CN109002048B - Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method - Google Patents
Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method Download PDFInfo
- Publication number
- CN109002048B CN109002048B CN201810603936.1A CN201810603936A CN109002048B CN 109002048 B CN109002048 B CN 109002048B CN 201810603936 A CN201810603936 A CN 201810603936A CN 109002048 B CN109002048 B CN 109002048B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- photovoltaic
- polygon
- image data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 4
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 9
- 238000007689 inspection Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000011218 segmentation Effects 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
- G05D1/08—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, 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
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)
- Image Analysis (AREA)
Abstract
The invention relates to a method for acquiring image data of a multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station. The unmanned aerial vehicle can process the visible light video stream information through the carrying processor; after the unmanned aerial vehicle is lifted off, the position and the arrangement direction of the photovoltaic string in the visual field can be calculated by combining the state information of the unmanned aerial vehicle, and the unmanned aerial vehicle can realize automatic tracking of the photovoltaic string according to the calculation result; by calculating the flight distance, the unmanned aerial vehicle can automatically acquire visible light images and infrared image data; when the unmanned aerial vehicle reaches the boundary of the region, automatically executing a steering strategy; repeating above-mentioned process, unmanned aerial vehicle can realize the image data acquisition task to whole centralized photovoltaic power plant to can further be used for fault detection. Compared with other data acquisition methods based on unmanned aerial vehicles, the method is simple and efficient to implement, does not depend on the position information of the photovoltaic module, only needs to acquire the regional information of the photovoltaic power station, and has strong environmental adaptability.
Description
Technical Field
The invention relates to application development of unmanned aerial vehicles and routing inspection of a large-scale centralized photovoltaic power station, in particular to a multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method.
Background
The unmanned aerial vehicle industry has met the development of well-jet type in the world, and the growth rate of consumption-level unmanned aerial vehicles in China market is always kept above 50% in recent years, and China unmanned aerial vehicle enterprises represented by Dajiang account for more than 70% of the world consumption-level unmanned aerial vehicle market. The guidance opinions about promoting and standardizing the development of the manufacturing industry of the civil unmanned aerial vehicle, which are issued by the ministry of industry and informatization, are clear, the industry of the civil unmanned aerial vehicle can be continuously and rapidly developed, the annual output value of 2020 reaches 600 hundred million yuan, and the annual average speed is increased by more than 40%; by 2025, the output value of civil unmanned aerial vehicles reaches 1800 billion yuan. The unmanned aerial vehicle industry is a booming industry.
Because the multi-rotor unmanned aerial vehicle can take off and land vertically and is simple to control, the multi-rotor unmanned aerial vehicle can be developed and popularized rapidly and is very suitable for tasks such as near-field investigation, monitoring, aerial photography, early warning, agricultural plant protection and the like; the development of unmanned aerial vehicle related technologies such as autonomous obstacle avoidance, automatic target tracking, autonomous track planning and the like enables the unmanned aerial vehicle to be gradually developed into a flying robot from a flying camera.
In the photovoltaic field, 53.06GW is newly added to China's photovoltaic in 2017, and a new history is created. Because the service life of the photovoltaic module is about 25 years, a large photovoltaic power station needs to be capable of stably and efficiently generating power in a long time period, and routing inspection is the core content of photovoltaic power station operation.
However, at present, the inspection of the photovoltaic power station is mainly performed manually, the inspection mode is extremely low in efficiency, and the manual inspection in most scenes is difficult to meet the requirements due to the fact that the installation environment of the centralized photovoltaic power station is complex.
Disclosure of Invention
Aiming at the defects of the existing large-scale centralized photovoltaic power station image data acquisition method, the invention provides a large-scale centralized photovoltaic power station image data acquisition method for a multi-rotor unmanned aerial vehicle.
The technical scheme adopted by the invention is as follows:
the method comprises the following steps that (1) regional boundary information of the large-scale centralized photovoltaic power station is obtained according to a photovoltaic power station design drawing, a high-definition satellite image or an unmanned aerial vehicle high-altitude image;
step (2), fitting the regional boundary information of the large-scale centralized photovoltaic power station obtained in the step (1) by using polygons to generate regional polygons, and if the photovoltaic strings are distributed in a plurality of regions, generating a plurality of regional polygons; recording the vertex coordinates of the region polygon in a clockwise direction;
step (3), selecting the vertex of the south end or the north end of the geography as the starting point of the area polygon for each area polygon; for the starting point of each region polygon, if the photovoltaic modules are distributed in the east of the starting point, the starting direction is east, and if the photovoltaic modules are distributed in the west of the starting point, the starting direction is west; if the starting point is located in the south of the regional polygon, the cruising direction is north, and if the starting point is located in the north of the regional polygon, the cruising direction is south;
step (4), if the region polygons determined in the step (2) are not unique, determining the data acquisition sequence of the region polygons, and sequentially executing the steps (5) to (10) for each region polygon;
step (5), starting the unmanned aerial vehicle, setting the yaw angle of the unmanned aerial vehicle and the yaw angle of the visible light camera to be 0 in the NED coordinate system, and setting the flight speed v of the unmanned aerial vehicle0Determining the initial flying speed of the unmanned aerial vehicle according to the initial direction determined in the step (3), wherein when the initial direction is east, the initial flying speed is
When the initial direction is west, the initial flying speed is
Setting dis to 0; wherein v isx、vyThe flight speeds in the north direction and the east direction are respectively, dis is the flight distance of the unmanned aerial vehicle when the unmanned aerial vehicle carries out data acquisition on each row of photovoltaic modules, n _ turn is the turning times of the unmanned aerial vehicle at the region boundary, and the initial value of n _ turn is 0;
step (6), the unmanned aerial vehicle processor acquires a visible light video stream, detects a photovoltaic module through an image processing algorithm for a current video frame, acquires a boundary straight line of a photovoltaic string, and calculates the arrangement direction of the photovoltaic string and the longitudinal pixel offset of the photovoltaic string relative to the central point of the video stream according to the slope and the position of the boundary straight line of the photovoltaic string and the combination of the flight height;
step (7), calculating the adjustment quantity and the speed instruction value of the pan-tilt yaw angle according to the photovoltaic group string arrangement direction and the offset obtained in the step (6);
step (8), repeatedly executing the step (6) and the step (7) at a fixed frequency which is not lower than 5Hz until the unmanned aerial vehicle reaches the zone boundary; in the process of executing the step (6) and the step (7), if abs (dis-n _ dis _ photo) is less than or equal to 0.1, the unmanned aerial vehicle visible light camera and the infrared camera acquire image data; wherein n is a natural number, dis _ photo is a distance interval for image data acquisition, and abs is an absolute value calculation;
step (9), when the unmanned aerial vehicle reaches the zone boundary, executing a steering strategy, wherein dis is 0, and n _ turn is n _ turn + 1;
and (10) continuously executing an image acquisition task on the photovoltaic module in the current row by the unmanned aerial vehicle, and executing the steps (6) to (9) according to the initial flight speed determined in the step (5) until the unmanned aerial vehicle finishes traversing the area polygon.
Further, the following condition is followed when the region polygon is generated in the step (2):
r010: if two distribution areas of the photovoltaic module are communicated, the two distribution areas are regarded as one area;
r020: on the basis of R010, generating a fitting polygon of each distribution area according to the area minimum principle;
r030: if the fitting polygon is a concave polygon, solving a circumscribed convex polygon of the concave polygon, and dividing the difference value part of the circumscribed convex polygon and the concave polygon into a plurality of non-connected areas according to connectivity; for any region of the difference part, if the east and west sides of the region are intersected with the concave polygon, the concave polygon cannot be used as a region polygon, otherwise, the concave polygon is used as a region polygon;
r040: all convex polygons can be used as regional polygons;
r050: if the concave polygon cannot be used as the regional polygon, the concave polygon needs to be decomposed until all the decomposed polygons can be used as the regional polygon, and the decomposition principle is that the south-north direction span sum of all the decomposed regional polygons is minimum.
Further, the step (6) of calculating the arrangement direction of the photovoltaic string and the vertical pixel offset of the photovoltaic string relative to the center point of the video stream specifically includes the following steps:
s010: the unmanned aerial vehicle processor acquires a visible light video frame, converts the visible light video frame into an HSV (hue, saturation, value) space through color space conversion, sets thresholds of all channels of the HSV space according to color characteristics of the surface of the photovoltaic component, and converts an HSV image into a binary image;
s020: performing morphological closing operation on the binary image to enable the binary images of the adjacent photovoltaic modules to be communicated, and obtaining an expanded binary image of the photovoltaic module string;
s030: extracting linear information of the edges of the extended photovoltaic string by Hough transform to obtain a photovoltaic string edge line segment, removing a line segment with the slope absolute value larger than 0.8 or the length smaller than half of the longest line segment, and calculating the average slope k _ ave of the remaining line segments and the longitudinal pixel offset pix _ err of the central line of the upper and lower boundaries of the extended photovoltaic string relative to the central point of the video stream;
s040: in NED coordinate system, according to the yaw angle theta of the unmanned aerial vehicle body1Yaw angle theta of pan-tilt2And inclination angle theta of photovoltaic module in unmanned aerial vehicle video frame3Determining the arrangement direction of the photovoltaic string, namely, the included angle theta between the parallel direction and the east-west direction is theta1+θ2+θ3A straight line of (a); wherein, theta3＝arctan(k_ave)。
Further, the method for calculating the yaw angle adjustment amount and the speed command value of the cloud platform in the step (7) includes:
r110: according to the calculation result of the step S040, the adjustment quantity of the yaw angle of the unmanned aerial vehicle holder is delta theta2＝θ3；
R120: according to the calculation result of the step S030, the actual offset of the center line of the upper and lower boundaries of the expanded photovoltaic string with respect to the position of the image center point is approximately d _ err/pix _ height H tan (0.5 FOV); h is the height difference between the unmanned aerial vehicle visible light camera and the photovoltaic module, pix _ height is the number of rows of pixels of the video frame, and FOV is a vertical field angle;
r130: according to the calculation result in the step R120, when the unmanned aerial vehicle flies from west to east, the speed command is
When the unmanned aerial vehicle flies from east to west, the speed command is
Wherein,
it can prevent the occurrence of too large | d _ err |, where a and b are normal numbers.
Further, the determination condition that the unmanned aerial vehicle reaches the zone boundary in the step (8) is as follows: the position of the unmanned aerial vehicle reaches the outside of the polygon of the region, and the two-value image obtained according to the step S010 meets the requirement
Wherein n is pix _ width pix _ height is the number of picture pixels,
number of pixels, x, belonging to photovoltaic module obtained by processing in step S010iThe color threshold is a threshold value for judging whether the photovoltaic module exists in the visual field or not.
Further, the distance intervals dis _ photo acquired by the visible light image and the infrared image in the step (8) are different, that is, different distance intervals are set for the visible light image and the infrared image according to parameters of the visible light camera and the infrared camera and imaging characteristics of the visible light image and the infrared image.
Further, the main process of the steering strategy in the step (9) is as follows:
s110: unmanned aerial vehicle flies in cruising direction S1Distance of (S)1About the photovoltaic string longitudinal distance separation;
s120: if the video frame of the unmanned aerial vehicle does not meet the area boundary judgment condition in the step (8), the flight direction of the unmanned aerial vehicle is the same as the flight direction of the unmanned aerial vehicle when the image data of the previous row of photovoltaic strings are acquired until the unmanned aerial vehicle meets the area boundary judgment condition in the step (8), and the position at the moment is used as the starting point of the acquisition of the image data of the new row of photovoltaic strings; if the video frame of the unmanned aerial vehicle meets the area boundary judgment condition in the step (8), the flight direction of the unmanned aerial vehicle is opposite to the flight direction of the unmanned aerial vehicle when the image data of the previous line of photovoltaic strings are acquired until the unmanned aerial vehicle just does not meet the area boundary judgment condition in the step (8), and the position at the moment is used as the starting point of the acquisition of the image data of the new line of photovoltaic strings;
s130: after the initial point of the new line of photovoltaic group string image data acquisition is determined, the flight direction of the unmanned aerial vehicle is set to be opposite to the flight direction of the previous line of photovoltaic group string image data acquisition, and the steering process is finished.
Furthermore, the multi-rotor unmanned aerial vehicle is provided with an obstacle avoidance module and a vertical distance measurement module, and the vertical distance measurement module ensures that the unmanned aerial vehicle and a photovoltaic module right below the unmanned aerial vehicle keep a stable height difference by controlling the lifting of the unmanned aerial vehicle.
Furthermore, the visible light camera and the infrared camera carried by the multi-rotor unmanned aerial vehicle are vertically downward and have a triaxial self-stabilizing function.
The invention has the following beneficial effects: the unmanned aerial vehicle is used for carrying the visible light camera and the infrared camera to collect image data, so that the image data collection efficiency of the large-scale centralized photovoltaic power station can be greatly improved, and the image data is an important basis for fault analysis and diagnosis and health degree assessment. Compared with the traditional manual acquisition method, the method has very high automation level, and can greatly improve the image data acquisition efficiency of the large-scale centralized photovoltaic power station; compared with other data acquisition methods based on unmanned aerial vehicles, the method is simple and efficient to implement, does not depend on the position information of the photovoltaic module, only needs to acquire the regional information of the photovoltaic power station, and has strong environmental adaptability.
Drawings
FIG. 1 is a flow chart of a large-scale centralized photovoltaic power station image data acquisition strategy based on a multi-rotor unmanned aerial vehicle according to the invention;
FIG. 2 is a schematic diagram of a fitted polygon generated from photovoltaic module boundary information;
FIG. 3.1 is a schematic diagram of a concave fitting polygon without decomposition;
FIG. 3.2 is a schematic diagram of a concave fitting polygon to be decomposed;
FIG. 4 is a schematic view of a start point, start direction and cruise direction of a region polygon;
FIG. 5.1 is an exemplary diagram of a video frame;
FIG. 5.2 shows the result of HSV threshold segmentation;
FIG. 5.3 is a computational schematic;
FIG. 5.4 is a calculation result of the average slope and offset of the boundary line of the photovoltaic string;
FIG. 6 is a schematic diagram showing the relationship among the yaw angle of the unmanned aerial vehicle, the yaw angle of the holder, and the rotation angle of the photovoltaic string in the NED coordinate system;
FIG. 7 is a schematic diagram of velocity command calculation in the NED coordinate system;
fig. 8.1 is a schematic view of a flight process with an initial position outside the area after the unmanned aerial vehicle starts turning;
fig. 8.2 is a schematic view of the flight process of the unmanned aerial vehicle in the area after the unmanned aerial vehicle starts turning.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings, which are included to provide a thorough and complete description of the present invention, and the following embodiments are only some embodiments but not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive work based on the embodiments of the present invention will fall within the protection scope of the present invention.
The directional vocabularies such as east, west and the like are used for many times in the invention and are mainly based on the following considerations: due to the characteristics of photovoltaic power generation, all photovoltaic modules approximately face to the geographical south, the transverse photovoltaic group strings are approximately arranged in the east-west direction, and although the directions of the photovoltaic modules and the arrangement direction deviate from the geographical direction in the actual situation, the information is still feasible for the unmanned aerial vehicle to specify a starting point and an approximate flight direction; on understanding the photovoltaic module distribution characteristics's basis, thereby reduce the deviation and make unmanned aerial vehicle realize realizing by the servo process of vision to the accurate tracking of photovoltaic group cluster.
Fig. 1 is a flow chart of a method for acquiring image data of a multi-rotor unmanned aerial vehicle in a scale centralized photovoltaic power station, which shows a main process of acquiring image data of the scale centralized photovoltaic power station, and the detailed and specific flow can be expressed as follows:
the method comprises the following steps that (1) regional boundary information of the large-scale centralized photovoltaic power station is obtained according to a photovoltaic power station design drawing, a high-definition satellite image or an unmanned aerial vehicle high-altitude image;
step (2), fitting the regional boundary information of the large-scale centralized photovoltaic power station obtained in the step (1) by using polygons to generate regional polygons, and if photovoltaic string strings are distributed in a plurality of regions and the regions are far apart, generating a plurality of regional polygons; the coordinates of the vertices of the area polygon are recorded in a clockwise direction. As an example, fig. 2 illustrates a schematic diagram of generating a plurality of regional polygons when there is a distinct regionality in the photovoltaic string distribution;
further, the step (2) generates the region polygon under the following conditions:
r010: if two distribution areas of the photovoltaic module are communicated, the two distribution areas are regarded as one area;
r020: on the basis of the condition R010, generating a fitting polygon of each distribution area according to the area minimum principle, wherein the fitting polygon can be a convex polygon or a concave polygon;
r030: if the fitting polygon is a concave polygon, solving a circumscribed convex polygon of the concave polygon, and dividing the difference value part of the circumscribed convex polygon and the concave polygon into a plurality of non-connected areas according to connectivity; for any region of the difference part, if the east and west sides of the region are intersected with the concave polygon, the concave polygon cannot be used as a region polygon, otherwise, the concave polygon is used as a region polygon;
r040: all convex polygons can be used as regional polygons;
r050: if the concave polygon cannot be used as the region polygon, the concave polygon needs to be decomposed until all decomposed polygons can be used as the region polygon, and the decomposition principle is that the south-north direction span of all decomposed region polygons is the minimum (fig. 3.1 visually shows the concave polygon which can be used as the region polygon and the concave polygon which cannot be used as the region polygon, and decomposes the concave polygon which cannot be used as the region polygon, and the existence of "difference region 2" in fig. 3.2 causes the concave fitting polygon to need to be decomposed);
step (3), selecting the vertex of the south end or the north end of the geography as the starting point of the area polygon for each area polygon; for the starting point of each region polygon, if the photovoltaic modules are distributed in the east of the starting point, the starting direction is east, and if the photovoltaic modules are distributed in the west of the starting point, the starting direction is west; for the starting point of each region polygon, if the starting point is positioned in the south of the region polygon, the cruising direction is north, and if the starting point is positioned in the north of the region polygon, the cruising direction is south; FIG. 4 illustrates the selection of the starting point, the starting direction and the determination of the cruising direction of the region polygon, where "south" and "north" refer to the vertices of the boundary of the region polygon south and north, and the diagram shows
A vector, s, formed by the coordinates of the starting point 1, the starting direction and the cruising direction2(x2,y2) As the position coordinates of the start point 2,
as a starting direction of the starting point 3,
cruising direction at starting point 4
Step (4), if the region polygons determined in the step (2) are not unique, determining the data acquisition sequence of the region polygons, and sequentially executing the steps (5) to (10) for each region polygon;
step (5), starting the unmanned aerial vehicle, setting the yaw angle of the unmanned aerial vehicle and the yaw angle of the visible light camera to be 0 in the NED coordinate system (navigation coordinate system), and setting the flight speed v of the unmanned aerial vehicle0Determining the initial flying speed of the unmanned aerial vehicle according to the initial direction determined in the step (3), wherein when the initial direction is east, the initial flying speed is
When the initial direction is west, the initial flying speed is
Setting dis to 0; wherein v isx、vyThe flight speeds in the north direction and the east direction are respectively, dis is the flight distance of the unmanned aerial vehicle when the unmanned aerial vehicle carries out data acquisition on each row of photovoltaic modules, n _ turn is the turning times of the unmanned aerial vehicle at the region boundary, and the initial value of n _ turn is 0;
step (6), the unmanned aerial vehicle processor acquires a visible light video stream, detects a photovoltaic module through an image processing algorithm for a current video frame, acquires a boundary straight line of a photovoltaic string, and calculates the arrangement direction of the photovoltaic string and the longitudinal pixel offset of the photovoltaic string relative to the central point of the video stream according to the slope and the position of the boundary straight line of the photovoltaic string and the combination of the flight height;
further, the step (6) of calculating the arrangement direction of the photovoltaic string and the vertical pixel offset of the photovoltaic string relative to the center point of the video stream specifically includes the following steps:
s010: the unmanned aerial vehicle processor acquires a visible light video frame, converts the visible light video frame into an HSV space through color space conversion, sets thresholds of all channels of the HSV space (for example, the thresholds are sensitive to blue and black tone of the surface of a photovoltaic component and are not sensitive to illumination) according to color characteristics of the surface of the photovoltaic component, and converts an HSV image into a binary image;
s020: performing morphological closing operation on the binary image to enable the binary images of the adjacent photovoltaic modules to be communicated, and obtaining an expanded binary image of the photovoltaic module string;
s030: extracting linear information of the edges of the extended photovoltaic string by Hough transform to obtain a photovoltaic string edge line segment, removing a line segment with the slope absolute value larger than 0.8 or the length smaller than half of the longest line segment, and calculating the average slope k _ ave of the remaining line segments and the longitudinal pixel offset pix _ err of the central line of the upper and lower boundaries of the extended photovoltaic string relative to the central point of the video stream;
s040: in NED coordinate system (navigation coordinate system), according to the yaw angle theta of the unmanned aerial vehicle body1Yaw angle theta of pan-tilt2And inclination angle theta of photovoltaic module in unmanned aerial vehicle video frame3Determining the arrangement direction of the photovoltaic string, namely, the included angle theta between the parallel direction and the east-west direction is theta1+θ2+θ3A straight line of (a); wherein, theta3＝arctan(k_ave)；
5.1-5.4 illustrate a process of calculating a rotation angle and an offset of a photovoltaic string in a video frame by taking an unmanned aerial vehicle aerial photograph of a photovoltaic module as an example; fig. 6 shows a schematic diagram of the relationship among the yaw angle of the unmanned aerial vehicle, the yaw angle of the holder, and the rotation angle of the photovoltaic string in the NED coordinate system;
step (7), calculating according to the arrangement direction and the offset of the photovoltaic string obtained in the step (6) to obtain an adjustment value and a speed instruction value of a pan-tilt yaw angle, so that the photovoltaic string is positioned in the center of the video stream, and the transverse rotation angle of the photovoltaic string in the video stream is zero;
further, the method for calculating the yaw angle adjustment amount and the speed command value of the cloud platform in the step (7) comprises the following steps:
r110: according to the calculation result of S040, the adjustment quantity of the yaw angle of the unmanned aerial vehicle holder is delta theta2＝θ3；
R120: according to the calculation result of S030, the actual offset of the center line of the upper and lower boundaries of the expanded photovoltaic group string relative to the position of the image center point is approximately d _ err/pix _ height H tan (0.5 FOV); h is the height difference between the unmanned aerial vehicle visible light camera and the photovoltaic module, pix _ height is the number of rows of pixels of the video frame, and FOV is a vertical field angle;
r130: according to the calculation result in the R120, when the unmanned aerial vehicle flies from west to east, the speed instruction is
When the unmanned aerial vehicle flies from east to west, the speed command is
Wherein,
can prevent the occurrence of overlarge | d _ err | with a and b being normal numbers; FIG. 7 shows a schematic of velocity command calculation in NED coordinate system;
step (8), repeatedly executing the step (6) and the step (7) at a fixed frequency which is not lower than 5Hz until the unmanned aerial vehicle reaches the zone boundary; in the process of executing the step (6) and the step (7), if abs (dis-n _ dis _ photo) is less than or equal to 0.1(n is a natural number), the unmanned aerial vehicle visible light camera and the infrared camera acquire image data; wherein dis photo is a distance interval of image data acquisition; abs is an absolute value calculation;
further, in the step (8), the condition for determining that the unmanned aerial vehicle reaches the zone boundary is as follows: the position of the unmanned aerial vehicle reaches the outside of the polygon of the region, and the two-value image obtained according to the S010 satisfies
Wherein n is pix _ width pix _ height is the number of picture pixels,
number of pixels belonging to photovoltaic module, x, obtained for S010 processingiThe image is a binary image pixel value, and ColorThreshold is a threshold value for judging whether a photovoltaic module exists in a visual field;
further, the distance intervals dis _ photo acquired by the visible light image and the infrared image in the step (8) may be different, that is, different distance intervals may be set for the visible light image and the infrared image according to parameters of the visible light camera and the infrared camera, and imaging characteristics of the visible light image and the infrared image;
and (9) when the unmanned aerial vehicle reaches the zone boundary, executing a steering strategy, wherein dis is 0, and n _ turn is n _ turn +1
Further, the main process of the steering strategy in step (9) is as follows:
s110: unmanned aerial vehicle flies in cruising direction S1Distance of (S)1About the longitudinal distance interval of the photovoltaic string
S120: if the video frame of the unmanned aerial vehicle does not meet the area boundary judgment condition in the step (8), the flight direction of the unmanned aerial vehicle is the same as the flight direction of the unmanned aerial vehicle when the image data of the previous row of photovoltaic strings are acquired until the unmanned aerial vehicle meets the area boundary judgment condition in the step (8), and the position at the moment is used as the starting point of the acquisition of the image data of the new row of photovoltaic strings; if the video frame of the unmanned aerial vehicle meets the area boundary judgment condition in the step (8), the flight direction of the unmanned aerial vehicle is opposite to the flight direction of the unmanned aerial vehicle when the image data of the previous line of photovoltaic strings are acquired until the unmanned aerial vehicle just does not meet the area boundary judgment condition in the step (8), and the position at the moment is used as the starting point of the acquisition of the image data of the new line of photovoltaic strings;
s130: after the initial point of the new line of photovoltaic group string image data acquisition is determined, the flight direction of the unmanned aerial vehicle is set to be opposite to the flight direction of the previous line of photovoltaic group string image data acquisition, and the steering process is finished; FIG. 8 depicts the steering strategy of the UAV at the zone polygon boundary determined in S110-S130;
step (10), the unmanned aerial vehicle continues to execute an image acquisition task on the photovoltaic module in the current row, specifically, the initial flying speed is determined according to the method in the step (5), and the steps (6) to (9) are executed until the unmanned aerial vehicle finishes traversing the area polygon;
the multi-rotor unmanned aerial vehicle platform is provided with an obstacle avoidance module and a vertical distance measurement module, and the vertical distance measurement module can ensure that the unmanned aerial vehicle and a photovoltaic assembly right below the unmanned aerial vehicle keep a stable height difference by controlling the lifting of the unmanned aerial vehicle; according to the method, the visible light camera and the infrared camera carried by the multi-rotor unmanned aerial vehicle platform are vertically downward and have a triaxial self-stabilizing function.
Claims (7)
1. The method for acquiring the image data of the multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station is characterized by comprising the following steps of:
the method comprises the following steps that (1) regional boundary information of the large-scale centralized photovoltaic power station is obtained according to a photovoltaic power station design drawing, a high-definition satellite image or an unmanned aerial vehicle high-altitude image;
step (2), fitting the regional boundary information of the large-scale centralized photovoltaic power station obtained in the step (1) by using polygons to generate regional polygons, and if the photovoltaic strings are distributed in a plurality of regions, generating a plurality of regional polygons; recording the vertex coordinates of the region polygon in a clockwise direction;
the following conditions are followed when the region polygon is generated in the step (2):
r010: if two distribution areas of the photovoltaic module are communicated, the two distribution areas are regarded as one area;
r020: on the basis of R010, generating a fitting polygon of each distribution area according to the area minimum principle;
r030: if the fitting polygon is a concave polygon, solving a circumscribed convex polygon of the concave polygon, and dividing the difference value part of the circumscribed convex polygon and the concave polygon into a plurality of non-connected areas according to connectivity; for any region of the difference part, if the east and west sides of the region are intersected with the concave polygon, the concave polygon cannot be used as a region polygon, otherwise, the concave polygon is used as a region polygon;
r040: all convex polygons can be used as regional polygons;
r050: if the concave polygon can not be used as the regional polygon, the concave polygon needs to be decomposed until all the decomposed polygons can be used as the regional polygon, and the decomposition principle is that the sum of the south-north spans of all the decomposed regional polygons is the minimum;
step (3), selecting the vertex of the south end or the north end of the geography as the starting point of the area polygon for each area polygon; for the starting point of each region polygon, if the photovoltaic modules are distributed in the east of the starting point, the starting direction is east, and if the photovoltaic modules are distributed in the west of the starting point, the starting direction is west; if the starting point is located in the south of the regional polygon, the cruising direction is north, and if the starting point is located in the north of the regional polygon, the cruising direction is south;
step (4), if the region polygons determined in the step (2) are not unique, determining the data acquisition sequence of the region polygons, and sequentially executing the steps (5) to (10) for each region polygon;
step (5), starting the unmanned aerial vehicle, setting the yaw angle of the unmanned aerial vehicle and the yaw angle of the visible light camera to be 0 in the NED coordinate system, and setting the flight speed v of the unmanned aerial vehicle0Determining the initial flying speed of the unmanned aerial vehicle according to the initial direction determined in the step (3), wherein when the initial direction is east, the initial flying speed is
When the initial direction is west, the initial flying speed is
Setting dis to 0; wherein v isx、vyThe flight speeds in the north direction and the east direction are respectively, dis is the flight distance of the unmanned aerial vehicle when the unmanned aerial vehicle carries out data acquisition on each row of photovoltaic modules, n _ turn is the turning times of the unmanned aerial vehicle at the region boundary, and the initial value of n _ turn is 0;
step (6), the unmanned aerial vehicle processor acquires a visible light video stream, detects a photovoltaic module through an image processing algorithm for a current video frame, acquires a boundary straight line of a photovoltaic string, and calculates the arrangement direction of the photovoltaic string and the longitudinal pixel offset of the photovoltaic string relative to the central point of the video stream according to the slope and the position of the boundary straight line of the photovoltaic string and the combination of the flight height;
step (7), calculating the adjustment quantity and the speed instruction value of the pan-tilt yaw angle according to the photovoltaic group string arrangement direction and the offset obtained in the step (6);
step (8), repeatedly executing the step (6) and the step (7) at a fixed frequency which is not lower than 5Hz until the unmanned aerial vehicle reaches the zone boundary; in the process of executing the step (6) and the step (7), if abs (dis-n _ dis _ photo) is less than or equal to 0.1, the unmanned aerial vehicle visible light camera and the infrared camera acquire image data; wherein n is a natural number, dis _ photo is a distance interval for image data acquisition, and abs is an absolute value calculation;
the judgment condition that the unmanned aerial vehicle reaches the zone boundary in the step (8) is as follows: the position of the unmanned aerial vehicle reaches the outside of the polygon of the region, and the two-value image obtained according to the step S010 meets the requirement
Wherein n is pix _ width pix _ height is the number of picture pixels,
number of pixels, x, belonging to photovoltaic module obtained by processing in step S010iThe image is a binary image pixel value, and ColorThreshold is a threshold value for judging whether a photovoltaic module exists in a visual field;
step (9), when the unmanned aerial vehicle reaches the zone boundary, executing a steering strategy, wherein dis is 0, and n _ turn is n _ turn + 1;
and (10) continuously executing an image acquisition task on the photovoltaic module in the current row by the unmanned aerial vehicle, and executing the steps (6) to (9) according to the initial flight speed determined in the step (5) until the unmanned aerial vehicle finishes traversing the area polygon.
2. The method for collecting image data of a multi-rotor unmanned aerial vehicle scaled centralized photovoltaic power station according to claim 1, wherein the step (6) of calculating the arrangement direction of the photovoltaic strings and the longitudinal pixel offset of the photovoltaic strings relative to the central point of the video stream specifically comprises the following steps:
s010: the unmanned aerial vehicle processor acquires a visible light video frame, converts the visible light video frame into an HSV (hue, saturation, value) space through color space conversion, sets thresholds of all channels of the HSV space according to color characteristics of the surface of the photovoltaic component, and converts an HSV image into a binary image;
s020: performing morphological closing operation on the binary image to enable the binary images of the adjacent photovoltaic modules to be communicated, and obtaining an expanded binary image of the photovoltaic module string;
s030: extracting linear information of the edges of the extended photovoltaic string by Hough transform to obtain a photovoltaic string edge line segment, removing a line segment with the slope absolute value larger than 0.8 or the length smaller than half of the longest line segment, and calculating the average slope k _ ave of the remaining line segments and the longitudinal pixel offset pix _ err of the central line of the upper and lower boundaries of the extended photovoltaic string relative to the central point of the video stream;
s040: in NED coordinate system, according to the yaw angle theta of the unmanned aerial vehicle body1Yaw angle theta of pan-tilt2And inclination angle theta of photovoltaic module in unmanned aerial vehicle video frame3Determining the arrangement direction of the photovoltaic string, namely, the included angle theta between the parallel direction and the east-west direction is theta1+θ2+θ3A straight line of (a); wherein, theta3＝arctan(k_ave)。
3. The method for collecting image data of the multi-rotor unmanned aerial vehicle scale centralized photovoltaic power station as claimed in claim 2, wherein the method for calculating the adjustment amount of the yaw angle and the speed instruction value of the cloud platform in the step (7) comprises:
r110: according to the calculation result of the step S040, the adjustment quantity of the yaw angle of the unmanned aerial vehicle holder is delta theta2＝θ3；
R120: according to the calculation result of the step S030, the actual offset of the center line of the upper and lower boundaries of the expanded photovoltaic string with respect to the position of the image center point is approximately d _ err/pix _ height H tan (0.5 FOV); h is the height difference between the unmanned aerial vehicle visible light camera and the photovoltaic module, pix _ height is the number of rows of pixels of the video frame, and FOV is a vertical field angle;
r130: according to the calculation result in the step R120, when the unmanned aerial vehicle flies from west to east, the speed command is
When the unmanned aerial vehicle flies from east to west, the speed command is
Wherein,
it can prevent the occurrence of too large | d _ err |, where a and b are normal numbers.
4. The method for collecting image data of a centralized photovoltaic power station on a scale with multi-rotor unmanned aerial vehicles according to claim 1, wherein the distance intervals dis _ photo collected by the visible light images and the infrared images in the step (8) are different, that is, different distance intervals are set for the visible light images and the infrared images according to the parameters of the visible light cameras and the infrared cameras and the imaging characteristics of the visible light images and the infrared images.
5. The method for collecting image data of a multi-rotor unmanned aerial vehicle scaled centralized photovoltaic power station as claimed in claim 1, wherein the main process of the steering strategy in step (9) is:
s110: unmanned aerial vehicle flies in cruising direction S1Distance of (S)1About the photovoltaic string longitudinal distance separation;
s120: if the video frame of the unmanned aerial vehicle does not meet the area boundary judgment condition in the step (8), the flight direction of the unmanned aerial vehicle is the same as the flight direction of the unmanned aerial vehicle when the image data of the previous row of photovoltaic strings are acquired until the unmanned aerial vehicle meets the area boundary judgment condition in the step (8), and the position at the moment is used as the starting point of the acquisition of the image data of the new row of photovoltaic strings; if the video frame of the unmanned aerial vehicle meets the area boundary judgment condition in the step (8), the flight direction of the unmanned aerial vehicle is opposite to the flight direction of the unmanned aerial vehicle when the image data of the previous line of photovoltaic strings are acquired until the unmanned aerial vehicle just does not meet the area boundary judgment condition in the step (8), and the position at the moment is used as the starting point of the acquisition of the image data of the new line of photovoltaic strings;
s130: after the initial point of the new line of photovoltaic group string image data acquisition is determined, the flight direction of the unmanned aerial vehicle is set to be opposite to the flight direction of the previous line of photovoltaic group string image data acquisition, and the steering process is finished.
6. The method for collecting image data of the multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station as claimed in claim 1, wherein the multi-rotor unmanned aerial vehicle is provided with an obstacle avoidance module and a vertical distance measurement module, and the vertical distance measurement module ensures that the unmanned aerial vehicle and a photovoltaic module right below the unmanned aerial vehicle keep a stable altitude difference by controlling the lifting of the unmanned aerial vehicle.
7. The method for collecting image data of the multi-rotor unmanned aerial vehicle scaled centralized photovoltaic power station as claimed in claim 1, wherein the visible light camera and the infrared camera carried by the multi-rotor unmanned aerial vehicle are vertically downward and have a triaxial self-stabilizing function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810603936.1A CN109002048B (en) | 2018-06-12 | 2018-06-12 | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810603936.1A CN109002048B (en) | 2018-06-12 | 2018-06-12 | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109002048A CN109002048A (en) | 2018-12-14 |
| CN109002048B true CN109002048B (en) | 2020-06-09 |
Family
ID=64601247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810603936.1A Active CN109002048B (en) | 2018-06-12 | 2018-06-12 | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109002048B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109765930B (en) * | 2019-01-29 | 2021-11-30 | 理光软件研究所（北京）有限公司 | Unmanned aerial vehicle vision navigation |
| CN110221621B (en) * | 2019-05-30 | 2021-11-09 | 深圳市道通智能航空技术股份有限公司 | Unmanned aerial vehicle, and method, device and storage medium for planning flight area of unmanned aerial vehicle |
| CN112132898A (en) * | 2020-09-21 | 2020-12-25 | 重庆中电自能科技有限公司 | Photovoltaic module positioning method |
| CN112365673B (en) * | 2020-11-12 | 2022-08-02 | 光谷技术有限公司 | Forest fire monitoring system and method |
| WO2022225449A1 (en) * | 2021-04-19 | 2022-10-27 | Quantified Energy Labs Pte. Ltd. | Automated imaging of photovoltaic devices using an aerial vehicle and automated flight of the aerial vehicle for performing the same |
| CN113326752B (en) * | 2021-05-20 | 2024-04-30 | 淮阴工学院 | Unmanned aerial vehicle-based photovoltaic power station identification method and system |
| CN113379703B (en) * | 2021-06-08 | 2023-05-02 | 西安理工大学 | Photovoltaic panel dark spot defect detection method based on Yolo-v4 network structure |
| CN113433958A (en) * | 2021-06-16 | 2021-09-24 | 广州发展新能源股份有限公司 | Unmanned aerial vehicle inspection method and device |
| CN117526852A (en) * | 2023-11-07 | 2024-02-06 | 重庆千信新能源有限公司 | Safe working method for anti-pollution photovoltaic panel based on photovoltaic power station |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2649702A1 (en) * | 2010-12-09 | 2013-10-16 | The Boeing Company | Unmanned vehicle and system |
| KR101541032B1 (en) * | 2015-02-13 | 2015-08-03 | (주)하이레벤 | System for collecting and analyzing data regarding module surface temperature of solar photovoltaic power facilities using unmanned air vehicle |
| CN105700544A (en) * | 2016-04-08 | 2016-06-22 | 暨南大学 | UAV tour inspection system and implementation method for electrical equipment of photovoltaic power station |
| CN105786017A (en) * | 2016-04-01 | 2016-07-20 | 常州天合光能有限公司 | Photovoltaic power station survey, operation and maintenance system based on unmanned aerial vehicle |
| CN106527475A (en) * | 2016-10-28 | 2017-03-22 | 中国电力科学研究院 | Distribution network inspection unmanned aerial vehicle and inspection method thereof |
| CN106873627A (en) * | 2017-03-31 | 2017-06-20 | 湘潭大学 | A kind of multi-rotor unmanned aerial vehicle and method of automatic detecting transmission line of electricity |
| CN107015560A (en) * | 2017-03-02 | 2017-08-04 | 浙江大学 | A kind of method for inspecting of the photovoltaic array based on unmanned plane |
| CN107026612A (en) * | 2017-05-17 | 2017-08-08 | 许昌学院 | A kind of solar power station automatic tour inspection system |
| EP3214758A1 (en) * | 2016-03-03 | 2017-09-06 | Solaredge Technologies Ltd. | Methods for mapping power generation installations |
| CN107219852A (en) * | 2017-06-27 | 2017-09-29 | 成都阿普奇科技股份有限公司 | A kind of large-sized photovoltaic power station Intelligent line patrolling device and its implementation |
| CN107330957A (en) * | 2017-05-24 | 2017-11-07 | 浙江大学 | A kind of image processing method with mapping interaction relation between figure layer |
| CN108037767A (en) * | 2017-12-13 | 2018-05-15 | 王俊梅 | A kind of unmanned plane visual dead angles turn to escape flight system |
| CN108132675A (en) * | 2017-11-23 | 2018-06-08 | 东南大学 | Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory |
-
2018
- 2018-06-12 CN CN201810603936.1A patent/CN109002048B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2649702A1 (en) * | 2010-12-09 | 2013-10-16 | The Boeing Company | Unmanned vehicle and system |
| KR101541032B1 (en) * | 2015-02-13 | 2015-08-03 | (주)하이레벤 | System for collecting and analyzing data regarding module surface temperature of solar photovoltaic power facilities using unmanned air vehicle |
| EP3214758A1 (en) * | 2016-03-03 | 2017-09-06 | Solaredge Technologies Ltd. | Methods for mapping power generation installations |
| CN105786017A (en) * | 2016-04-01 | 2016-07-20 | 常州天合光能有限公司 | Photovoltaic power station survey, operation and maintenance system based on unmanned aerial vehicle |
| CN105700544A (en) * | 2016-04-08 | 2016-06-22 | 暨南大学 | UAV tour inspection system and implementation method for electrical equipment of photovoltaic power station |
| CN106527475A (en) * | 2016-10-28 | 2017-03-22 | 中国电力科学研究院 | Distribution network inspection unmanned aerial vehicle and inspection method thereof |
| CN107015560A (en) * | 2017-03-02 | 2017-08-04 | 浙江大学 | A kind of method for inspecting of the photovoltaic array based on unmanned plane |
| CN106873627A (en) * | 2017-03-31 | 2017-06-20 | 湘潭大学 | A kind of multi-rotor unmanned aerial vehicle and method of automatic detecting transmission line of electricity |
| CN107026612A (en) * | 2017-05-17 | 2017-08-08 | 许昌学院 | A kind of solar power station automatic tour inspection system |
| CN107330957A (en) * | 2017-05-24 | 2017-11-07 | 浙江大学 | A kind of image processing method with mapping interaction relation between figure layer |
| CN107219852A (en) * | 2017-06-27 | 2017-09-29 | 成都阿普奇科技股份有限公司 | A kind of large-sized photovoltaic power station Intelligent line patrolling device and its implementation |
| CN108132675A (en) * | 2017-11-23 | 2018-06-08 | 东南大学 | Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory |
| CN108037767A (en) * | 2017-12-13 | 2018-05-15 | 王俊梅 | A kind of unmanned plane visual dead angles turn to escape flight system |
Non-Patent Citations (3)
| Title |
|---|
| Overhead Power Line Detection from UAV Video;Tang Wen YANG等;《2012 19th International Conference on Mechatronics and Machine Vision in Practice 》;20121230;第71-76页 * |
| 基于遗传算法的输电线路无人机巡检路径规划;邓荣军;《算法、设计与应用》;20150430;第23卷(第04期);第1299-1301页 * |
| 红外热像仪搭载无人机在光伏电站中的应用;王斌 等;《新能源科技》;20170228(第2期);第44-47页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109002048A (en) | 2018-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109002048B (en) | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method | |
| CN110244766B (en) | Planning method and system for unmanned aerial vehicle routing inspection route of photovoltaic power station | |
| CN108109437B (en) | Unmanned aerial vehicle autonomous route extraction and generation method based on map features | |
| CN106326892B (en) | Visual landing pose estimation method of rotary wing type unmanned aerial vehicle | |
| CN108229587B (en) | Autonomous transmission tower scanning method based on hovering state of aircraft | |
| CN109792951B (en) | Unmanned aerial vehicle air route correction system for pollination of hybrid rice and correction method thereof | |
| CN103544505B (en) | Ship identification system and method towards unmanned plane Aerial Images | |
| CN106780560B (en) | Bionic robot fish visual tracking method based on feature fusion particle filtering | |
| Vidal et al. | UAV vision aided positioning system for location and landing | |
| CN110516532B (en) | Unmanned aerial vehicle railway track line identification method based on computer vision | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| CN111709994B (en) | Autonomous unmanned aerial vehicle visual detection and guidance system and method | |
| CN112014856A (en) | Road edge extraction method and device suitable for cross road section | |
| Chiu et al. | Vision-only automatic flight control for small UAVs | |
| CN109765931A (en) | A kind of near-infrared video automatic navigation method suitable for the patrol unmanned machine of breakwater | |
| CN113433958A (en) | Unmanned aerial vehicle inspection method and device | |
| CN114428518A (en) | Fan orientation method for automatic inspection of fan blade of unmanned aerial vehicle | |
| WO2018211396A1 (en) | Detection of powerlines in aerial images | |
| Kong et al. | Infrared vision based automatic navigation and inspection strategy for photovoltaic power plant using UAVs | |
| CN112542800A (en) | Method and system for identifying transmission line fault | |
| CN114283167B (en) | Vision-based cleaning area detection method | |
| CN116893685A (en) | Unmanned aerial vehicle route planning method and system | |
| Xu et al. | Graph-based horizon line detection for UAV navigation | |
| CN115437394A (en) | Unmanned aerial vehicle system for river channel monitoring and autonomous line patrol method thereof | |
| CN112327891A (en) | Unmanned aerial vehicle autonomous landing system and method |
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 |