CN115586792B - Unmanned aerial vehicle power inspection system and method based on iron tower parameters - Google Patents
Unmanned aerial vehicle power inspection system and method based on iron tower parameters Download PDFInfo
- Publication number
- CN115586792B CN115586792B CN202211212809.1A CN202211212809A CN115586792B CN 115586792 B CN115586792 B CN 115586792B CN 202211212809 A CN202211212809 A CN 202211212809A CN 115586792 B CN115586792 B CN 115586792B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- cable line
- parameters
- iron tower
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 title claims abstract description 90
- 229910052742 iron Inorganic materials 0.000 title claims abstract description 45
- 238000007689 inspection Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000005856 abnormality Effects 0.000 claims description 16
- 238000013145 classification model Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 229920003023 plastic Polymers 0.000 claims description 7
- 239000004033 plastic Substances 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 230000009194 climbing Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000005484 gravity Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electric Cable Installation (AREA)
Abstract
The application discloses unmanned aerial vehicle power inspection method and system based on iron tower parameters, comprising the following steps: determining a cable line of unmanned aerial vehicle inspection; acquiring parameters of an iron tower and the cable line; calculating curve representation of the cable line according to the starting point positioning coordinates, the ending point positioning coordinates and the cable line sag parameters; selecting points in the curve as positioning points at certain intervals, converting out coordinates of each positioning point, and outputting a coordinate value set of the cable line from near to far according to the distance between the positioning points and the positioning coordinates of the starting point; adding an offset to each parameter in the output cable line coordinate set to obtain a flight coordinate set; uploading the flight coordinate set to the unmanned aerial vehicle, so that the unmanned aerial vehicle flies and shoots along each coordinate in the flight coordinate set in sequence. The scheme can realize the inspection of the cable line with higher automation degree.
Description
Technical Field
The application relates to image recognition and unmanned aerial vehicle technology, in particular to an unmanned aerial vehicle power inspection system and method based on iron tower parameters.
Background
A large part of high-voltage cables are deployed in suburbs, and the high-voltage cables are deployed in deep mountain dense forests, so that the inspection difficulty is high. In the past, manual inspection methods, a group of inspection personnel may only be able to perform inspection of one to two towers each day. The difficulty is very high if one wants to check the cable status.
In the current inspection technology, the climbing robot is used for implementing inspection, and the climbing robot has the advantage of stable inspection quality. But is less efficient during the deployment phase of the robot.
In addition, a part adopts an unmanned aerial vehicle inspection mode, and when the unmanned aerial vehicle is inspected, the unmanned aerial vehicle inspection mode is usually only aimed at an iron tower, and the cable part is mostly operated manually. Such inspection efficiency remains to be improved.
Disclosure of Invention
In order to solve at least one of the above problems. Therefore, the invention provides an unmanned aerial vehicle power inspection system and method based on iron tower parameters, so as to realize automatic cable inspection.
The embodiment of the application provides an unmanned aerial vehicle power inspection method based on iron tower parameters, which comprises the following steps:
determining a cable line of unmanned aerial vehicle inspection;
acquiring parameters of an iron tower and the cable line, wherein the parameters comprise a starting point positioning coordinate of the cable line at a first iron tower, a final point positioning coordinate of the cable line at a second iron tower and sag parameters of at least one point of the cable line; the cable line is hung between the first iron tower and the second iron tower;
calculating curve representation of the cable line according to the starting point positioning coordinates, the ending point positioning coordinates and the cable line sag parameters;
selecting points in the curve as positioning points at certain intervals, converting out coordinates of each positioning point, and outputting a coordinate value set of the cable line from near to far according to the distance between the positioning points and the positioning coordinates of the starting point;
adding an offset to each parameter in the output cable line coordinate set to obtain a flight coordinate set;
uploading the flight coordinate set to the unmanned aerial vehicle, so that the unmanned aerial vehicle flies and shoots along each coordinate in the flight coordinate set in sequence.
In some embodiments, the curve representation of the cabling is calculated from the start location coordinates, end location coordinates, and cabling sag parameters, in particular:
determining the midpoints of the starting point positioning coordinates and the ending point positioning coordinates, and determining the midpoint positioning coordinates of the cable line at the position corresponding to the midpoint sag parameters according to the midpoint sag parameters of the cable line;
and solving the curve representation of the cable line by using the three points of the starting point positioning coordinate, the ending point positioning coordinate and the middle point positioning coordinate.
In some embodiments, the midpoint sag parameter is measured by a sag measurement device on the tower or is obtained by looking up a table based on a lookup table determined at the time of construction.
In some embodiments, the method further comprises the steps of:
detecting foreign matters hung by a high-voltage cable according to an image shot by an unmanned aerial vehicle, extracting the outline of a target object from the image shot by the unmanned aerial vehicle, and checking whether the outline of the target object is interrupted in the image, wherein the interruption means that the outline of the target object is interrupted into more than two connected domains;
when the gap width of the interruption is larger than a threshold value, marking abnormality;
and determining the position of the suspected foreign object based on the position of the notch, intercepting a region with a certain size, and sending the region into a classification network for classification.
In some embodiments, the offset is determined according to a cable safety standard.
In some embodiments, the classification network includes: light reflection abnormality classification, branch classification, plastic classification, aircraft classification, kite classification and other sundries classification;
the classification model takes a yoloV4 model as a basic network;
the classification model is obtained after the yoloV4 model is trained through a training set;
the training set sample is obtained by the following steps:
shooting blank background pictures of cables hung with branches, plastics, aircrafts, kites or other sundries for classification, and obtaining a first picture set;
illuminating the cable with a spotlight to shoot a blank background picture containing the cable with partial reflection to obtain a second image set;
the blank background of the pictures in the first picture set and the second picture set is replaced by a background image of the environment where the iron tower is located, a third picture set is obtained, and the third picture set is marked;
and training the yoloV4 model according to the third image set to obtain a classification model.
In some embodiments, the method further comprises the steps of:
before detecting foreign matters hung by a high-voltage cable according to images shot by the unmanned aerial vehicle, determining intervals of picture frames for identifying the foreign matters according to the flying speed of the unmanned aerial vehicle, the set offset and lens parameters;
wherein, the selection interval of the picture frames is smaller than the first time;
the first time is: and dividing the cable line length shot by one frame of picture determined based on the offset and the lens parameters by the quotient of the unmanned aerial vehicle flying speed.
In some embodiments, when an abnormality is detected in the image, a number of image frames including the abnormality location are selected for analysis based on the abnormality location in the current image frame.
Another aspect of the embodiments of the present application discloses an unmanned aerial vehicle power inspection system based on iron tower parameters, which is characterized by comprising:
a memory for storing a program;
and the processor is used for loading the program to execute the method.
In yet another aspect, an embodiment of the present application discloses an unmanned aerial vehicle power inspection system based on tower parameters, including:
the unmanned aerial vehicle is used for executing inspection of the cable line;
and the ground receiving station is used for receiving information returned by the unmanned aerial vehicle and executing the method.
According to the method, firstly, the cable line of the unmanned aerial vehicle inspection is determined, then the parameters of the iron tower and the cable line are obtained, the curve representation of the cable line is calculated through the parameters, the curve representation of the cable line is converted through a curve equation, the positioning coordinates of the cable line passing through can be calculated based on the curve, and the points on the curve are selected as positioning points at certain intervals through the scheme, and certain offset is added, so that the unmanned aerial vehicle can overcome the influence of the radian of the cable line between the iron towers on the shooting under the condition of keeping a safe distance when the unmanned aerial vehicle performs aerial shooting, and therefore aerial photo images with stable and clear quality are obtained under the condition that the unmanned aerial vehicle is not required to be controlled manually, and the inspection with higher degree of automation is achieved.
Drawings
The contents of the drawings are briefly described below.
FIG. 1 is a flow chart of steps of an embodiment of the present application;
fig. 2 is a schematic illustration of a cable line sag of an embodiment of the present application.
Description of the embodiments
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described by embodiments with reference to the drawings in the examples of the present application.
Referring to fig. 1, an unmanned aerial vehicle power inspection method based on iron tower parameters includes:
s1, determining a cable line of unmanned aerial vehicle inspection. And after the cable lines are determined, related iron tower parameters can be acquired according to the lines.
S2, acquiring parameters of the iron towers and the cable lines, wherein the parameters comprise the starting point positioning coordinates of the cable lines on the first iron tower, the ending point positioning coordinates of the cable lines on the second iron tower and sag parameters of at least one point of the cable lines; the cable line is hung between the first iron tower and the second iron tower. As shown in fig. 2, it can be understood that the starting point positioning coordinates can be represented by (x 1, y1, z 1), the x1 and y1 can be actually represented by longitude and latitude data of navigation positioning, and z1 represents the starting point altitude, so that the current industrial unmanned aerial vehicle can reach the centimeter level by adopting GNSS positioning. Similarly, the endpoint location coordinates may also be represented by (x 2, y2, z 2), x2 and y2 may also be represented by latitude and longitude data of the navigational location, and z2 represents the endpoint altitude. z1 and z2 can be determined after assuming the cable. The sag parameter is actually used to determine coordinate information, such as (x 3, y3, z 3), at a point in the middle of the cabling. Of course, since there may be a plurality of sag parameters, including but not limited to, midpoint sag, sag minimum, sag of any point, etc., from these measured parameters, a curve representation of the cable line may be calculated, thereby calculating any point coordinates.
Specifically, in one embodiment, when step S2 is performed, the midpoints of the start positioning coordinate and the end positioning coordinate may be determined, and the midpoint positioning coordinate of the cable line at the position corresponding to the midpoint sag parameter is determined according to the midpoint sag parameter of the cable line. Since the coordinates of the starting point and the ending point on the horizontal plane are determined, the coordinates of the middle point on the horizontal plane can be directly determined, and the coordinates of the middle point arc corresponding to the line can be converted based on the heights of the starting point and the ending point and the length of the end point arc. And solving the curve representation of the cable line by using the three points of the starting point positioning coordinate, the ending point positioning coordinate and the middle point positioning coordinate. The midpoint sag parameter is obtained by measuring a sag measuring device on the iron tower or by looking up a table based on a lookup table measured during construction.
And S3, calculating curve representation of the cable line according to the starting point positioning coordinates, the ending point positioning coordinates and the cable line sag parameters. Since the cabling is subject to gravity, it is in fact in a plane perpendicular to the horizontal plane and assumes a parabolic state. Thus, calculating the curve of the cabling is effectively a problem of solving a parabola in a plane. Based on the above parameters, a parabolic equation can be solved by selecting a minimum of three points.
S4, selecting points in the curve as positioning points according to a certain interval, converting out coordinates of each positioning point, and outputting a coordinate value set of the cable line from near to far according to the distance between the positioning points and the positioning coordinates of the starting point.
In the step, in order to simplify the control difficulty of the unmanned aerial vehicle during flight, positioning points are selected according to a certain interval, the flight between the positioning points is set to be linear flight, and a parabolic state of a cable line can be restored by utilizing a plurality of line segments. The interval selection anchor points may be evenly distributed along the projection of the start and end lines on the horizontal plane, and thus the interval may be a measure on the projection.
And S5, adding an offset to each parameter in the output cable line coordinate set to obtain a flight coordinate set. The offset is used for keeping the distance between the unmanned aerial vehicle and the cable, so that the unmanned aerial vehicle is safe when flying. The setting can thus be made according to the safety regulations of the cabling and the interference situation between the drone and the cable, the offset for each parameter in the set of coordinates being the same, typically a vector projected on the horizontal plane perpendicular to the cabling. For example, the drone may be set to fly 3 meters out of one side of the cabling, or set to fly 5 meters at the top of the cable. The offset needs to be set according to the interference caused by the voltage of the cable to the unmanned aerial vehicle and the safety distance required by the cable itself.
S6, uploading the flight coordinate set to the unmanned aerial vehicle, so that the unmanned aerial vehicle flies and shoots along each coordinate in the flight coordinate set in sequence. After the offset is added, the unmanned aerial vehicle directly flies in sequence according to each point in the flight coordinate set, and the unmanned aerial vehicle can fly according to a straight line between adjacent flight coordinates. Of course, the camera needs to be faced with the cable before flying.
By means of the method, under the condition that manual operation is separated from an unmanned aerial vehicle, in a safe distance, the sag influence of a cable line between iron towers is overcome, stable and complete cable line images are shot, and therefore unmanned aerial vehicle inspection with high automation degree is achieved by utilizing some parameters of the iron towers.
In some embodiments, the data is analyzed by the ground-based receiving station after aerial photography is performed, and the method therefore further comprises the steps of:
according to the method, foreign matters hung by a high-voltage cable are detected from an image shot by an unmanned aerial vehicle, the outline of a target object is extracted from the image shot by the unmanned aerial vehicle, whether the outline of the target object is interrupted in the image is checked, and the interruption means that the outline of the target object is interrupted into more than two connected domains. It should be understood that the above-described manner of detection is adopted because the environment in which the cable is located usually has a complex background and the type and shape of the foreign matter are not certain. Particularly, if a foreign matter such as a branch is hung on a cable in suburbs, the foreign matter can be fused with a background, and the foreground and the background are difficult to distinguish, so that the model cannot correctly detect the foreign matter, or a large number of false positives are generated. Therefore, the contour of the cable line can be identified by using an edge detection algorithm (such as a canny operator adopted in the present embodiment), if a foreign object is hung on the cable, it can shade the cable line as long as a certain volume exists, so that the contour of the cable line is changed from a complete contour penetrating through the picture into two or more segments (connected domains).
And marking abnormality when the gap width of the interruption is larger than a threshold value. In this embodiment, a threshold value is set. To reduce the error detection rate, the threshold may be set to a certain number of pixels.
And determining the position of the suspected foreign object based on the position of the notch, and intercepting a region with a certain size (which can be a set size) to be sent into a classification network for classification. The classification network mainly performs classification of several common items, including plastics, kites, unmanned aerial vehicles, branches, etc. Other categories may be assigned to targets that cannot be classified.
In some embodiments, the classification network includes: light reflection abnormality classification, branch classification, plastic classification, aircraft classification, kite classification and other sundries classification. It should be noted that, the abnormal classification of light reflection refers to that under the irradiation of sunlight, the unmanned aerial vehicle camera can shoot the light reflection part, and the light reflection part and other parts present the difference in brightness and color, which can lead to the edge detection algorithm to be unable to correctly identify the edge when detecting, resulting in detecting the broken cable profile. Accordingly, the false alarm conditions can be eliminated by means of training a model.
In this embodiment, the classification model is based on the yoloV4 model. And then training the yoloV4 model through the training set to obtain the classification model.
The training set sample is obtained by the following steps:
and shooting a blank background picture of a cable hung with branches, plastics, aircrafts, kites or other sundries to obtain a first picture set. In this step, the sample can be obtained relatively simply by photographing a solid background such as green cloth or white cloth, hanging the cable with the foreign matter, and photographing the cable in a blank background (solid background).
And irradiating the cable by using a spotlight to shoot a blank background picture containing the cable with partial reflection, so as to obtain a second image set. The state of the cable line under sunlight irradiation can be simulated by means of light irradiation, and then the samples are obtained by the same shooting method.
And replacing blank backgrounds of pictures in the first picture set and the second picture set with background pictures of the environment where the iron tower is located to obtain a third picture set, and marking the third picture set. Then the background is randomly replaced by image processing software, the environment where the iron tower is positioned is usually grassland, sky, mountain forest and the like, and by randomly replacing the backgrounds, cables for hanging sundries can be rotated and shot from different angles, so that a plurality of training samples can be generated, and the method is suitable for acquiring the training samples in the scene. In this embodiment, the sample is produced by adopting the image enhancement mode mainly considering that the sample of the cable hanging foreign matter is difficult to collect.
And training the yoloV4 model according to the third image set to obtain a classification model.
In some embodiments, to reduce the number of detections and reduce the amount of computation of the ground station, the image frames may be extracted at intervals for analysis, thereby reducing the amount of analysis, and the method further includes the steps of:
before detecting foreign matters hung by the high-voltage cable according to images shot by the unmanned aerial vehicle, determining and selecting intervals of picture frames for identifying the foreign matters according to the flying speed, the set offset and the lens parameters of the unmanned aerial vehicle.
Wherein the selection interval of the picture frames is smaller than the first time.
The first time is: and dividing the cable line length shot by one frame of picture determined based on the offset and the lens parameters by the quotient of the unmanned aerial vehicle flying speed.
It will be appreciated that the drone is flying along the length of the cable (i.e. the heading is parallel to the line between the two towers), so that the length of the cable taken in the frame of the picture is determined given that the distance between the drone and the cable is assumed to be constant and the parameters of the camera of the drone are determined. Since the flight trajectory of the unmanned aerial vehicle is parallel to the plane of the cable course, the unmanned aerial vehicle is assumed to fly at a constant speed, and the distance of the unmanned aerial vehicle at the first time should not exceed the length of the cable captured by one frame. So that no cable portions are left out, there will be an overlap between selected adjacent picture frames. Accordingly, when the shooting time interval of the picture frame is selected, the time interval can be made smaller than the time required for the unmanned aerial vehicle to fly through the cable length shot by one picture frame. The time required is the cable length taken by the image frame divided by the unmanned aerial vehicle's time of flight. Of course, a fault tolerance value is typically reserved. For example, the selection interval of the picture frames is less than 80% of the first time. This ensures that there is an overlap between the image frames used for detection (overlapping means that the same part of the cable is present in both image frames).
In some embodiments, in order to reduce the false detection rate and improve the classification accuracy, image frames containing abnormal positions before and after the image is extracted for analysis in the case that the image detects an abnormality, and when the image is detected to have an abnormality, a plurality of image frames containing abnormal positions before and after the image frame are selected for analysis according to the abnormal positions in the current image frame. Based on the analysis of the foregoing embodiment, the unmanned aerial vehicle may photograph a cable line with a certain length, and when an abnormality occurs in the cable line, the abnormal position may be in some frames of the front and rear frames of the picture, for example, the current foreign object is in the middle of the picture, and then the foreign object may appear in other frames of the picture within a period of time before and after the photographing of the frame of the picture. To ensure accuracy of model recognition, several more frames containing abnormal positions may be extracted for recognition. Thereby improving the accuracy. For example, two frames before and after the occurrence of the abnormal object are additionally extracted, and the foreign object is classified, and when all of them are confirmed as the foreign object, the presence of the foreign object is determined.
Another aspect of the embodiments of the present application discloses an unmanned aerial vehicle power inspection system based on iron tower parameters, which is characterized by comprising:
a memory for storing a program;
and the processor is used for loading the program to execute the method.
In yet another aspect, an embodiment of the present application discloses an unmanned aerial vehicle power inspection system based on tower parameters, including:
the unmanned aerial vehicle is used for executing inspection of the cable line;
ground-based receiving station for receiving information transmitted back by a drone and for performing the method according to any one of claims 1-8.
Note that the above is only a preferred embodiment of the present application and the technical principle applied. Those skilled in the art will appreciate that the present application is not limited to the particular embodiments described herein, but is capable of numerous obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the present application. Therefore, while the present application has been described in connection with the above embodiments, the present application is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the present application, the scope of which is defined by the scope of the appended claims.
Claims (8)
1. An unmanned aerial vehicle power inspection method based on iron tower parameters is characterized by comprising the following steps:
determining a cable line of unmanned aerial vehicle inspection;
acquiring parameters of an iron tower and the cable line, wherein the parameters comprise a starting point positioning coordinate of the cable line at a first iron tower, a final point positioning coordinate of the cable line at a second iron tower and sag parameters of at least one point of the cable line; the cable line is hung between the first iron tower and the second iron tower;
calculating curve representation of the cable line according to the starting point positioning coordinates, the ending point positioning coordinates and the cable line sag parameters;
selecting points in the curve as positioning points at certain intervals, converting out coordinates of each positioning point, and outputting a coordinate value set of the cable line from near to far according to the distance between the positioning points and the positioning coordinates of the starting point;
adding an offset to each parameter in the output cable line coordinate set to obtain a flight coordinate set;
uploading the flight coordinate set to the unmanned aerial vehicle, so that the unmanned aerial vehicle flies and shoots along each coordinate in the flight coordinate set in sequence;
detecting foreign matters hung by a high-voltage cable according to an image shot by an unmanned aerial vehicle, extracting the outline of a target object from the image shot by the unmanned aerial vehicle, and checking whether the outline of the target object is interrupted in the image, wherein the interruption means that the outline of the target object is interrupted into more than two connected domains;
when the gap width of the interruption is larger than a threshold value, marking abnormality;
determining the position of a suspected foreign object based on the position of the notch, intercepting a region with a certain size, and sending the region into a classification network for classification;
the classification network comprises the following steps: light reflection abnormality classification, branch classification, plastic classification, aircraft classification, kite classification and other sundries classification;
the classification model takes a yoloV4 model as a basic network;
the classification model is obtained after the yoloV4 model is trained through a training set;
the training set sample is obtained by the following steps:
shooting blank background pictures of cables hung with branches, plastics, aircrafts, kites or other sundries for classification, and obtaining a first picture set;
illuminating the cable with a spotlight to shoot a blank background picture containing the cable with partial reflection to obtain a second image set;
the blank background of the pictures in the first picture set and the second picture set is replaced by a background image of the environment where the iron tower is located, a third picture set is obtained, and the third picture set is marked;
and training the yoloV4 model according to the third image set to obtain a classification model.
2. The unmanned aerial vehicle power inspection method based on iron tower parameters of claim 1, wherein the curve representation of the cable line is calculated according to the start point positioning coordinates, the end point positioning coordinates and the cable line sag parameters, specifically:
determining the midpoints of the starting point positioning coordinates and the ending point positioning coordinates, and determining the midpoint positioning coordinates of the cable line at the position corresponding to the midpoint sag parameters according to the midpoint sag parameters of the cable line;
and solving the curve representation of the cable line by using the three points of the starting point positioning coordinate, the ending point positioning coordinate and the middle point positioning coordinate.
3. The unmanned aerial vehicle power inspection method based on iron tower parameters according to claim 2, wherein the midpoint sag parameter is measured by a sag measurement device on the iron tower or is obtained based on a lookup table determined during construction.
4. The method for unmanned aerial vehicle power inspection based on iron tower parameters of claim 1, wherein the offset is determined according to a cable safety standard.
5. The method for unmanned aerial vehicle power inspection based on iron tower parameters of claim 1, further comprising the steps of:
before detecting foreign matters hung by a high-voltage cable according to images shot by the unmanned aerial vehicle, determining intervals of picture frames for identifying the foreign matters according to the flying speed of the unmanned aerial vehicle, the set offset and lens parameters;
wherein, the selection interval of the picture frames is smaller than the first time;
the first time is: and dividing the cable line length shot by one frame of picture determined based on the offset and the lens parameters by the quotient of the unmanned aerial vehicle flying speed.
6. The unmanned aerial vehicle power inspection method based on iron tower parameters according to claim 5, wherein when an abnormality is detected in the image, a plurality of image frames including the abnormality position before and after the abnormality position are selected for analysis according to the abnormality position in the current image frame.
7. Unmanned aerial vehicle power inspection system based on iron tower parameter, characterized by comprising:
a memory for storing a program;
a processor for loading the program to perform the method of any of claims 1-6.
8. Unmanned aerial vehicle power inspection system based on iron tower parameter, characterized by comprising:
the unmanned aerial vehicle is used for executing inspection of the cable line;
a ground-based receiving station for receiving information transmitted back by a drone and for performing the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211212809.1A CN115586792B (en) | 2022-09-30 | 2022-09-30 | Unmanned aerial vehicle power inspection system and method based on iron tower parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211212809.1A CN115586792B (en) | 2022-09-30 | 2022-09-30 | Unmanned aerial vehicle power inspection system and method based on iron tower parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115586792A CN115586792A (en) | 2023-01-10 |
| CN115586792B true CN115586792B (en) | 2023-06-27 |
Family
ID=84777872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211212809.1A Active CN115586792B (en) | 2022-09-30 | 2022-09-30 | Unmanned aerial vehicle power inspection system and method based on iron tower parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115586792B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520274A (en) * | 2018-03-27 | 2018-09-11 | 天津大学 | High reflecting surface defect inspection method based on image procossing and neural network classification |
| CN110751630A (en) * | 2019-09-30 | 2020-02-04 | 山东信通电子股份有限公司 | Power transmission line foreign matter detection method and device based on deep learning and medium |
| CN111967323A (en) * | 2020-07-16 | 2020-11-20 | 电子科技大学 | Electric power live working safety detection method based on deep learning algorithm |
| WO2022099598A1 (en) * | 2020-11-13 | 2022-05-19 | 浙江大学 | Video dynamic target detection method based on relative statistical features of image pixels |
| CN114723675A (en) * | 2022-03-17 | 2022-07-08 | 武汉飞流智能技术有限公司 | Photovoltaic module detection method, device, equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559360B (en) * | 2013-11-13 | 2017-01-04 | 云南电网公司昭通供电局 | The construction method of a kind of three-dimensional overhead electrical power line model and system |
| EP3506148A4 (en) * | 2016-08-25 | 2019-07-24 | China Communication Technology Co., Ltd. | Millimetre wave image-based human body foreign matter detection method and system |
| CN108734143A (en) * | 2018-05-28 | 2018-11-02 | 江苏迪伦智能科技有限公司 | A kind of transmission line of electricity online test method based on binocular vision of crusing robot |
| CN111474957A (en) * | 2020-05-07 | 2020-07-31 | 重庆工程学院 | Transmission line inspection unmanned aerial vehicle system based on deep learning |
| CN111552319B (en) * | 2020-05-18 | 2023-03-28 | 广东电网有限责任公司 | Overhead transmission line conductor tracking and patrolling method and related device |
| CN111738307A (en) * | 2020-06-02 | 2020-10-02 | 国网宁夏电力有限公司检修公司 | Foreign matter identification method and system in power transmission line environment based on fast RCNN and computer readable storage medium |
| CN112489018B (en) * | 2020-11-30 | 2024-05-28 | 深圳供电局有限公司 | Intelligent line inspection method and line inspection method for power line |
-
2022
- 2022-09-30 CN CN202211212809.1A patent/CN115586792B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520274A (en) * | 2018-03-27 | 2018-09-11 | 天津大学 | High reflecting surface defect inspection method based on image procossing and neural network classification |
| CN110751630A (en) * | 2019-09-30 | 2020-02-04 | 山东信通电子股份有限公司 | Power transmission line foreign matter detection method and device based on deep learning and medium |
| CN111967323A (en) * | 2020-07-16 | 2020-11-20 | 电子科技大学 | Electric power live working safety detection method based on deep learning algorithm |
| WO2022099598A1 (en) * | 2020-11-13 | 2022-05-19 | 浙江大学 | Video dynamic target detection method based on relative statistical features of image pixels |
| CN114723675A (en) * | 2022-03-17 | 2022-07-08 | 武汉飞流智能技术有限公司 | Photovoltaic module detection method, device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| Surface defect detection of electric power equipment in substation based on improved yolov4 algorithm;Xiaojiao Chen;2020 10th international conference on power and energy systems;全文 * |
| 基于卷积神经网络的输电线路金具缺陷检测方法;裘瑾怡;自动化与信息工程;36-41+47 * |
| 自然光照影响下基于深度卷积神经网络和颜色迁移的杂草识别方法;温德圣;许燕;周建平;樊湘鹏;刘洋;;中国科技论文(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115586792A (en) | 2023-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
| JP7045030B2 (en) | Inspection system, inspection method, server equipment, and program | |
| CN111402541A (en) | Forest fire extinguishing method and system based on unmanned aerial vehicle cluster | |
| CN110910341B (en) | Method and device for detecting defects of rusted areas of power transmission line | |
| CN105957109A (en) | Target tracking method and device | |
| US11132802B2 (en) | Method of detecting moving objects from a temporal sequence of images | |
| CN110493524A (en) | A kind of survey light method of adjustment, device, equipment and storage medium | |
| CN112950634A (en) | Method, equipment and system for identifying damage of wind turbine blade based on unmanned aerial vehicle routing inspection | |
| WO2022247597A1 (en) | Papi flight inspection method and system based on unmanned aerial vehicle | |
| CN115035141A (en) | Tunnel crack remote monitoring and early warning method based on image processing | |
| CN115937746A (en) | Smoke and fire event monitoring method and device and storage medium | |
| CN112365763B (en) | Unmanned aerial vehicle inspection training method and system for power equipment | |
| CN112861676B (en) | Smoke and fire identification marking method, system, terminal and storage medium | |
| CN114266737A (en) | Defect detection method, device, equipment and storage medium | |
| CN115586792B (en) | Unmanned aerial vehicle power inspection system and method based on iron tower parameters | |
| CN112580489A (en) | Traffic light detection method and device, electronic equipment and storage medium | |
| KR102514703B1 (en) | An unmanned aerial vehicle for photographing a damaged area of a structure using a plurality of cameras and an apparatus for inspecting damage to a structure using the same | |
| CN114740878B (en) | Unmanned aerial vehicle flight obstacle detection method based on computer image recognition | |
| JP6934386B2 (en) | Moving object tracking device and its program | |
| Majidi et al. | Real time aerial natural image interpretation for autonomous ranger drone navigation | |
| CN115755946A (en) | Power inspection method, device and system based on digital twinning | |
| CN114140707A (en) | Power grid fault inspection method | |
| CN113920089A (en) | Target detection method and device and electronic controller | |
| CN116027798B (en) | Unmanned aerial vehicle power inspection system and method based on image correction | |
| Shahbazi et al. | Vehicle Tracking and Speed Estimation from Unmanned Aerial Videos |
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 |