CN115547003A - External damage prevention alarm method and system for power transmission line - Google Patents
External damage prevention alarm method and system for power transmission line Download PDFInfo
- Publication number
- CN115547003A CN115547003A CN202211479289.0A CN202211479289A CN115547003A CN 115547003 A CN115547003 A CN 115547003A CN 202211479289 A CN202211479289 A CN 202211479289A CN 115547003 A CN115547003 A CN 115547003A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- monitoring equipment
- surrounding environment
- cloud data
- suspicious
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000002265 prevention Effects 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 claims abstract description 103
- 238000009434 installation Methods 0.000 claims abstract description 85
- 238000013135 deep learning Methods 0.000 claims abstract description 31
- 230000004888 barrier function Effects 0.000 claims abstract description 12
- 238000012806 monitoring device Methods 0.000 claims description 34
- 238000013145 classification model Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 238000009616 inductively coupled plasma Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses an external damage prevention alarm method and system for a power transmission line, wherein the external damage prevention alarm method for the power transmission line comprises the following steps: scanning the surrounding environment of the installation of the monitoring equipment by using an unmanned airborne radar to obtain base map three-dimensional point cloud; calibrating the installation position of the monitoring equipment according to the base map three-dimensional point cloud to obtain the position and attitude information of the monitoring equipment; according to the position posture information, the laser radar and the video camera respectively capture point cloud data and video images of the surrounding environment; judging whether suspicious fault targets exist in the surrounding environment according to the foreground point cloud in the point cloud data; if yes, performing graded alarm according to the alarm grade distance range of the moving distance between the suspicious fault target and the transmission line coordinate; and carrying out deep learning on the video image of the suspicious fault target to obtain the barrier type. The technical scheme of the invention can solve the problems of low detection efficiency and poor judgment accuracy of the external damage prevention risk in the prior art.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to an external damage prevention alarm method and system for a power transmission line.
Background
In the operation process of the power facility, many transmission lines have the problems of disconnection, tripping and the like due to external force damage, so that the safe operation of the power equipment is threatened greatly. Along with the increase of urban power consumption, the power transmission line is also increasingly complex, correspondingly, the external force damage events of the power transmission line occur frequently, and in order to ensure the power utilization safety, the external force damage prevention (external damage prevention for short) capability of the power transmission line becomes the central importance of the line operation work.
At present, a manual inspection mode is mainly adopted for an external damage prevention mode in the operation of a power grid, and the mode has large workload and low efficiency; in order to solve the problems, the prior art provides a power transmission line laser radar point cloud acquisition and external damage prevention real-time monitoring method, which aims at a power transmission line channel to be monitored in a long distance; then, the laser radar scans for multiple times to obtain point cloud data of the power transmission line channel, and high-density point cloud data are obtained; separating the power transmission line point cloud data and the non-power transmission line point cloud data and storing the data; scanning a power transmission line channel by using a laser radar, and acquiring point cloud data of the power transmission line channel in real time; and then, according to the point cloud data of the power transmission line, the point cloud data of a single power transmission conductor is obtained, whether other point cloud data exist in a safety range or not is searched for at an interval distance set by a user along the erection direction of the conductor, and whether the power transmission line has an external damage risk or not is judged.
However, the method mainly adopts deep learning to obtain the point cloud processing model, adopts the laser radar point cloud mode for processing, detects by utilizing the deep learning, has higher requirements on model training and scenes, and cannot truly simulate the geographic information corresponding to the point cloud. Therefore, the external damage prevention mode can cause low external damage prevention monitoring efficiency, poor judgment accuracy of external damage prevention risks and the like.
Disclosure of Invention
The invention provides an external damage prevention alarm scheme for an electric power facility, and aims to solve the problems that the external damage prevention detection efficiency is low and the judgment accuracy of external damage prevention risks is poor in a transmission line external damage prevention monitoring method provided by the prior art.
In order to achieve the above object, according to a first aspect of the present invention, the present invention provides an external damage prevention alarm method for a power transmission line, the method is used for an external damage prevention alarm system for a power transmission line, the external damage prevention alarm system comprises a monitoring device, and a laser radar and a video camera mounted on the monitoring device; the external damage prevention alarm method comprises the following steps:
scanning the installation surrounding environment of the monitoring equipment by using an unmanned airborne radar to obtain a base map three-dimensional point cloud, wherein the base map three-dimensional point cloud comprises the coordinates of the power transmission line in the installation surrounding environment;
calibrating the installation position of the monitoring equipment according to the base map three-dimensional point cloud to obtain the position and attitude information of the monitoring equipment;
according to the position and posture information of the monitoring equipment, shooting point cloud data of the surrounding environment by using a laser radar, and shooting a video image of the surrounding environment by using a video camera;
judging whether suspicious fault targets exist in the surrounding environment according to the foreground point cloud in the point cloud data;
when the suspicious fault target exists in the surrounding environment, the suspicious fault target is subjected to graded alarm according to the alarm grade distance range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line;
and carrying out deep learning on the image area of the suspicious fault target in the video image, and detecting to obtain the barrier type corresponding to the suspicious fault target.
Preferably, in the method for alarming against external damage, the step of calibrating the installation position of the monitoring device according to the base map three-dimensional point cloud includes:
using an RTK technology to perform dotting operation on the installation position of the monitoring equipment to obtain a geographic coordinate corresponding to the installation position;
collecting point cloud data of the surrounding environment by using a laser radar of monitoring equipment;
and matching the point cloud data and the base map three-dimensional point cloud according to the geographic coordinates corresponding to the installation position to obtain the position and attitude information of the monitoring equipment.
Preferably, the method for alarming for preventing the external damage comprises the step of matching point cloud data with base map three-dimensional point cloud according to the geographic coordinate corresponding to the installation position to obtain the position and posture information of the monitoring equipment, and comprises the following steps:
rotating and translating the point cloud data according to the geographic coordinates corresponding to the installation position so as to enable the point cloud data to be matched with the three-dimensional point cloud position of the base map;
extracting a transformation matrix of the point cloud data;
carrying out ICP registration on the point cloud data and the point cloud of the overlapped part of the base map three-dimensional point cloud to obtain a new transformation matrix;
and calculating the position and attitude information of the monitoring device by using the new transformation matrix.
Preferably, after the step of performing a classification alarm on the suspected fault object, the method further includes:
establishing geographic information of the monitoring equipment by using position and attitude information of the monitoring equipment and a video image of the surrounding environment, which is shot by a video camera;
and storing and displaying the geographic information of the monitoring equipment.
Preferably, the external damage prevention alarm method includes the step of performing a graded alarm on the suspicious fault target according to an alarm grade distance range corresponding to a moving distance between the suspicious fault target and the transmission line coordinate, and includes:
when the moving distance is within the distance range of the first alarm level, prompting a suspicious fault target;
when the moving distance is within the distance range of the second alarm level, uploading point cloud data and video images of the suspicious fault target;
and when the moving distance is within the distance range of the third alarm level, uploading the equipment information of the monitoring equipment to a server.
Preferably, the anti-external-damage alarm method, which performs deep learning on the image region of the suspected fault target in the video image, includes:
establishing a deep learning network classification model;
training the deep learning network classification model by using a fault target training set until the loss function of the deep learning network classification model is converged;
and inputting the image area of the suspicious fault target into a deep learning network classification model with loss function convergence, and outputting the obstacle type of the suspicious fault target.
Preferably, the anti-external-damage alarm method, before the step of judging whether the suspicious fault target exists in the installation surrounding environment according to the foreground point cloud in the point cloud data, further includes:
denoising the point cloud data to obtain a denoised point cloud pattern;
comparing an overlapping area by using base map three-dimensional point cloud or historical point cloud data and the denoised point cloud pattern;
marking the part of the denoised point cloud pattern and the base map three-dimensional point cloud or the historical point cloud data in the overlapping area as background point cloud;
marking the part of the denoised point cloud pattern, the base map three-dimensional point cloud or the historical point cloud data without an overlapping area as a foreground point cloud;
and extracting foreground point cloud in the denoised point cloud pattern, and adding the point cloud pattern into historical point cloud data.
Preferably, the anti-external-damage alarm method includes the step of judging whether a suspicious fault target exists in the installation surrounding environment according to the foreground point cloud in the point cloud data, and includes:
carrying out size filtering and neighbor searching on the foreground point cloud, and eliminating isolated noise points and tiny noise points in the foreground point cloud to obtain a filtered suspicious obstacle target;
and taking the filtered suspicious obstacle target as a seed, performing region growth in the foreground point cloud, and extracting a point cloud region with corresponding characteristics of the effective suspicious fault target from the foreground point cloud.
According to a second aspect of the invention, the invention also provides an external damage prevention alarm system of the power transmission line, which comprises an unmanned aerial vehicle-mounted radar, monitoring equipment, a laser radar and a video camera, wherein the laser radar and the video camera are carried on the monitoring equipment; wherein, the first and the second end of the pipe are connected with each other,
the system comprises an unmanned airborne radar, a monitoring device and a monitoring system, wherein the unmanned airborne radar is used for scanning the installation surrounding environment of the monitoring device to obtain a base map three-dimensional point cloud, and the base map three-dimensional point cloud comprises the coordinates of a power transmission line in the installation surrounding environment;
the laser radar is also used for shooting point cloud data of the surrounding environment,
the video camera is used for shooting a video image of the surrounding environment;
the monitoring equipment is used for judging whether suspicious fault targets exist in the surrounding environment according to the foreground point cloud in the point cloud data;
the monitoring equipment is also used for carrying out graded alarm on the suspicious fault target according to an alarm grade distance range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line when the suspicious fault target is judged to exist in the surrounding environment;
and the monitoring equipment is also used for carrying out deep learning on the image area of the suspicious fault target in the video image and detecting to obtain the barrier type corresponding to the suspicious fault target.
Preferably, the external-damage-prevention alarm system further includes:
the monitoring equipment is also used for carrying out dotting operation on the installation position of the monitoring equipment by using an RTK technology to obtain a geographic coordinate corresponding to the installation position;
the laser radar is also used for acquiring point cloud data of the surrounding environment;
and the monitoring equipment is also used for matching the point cloud data and the base map three-dimensional point cloud according to the geographic coordinate corresponding to the installation position to obtain the position and attitude information of the monitoring equipment.
In summary, according to the anti-external-damage alarm scheme for the power transmission line provided by the invention, the installation surrounding environment of the monitoring equipment is scanned by using the unmanned airborne radar, so that the base map three-dimensional point cloud of the installation surrounding environment is obtained, wherein the base map three-dimensional point cloud comprises the coordinates of the power transmission line in the installation surrounding environment; and then, capturing point cloud data in the surrounding environment by using a laser radar of the monitoring device, simultaneously capturing a video image in the surrounding environment by using a video camera, judging whether a suspicious fault target exists in the surrounding environment according to foreground point cloud in the point cloud data, and carrying out grading alarm on the suspicious fault target according to an alarm level range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line when the suspicious fault target exists, so that the distance between the power transmission line and the suspicious fault target can be rapidly detected in a point cloud coordinate mode. The external damage prevention alarm mode can solve the problems that the detection efficiency is low and the judgment accuracy of the external damage prevention risk is poor in a mode of obtaining a point cloud processing model by using deep learning in the background technology.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a first method for alarming against external damage of a power transmission line according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for calibrating an installation position of a monitoring device according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of a method for acquiring position and attitude information of a monitoring device according to the embodiment shown in fig. 2;
fig. 4 is a schematic flow chart of a second method for alarming external damage to a power transmission line according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating a method for alarming in a hierarchy of suspicious failure targets according to the embodiment shown in FIG. 1;
FIG. 6 is a flowchart illustrating a method for deep learning of image regions of a suspected faulty target according to the embodiment shown in FIG. 1;
fig. 7 is a schematic flowchart of a third method for alarming against external damage of a power transmission line according to an embodiment of the present invention;
FIG. 8 is a flowchart illustrating a method for determining a possible failure target according to the embodiment shown in FIG. 1;
fig. 9 is a schematic structural diagram of geographic information of a monitoring device according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of an external damage prevention alarm system for a power transmission line according to an embodiment of the present invention.
The objects, features and advantages of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention mainly solves the technical problems that:
according to the method for collecting the laser radar point cloud and monitoring the anti-external damage of the power transmission line in the prior art, a point cloud processing model is obtained mainly through deep learning, the point cloud processing model is processed in a laser radar point cloud mode, deep learning is utilized for detection, requirements on model training and scenes are high, and geographic information corresponding to the point cloud cannot be simulated really. Therefore, the external damage prevention mode can cause low external damage prevention monitoring efficiency, poor judgment accuracy of external damage prevention risks and the like.
In order to solve the above problems, embodiments of the present invention provide an anti-external-damage alarm scheme for a power transmission line, where a laser radar and a camera device mounted on a monitoring device are used to monitor a surrounding environment, and when a dangerous suspicious obstacle is detected, alarm information is transmitted to a background server to perform services such as alarm, summarization, display, and reminding, so as to improve the anti-external-damage detection efficiency, improve the accuracy of judging the anti-external-damage risk, and timely perform the anti-external-damage alarm reminding.
To achieve the above purpose, referring to fig. 1 in particular, fig. 1 is a schematic flow chart of an external damage prevention alarm method for a power transmission line according to an embodiment of the present invention. As shown in fig. 1, the method is used for an external damage prevention alarm system of a power transmission line, and the external damage prevention alarm system comprises monitoring equipment, a laser radar and a video camera which are carried on the monitoring equipment; the external damage prevention alarm method comprises the following steps:
s110: scanning the installation surrounding environment of the monitoring equipment by using the unmanned airborne radar to obtain a base map three-dimensional point cloud, wherein the base map three-dimensional point cloud comprises the coordinates of the power transmission line in the installation surrounding environment. Laser radar and video camera all carry on monitoring facilities to monitoring facilities direct monitoring transmission line, therefore laser radar scans monitoring facilities's installation all ring border environment, can acquire the environment image including monitoring facilities and transmission line etc.. The base map three-dimensional point cloud can also be used for comparing with a laser point cloud scanned by a laser radar later and searching a suspicious fault target.
In addition, after the step of scanning the surrounding environment of the monitoring equipment by the laser radar, the laser radar of the monitoring equipment is used for acquiring point cloud data, and the position coordinate matching of the feature objects is carried out by combining the base map three-dimensional point cloud acquired by the unmanned airborne radar, so that the mounting position of the monitoring equipment is calibrated, and the position posture information of the monitoring equipment is obtained. By extracting the coordinates of the power transmission line to be monitored and then installing and calibrating the monitoring equipment, the position and the attitude of the monitoring equipment can be obtained, and the geographic information of the data acquired by the current monitoring equipment is further established, so that the geographic scene comprising the monitoring equipment, the laser radar, the video camera and the power transmission line is fed back in the form of a video image. The browsing and viewing mode established based on the geographic information can be intuitively positioned to the monitoring equipment terminal, so that the upper computer can conveniently carry out unified management and viewing on a plurality of monitoring equipment.
S120: and according to the position posture information of the monitoring equipment, capturing point cloud data of the surrounding environment by using a laser radar, and capturing a video image of the surrounding environment by using a video camera. Laser radar and video camera all install on monitoring facilities, consequently behind the position gesture information of acquireing monitoring facilities, can the coordinate position of accurate adjustment laser radar and video camera, control laser radar and video camera carry out data acquisition according to the mode that sets up in advance, carry out the preliminary treatment with the point cloud data of gathering, and use video camera to shoot the video image of installation all ring border environment, use point cloud data and video image to compare like this and verify, judge whether there is suspicious trouble target, improve suspicious trouble target's inspection precision.
S130: and judging whether suspicious fault targets exist in the surrounding environment according to the foreground point cloud in the point cloud data. In the point cloud data provided by the embodiment of the application, the background point cloud is an overlapped part between the point cloud data acquired in real time and the historical point cloud or the base map three-dimensional point cloud, the foreground point cloud covers the original overlapped part, namely the part covering the original background point cloud in the historical point cloud or the base map three-dimensional point cloud, and the foreground point cloud reflects an object which is moved in the installation surrounding environment and covers the original environment. If the foreground point cloud exists in the point cloud data, the foreground point cloud can be used for accurately judging that the suspicious fault target exists in the installation surrounding environment.
S140: and when the suspicious fault target exists in the surrounding environment, performing graded alarm on the suspicious fault target according to the alarm grade distance range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line. The three-dimensional coordinates of the three-dimensional point cloud of the suspicious fault target and the three-dimensional coordinates of the power transmission line are subtracted, so that the moving distance between the suspicious fault target and the power transmission line can be calculated, and the suspicious fault target can be subjected to graded alarm by using the alarm grade distance range corresponding to the moving distance. And the risk of external damage prevention of the power transmission line is reduced.
S150: and carrying out deep learning on the image area of the suspicious fault target in the video image, and detecting to obtain the barrier type corresponding to the suspicious fault target.
In summary, according to the method for preventing the external damage to the power transmission line provided by the embodiment of the application, the installation surrounding environment of the monitoring equipment is scanned by using the laser radar, so that the base map three-dimensional point cloud of the installation surrounding environment is obtained, wherein the base map three-dimensional point cloud comprises the coordinates of the power transmission line in the installation surrounding environment; and then, shooting point cloud data in the surrounding environment by using a laser radar, shooting video images in the surrounding environment by using a video camera, judging whether a suspicious fault target exists in the surrounding environment according to foreground point cloud in the point cloud data, and when the suspicious fault target exists, carrying out graded alarm on the suspicious fault target according to an alarm level range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line, so that the distance between the power transmission line and the suspicious fault target can be quickly detected in a point cloud coordinate mode. The external damage prevention alarm mode can solve the problems that the detection efficiency is low and the judgment accuracy of the external damage prevention risk is poor in a mode of obtaining a point cloud processing model by using deep learning in the background technology.
As shown in fig. 2, the step of calibrating the installation position of the monitoring device according to the base map three-dimensional point cloud includes:
s111: and performing dotting operation on the installation position of the monitoring equipment by using an RTK technology to obtain the geographic coordinate corresponding to the installation position. The RTK technology is a real-time dynamic measurement technology, and the technology is a real-time dynamic positioning technology based on a carrier phase observation value, can provide a three-dimensional positioning result of a station under test in a specified coordinate system in real time, and achieves centimeter-level precision. By using the RTK technology to perform dotting operation on the installation position of the monitoring equipment, the geographical coordinate corresponding to the accurate installation position of the monitoring equipment can be obtained, and then the accurate position posture information of the detection equipment is obtained.
S112: and collecting point cloud data of the surrounding environment by using a laser radar of the monitoring equipment. After the installation position of the monitoring equipment is dotted and the geographic coordinate corresponding to the installation position is obtained, the point cloud data of the installation surrounding environment are collected by using the laser radar, the position coordinate of the installation surrounding environment of the monitoring equipment can be accurately obtained, and therefore coordinate calibration is carried out on the installation surrounding environment of the monitoring equipment.
S113: and matching the point cloud data and the base map three-dimensional point cloud according to the geographic coordinates corresponding to the installation position to obtain the position posture information of the monitoring equipment.
According to the technical scheme, the geographical coordinates corresponding to the installation position of the monitoring equipment are obtained, the point cloud data of the surrounding environment are collected and installed through the laser radar, the point cloud data and the base map three-dimensional point cloud are matched according to the geographical coordinates corresponding to the installation position, the position posture information of the monitoring equipment can be accurately obtained, the monitoring equipment is accurately positioned, coordinates of the installation surrounding environment of the monitoring equipment are calibrated, and the three-dimensional coordinates of the power transmission line and the intrusion barrier in the installation surrounding environment are calculated with high accuracy.
As a preferred embodiment, as shown in fig. 3, in the external damage prevention alarm method, step S113: according to the geographic coordinates corresponding to the installation position, matching the point cloud data with the base map three-dimensional point cloud to obtain the position and attitude information of the monitoring equipment, wherein the step of obtaining the position and attitude information of the monitoring equipment specifically comprises the following steps:
s1131: and according to the geographic coordinates corresponding to the installation position, performing rotary translation on the point cloud data so as to enable the point cloud data to be matched with the three-dimensional point cloud position of the base map.
S1132: and extracting a transformation matrix of the point cloud data.
S1133: and carrying out ICP registration on the point cloud data and the overlapped point cloud of the base map three-dimensional point cloud to obtain a new transformation matrix.
S1134: and calculating to obtain the position and posture information of the monitoring equipment by using the new transformation matrix.
According to the technical scheme, the monitoring device is electrified to collect at least one group of point cloud data, manual rough registration and ICP (inductively coupled plasma) precise registration are carried out on the collected point cloud data and the base map three-dimensional point cloud, accurate position and attitude information of the monitoring device can be obtained, the point cloud data collected by the monitoring device are specifically extracted, the point cloud data are subjected to down-sampling processing, then the installation position of the monitoring device is obtained by using an RTK (real-time kinematic) technology, the point cloud data of relative coordinates are subjected to rotational translation, the point cloud data are registered to the position basically matched with the base map three-dimensional point cloud, and a corresponding transformation matrix is obtained. And performing ICP registration on the overlapped part of the point cloud data and the base map three-dimensional point cloud to obtain a new transformation matrix, so as to obtain accurate position and attitude information of the monitoring equipment.
In addition, as a preferred embodiment, as shown in fig. 4, in the external-damage-prevention alarm method, in step S140: after the step of performing a classified alarm on the suspicious fault target, the method further comprises the following steps:
s160: and establishing geographic information of the monitoring equipment by using the position and posture information of the monitoring equipment and the video image of the surrounding environment for installation, which is shot by the video camera.
S170: and storing and displaying the geographic information of the monitoring equipment.
According to the technical scheme, the geographic information including the monitoring equipment and the power transmission line is established by using the position and posture information of the monitoring equipment and the video image of the surrounding environment, which is shot by the video camera. Thus, as shown in fig. 9, by storing and displaying the geographic information of the monitoring device, a browsing and viewing manner can be established based on the geographic information, and the monitoring device can be positioned at the monitoring device side in a more intuitive manner, so that a plurality of monitoring devices can be managed and viewed in a unified manner.
In addition, as a preferred embodiment, as shown in fig. 5, in the above-mentioned external-damage-prevention alarm method, step S140: according to the alarm grade distance range corresponding to the moving distance between the suspicious fault target and the transmission line coordinate, the method for carrying out graded alarm on the suspicious fault target specifically comprises the following steps:
s141: and when the moving distance is within the distance range of the first alarm level, prompting the suspicious fault target. Specifically, a loudspeaker, a light source, a buzzer and the like can be used for performing sound-light alarm to prompt that a barrier target exists, and damage to the power transmission line caused by a suspicious fault target is avoided.
S142: and when the moving distance is within the distance range of the second alarm level, uploading point cloud data and video images of the suspicious fault target. By uploading point cloud data and video images of suspicious fault targets and related alarm information to the server, the server can file alarm results, and later-stage retrieval and query are facilitated.
S143: and when the moving distance is within the distance range of the third alarm level, uploading the equipment information of the monitoring equipment to a server. The equipment information of the monitoring equipment comprises information such as power supply electric quantity and temperature of the monitoring equipment and relevant parameters of an equipment system, and for the monitoring equipment with abnormal conditions, the server sends alarm information to an alarm attendant to process in time, so that the problem of monitoring failure of the equipment due to unfairness of abnormal conditions can be avoided.
According to the technical scheme provided by the embodiment of the application, after the distance calculation is carried out on each fault target, the moving distance between the suspicious fault target and the adjacent power transmission line can be obtained, then the classified alarm processing is carried out according to the set alarm grade distance range, and therefore the alarm grade is higher when the suspicious fault target is closer to the power transmission line.
In addition, as a preferred embodiment, as shown in fig. 6, in the external-damage-prevention alarm method, step S150: the method for deep learning of the image area of the suspicious fault target in the video image specifically comprises the following steps:
s151: and establishing a deep learning network classification model.
S152: and training the deep learning network classification model by using a fault target training set until the loss function of the deep learning network classification model converges.
S153: and inputting the image area of the suspicious fault target into a deep learning network classification model with loss function convergence, and outputting the obstacle type of the suspicious fault target.
According to the technical scheme, the deep learning network classification model is established, and the classification model can be used for convolving the images of the suspicious fault targets, further performing characteristic analysis and classification, and accurately outputting the barrier types corresponding to the suspicious fault targets.
In addition, as a preferred embodiment, as shown in fig. 7, in the above-mentioned external-damage-prevention alarm method, step S130: the method for judging whether the suspicious fault target exists in the installation surrounding environment according to the foreground point cloud in the point cloud data further comprises the following steps:
s310: and denoising the point cloud data to obtain a denoised point cloud pattern. The denoising treatment can comprise the modes of point cloud grid thinning, sunlight noise point removal, water drop noise point removal and the like.
S320: and comparing the overlapping area by using the base map three-dimensional point cloud or historical point cloud data and the denoised point cloud pattern.
S330: and marking the part of the denoised point cloud pattern and the base map three-dimensional point cloud or the historical point cloud data in the overlapped area as background point cloud.
S340: and marking the part of the denoised point cloud pattern, the base map three-dimensional point cloud or the historical point cloud data without an overlapping area as a foreground point cloud.
S350: and extracting foreground point clouds in the denoised point cloud patterns, and adding the point cloud patterns to historical point cloud data.
According to the technical scheme provided by the embodiment of the application, the foreground point cloud and the background point cloud in the point cloud pattern can be separated by comparing the real-time point cloud pattern acquired by the laser radar with the base map three-dimensional point cloud; or comparing the real-time point cloud pattern and the historical point cloud data acquired by the laser radar, and separating the foreground point cloud and the background point cloud in the point cloud pattern. The separation mode of the foreground point cloud and the background point cloud mainly adopts a neighborhood search mode, after the point clouds are rasterized, an overlapping area of the two groups of point clouds is detected, if the overlapping area exists in the two groups of point clouds, the overlapping area is judged to be the background point cloud, otherwise, the non-overlapping area is judged to be the foreground point cloud possibly. And updating the separated foreground point cloud and background point cloud into historical point cloud data to prepare for next judgment.
In addition, as a preferred embodiment, as shown in fig. 8, in the technical solution provided in the embodiment of the present application, the step S130: the method comprises the following steps of judging whether suspicious fault targets exist in the surrounding environment according to foreground point cloud in the point cloud data, and specifically comprises the following steps:
s131: and (3) carrying out size filtering and neighbor searching on the foreground point cloud, and eliminating isolated noise points and tiny noise points in the foreground point cloud to obtain a filtered suspicious obstacle target. Where minor noise points such as 2 x 2 points.
S132: and taking the filtered suspicious obstacle target as a seed, performing region growth in the foreground point cloud, and extracting a point cloud region with corresponding characteristics of the effective suspicious fault target from the foreground point cloud.
According to the technical scheme provided by the embodiment of the application, the filtered point cloud data is subjected to clustering analysis, so that an effective fault target is extracted, specifically, firstly, size filtering and neighbor searching are carried out on a candidate suspicious fault target, and isolated and small noise points in foreground point cloud are removed; and then, by using a region growing mode, taking the detected barrier as a seed, performing region growing on the original point cloud, thereby extracting the point cloud with more abundant characteristics under an effective fault target, and taking a point cloud region corresponding to the suspicious barrier target as an alarm barrier to prepare for uploading.
Based on the same concept of the embodiment of the method, the embodiment of the invention also provides an external damage prevention alarm system for the power transmission line, which is used for realizing the method of the invention.
Referring to fig. 10, fig. 10 is a schematic structural diagram of an external damage prevention alarm system for a power transmission line according to the present invention. As shown in fig. 10, the external-damage-prevention alarm system for the power transmission line includes: a monitoring device 100, and a laser radar 200 and a video camera 300 mounted on the monitoring device 100; in addition, an unmanned airborne radar (not marked in the figure) is also included; wherein the content of the first and second substances,
the unmanned airborne radar is used for scanning the installation surrounding environment of the monitoring equipment 100 to obtain base map three-dimensional point cloud, wherein the base map three-dimensional point cloud comprises the coordinates of the power transmission line in the installation surrounding environment;
the laser radar 200 is also used for shooting point cloud data of the surrounding environment,
a video camera 300 for taking a video image of the installation surrounding environment;
the monitoring equipment 100 is used for judging whether suspicious fault targets exist in the surrounding environment according to the foreground point cloud in the point cloud data;
the monitoring equipment 100 is further configured to perform a graded alarm on the suspicious fault target according to an alarm grade distance range corresponding to a moving distance between the suspicious fault target and the coordinates of the power transmission line when it is determined that the suspicious fault target exists in the surrounding installation environment;
the monitoring device 100 is further configured to perform deep learning on an image region of a suspicious faulty target in the video image, and detect a barrier type corresponding to the suspicious faulty target.
In summary, according to the external damage prevention alarm system for the power transmission line provided by the embodiment of the present application, firstly, an unmanned airborne radar is used to scan the installation surrounding environment of the monitoring device 100, so as to obtain a base map three-dimensional point cloud of the installation surrounding environment, where the base map three-dimensional point cloud includes power transmission line coordinates in the installation surrounding environment; and then capturing point cloud data in the surrounding environment by using a laser radar 200, capturing a video image in the surrounding environment by using a video camera 300, judging whether a suspicious fault target exists in the surrounding environment according to foreground point cloud in the point cloud data, and when the suspicious fault target exists, performing graded alarm on the suspicious fault target according to an alarm level range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line, so that the distance between the power transmission line and the suspicious fault target can be quickly detected in a point cloud coordinate mode. The external damage prevention alarm mode can solve the problems that the detection efficiency is low and the judgment accuracy of the external damage prevention risk is poor in a mode of obtaining a point cloud processing model by using deep learning in the background technology.
In addition, as a preferred embodiment, as shown in fig. 10, in the above-mentioned external-damage-prevention alarm system:
the monitoring device 100 is further configured to perform a dotting operation on the installation position of the monitoring device by using an RTK technique, so as to obtain a geographic coordinate corresponding to the installation position;
the laser radar 200 is also used for collecting point cloud data of the surrounding environment;
the monitoring device 100 is further configured to match the point cloud data with the base map three-dimensional point cloud according to the geographic coordinate corresponding to the installation position, so as to obtain position and attitude information of the monitoring device.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. The external damage prevention alarm method for the power transmission line is characterized by being used for an external damage prevention alarm system of the power transmission line, wherein the external damage prevention alarm system comprises monitoring equipment, a laser radar and a video camera, wherein the laser radar and the video camera are carried on the monitoring equipment; the external damage prevention alarm method comprises the following steps:
scanning the installation surrounding environment of the monitoring equipment by using an unmanned airborne radar to obtain a base map three-dimensional point cloud, wherein the base map three-dimensional point cloud comprises the coordinates of the power transmission line in the installation surrounding environment;
calibrating the installation position of the monitoring equipment according to the base map three-dimensional point cloud to obtain the position and attitude information of the monitoring equipment;
according to the position and posture information of the monitoring equipment, capturing point cloud data of the installation surrounding environment by using the laser radar, and capturing a video image of the installation surrounding environment by using the video camera;
judging whether a suspicious fault target exists in the installation surrounding environment or not according to the foreground point cloud in the point cloud data;
when the suspicious fault target exists in the installation surrounding environment, performing graded alarm on the suspicious fault target according to an alarm grade distance range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line;
and carrying out deep learning on an image area of a suspicious fault target in the video image, and detecting to obtain a barrier type corresponding to the suspicious fault target.
2. The anti-external-damage alarm method according to claim 1, wherein the step of calibrating the installation position of the monitoring device according to the base map three-dimensional point cloud to obtain the position and posture information of the monitoring device comprises:
using an RTK technology to perform dotting operation on the installation position of the monitoring equipment to obtain a geographic coordinate corresponding to the installation position;
collecting point cloud data of the surrounding environment by using a laser radar of the monitoring equipment;
and matching the point cloud data with the base map three-dimensional point cloud according to the geographic coordinates corresponding to the installation position to obtain the position and attitude information of the monitoring equipment.
3. The anti-external-damage alarm method according to claim 2, wherein the step of matching the point cloud data with the base map three-dimensional point cloud according to the geographic coordinates corresponding to the installation position to obtain the position and posture information of the monitoring device comprises:
according to the geographic coordinates corresponding to the installation positions, performing rotational translation on the point cloud data to enable the point cloud data to be matched with the three-dimensional point cloud position of the base map;
extracting a transformation matrix of the point cloud data;
performing ICP registration on the point cloud data and the overlapped point cloud of the base map three-dimensional point cloud to obtain a new transformation matrix;
and calculating to obtain the position and attitude information of the monitoring equipment by using the new transformation matrix.
4. The anti-outburst alarm method of claim 2, wherein after the step of hierarchically alarming the suspected faulty target, the method further comprises:
establishing geographic information of the monitoring device by using position and posture information of the monitoring device and a video image of the installation surrounding environment shot by the video camera;
and storing and displaying the geographic information of the monitoring equipment.
5. The anti-external-damage alarm method according to claim 1, wherein the step of performing a classified alarm on the suspicious faulty target according to an alarm level distance range corresponding to a moving distance between the suspicious faulty target and the coordinates of the power transmission line comprises:
when the moving distance is within a first alarm level distance range, prompting the suspicious fault target;
when the moving distance is within a second alarm level distance range, uploading point cloud data and a video image of the suspicious fault target;
and when the moving distance is within a third alarm level distance range, uploading the equipment information of the monitoring equipment to a server.
6. The anti-theft alarm method according to claim 1, wherein the step of performing deep learning on the image region of the suspected faulty target in the video image comprises:
establishing a deep learning network classification model;
training the deep learning network classification model by using a fault target training set until a loss function of the deep learning network classification model converges;
and inputting the image area of the suspicious fault target into the deep learning network classification model with loss function convergence, and outputting the obstacle type of the suspicious fault target.
7. The anti-external-damage alarm method according to claim 1, wherein before the step of determining whether there is a suspicious fault target in the installation environment according to a foreground point cloud in the point cloud data, the method further comprises:
denoising the point cloud data to obtain a denoised point cloud pattern;
comparing an overlapping region by using the base map three-dimensional point cloud or historical point cloud data and the denoised point cloud pattern;
marking the part of the denoised point cloud pattern and the base map three-dimensional point cloud or historical point cloud data in an overlapping area as background point cloud;
marking the part of the denoised point cloud pattern, which does not have an overlapping area with the base map three-dimensional point cloud or the historical point cloud data, as a foreground point cloud;
and extracting foreground point cloud in the denoised point cloud pattern, and adding the point cloud pattern to the historical point cloud data.
8. The anti-external-damage alarm method according to claim 7, wherein the step of determining whether there is a suspicious fault target in the installation surrounding environment according to a foreground point cloud in the point cloud data comprises:
carrying out size filtering and neighbor searching on the foreground point cloud, and eliminating isolated noise points and tiny noise points in the foreground point cloud to obtain the filtered suspicious obstacle target;
and taking the filtered suspicious obstacle target as a seed, performing region growing in the foreground point cloud, and extracting a point cloud region with corresponding characteristics of the effective suspicious fault target from the foreground point cloud.
9. The external damage prevention alarm system for the power transmission line is characterized by comprising an unmanned aerial vehicle-mounted radar and monitoring equipment, wherein the monitoring equipment is provided with a laser radar and a video camera; wherein, the first and the second end of the pipe are connected with each other,
the unmanned airborne radar is used for scanning the installation surrounding environment of the monitoring equipment to obtain base map three-dimensional point cloud, wherein the base map three-dimensional point cloud comprises the coordinates of the power transmission line in the installation surrounding environment;
the laser radar is used for shooting point cloud data of the surrounding environment,
the video camera is used for shooting a video image of the surrounding environment;
the monitoring equipment is used for judging whether a suspicious fault target exists in the installation surrounding environment according to the foreground point cloud in the point cloud data;
the monitoring equipment is also used for carrying out graded alarm on the suspicious fault target according to an alarm grade distance range corresponding to the moving distance between the suspicious fault target and the coordinates of the power transmission line when the suspicious fault target exists in the installation surrounding environment;
the monitoring device is further configured to perform deep learning on an image region of a suspicious faulty target in the video image, and detect to obtain an obstacle type corresponding to the suspicious faulty target.
10. The anti-vandalism warning system according to claim 9, further comprising:
the monitoring equipment is also used for carrying out dotting operation on the installation position of the monitoring equipment by using an RTK technology to obtain a geographic coordinate corresponding to the installation position;
the laser radar is also used for acquiring point cloud data of the installation surrounding environment;
the monitoring equipment is further used for matching the point cloud data with the base map three-dimensional point cloud according to the geographic coordinates corresponding to the installation positions to obtain position and attitude information of the monitoring equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211479289.0A CN115547003A (en) | 2022-11-24 | 2022-11-24 | External damage prevention alarm method and system for power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211479289.0A CN115547003A (en) | 2022-11-24 | 2022-11-24 | External damage prevention alarm method and system for power transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115547003A true CN115547003A (en) | 2022-12-30 |
Family
ID=84720846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211479289.0A Pending CN115547003A (en) | 2022-11-24 | 2022-11-24 | External damage prevention alarm method and system for power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115547003A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116545122A (en) * | 2023-07-06 | 2023-08-04 | 中国电力科学研究院有限公司 | Power transmission line external damage prevention monitoring device and external damage prevention monitoring method |
| CN117011772A (en) * | 2023-07-31 | 2023-11-07 | 广东电网有限责任公司 | Risk prompting method, device and storage medium for power transmission line |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012079340A (en) * | 2011-12-26 | 2012-04-19 | Toshiba Corp | Suspicious object detection system, suspicious object detection device, suspicious object detection method and program |
| CN114241298A (en) * | 2021-11-22 | 2022-03-25 | 腾晖科技建筑智能(深圳)有限公司 | Tower crane environment target detection method and system based on laser radar and image fusion |
| CN114578374A (en) * | 2022-01-26 | 2022-06-03 | 国网江苏省电力有限公司南京供电分公司 | Power transmission line laser radar point cloud acquisition and external damage prevention real-time monitoring method |
| CN114594490A (en) * | 2022-01-26 | 2022-06-07 | 国网江苏省电力有限公司南京供电分公司 | Laser external damage prevention method and device for power line |
| CN114637026A (en) * | 2022-03-18 | 2022-06-17 | 福建和盛高科技产业有限公司 | Method for realizing online monitoring and intelligent inspection of power transmission line based on three-dimensional simulation technology |
-
2022
- 2022-11-24 CN CN202211479289.0A patent/CN115547003A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012079340A (en) * | 2011-12-26 | 2012-04-19 | Toshiba Corp | Suspicious object detection system, suspicious object detection device, suspicious object detection method and program |
| CN114241298A (en) * | 2021-11-22 | 2022-03-25 | 腾晖科技建筑智能(深圳)有限公司 | Tower crane environment target detection method and system based on laser radar and image fusion |
| CN114578374A (en) * | 2022-01-26 | 2022-06-03 | 国网江苏省电力有限公司南京供电分公司 | Power transmission line laser radar point cloud acquisition and external damage prevention real-time monitoring method |
| CN114594490A (en) * | 2022-01-26 | 2022-06-07 | 国网江苏省电力有限公司南京供电分公司 | Laser external damage prevention method and device for power line |
| CN114637026A (en) * | 2022-03-18 | 2022-06-17 | 福建和盛高科技产业有限公司 | Method for realizing online monitoring and intelligent inspection of power transmission line based on three-dimensional simulation technology |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116545122A (en) * | 2023-07-06 | 2023-08-04 | 中国电力科学研究院有限公司 | Power transmission line external damage prevention monitoring device and external damage prevention monitoring method |
| CN116545122B (en) * | 2023-07-06 | 2023-09-19 | 中国电力科学研究院有限公司 | Power transmission line external damage prevention monitoring device and external damage prevention monitoring method |
| CN117011772A (en) * | 2023-07-31 | 2023-11-07 | 广东电网有限责任公司 | Risk prompting method, device and storage medium for power transmission line |
| CN117011772B (en) * | 2023-07-31 | 2024-04-30 | 广东电网有限责任公司 | Risk prompting method, device and storage medium for power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115547003A (en) | External damage prevention alarm method and system for power transmission line | |
| CN107392247B (en) | Real-time detection method for ground object safety distance below power line | |
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| WO2018028103A1 (en) | Unmanned aerial vehicle power line inspection method based on characteristics of human vision | |
| CN113345019B (en) | Method, equipment and medium for measuring potential hazards of transmission line channel target | |
| CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
| CN107300703B (en) | Radar data networking processing system | |
| CN109829908B (en) | Binocular image-based method and device for detecting safety distance of ground object below power line | |
| CN104050715A (en) | High-precision three-dimensional reconstruction method for power transmission line and corridor | |
| CN115565324A (en) | External damage prevention monitoring method and system for power line | |
| CN114972490B (en) | Automatic data labeling method, device, equipment and storage medium | |
| CN112381041A (en) | Tree identification method and device for power transmission line and terminal equipment | |
| CN116231504A (en) | Remote intelligent inspection method, device and system for booster station | |
| CN112528979A (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN113722870B (en) | Power grid operation full-space monitoring method, system, equipment and medium | |
| Manninen et al. | Multi-stage deep learning networks for automated assessment of electricity transmission infrastructure using fly-by images | |
| CN115649501B (en) | Unmanned aerial vehicle night lighting system and method | |
| CN116052023A (en) | Three-dimensional point cloud-based electric power inspection ground object classification method and storage medium | |
| Sushant et al. | Localization of an unmanned aerial vehicle for crack detection in railway tracks | |
| CN115272815A (en) | Cable tunnel environment abnormity identification method based on image | |
| CN115937086A (en) | Ultrahigh voltage transmission line defect detection method based on unmanned aerial vehicle image recognition technology | |
| JP2024514175A (en) | Bird detection and species determination | |
| CN110910379B (en) | Incomplete detection method and device | |
| CN113850173A (en) | Method, device and medium for eliminating repeated positioning of faulty photovoltaic module | |
| CN112346481A (en) | Method and system for unmanned aerial vehicle power inspection operation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221230 |
|
| RJ01 | Rejection of invention patent application after publication |