template image with the highest matching degree with the image area, wherein the pixel positions of a plurality of spacers in the detection template image are used as the pixel positions of a plurality of spacers on each group of transmission wires in the first frame image.
7. The method according to claim 6, wherein the obtaining of the tracking pixel position information of the spacers in each frame of image of the scene video image except the first frame of image according to the pixel position information of the spacers comprises:
expanding the initial pixel Size of each spacer to obtain TrackSize ═ Size × b, wherein Size is the initial pixel Size of the spacer, and b is a multiple of Size expansion;
taking TrackSize as a tracking parameter of a KCF algorithm, and acquiring and storing tracking pixel position information of each spacer on a transmission wire through the KCF algorithm for each frame image except a first frame image in the scene video image;
and taking the image frame as an abscissa and the tracking pixel position information of each spacer in the vertical direction of the image as an ordinate to obtain a position change diagram of each spacer.
8. A monocular vision based transmission conductor galloping monitoring method according to claim 1, wherein after said determining the amplitude and frequency of galloping of the transmission conductor, said method further comprises:
matching the galloping amplitude and the galloping frequency of the power transmission conductor with amplitudes and frequencies corresponding to different galloping types of the power transmission conductor to determine the galloping type of the power transmission conductor; wherein the waving types comprise breeze vibration, wire waving and subspan vibration;
and sending the galloping type of the power transmission conductor and the corresponding scene video image to a monitoring platform.
9. The method for monitoring transmission line galloping based on monocular vision according to claim 1, wherein the controlling a monitoring device installed on a transmission tower to record a transmission line scene video image based on the wind speed exceeding a preset threshold or based on a preset time interval specifically comprises:
the monitoring equipment is triggered to record a scene video of the power transmission conducting wire by installing a wind sensor or a microclimate sensor on the monitoring equipment when the wind sensor monitors that the wind speed is higher than a second preset threshold; or
When the microclimate sensor monitors that the wind speed is higher than a second preset threshold value, triggering the monitoring equipment to record a power transmission conductor scene video; or
And shooting the scene video of the power transmission line according to a preset time interval.
10. A monitoring device for transmission conductor galloping based on monocular vision is characterized by comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:
controlling a monitoring device arranged on the power transmission iron tower to record a scene video image of the power transmission line based on the fact that the wind speed exceeds a preset threshold value or based on a preset time interval;
extracting position information of the power transmission conductors from a first frame image in the power transmission conductor scene video image, clustering and grouping the position information, and determining the position information of each spacer on each group of power transmission conductors in the first frame image; acquiring tracking pixel position information of each spacer in each frame of image except the first frame of image in the scene video image according to the pixel information of each spacer;
and determining the galloping amplitude and the galloping frequency of the power transmission conductor according to the change condition of the position information of the tracking pixel of each spacer along with time in each frame of image of the scene video image.
CN202011531510.3A 2020-12-22 2020-12-22 Monocular vision-based transmission conductor galloping monitoring method and device Active CN112561968B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011531510.3A CN112561968B (en) 2020-12-22 2020-12-22 Monocular vision-based transmission conductor galloping monitoring method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011531510.3A CN112561968B (en) 2020-12-22 2020-12-22 Monocular vision-based transmission conductor galloping monitoring method and device

Publications (2)

Publication Number Publication Date
CN112561968A true CN112561968A (en) 2021-03-26
CN112561968B CN112561968B (en) 2022-09-02

Family

ID=75032160

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011531510.3A Active CN112561968B (en) 2020-12-22 2020-12-22 Monocular vision-based transmission conductor galloping monitoring method and device

Country Status (1)

Country Link
CN (1) CN112561968B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113629574A (en) * 2021-08-18 2021-11-09 国网湖北省电力有限公司襄阳供电公司 Strong wind sand area transmission conductor galloping early warning system based on video monitoring technology
CN113917935A (en) * 2021-09-09 2022-01-11 山东信通电子股份有限公司 Unmanned aerial vehicle nest control method and unmanned aerial vehicle nest

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104574390A (en) * 2014-12-29 2015-04-29 华北电力大学（保定） Computation method of transmission conductor wave amplitude and frequency based on video monitoring technology
CN104933403A (en) * 2015-05-18 2015-09-23 西安工程大学 Method for monitoring conductor galloping based on spacer recognition
CN107044884A (en) * 2017-04-18 2017-08-15 沈阳工业大学 A kind of monitoring method of overhead transmission line galloping
CN107796434A (en) * 2016-08-30 2018-03-13 北京国网富达科技发展有限责任公司 A kind of transmission line galloping on-line monitoring and early warning system
CN207218379U (en) * 2017-09-15 2018-04-10 北京国网富达科技发展有限责任公司 The monitoring device of transmission line of electricity
CN108898598A (en) * 2018-06-29 2018-11-27 山东鲁能智能技术有限公司 Transmission pressure monitoring method and device
CN110276787A (en) * 2019-06-27 2019-09-24 安徽勘派斯导航信息科技有限公司 Conductor galloping monitoring method based on marker image detection

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104574390A (en) * 2014-12-29 2015-04-29 华北电力大学（保定） Computation method of transmission conductor wave amplitude and frequency based on video monitoring technology
CN104933403A (en) * 2015-05-18 2015-09-23 西安工程大学 Method for monitoring conductor galloping based on spacer recognition
CN107796434A (en) * 2016-08-30 2018-03-13 北京国网富达科技发展有限责任公司 A kind of transmission line galloping on-line monitoring and early warning system
CN107044884A (en) * 2017-04-18 2017-08-15 沈阳工业大学 A kind of monitoring method of overhead transmission line galloping
CN207218379U (en) * 2017-09-15 2018-04-10 北京国网富达科技发展有限责任公司 The monitoring device of transmission line of electricity
CN108898598A (en) * 2018-06-29 2018-11-27 山东鲁能智能技术有限公司 Transmission pressure monitoring method and device
CN110276787A (en) * 2019-06-27 2019-09-24 安徽勘派斯导航信息科技有限公司 Conductor galloping monitoring method based on marker image detection

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
黄新波 等: "基于图像匹配的输电导线舞动监测方法", 《高电压技术》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113629574A (en) * 2021-08-18 2021-11-09 国网湖北省电力有限公司襄阳供电公司 Strong wind sand area transmission conductor galloping early warning system based on video monitoring technology
CN113917935A (en) * 2021-09-09 2022-01-11 山东信通电子股份有限公司 Unmanned aerial vehicle nest control method and unmanned aerial vehicle nest
CN113917935B (en) * 2021-09-09 2023-10-20 山东信通电子股份有限公司 Unmanned aerial vehicle nest control method and unmanned aerial vehicle nest

Also Published As

Publication number Publication date
CN112561968B (en) 2022-09-02

Similar Documents

Publication Publication Date Title
CN105652154B (en) Contact Running State security auditing system
CN112561968B (en) Monocular vision-based transmission conductor galloping monitoring method and device
CN113313005B (en) Power transmission conductor on-line monitoring method and system based on target identification and reconstruction
CN105158257B (en) Slide plate measurement method and device
US20230005176A1 (en) Throwing position acquisition method and apparatus, computer device and storage medium
CN111911364B (en) Blade tip tower barrel clearance monitoring method
CN107194360B (en) Reverse current object identifying method, apparatus and system
CN116259005B (en) Intelligent monitoring system based on roof photovoltaic fire control
CN117274722B (en) Intelligent detection method for distribution box based on infrared image
CN115218801B (en) Wind driven generator clearance distance measuring method and device based on machine vision
CN103559508A (en) Video vehicle detection method based on continuous Adaboost
CN112991432A (en) Icing shape identification method based on image processing
CN115311585A (en) A discernment detecting system for electric wire netting overhead line foreign matter
CN116939532A (en) 5G-based communication tower remote monitoring system
Lin et al. Identification of icing thickness of transmission line based on strongly generalized convolutional neural network
CN112669302B (en) Hanger defect detection method and device, electronic equipment and storage medium
KR101542134B1 (en) The apparatus and method of surveillance a rock fall based on smart video analytic
CN103198326B (en) A kind of image classification method of transmission line of electricity helicopter routing inspection
CN114396921B (en) Method for measuring tidal height and propagation speed of Yangtze river on basis of unmanned aerial vehicle
CN114325878A (en) Early warning analysis system based on tornado activity characteristics
CN113496136B (en) Unmanned aerial vehicle and image recognition method thereof
CN113096063A (en) Transmission conductor galloping detection method based on short video
CN113958463A (en) Online monitoring method, system and device for fan blade
JP4723771B2 (en) Lightning determination system and lightning determination method
CN111105395A (en) A AI intelligence cloud platform for transmission of electricity operation monitoring

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