CN113433958A - Unmanned aerial vehicle inspection method and device - Google Patents
Unmanned aerial vehicle inspection method and device Download PDFInfo
- Publication number
- CN113433958A CN113433958A CN202110668695.0A CN202110668695A CN113433958A CN 113433958 A CN113433958 A CN 113433958A CN 202110668695 A CN202110668695 A CN 202110668695A CN 113433958 A CN113433958 A CN 113433958A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- photovoltaic module
- photovoltaic
- string
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
Abstract
The invention discloses an unmanned aerial vehicle inspection method and device, wherein the method comprises the following steps: calculating a color characteristic value in a video frame of the video data according to the video data acquired by the unmanned aerial vehicle; converting the video frame into a binary image based on the color feature value; extracting a connected region in the binary image according to the color characteristics, and judging whether the connected region is a photovoltaic module; processing the connected region by a morphological method to obtain a photovoltaic module string; sampling and calculating contour points of the photovoltaic component string to obtain linear information of the upper edge and the lower edge of the photovoltaic component string, and determining a theoretical flight path of the unmanned aerial vehicle according to the linear information; and calculating the arrangement direction of the photovoltaic module string and the distance between the unmanned aerial vehicle and the central point of the photovoltaic module string to adjust the flight direction and the pan-tilt yaw angle in the theoretical flight path convergence and control the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic module string. The implementation of the invention can effectively improve the inspection effect.
Description
Technical Field
The invention relates to the technical field of electric power overhaul, in particular to an unmanned aerial vehicle inspection method and device.
Background
Under the background of low-carbon economy and sustainable development, new energy represented by photovoltaic energy will continuously lead the development of energy industry. Meanwhile, the generated power of the photovoltaic module is seriously degraded, so that effective inspection and operation and maintenance means are urgently needed, and the power generation benefit of the photovoltaic power station is guaranteed. At present, the inspection mode of the centralized photovoltaic power station is mainly manual inspection. In recent years, the unmanned aerial vehicle is used for carrying a visible light camera and an infrared camera to inspect photovoltaic power stations, but most unmanned aerial vehicles adopt GPS navigation positioning for inspection. For unmanned aerial vehicle routing inspection adopting GPS navigation positioning, in a centralized photovoltaic power station environment with a complex regional environment and a large installed capacity, the situation that GPS signals are weak or accuracy is not high exists, and GPS navigation is difficult to meet requirements generally, so that the routing inspection effect is poor.
Disclosure of Invention
The invention provides an unmanned aerial vehicle inspection method and device, and aims to solve the technical problem that the conventional unmanned aerial vehicle inspection method is poor in inspection effect.
The first embodiment of the invention provides an unmanned aerial vehicle inspection method, which comprises the following steps:
calculating a color characteristic value of each pixel point in a video frame of the video data according to the video data acquired by the unmanned aerial vehicle, wherein the color characteristic value is a color characteristic value of the photovoltaic module;
converting the video frame into a binary image based on the color feature values;
extracting a connected region in the binary image according to the color features, and judging whether the connected region is a photovoltaic module or not according to the geometric features of the connected region;
after the connected region is judged to be the photovoltaic module, performing morphological processing on the connected region to obtain a photovoltaic module string;
sampling and calculating contour points of the photovoltaic module string to obtain linear information of the upper edge and the lower edge of the photovoltaic module string, and determining a theoretical flight path of the unmanned aerial vehicle according to the linear information;
calculating the arrangement direction of the photovoltaic component string and the distance between the unmanned aerial vehicle and the central point of the photovoltaic component string, adjusting the flight direction and the pan-tilt yaw angle in the theoretical flight path convergence according to the arrangement direction, and controlling the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic component string.
Further, after "according to the projection distance control of unmanned aerial vehicle current position on the photovoltaic module cluster the flying speed of unmanned aerial vehicle" still includes:
and judging whether the current position of the unmanned aerial vehicle is in the boundary of the target inspection area or not, and if so, controlling the unmanned aerial vehicle to execute a turning action.
Further, after "judge according to sub-area summit coordinate set and unmanned aerial vehicle's current position whether unmanned aerial vehicle arrives regional boundary, if, then control unmanned aerial vehicle carries out the action of turning", still include:
and judging whether the unmanned aerial vehicle finishes image acquisition of a target inspection area, if so, stopping controlling the unmanned aerial vehicle to acquire images to finish inspection.
Further, according to the video data that unmanned aerial vehicle gathered, calculate the color eigenvalue of each pixel in the video frame of video data, wherein, color eigenvalue is photovoltaic module's color eigenvalue, specifically is:
the method comprises the steps of obtaining video data collected by the unmanned aerial vehicle, and calculating color characteristic values of the composition colors of the photovoltaic modules in the video data according to different distribution characteristics of the composition colors of the photovoltaic modules in an RGB histogram, wherein the composition colors of the photovoltaic modules comprise blue and black.
Further, the morphological method includes, but is not limited to, expansion processing and corrosion processing, and after the connected region is judged to be a photovoltaic module, the morphological method processing is performed on the connected region to obtain a photovoltaic module string, specifically:
and after the connected region is judged to be the photovoltaic module, performing expansion treatment and corrosion treatment on the connected region, eliminating intervals among different photovoltaic modules, and obtaining a photovoltaic module string.
Further, sampling calculation is performed on contour points of the photovoltaic module string to obtain linear information of the upper edge and the lower edge of the photovoltaic module string, and a theoretical flight path of the unmanned aerial vehicle is determined according to the linear information, specifically:
and acquiring a plurality of contour points of the photovoltaic module string to determine a plurality of line segments, and determining the theoretical flight path of the unmanned aerial vehicle by judging whether the plurality of line segments are collinear according to a preset coordinate system.
Further, judge whether unmanned aerial vehicle's current position is judged to be in the target and patrols and examines regional boundary, if, then control unmanned aerial vehicle carries out the action of turning, specifically is:
acquiring whether the ratio of the pixel value of any point on the binary image of the photovoltaic module string to the total number of pixels of the video frame is within a preset threshold range, if so, judging that the current position of the unmanned aerial vehicle is at the boundary of the target inspection area, and controlling the unmanned aerial vehicle to execute a turning action.
A second embodiment of the present invention provides an unmanned aerial vehicle inspection apparatus, including:
the first calculation module is used for calculating a color characteristic value of each pixel point in a video frame of the video data according to the video data acquired by the unmanned aerial vehicle, wherein the color characteristic value is the color characteristic value of the photovoltaic module;
a conversion module for converting the video frame into a binary image based on the color feature values;
the first judgment module is used for extracting a connected region in the binary image according to the color features and judging whether the connected region is a photovoltaic module or not according to the geometric features of the connected region;
the processing module is used for processing the connected region by a morphological method to obtain a photovoltaic module string after judging that the connected region is a photovoltaic module;
the second calculation module is used for sampling and calculating contour points of the photovoltaic assembly string to obtain linear information of the upper edge and the lower edge of the photovoltaic assembly string and determining a theoretical flight path of the unmanned aerial vehicle according to the linear information;
the adjusting module is used for calculating the arrangement direction of the photovoltaic component string and the distance between the unmanned aerial vehicle and the central point of the photovoltaic component string, adjusting the flight direction and the pan-tilt yaw angle in the convergence of the theoretical flight path according to the arrangement direction, and controlling the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic component string.
Further, still include the second and judge the module, be used for judging whether unmanned aerial vehicle's current position judges to be in the target and patrols and examines regional boundary, if, then control unmanned aerial vehicle carries out the action of turning.
Further, the second judgment module is specifically configured to determine whether a ratio of a pixel value of any one point on the binary image of the photovoltaic module string to a total number of pixels of the video frame is within a preset threshold range, and if so, judge that the current position of the unmanned aerial vehicle is located on a boundary of the target inspection area, and control the unmanned aerial vehicle to execute a turning action.
According to the embodiment of the invention, the photovoltaic power station is patrolled according to the video data acquired by the unmanned aerial vehicle, and whether the photovoltaic module exists in the video frame of the video data is judged according to the color characteristic value of the photovoltaic module, so that the patrolling efficiency of the photovoltaic power station can be effectively improved; according to the embodiment of the invention, the contour points of the photovoltaic module are sampled and calculated by adopting an edge detection method to determine the theoretical flight path of the unmanned aerial vehicle, and the theoretical flight path is adjusted by calculating the flight deviation amount of the unmanned aerial vehicle in actual routing inspection, so that the integrity of image data acquired by the unmanned aerial vehicle can be effectively improved, the accurate position information of the photovoltaic module can be obtained, and the routing inspection effect can be effectively improved.
Drawings
Fig. 1 is a schematic flow diagram of an unmanned aerial vehicle inspection method provided by an embodiment of the invention;
fig. 2 is a schematic structural diagram of an unmanned aerial vehicle inspection device provided by the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the description of the present application, it is to be understood that the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless otherwise specified.
In the description of the present application, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
Referring to fig. 1, a first embodiment of the present invention provides an unmanned aerial vehicle inspection method, including:
s1, calculating color characteristic values of all pixel points in a video frame of the video data according to the video data acquired by the unmanned aerial vehicle, wherein the color characteristic values are color characteristic values of the photovoltaic module;
s2, converting the video frame into a binary image based on the color characteristic value;
s3, extracting a connected region in the binary image according to the color features, and judging whether the connected region is a photovoltaic module according to the geometric features of the connected region;
s4, after the connected region is judged to be a photovoltaic module, performing morphological processing on the connected region to obtain a photovoltaic module string;
s5, sampling and calculating contour points of the photovoltaic module string to obtain linear information of the upper edge and the lower edge of the photovoltaic module string, and determining a theoretical flight path of the unmanned aerial vehicle according to the linear information;
s6, calculating the arrangement direction of the photovoltaic module string and the distance between the unmanned aerial vehicle and the central point of the photovoltaic module string, adjusting the flight direction and the pan-tilt yaw angle in the theoretical flight path convergence according to the arrangement direction, and controlling the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic module string.
Optionally, in the navigational coordinates, the drone yaw angle θ1Yaw angle theta of pan-tilt2The inclination angle theta of the photovoltaic module in a video frame is acquired in real time through an unmanned aerial vehicle onboard processor3Calculated by the following formula:
θ3＝arctan((ku+kd)/2)；
the arrangement direction of the photovoltaic assembly strings in the navigation coordinate system is as follows:
θ＝θ1+θ2+θ3；
the distance between the unmanned aerial vehicle and the center line of the photovoltaic module string is as follows:
derr＝[(du-dd)/hi]Htan(F/2)cosθ3。
as a specific implementation mode, when the unmanned aerial vehicle is controlled to fly along the direction of the photovoltaic module string in the inspection process of the unmanned aerial vehicle, theta in a video frame is enabled to be achieved3、derrAnd the minimum is realized, so that the integrity of the image information acquired by the unmanned aerial vehicle is improved.
Specifically, the unmanned aerial vehicle pan-tilt angle adjustment amount is:
Δθ2＝θ3
selecting a point s with a projection distance delta from the current position of the unmanned aerial vehicle on the center line of the photovoltaic string as a virtual path point, controlling the flight direction of the unmanned aerial vehicle to face the point s, continuously updating the course, and controllingThe flight speed of the unmanned aerial vehicle is as follows:
according to the embodiment of the invention, the photovoltaic power station is patrolled according to the video data acquired by the unmanned aerial vehicle, and whether the photovoltaic module exists in the video frame of the video data is judged according to the color characteristic value of the photovoltaic module, so that the patrolling efficiency of the photovoltaic power station can be effectively improved; according to the embodiment of the invention, the contour points of the photovoltaic module are sampled and calculated by adopting an edge detection method to determine the theoretical flight path of the unmanned aerial vehicle, and the theoretical flight path is adjusted by calculating the flight deviation amount of the unmanned aerial vehicle in actual routing inspection, so that the integrity of image data acquired by the unmanned aerial vehicle can be effectively improved, the accurate position information of the photovoltaic module can be obtained, and the routing inspection effect can be effectively improved.
As a specific implementation manner of the embodiment of the present invention, after "controlling the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic module string", the method further includes:
judging whether the current position of the unmanned aerial vehicle is in the boundary of the target patrol area or not, and if so, controlling the unmanned aerial vehicle to execute a turning action.
In the embodiment of the invention, when the current position of the unmanned aerial vehicle is judged not to be in the boundary of the target inspection area, the unmanned aerial vehicle is controlled to continuously fly and the image information of the photovoltaic power station is acquired, so that the integral inspection of the photovoltaic power station is realized.
As a specific implementation manner of the embodiment of the present invention, after "determining whether the unmanned aerial vehicle reaches the boundary of the area according to the vertex coordinate set of the sub-area and the current position of the unmanned aerial vehicle, and if so, controlling the unmanned aerial vehicle to execute a turning action", the method further includes:
and judging whether the unmanned aerial vehicle finishes image acquisition of the target inspection area, if so, stopping controlling the unmanned aerial vehicle to acquire images, and finishing inspection.
As a specific implementation manner of the embodiment of the present invention, according to video data acquired by an unmanned aerial vehicle, a color characteristic value of each pixel point in a video frame of the video data is calculated, where the color characteristic value is a color characteristic value of a photovoltaic module, and specifically:
the method comprises the steps of obtaining video data collected by the unmanned aerial vehicle, and calculating color characteristic values of the composition colors of the photovoltaic modules in the video data according to different distribution characteristics of the composition colors of the photovoltaic modules in an RGB histogram, wherein the composition colors of the photovoltaic modules comprise blue and black.
Optionally, the color of the photovoltaic modules is mainly blue and black, the color difference between the photovoltaic modules is related to the module specification and the production process, the color characteristic value of the photovoltaic module is calculated according to different distribution characteristics followed by the RGB histograms of the photovoltaic modules with different colors, and the color characteristic value is expressed by an image characteristic spectrogram, specifically:
wherein R, G, B represents the 3 components of the input image RGB color space, respectively;
the terms 2 on the right side of the equation represent the black and blue eigenvalues of the photovoltaic module, respectively.
Wherein the expression of k is:
after color characteristic values of the constituent colors of the photovoltaic module are obtained through calculation, converting the video frame into a binary image based on the color characteristic values, specifically:
Fi,j≤1
if the above equation is satisfied, the image pixel is 255, otherwise the image pixel is 0.
As a specific implementation manner of the embodiment of the present invention, the morphological method includes, but is not limited to, expansion processing and corrosion processing, and after it is determined that the connected region is a photovoltaic module, the morphological method processing is performed on the connected region to obtain a photovoltaic module string, specifically:
and after the connected region is judged to be the photovoltaic module, performing expansion treatment and corrosion treatment on the connected region, eliminating intervals among different photovoltaic modules, and obtaining the photovoltaic module string.
In the embodiment of the invention, the foreground area of the connected area is expanded by expanding the connected area, so that the interval between the photovoltaic modules is eliminated; the periphery of the photovoltaic module string is conveniently kept consistent with that before expansion through corrosion treatment on the communicated region, so that the accurate photovoltaic module string is obtained.
Specifically, the expression of the dilation process is:
the expression for the etching treatment is:
as a specific implementation manner of the embodiment of the present invention, by sampling and calculating contour points of a photovoltaic module string, linear information of upper and lower edges of the photovoltaic module string is obtained, and a theoretical flight path of an unmanned aerial vehicle is determined according to the linear information, specifically:
the method comprises the steps of obtaining a plurality of contour points of a photovoltaic assembly string to determine a plurality of line segments, and determining the theoretical flight path of the unmanned aerial vehicle by judging whether the plurality of line segments are collinear according to a preset coordinate system.
Specifically, 1 line segment is determined at 2 adjacent sampling points on the photovoltaic module string, the same edge of the photovoltaic module string comprises a plurality of approximately collinear line segments, and on the basis of selecting a proper coordinate system, whether the 2 line segments belong to the same edge of the photovoltaic module string is judged, wherein the judgment formula is as follows:
p＝(1-2|arctank1-arctank2|/π)(1-|b1-b2|/bnor)；
wherein k is1、k2And b1、b2Respectively representing the slope and intercept of 2 straight lines in the same coordinate system; bnorAdapted to a coordinate systemNormalizing the scale; p represents the degree of co-linearity of 2 straight lines. If the 2 line segments are approximately collinear, the slope and the intercept are approximately equal, the 2-term factors on the right side of the equation equal sign are all approximately 1.0, and the conditions are met:
p>pthr
in the formula pthrIndicating a threshold for determining whether the line segments are collinear.
As a specific implementation manner of the embodiment of the present invention, it is determined whether the current position of the unmanned aerial vehicle is located at the boundary of the target inspection area, and if so, the unmanned aerial vehicle is controlled to execute a turning action, specifically:
whether the ratio of the pixel value of any point on the binary image of the photovoltaic module string to the total number of pixels of the video frame is within a preset threshold range or not is obtained, if yes, the current position of the unmanned aerial vehicle is judged to be located on the boundary of the target inspection area, and the unmanned aerial vehicle is controlled to execute a turning action.
Optionally, a boundary vertex coordinate set V of the target inspection area is obtained, and whether the current position of the unmanned aerial vehicle is located at the boundary of the target inspection area is judged by calculating whether a photovoltaic string exists in the video frame, specifically:
∑xi,j/npix≥TPV
wherein x isi，jE {0, 1} is a pixel value of any point (i, j) on the binary image of the photovoltaic group string; n ispixIs the total number of video frame pixels; t isPV∈[0.2，0.3]Is a threshold value.
The judgment condition that the unmanned aerial vehicle reaches the boundary of the target patrol area is as follows: the unmanned aerial vehicle is located outside the target patrol area determined by the set V, and the above formula does not hold. When the unmanned aerial vehicle reaches the boundary of the target inspection area, a turning process needs to be executed; if the unmanned aerial vehicle finishes image acquisition of the whole target inspection area, the inspection process is finished.
According to the embodiment of the invention, whether the current position of the unmanned aerial vehicle reaches the boundary of the target inspection area or not is judged, whether the unmanned aerial vehicle needs to turn or not is controlled, so that the image information of the photovoltaic power station is continuously acquired, the integrity of the image information acquired by the unmanned aerial vehicle in inspection can be effectively improved, and the inspection effect can be effectively improved.
The embodiment of the invention has the following beneficial effects:
according to the embodiment of the invention, the photovoltaic power station is patrolled according to the video data acquired by the unmanned aerial vehicle, and whether the photovoltaic module exists in the video frame of the video data is judged according to the color characteristic value of the photovoltaic module, so that the patrolling efficiency of the photovoltaic power station can be effectively improved; according to the embodiment of the invention, the contour points of the photovoltaic module are sampled and calculated by adopting an edge detection method to determine the theoretical flight path of the unmanned aerial vehicle, and the theoretical flight path is adjusted by calculating the flight deviation amount of the unmanned aerial vehicle in actual routing inspection, so that the integrity of image data acquired by the unmanned aerial vehicle can be effectively improved, the accurate position information of the photovoltaic module can be obtained, and the routing inspection effect can be effectively improved.
Referring to fig. 2, a second embodiment of the present invention provides an unmanned aerial vehicle inspection device, including:
the first calculation module 10 is configured to calculate a color characteristic value of each pixel point in a video frame of video data according to the video data acquired by the unmanned aerial vehicle, where the color characteristic value is a color characteristic value of the photovoltaic module;
a conversion module 20 for converting the video frame into a binary image based on the color feature value;
the first judging module 30 is configured to extract a connected region in the binary image according to the color feature, and judge whether the connected region is a photovoltaic module according to a geometric feature of the connected region;
the processing module 40 is configured to perform morphological processing on the connected region to obtain a photovoltaic module string after the connected region is judged to be a photovoltaic module;
the second calculation module 50 is used for performing sampling calculation on contour points of the photovoltaic module string to obtain linear information of the upper edge and the lower edge of the photovoltaic module string, and determining a theoretical flight path of the unmanned aerial vehicle according to the linear information;
and the adjusting module 60 is used for calculating the arrangement direction of the photovoltaic module string and the distance between the unmanned aerial vehicle and the central point of the photovoltaic module string, adjusting the flight direction and the pan-tilt yaw angle in the theoretical flight path convergence according to the arrangement direction, and controlling the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic module string.
Optionally, in the navigational coordinates, the drone yaw angle θ1Yaw angle theta of pan-tilt2The inclination angle theta of the photovoltaic module in a video frame is acquired in real time through an unmanned aerial vehicle onboard processor3Calculated by the following formula:
θ3＝arctan((ku+kd)/2)；
the arrangement direction of the photovoltaic assembly strings in the navigation coordinate system is as follows:
θ＝θ1+θ2+θ3；
the distance between the unmanned aerial vehicle and the center line of the photovoltaic module string is as follows:
derr＝[(du-dd)/hi]Htan(F/2)cosθ3。
as a specific implementation mode, when the unmanned aerial vehicle is controlled to fly along the direction of the photovoltaic module string in the inspection process of the unmanned aerial vehicle, theta in a video frame is enabled to be achieved3、derrAnd the minimum is realized, so that the integrity of the image information acquired by the unmanned aerial vehicle is improved.
Specifically, the unmanned aerial vehicle pan-tilt angle adjustment amount is:
Δθ2＝θ3
selecting a point s with a projection distance delta from the current position of the unmanned aerial vehicle on the center line of the photovoltaic string as a virtual path point, controlling the flight direction of the unmanned aerial vehicle to face the point s and continuously updating the course, and controlling the flight speed of the unmanned aerial vehicle to be:
according to the embodiment of the invention, the photovoltaic power station is patrolled according to the video data acquired by the unmanned aerial vehicle, and whether the photovoltaic module exists in the video frame of the video data is judged according to the color characteristic value of the photovoltaic module, so that the patrolling efficiency of the photovoltaic power station can be effectively improved; according to the embodiment of the invention, the contour points of the photovoltaic module are sampled and calculated by adopting an edge detection method to determine the theoretical flight path of the unmanned aerial vehicle, and the theoretical flight path is adjusted by calculating the flight deviation amount of the unmanned aerial vehicle in actual routing inspection, so that the integrity of image data acquired by the unmanned aerial vehicle can be effectively improved, the accurate position information of the photovoltaic module can be obtained, and the routing inspection effect can be effectively improved.
As a specific implementation manner of the embodiment of the invention, the unmanned aerial vehicle further comprises a second judgment module, which is used for judging whether the current position of the unmanned aerial vehicle is positioned at the boundary of the target inspection area or not, and if so, controlling the unmanned aerial vehicle to execute a turning action.
In the embodiment of the invention, when the current position of the unmanned aerial vehicle is judged not to be in the boundary of the target inspection area, the unmanned aerial vehicle is controlled to continuously fly and the image information of the photovoltaic power station is acquired, so that the integral inspection of the photovoltaic power station is realized.
As a specific implementation manner of the embodiment of the present invention, the second determining module is specifically configured to determine whether a ratio of a pixel value of any one point on the binary image of the photovoltaic module string to a total number of pixels of the video frame is within a preset threshold range, and if so, determine that the current position of the unmanned aerial vehicle is located at a boundary of the target inspection area, and control the unmanned aerial vehicle to execute a turning action.
Optionally, a boundary vertex coordinate set V of the target inspection area is obtained, and whether the current position of the unmanned aerial vehicle is located at the boundary of the target inspection area is judged by calculating whether a photovoltaic string exists in the video frame, specifically:
∑xi,j/npix≥TPV
wherein x isi，jE {0, 1} is a pixel value of any point (i, j) on the binary image of the photovoltaic group string; n ispixIs the total number of video frame pixels; t isPV∈[0.2，0.3]Is a threshold value.
The judgment condition that the unmanned aerial vehicle reaches the boundary of the target patrol area is as follows: the unmanned aerial vehicle is located outside the target patrol area determined by the set V, and the above formula does not hold. When the unmanned aerial vehicle reaches the boundary of the target inspection area, a turning process needs to be executed; if the unmanned aerial vehicle finishes image acquisition of the whole target inspection area, the inspection process is finished.
According to the embodiment of the invention, whether the current position of the unmanned aerial vehicle reaches the boundary of the target inspection area or not is judged, whether the unmanned aerial vehicle needs to turn or not is controlled, so that the image information of the photovoltaic power station is continuously acquired, the integrity of the image information acquired by the unmanned aerial vehicle in inspection can be effectively improved, and the inspection effect can be effectively improved.
The embodiment of the invention has the following beneficial effects:
according to the embodiment of the invention, the photovoltaic power station is patrolled according to the video data acquired by the unmanned aerial vehicle, and whether the photovoltaic module exists in the video frame of the video data is judged according to the color characteristic value of the photovoltaic module, so that the patrolling efficiency of the photovoltaic power station can be effectively improved; according to the embodiment of the invention, the contour points of the photovoltaic module are sampled and calculated by adopting an edge detection method to determine the theoretical flight path of the unmanned aerial vehicle, and the theoretical flight path is adjusted by calculating the flight deviation amount of the unmanned aerial vehicle in actual routing inspection, so that the integrity of image data acquired by the unmanned aerial vehicle can be effectively improved, the accurate position information of the photovoltaic module can be obtained, and the routing inspection effect can be effectively improved.
The foregoing is a preferred embodiment of the present invention, and it should be noted that it would be apparent to those skilled in the art that various modifications and enhancements can be made without departing from the principles of the invention, and such modifications and enhancements are also considered to be within the scope of the invention.
Claims (10)
1. An unmanned aerial vehicle inspection method is characterized by comprising the following steps:
calculating a color characteristic value of each pixel point in a video frame of the video data according to the video data acquired by the unmanned aerial vehicle, wherein the color characteristic value is a color characteristic value of the photovoltaic module;
converting the video frame into a binary image based on the color feature values;
extracting a connected region in the binary image according to the color characteristic value, and judging whether the connected region is a photovoltaic module or not according to the geometric characteristic of the connected region;
after the connected region is judged to be the photovoltaic module, performing morphological processing on the connected region to obtain a photovoltaic module string;
sampling and calculating contour points of the photovoltaic module string to obtain linear information of the upper edge and the lower edge of the photovoltaic module string, and determining a theoretical flight path of the unmanned aerial vehicle according to the linear information;
calculating the arrangement direction of the photovoltaic component string and the distance between the unmanned aerial vehicle and the central point of the photovoltaic component string, adjusting the flight direction and the pan-tilt yaw angle in the theoretical flight path convergence according to the arrangement direction, and controlling the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic component string.
2. The unmanned aerial vehicle inspection method according to claim 1, wherein after "controlling the flying speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic module string", the method further comprises:
and judging whether the current position of the unmanned aerial vehicle is in the boundary of the target inspection area or not, and if so, controlling the unmanned aerial vehicle to execute a turning action.
3. The unmanned aerial vehicle inspection method according to claim 2, wherein after determining whether the unmanned aerial vehicle reaches a boundary of the area according to the sub-area vertex coordinate set and the current position of the unmanned aerial vehicle, and if so, controlling the unmanned aerial vehicle to perform a turning action, the method further comprises:
and judging whether the unmanned aerial vehicle finishes image acquisition of a target inspection area, if so, stopping controlling the unmanned aerial vehicle to acquire images to finish inspection.
4. The unmanned aerial vehicle inspection method according to claim 1, wherein the color characteristic value of each pixel point in a video frame of the video data is calculated according to the video data collected by the unmanned aerial vehicle, wherein the color characteristic value is a color characteristic value of a photovoltaic module, and specifically is:
the method comprises the steps of obtaining video data collected by the unmanned aerial vehicle, and calculating color characteristic values of the composition colors of the photovoltaic modules in the video data according to different distribution characteristics of the composition colors of the photovoltaic modules in an RGB histogram, wherein the composition colors of the photovoltaic modules comprise blue and black.
5. The unmanned aerial vehicle inspection method according to claim 1, wherein the morphological method includes, but is not limited to, an expansion process and a corrosion process, and after the connected region is judged to be a photovoltaic module, the connected region is subjected to the morphological method process to obtain a photovoltaic module string, specifically:
and after the connected region is judged to be the photovoltaic module, performing expansion treatment and corrosion treatment on the connected region, eliminating intervals among different photovoltaic modules, and obtaining a photovoltaic module string.
6. The unmanned aerial vehicle inspection method according to claim 1, wherein the straight line information of the upper and lower edges of the photovoltaic module string is obtained by sampling and calculating the contour points of the photovoltaic module string, and the theoretical flight path of the unmanned aerial vehicle is determined according to the straight line information, specifically:
and acquiring a plurality of contour points of the photovoltaic module string to determine a plurality of line segments, and determining the theoretical flight path of the unmanned aerial vehicle by judging whether the plurality of line segments are collinear according to a preset coordinate system.
7. The unmanned aerial vehicle inspection method according to claim 2, wherein the current position of the unmanned aerial vehicle is judged to judge whether the current position is located at the boundary of the target inspection area, and if so, the unmanned aerial vehicle is controlled to perform a turning action, specifically:
acquiring whether the ratio of the pixel value of any point on the binary image of the photovoltaic module string to the total number of pixels of the video frame is within a preset threshold range, if so, judging that the current position of the unmanned aerial vehicle is at the boundary of the target inspection area, and controlling the unmanned aerial vehicle to execute a turning action.
8. An unmanned aerial vehicle inspection device, its characterized in that includes:
the first calculation module is used for calculating a color characteristic value of each pixel point in a video frame of the video data according to the video data acquired by the unmanned aerial vehicle, wherein the color characteristic value is the color characteristic value of the photovoltaic module;
a conversion module for converting the video frame into a binary image based on the color feature values;
the first judgment module is used for extracting a connected region in the binary image according to the color features and judging whether the connected region is a photovoltaic module or not according to the geometric features of the connected region;
the processing module is used for processing the connected region by a morphological method to obtain a photovoltaic module string after judging that the connected region is a photovoltaic module;
the second calculation module is used for sampling and calculating contour points of the photovoltaic assembly string to obtain linear information of the upper edge and the lower edge of the photovoltaic assembly string and determining a theoretical flight path of the unmanned aerial vehicle according to the linear information;
the adjusting module is used for calculating the arrangement direction of the photovoltaic component string and the distance between the unmanned aerial vehicle and the central point of the photovoltaic component string, adjusting the flight direction and the pan-tilt yaw angle in the convergence of the theoretical flight path according to the arrangement direction, and controlling the flight speed of the unmanned aerial vehicle according to the projection distance of the current position of the unmanned aerial vehicle on the photovoltaic component string.
9. The inspection device according to claim 8, further including a second determination module for determining whether the current position of the unmanned aerial vehicle is within the boundary of the target inspection area, and if so, controlling the unmanned aerial vehicle to execute a turning action.
10. The unmanned aerial vehicle inspection device according to claim 9, wherein the second determination module is specifically configured to determine whether a ratio of a pixel value of any one point on the binary image of the photovoltaic module string to a total number of pixels of a video frame is within a preset threshold range, and if so, determine that the current position of the unmanned aerial vehicle is located at a boundary of the target inspection area, and control the unmanned aerial vehicle to perform a turning action.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110668695.0A CN113433958A (en) | 2021-06-16 | 2021-06-16 | Unmanned aerial vehicle inspection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110668695.0A CN113433958A (en) | 2021-06-16 | 2021-06-16 | Unmanned aerial vehicle inspection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113433958A true CN113433958A (en) | 2021-09-24 |
Family
ID=77756368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110668695.0A Pending CN113433958A (en) | 2021-06-16 | 2021-06-16 | Unmanned aerial vehicle inspection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113433958A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023223036A1 (en) * | 2022-05-18 | 2023-11-23 | Above Surveying Limited | Uav flight path optimisation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108923749A (en) * | 2018-06-11 | 2018-11-30 | 东北电力大学 | Photovoltaic module hot spot based on infrared video detects localization method |
| CN109002048A (en) * | 2018-06-12 | 2018-12-14 | 浙江大学 | A kind of scale centralization photovoltaic plant image data acquiring method based on multi-rotor unmanned aerial vehicle |
| CN111740699A (en) * | 2020-05-29 | 2020-10-02 | 南京航空航天大学 | Photovoltaic panel fault detection and identification method and device and unmanned aerial vehicle |
-
2021
- 2021-06-16 CN CN202110668695.0A patent/CN113433958A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108923749A (en) * | 2018-06-11 | 2018-11-30 | 东北电力大学 | Photovoltaic module hot spot based on infrared video detects localization method |
| CN109002048A (en) * | 2018-06-12 | 2018-12-14 | 浙江大学 | A kind of scale centralization photovoltaic plant image data acquiring method based on multi-rotor unmanned aerial vehicle |
| CN111740699A (en) * | 2020-05-29 | 2020-10-02 | 南京航空航天大学 | Photovoltaic panel fault detection and identification method and device and unmanned aerial vehicle |
Non-Patent Citations (2)
| Title |
|---|
| 席志鹏等: "集中式光伏电站巡检无人机视觉定位与导航", 《浙江大学学报(工学版)》 * |
| 徐伟等: "基于图像处理的光伏组件串识别技术研究", 《信息技术与信息化》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023223036A1 (en) * | 2022-05-18 | 2023-11-23 | Above Surveying Limited | Uav flight path optimisation |
| GB2619006A (en) * | 2022-05-18 | 2023-11-29 | Above Surveying Ltd | UAV flight path optimisation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110244766B (en) | Planning method and system for unmanned aerial vehicle routing inspection route of photovoltaic power station | |
| CN104865971B (en) | The control method and unmanned plane of a kind of polling transmission line unmanned plane | |
| CN109002048B (en) | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method | |
| CN109765930B (en) | Unmanned aerial vehicle vision navigation | |
| CN115439424B (en) | Intelligent detection method for aerial video images of unmanned aerial vehicle | |
| WO2016015546A1 (en) | System and method for aircraft docking guidance and aircraft type identification | |
| CN108229587B (en) | Autonomous transmission tower scanning method based on hovering state of aircraft | |
| CN112215860A (en) | Unmanned aerial vehicle positioning method based on image processing | |
| CN105373135A (en) | Method and system for guiding airplane docking and identifying airplane type based on machine vision | |
| CN109685858A (en) | A kind of monocular cam online calibration method | |
| CN107305632A (en) | Destination object distance measurement method and system based on monocular computer vision technique | |
| CN108334844A (en) | A kind of automatic tracking method along the line of polling transmission line | |
| CN109445455B (en) | Unmanned aerial vehicle autonomous landing method and control system thereof | |
| Xi et al. | A vision-based inspection strategy for large-scale photovoltaic farms using an autonomous UAV | |
| CN110083177A (en) | A kind of quadrotor and control method of view-based access control model landing | |
| CN113433958A (en) | Unmanned aerial vehicle inspection method and device | |
| Chiu et al. | Vision-only automatic flight control for small UAVs | |
| CN114689030A (en) | Unmanned aerial vehicle auxiliary positioning method and system based on airborne vision | |
| CN109765931A (en) | A kind of near-infrared video automatic navigation method suitable for the patrol unmanned machine of breakwater | |
| CN116866719B (en) | Intelligent analysis processing method for high-definition video content based on image recognition | |
| CN112542800A (en) | Method and system for identifying transmission line fault | |
| CN104858877B (en) | High-tension line drop switch changes the control method of control system automatically | |
| CN111476818A (en) | Multi-camera low-altitude unmanned aerial vehicle target tracking device and tracking method | |
| CN114463648B (en) | Method for keeping fan blade positioned in middle of camera vision based on pure vision | |
| Kong et al. | Infrared vision based automatic navigation and inspection strategy for photovoltaic power plant using UAVs |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210924 |