CN115311587A - Intelligent generation method for photovoltaic power station inspection waypoints - Google Patents
Intelligent generation method for photovoltaic power station inspection waypoints Download PDFInfo
- Publication number
- CN115311587A CN115311587A CN202211087071.0A CN202211087071A CN115311587A CN 115311587 A CN115311587 A CN 115311587A CN 202211087071 A CN202211087071 A CN 202211087071A CN 115311587 A CN115311587 A CN 115311587A
- Authority
- CN
- China
- Prior art keywords
- strings
- group
- photovoltaic power
- power station
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000007689 inspection Methods 0.000 title claims abstract description 40
- 238000012545 processing Methods 0.000 claims description 23
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 10
- 238000005520 cutting process Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 101100391182 Dictyostelium discoideum forI gene Proteins 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Processing (AREA)
Abstract
The invention provides an intelligent generation method of a photovoltaic power station inspection waypoint, which comprises the following steps: identifying and obtaining a plurality of standard group strings from the picture of the photovoltaic power station; acquiring the set number of serial columns of a group required to be covered for shooting a single picture; dividing the standard group strings into a plurality of areas according to the number of the group serial columns, wherein the number of the standard group strings of each area meets the number of the rows and the columns; determining a shooting central point of each area according to the coordinates of each standard group string of each area; and generating all routing inspection waypoints of the photovoltaic power station based on the shooting central point of each area. The method solves the technical problems that the existing method for generating the flight route waypoint is low in efficiency and has redundant data.
Description
Technical Field
The invention relates to the field of photovoltaic inspection, in particular to an intelligent generation method of an inspection waypoint of a photovoltaic power station.
Background
Under the trend of photovoltaic power generation capacity continuous growth, use unmanned aerial vehicle to carry out full-automatic patrolling and examining to photovoltaic power plant, become photovoltaic power plant operation and maintenance's mainstream way gradually, this mainly embodies patrolling and examining nimble reliable, the characteristic of safety and stability at unmanned aerial vehicle. Generally speaking, for operation and maintenance of an established power station, planning a flight path of a field station is needed, after the flight path is planned, controlling an unmanned aerial vehicle to carry out inspection according to the planned flight path, wherein a plurality of flight points exist in the planned flight path, the unmanned aerial vehicle takes a picture at each flight point of the planned flight path, and then carrying out defect identification on the picture to generate an inspection report of the photovoltaic power station.
It should be noted that the current route generation mode mainly depends on manual drawing or automatic filling of a plurality of waypoints by means of an existing tool, and the plurality of waypoints form a routing inspection route, the manual-based mode mainly has the problems of low efficiency, difficulty in determining the route height and the tilt angle of a holder and the like, and the method for automatically filling the waypoints by means of the tool mainly has the problems of more coverage and more data redundancy, so that the time consumed by flying of the unmanned aerial vehicle is long.
In summary, the existing methods for generating waypoints are inefficient and have redundant data.
The invention is provided in view of the above.
Disclosure of Invention
The invention provides an intelligent generation method of a photovoltaic power station inspection waypoint, which aims to solve the technical problems that the existing generation method of a route waypoint is low in efficiency and has redundant data.
The intelligent generation method of the routing inspection waypoint of the photovoltaic power station comprises the following steps: identifying a plurality of standard group strings from a picture of a photovoltaic power station; acquiring a set group serial column number required to be covered for shooting a single picture; dividing the standard group strings into a plurality of areas according to the number of the group serial columns, wherein the number of the standard group strings of each area meets the number of the rows and the columns; determining a shooting central point of each area according to the coordinates of each standard group string of each area; and generating all routing inspection waypoints of the photovoltaic power station based on the shooting central point of each area.
Further, a plurality of standard group strings are obtained from the picture identification of the photovoltaic power station, and the standard group strings comprise: performing string segmentation on the pictures of the photovoltaic power station to obtain a plurality of initial strings; calculating to obtain average size parameters of the plurality of initial group strings; and cutting one or more of the plurality of initial group strings according to the size parameter and the average size parameter of each initial group string to obtain the plurality of standard group strings.
Further, performing a cutting process on one or more of the plurality of initial group strings according to the size parameter and the average size parameter of each initial group string, including: calculating a multiple critical value of each initial group string relative to the average size parameter, wherein the multiple critical value comprises an upper critical value and a lower critical value, and the difference between the upper critical value and the lower critical value is smaller than a preset threshold value; dividing each initial group string into a number of segments of a lower threshold number if the ratio of the size parameter of each initial group string to the average size parameter is between the upper threshold and the lower threshold; and under the condition that the ratio of the size parameter of each initial group string to the average size parameter is less than or equal to a preset threshold value, not processing each initial group string.
Further, acquiring the set number of serial columns of the group required to be covered for shooting a single picture includes: the number of the group of series rows is odd.
Further, all patrol inspection waypoints of the photovoltaic power station are generated based on the shooting central point of each area, and the method comprises the following steps: acquiring an inclination angle of a photovoltaic group string of the photovoltaic power station and a digital surface model of the photovoltaic power station; and generating the height and horizontal plane coordinates of all routing inspection navigation points of the photovoltaic power station based on the inclination angle of the photovoltaic group string, the digital surface model and the shooting central point of each area.
Further, generating the height and horizontal plane coordinates of all patrol inspection waypoints of the photovoltaic power station based on the inclination angle of the photovoltaic group string, the digital surface model and the shooting central point of each region, and comprising: indexing is carried out from the digital surface model through the coordinates of the shooting central point of each area, and the actual altitude of the shooting central point is obtained; acquiring a first distance from a preset inspection waypoint to the shooting center; and calculating the heights and horizontal plane coordinates of all routing inspection navigation points of the photovoltaic power station according to the actual altitude of the shooting central point, the first distance and the inclination angle of the photovoltaic group string.
Further, the method comprises the steps of carrying out string segmentation on the picture of the photovoltaic power station through a trained segmentation model to obtain a plurality of initial strings, wherein the training of the segmentation model comprises the following steps: acquiring an orthoimage and a digital surface model of a photovoltaic power station; determining a minimum altitude of the photovoltaic power plant from the digital surface model; obtaining a surface model of the relative elevation of the photovoltaic power plant from all elevations on the digital surface model and the minimum altitude; extracting a first RGB three-channel image of the surface model with the relative elevation and a second RGB three-channel image of the orthoimage; and processing the first RGB three-channel image and the second RGB three-channel image into four-channel images, and inputting the four-channel images into a depth network to train so as to obtain the segmentation model.
Further, dividing the plurality of standard strings into a plurality of regions according to the number of the set of serial columns includes: acquiring coordinates of a plurality of standard group strings and sequencing the coordinates to obtain the sequence of each standard group string; respectively differentiating the coordinates of every two adjacent standard group strings in the plurality of standard group strings based on the sequence of each standard group string to obtain a plurality of differential results; dividing the plurality of standard group strings into lines according to the plurality of difference results to obtain a plurality of lines of standard group strings; the plurality of rows of standard set strings are divided into a plurality of regions according to the number of sets of serial columns.
The invention also provides an electronic device comprising a memory and a processor, the memory having stored thereon computer instructions, wherein the computer instructions, when executed by the processor, perform any of the methods described above.
The invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, causes any of the methods described above to be performed.
The invention provides an intelligent generation method of a photovoltaic power station routing inspection waypoint, which comprises the following steps: identifying and obtaining a plurality of standard group strings from the picture of the photovoltaic power station; acquiring the set number of serial columns of a group required to be covered for shooting a single picture; dividing the standard group strings into a plurality of areas according to the number of the group serial columns, wherein the number of the standard group strings of each area meets the number of the rows and the columns; determining a shooting central point of each area according to the coordinates of each standard group string of each area; and generating all routing inspection waypoints of the photovoltaic power station based on the shooting central point of each area. The method solves the technical problems that the existing method for generating the route waypoints is low in efficiency and has redundant data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of an intelligent generation method of a photovoltaic power station inspection waypoint provided by the invention;
FIG. 2 is a schematic diagram of the present invention providing a capture center computed over a plurality of initial cluster sets;
fig. 3 is a schematic diagram of a string of cutting sets provided by the present invention.
Detailed Description
In order to make the above and other features and advantages of the present invention more apparent, the present invention is further described below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are for purposes of illustration only and are not intended to be limiting.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the specific details need not be employed to practice the present invention. In other instances, well-known steps or operations are not described in detail to avoid obscuring the invention.
Example one
The invention provides an intelligent generation method of a photovoltaic power station inspection waypoint, which is combined with a figure 1 and comprises the following steps:
and S11, identifying and obtaining a plurality of standard group strings from the picture of the photovoltaic power station.
Specifically, in this scheme, a device with a data processing function, such as a server, may be used as an execution main body of the method steps of this scheme, where the photovoltaic power station may be a centralized photovoltaic power station or a distributed photovoltaic power station, and the photovoltaic power station may include a plurality of photovoltaic group strings (herein, a photovoltaic group string may be referred to as a group string for short), after obtaining a picture of the photovoltaic power station, this scheme may obtain a plurality of standard group strings by identifying from the picture through image identification, where it is to be noted that a standard group string refers to a size, and a size of each group string is within a certain range, that is, does not exceed a set standard size too much.
Optionally, the picture of the photovoltaic power station may be an orthophoto DOM of the photovoltaic power station.
And step S13, acquiring the set serial columns required to be covered for taking the single picture.
Specifically, the user may set the number of strings that are required to be covered (or included) in taking a single picture, that is, the number of horizontal and vertical strings that need to be covered in a single picture of the drone camera if the drone is at a waypoint for taking a picture.
And S15, dividing the plurality of standard group strings into a plurality of areas according to the number of the group of serial columns, wherein the number of the standard group strings of each area meets the number of the rows and the columns.
Specifically, the standard group string may be divided into a plurality of areas according to the present solution, where the number of rows and columns of the group string in each area is the number of group serial columns covered by a single picture set by a user. For example, a single picture set by a user requires that the number of covered group serial columns is 3 rows and 2 columns, and then, after the plurality of standard group strings are divided into a plurality of regions by using the group serial column number "3 rows and 2 columns", the number of the group strings in each region is "3 rows and 2 columns".
And S17, determining the shooting central point of each area according to the coordinates of each standard group string of each area.
Specifically, in the present scheme, after the area is divided into a plurality of areas, the present scheme determines the shooting center point of each area according to the coordinates of all the group strings of each area, where it should be noted that the shooting center point refers to a shooting viewpoint of the unmanned aerial vehicle camera after the unmanned aerial vehicle is at a waypoint in the future, each area corresponds to one shooting viewpoint, and the unmanned aerial vehicle camera shoots according to the shooting viewpoint and can take the picture of the group string of the area. According to the scheme, the shooting central points of all the areas in the photovoltaic power station can be obtained through the method in the step S17.
Specifically, step S17, determining a shooting center point of each area according to the coordinates of each standard group string of each area, includes:
step S171, connecting the coordinates of each standard group string of the current area, thereby determining a polygon;
step S172, acquiring a plurality of standard group strings within a preset distance from the vertex of the polygon;
and step S172, obtaining the shooting central point of the current area according to the coordinates of the plurality of standard group strings within the preset distance.
Specifically, with reference to fig. 2, if there are 3 rows and 2 columns of group strings in the current area, and the 3 rows and 2 columns of group strings include the group string 1, the group string 2, the group string 3, the group string 4, the group string 5, and the group string 6, a polygon may be determined by connecting coordinates of the six group strings (in this embodiment, coordinates of the group strings are coordinates of a center of the group string), then four group strings closest to four vertices of the quadrangle (the group string 1, the group string 2, the group string 5, and the group string 6) are screened, and a shooting center point of the current area is obtained according to the group string 1, the group string 2, the group string 5, and the group string 6.
As an example, referring to fig. 2, the coordinates of the center of the group string 1 are (a 1, a 2), the coordinates of the center of the group string 2 are (b 1, b 2), the coordinates of the center of the group string 5 are (c 1, c 2), and the coordinates of the center of the group string 6 are (d 1, d 2), and the coordinates (x, y) of the shooting center point for the current area can be calculated by the following formula:
by the mode, the shooting central point of the current area can be rapidly calculated, all the group strings of the current area can be shot through the shooting central point, and omission of the group strings cannot occur.
And S19, generating all routing inspection navigation points of the photovoltaic power station based on the shooting central point of each area.
And S21, generating all routing inspection navigation points of the photovoltaic power station based on the shooting central point of each area.
Specifically, in this scheme, can be based on the current regional waypoint of patrolling and examining of shooting center generation in every region, and then obtain all of photovoltaic power plant's all regions and patrol and examine the waypoint, all patrol and examine the waypoint and constitute unmanned aerial vehicle's the route of patrolling and examining, unmanned aerial vehicle can fly according to the above-mentioned route of patrolling and examining when carrying out the task of patrolling and examining, and then realize the acquisition of photovoltaic group cluster picture.
It should be noted that, in the prior art, the manual drawing of the patrol waypoints easily results in missing of the group strings and low efficiency, and the waypoints are automatically filled according to the specific area through the existing software, because the existing software only aims to completely cover the specific area, a large amount of redundant unnecessary waypoints are generated, so that the patrol collection data amount is increased. On the one hand, this scheme is different from drawing the waypoint through artifical manual work among the prior art, but through discerning the coordinate of every photovoltaic group cluster and then automatic generation patrol and examine the waypoint, higher promotion the efficiency that the waypoint generated, on the other hand, because the waypoint of this scheme is generated according to the coordinate of every regional every standard group cluster, therefore the waypoint quantity of this scheme examination can not take place the redundancy, can just in time cover every group cluster, this scheme can gather the picture of all group clusters of power station with minimum waypoint, the redundancy of data acquisition has been reduced.
Optionally, step S11 obtains a plurality of standard strings from the picture identification of the photovoltaic power station, including:
and step S111, performing string segmentation on the pictures of the photovoltaic power station to obtain a plurality of initial strings.
Specifically, after the orthographic image of the photovoltaic power station is obtained, the method can adopt the group string segmentation model to carry out group string segmentation or recognition on the picture of the photovoltaic power station so as to obtain a plurality of initial group strings.
Step S113, calculating an average size parameter of the plurality of initial group strings.
Specifically, the method may count a size parameter of each initial string set, and then calculate to obtain an average size parameter of the initial string set, where the size parameter may be a width of the string set or a high level, and the average size parameter is an average width of all the initial string setsOr average height。
And step S115, cutting one or more of the plurality of initial group strings according to the size parameter and the average size parameter of each initial group string to obtain the plurality of standard group strings.
Specifically, for the initial group strings whose width or height is significantly higher than the average size parameter, it means that an error occurs during image recognition, and two group strings may be mistakenly recognized as one group string, and at that time, the size of the initial group string after being mistakenly recognized is inevitably higher than the average size, so for the initial group string whose size parameter is higher than the average size parameter, the present scheme performs a cutting process, and obtains a plurality of standard group strings.
Optionally, the size parameter of each initial group string is a width and a height of each initial group string, where in step S115, the cutting process is performed on one or more of the plurality of initial group strings according to the size parameter of each initial group string and the average size parameter, so as to obtain the plurality of standard group strings, and the method includes:
step S1151, calculating a multiple critical value of each initial group string relative to the average size parameter, wherein the multiple critical value includes an upper critical value and a lower critical value, and a difference between the upper critical value and the lower critical value is smaller than a preset threshold;
step S1152, dividing each initial group string into the number of segments of the lower bound critical value number when the ratio of the size parameter of each initial group string to the average size parameter is between the upper bound critical value and the lower bound critical value;
and under the condition that the ratio of the size parameter of each initial group string to the average size parameter is less than or equal to a preset threshold value, not processing each initial group string.
The following exemplifies steps S1151 to S1152:
each initial string is any one of a plurality of initial strings, the size parameters of the initial strings can be width W and height H, and the average size parameter is the median of width WMedian of high HFirstly, the methodCalculate W, H forIs assumed to have an upper bound corresponding to W max 、H max The lower bound corresponds to W min 、H min Wherein W is max 、H max 、W min 、H min Are all positive integers greater than 1, and:
W max -W min =1
H max -H min =1
satisfies the following conditions:
in this case, W should be equally divided into W min Segment H is divided into H min Section one, whenOrAnd if so, not processing the current group string.
Continuing with the example from step S1151 to step S1152, for example, if the parameter of the initial group string (taking width as an example) is 11, and the average size parameter of the initial group string (average height of all the initial group strings) is 5, then at this time, through calculation, 11 ÷ 5=2.2, the quotient 2 of the parameter of the initial group string and the average size parameter is the lower-bound threshold value, and the quotient of the parameter of the initial group string and the average size parameter is increased by 1 if there is a remainder, that is, 2 = 1=3,3 is the upper-bound threshold value. Then 2.2 is between the lower bound of 2 and the upper bound of 3, then the initial group string is divided into 2 segments.
For example, referring to fig. 3, fig. 3 is a plurality of initial group strings after image recognition, in fig. 2, there are 5 group strings, group string a, group string B, group string C, group string D, and group string E, where the size of group string E is significantly different from that of group string a, group string B, group string C, and group string D, and this scheme may determine to cut group string D after the calculation in steps S1151 to S1152, so as to cut group string D into two segments.
Optionally, the number of the group series rows and columns required to be covered by the single picture is odd. The technical effect of this way of setting is described below:
when the number of the series of rows and columns covered by a single picture is required to be shot is odd, the shooting center can be positioned at the centers of all the series of columns in the single picture, and therefore when the inspection tour waypoint collects the inspection tour image, as many series of columns as possible are close to the image center, and the influence of later-stage distortion on the inspection tour image processing is reduced as much as possible.
It should be noted that, in the prior art, in actual inspection shooting, the boundary of an image inevitably has distortion, which affects subsequent image processing, and in order to reduce the distortion in inspection image processing, the distortion problem can be solved at low cost and low cost by controlling the number of series rows and columns covered by a single image to be an odd number.
It should be further noted that, according to the scheme, the number of rows and columns to be covered in the process of shooting a single picture is determined, and then the shooting center and the waypoint are obtained by calculating based on the number of rows and columns to be covered, and the image is acquired through the shooting center and the waypoint, so that the image influence caused by distortion can be effectively relieved.
Optionally, step S19 generates all routing inspection waypoints of the photovoltaic power station based on the shooting center point of each region, including:
and step S191, acquiring the inclination angle of the photovoltaic string of the photovoltaic power station and a Digital Surface Model (DSM) of the photovoltaic power station.
And step S192, generating all routing inspection navigation points of the photovoltaic power station based on the inclination angle theta of the photovoltaic group string, a Digital Surface Model (DSM) and the shooting central point of each area.
Optionally, step S192 generates all routing inspection waypoints of the photovoltaic power station based on the inclination angle of the photovoltaic string, the digital surface model, and the shooting center point of each area, including:
step S1921, indexing is carried out from the digital surface model through the coordinates of the shooting central point of each area, and the actual altitude of the shooting central point is obtained.
Step S1922, a first distance from a preset routing inspection waypoint to the shooting center is obtained.
And S1923, calculating the heights and horizontal plane coordinates of all routing inspection waypoints of the photovoltaic power station according to the actual altitude of the shooting central point, the first distance and the inclination angle of the photovoltaic group string.
Specifically, the scheme can be based on the coordinate (x) of the shooting center 1 ,y 1 ) Indexing the actual altitude h of the shooting center on the digital surface model DSM d Assuming that the inclination angle of the cluster is θ and the distance from the waypoint to the shooting center is a fixed value m (i.e., the first distance), the actual flying height of the unmanned aerial vehicle (i.e., the flying height of the waypoint) is h d + m sin θ, corresponding to the projection coordinates of the patrol waypoint on the horizontal plane as (x) 2 ,y 2 ) Wherein:
x 2 =x 1
y 2 =y 1 -m cosθ
optionally, the trained segmentation model is used to perform string segmentation on the picture of the photovoltaic power station to obtain a plurality of initial strings, wherein the training of the segmentation model includes:
and step S1101, acquiring an orthoimage and a digital surface model of the photovoltaic power station.
And step S1102, determining the lowest altitude of the photovoltaic power station through the digital surface model.
Step S1103, obtaining a surface model of the relative elevation of the photovoltaic power station through all elevations on the digital surface model and the lowest elevation.
And step S1104, extracting a first RGB three-channel image of the surface model with the relative elevation and a second RGB three-channel image of the ortho-image.
Step S1105, processing the first RGB three-channel image and the second RGB three-channel image into four-channel images, and inputting the four-channel images into a depth network to train and obtain the segmentation model.
The following describes the steps S1101 to S1105 further:
the orthographic image (DOM) contains appearance information and geographic coordinates of the power station, and the Digital Surface Model (DSM) contains elevation information of the power station. For the processing of the surface model, firstly, an interval image used for training is extracted according to the same geographic interval and range, then the lowest elevation of the whole DSM is calculated, then the lowest elevation of the DSM is subtracted from the elevation of all geographic coordinates on the whole DSM to obtain the surface model representing the relative elevation, and finally the surface model containing the relative elevation is subjected to normalization processing to obtain the final processing result of the DSM. And extracting images of R, G and B3 channels of the DOM, carrying out normalization processing on each channel to obtain a DOM processing result, carrying out CAT processing on 3 channel images after DOM processing and 3 channel images after DSM processing, and sending the 3 channel images as a normal 4 channel image into a deep learning model for training.
It should be noted that, when performing cluster segmentation, the appearance information of the orthographic image DOM and the elevation information of the digital surface model DSM may be fused to perform combination training, so as to achieve the purpose of improving the cluster extraction accuracy.
It should be further noted that, in this embodiment, a DOM and DSM fusion training mode is adopted, so that the accuracy of string segmentation is improved, multiple post-processing methods are adopted for segmentation results, the robustness of a route generation tool is ensured, and meanwhile, an inspection center is set according to the arrangement of strings, so that images of the whole power station can be acquired at the minimum number of shooting points, and the redundancy of acquired data is reduced.
Optionally, step S15 divides the plurality of standard group strings into a plurality of areas according to the number of the group of serial columns, and includes:
step S151, obtaining coordinates of a plurality of standard group strings and sequencing the coordinates to obtain the sequence of each standard group string.
Specifically, the coordinates of the plurality of standard group strings may be vertical coordinates, and the present solution may sort the plurality of standard group strings according to the size of the vertical coordinates, where it should be noted that, in this document, the coordinates of the group strings refer to the coordinates of the center of the extracted group string. Suppose that the ordinate arrangement order (order) of the extraction group string centers is y 1 、y 2 、y 3 …y n Wherein y is satisfied 1 ≤y 2 ≤y 3 …y n 。
And step S152, respectively carrying out difference processing on the coordinates of every two standard group strings adjacent to each other in the sequence in the plurality of standard group strings based on the sequence of each standard group string to obtain a plurality of difference results.
Specifically, the present solution may perform difference on the above ordinate, and the difference result is: d is a radical of 1 =y 2 -y 1 ,d 2 =y 3 -y 2 ,…d n-1 =y n -y n-1 (ii) a D above 1 To d n-1 For a plurality of difference results, it should be noted that the difference result may be a row pitch of the group string.
Step S153, dividing the plurality of standard group strings into rows according to the plurality of difference results to obtain a plurality of rows of standard group strings.
Specifically, the differential result is counted by the scheme, and more specifically, the distance can be adopted as a basis to perform DBSCAN clustering on the differential result, and the clustering is performed by 1.5As a cluster radius, 2And clustering the effective interval to obtain a single type of the clustering results, namely the line type results divided according to the line spacing, namely the method classifies the difference values belonging to a range as the group strings of the same line.
The above steps S151 to S153 may be a process of grouping strings according to the line spacing.
Step S154, dividing the plurality of standard group strings into a plurality of areas according to the number of the group of serial columns.
Specifically, after knowing the rows of the group strings (i.e., which row the group string belongs to), the scheme can quickly and accurately divide the group strings from the multi-row standard group strings into a plurality of areas according to the number of the group strings to be covered by a set single picture.
It will be understood that the specific features, operations, and details described herein above with respect to the method of the present invention may be similarly applied to the apparatus and system of the present invention, or vice versa. Further, each step of the method of the invention described above may be performed by a respective component or unit of the device or system of the invention.
It should be understood that the various modules/units of the apparatus of the present invention may be implemented in whole or in part by software, hardware, firmware, or a combination thereof. The modules/units may be embedded in the processor of the computer device in the form of hardware or firmware or independent from the processor, or may be stored in the memory of the computer device in the form of software for being called by the processor to execute the operations of the modules/units. Each of the modules/units may be implemented as a separate component or module, or two or more modules/units may be implemented as a single component or module.
In one embodiment, a computer device is provided that includes a memory and a processor, the memory having stored thereon computer instructions executable by the processor that, when executed by the processor, instruct the processor to perform the steps of the method of an embodiment of the invention. The computer device may broadly be a server, a terminal, or any other electronic device having the necessary computing and/or processing capabilities. In one embodiment, the computer device may include a processor, memory, a network interface, a communication interface, etc., connected by a system bus. The processor of the computer device may be used to provide the necessary computing, processing and/or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, and the like may be stored in or on the non-volatile storage medium. The internal memory may provide an environment for the operating system and the computer programs in the non-volatile storage medium to run. The network interface and the communication interface of the computer device may be used to connect and communicate with an external device via a network. Which when executed by a processor performs the steps of the method of the invention.
The invention may be implemented as a computer readable storage medium having stored thereon a computer program which, when executed by a processor, causes the steps of a method of an embodiment of the invention to be performed. In one embodiment, the computer program is distributed across a plurality of computer devices or processors coupled by a network such that the computer program is stored, accessed, and executed by one or more computer devices or processors in a distributed fashion. A single method step/operation, or two or more method steps/operations, may be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps/operations may be performed by one or more computer devices or processors, and one or more other method steps/operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step/operation, or perform two or more method steps/operations.
It will be appreciated by those of ordinary skill in the art that the method steps of the present invention may be directed to associated hardware, such as a computer device or processor, for performing the steps of the present invention by a computer program, which may be stored in a non-transitory computer readable storage medium, which when executed causes the steps of the present invention to be performed. Any reference herein to memory, storage, databases, or other media may include non-volatile and/or volatile memory, as appropriate. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, hard disk, solid state disk, and the like. Examples of volatile memory include Random Access Memory (RAM), external cache memory, and the like.
The respective technical features described above may be arbitrarily combined. Although not all possible combinations of features are described, any combination of features should be considered to be covered by the present specification as long as such combination is not contradictory.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent generation method for a photovoltaic power station routing inspection waypoint is characterized by comprising the following steps:
identifying and obtaining a plurality of standard group strings from the picture of the photovoltaic power station;
acquiring the set number of serial columns of a group required to be covered for shooting a single picture;
dividing the standard group strings into a plurality of areas according to the number of the group serial columns, wherein the number of the standard group strings of each area meets the number of the rows and the columns;
determining a shooting central point of each area according to the coordinates of each standard group string of each area;
and generating all routing inspection waypoints of the photovoltaic power station based on the shooting central point of each area.
2. The method of claim 1, wherein identifying the plurality of standard group strings from the picture of the photovoltaic power plant comprises:
performing string segmentation on the pictures of the photovoltaic power station to obtain a plurality of initial strings;
calculating to obtain average size parameters of the plurality of initial group strings;
and cutting one or more of the plurality of initial group strings according to the size parameter and the average size parameter of each initial group string to obtain the plurality of standard group strings.
3. The method of claim 2, wherein the cutting one or more of the plurality of initial group strings according to the size parameter and the average size parameter of each initial group string comprises:
calculating a multiple critical value of each initial group string relative to the average size parameter, wherein the multiple critical value comprises an upper critical value and a lower critical value, and the difference between the upper critical value and the lower critical value is smaller than a preset threshold value;
dividing each initial group string into a number of segments of a lower threshold number if the ratio of the size parameter of each initial group string to the average size parameter is between the upper threshold and the lower threshold;
and under the condition that the ratio of the size parameter of each initial group string to the average size parameter is less than or equal to a preset threshold value, not processing each initial group string.
4. The method according to claim 1, wherein obtaining the set number of serial columns of the group required to be covered for taking a single picture comprises:
the number of the group of series rows is odd.
5. The method of claim 1, wherein generating all inspection waypoints for the photovoltaic power plant based on the center point of capture for each area comprises:
acquiring an inclination angle of a photovoltaic group string of the photovoltaic power station and a digital surface model of the photovoltaic power station;
and generating the height and horizontal plane coordinates of all routing inspection navigation points of the photovoltaic power station based on the inclination angle of the photovoltaic group string, the digital surface model and the shooting central point of each area.
6. The method of claim 5, wherein generating the height and horizontal plane coordinates of all inspection waypoints of the photovoltaic power plant based on the inclination of the string of photovoltaic strings, the digital surface model, and the shot center point for each region comprises:
indexing is carried out from the digital surface model through the coordinates of the shooting central point of each area, and the actual altitude of the shooting central point is obtained;
acquiring a first distance from a preset inspection waypoint to the shooting center;
and calculating the heights and horizontal plane coordinates of all routing inspection navigation points of the photovoltaic power station according to the actual altitude of the shooting central point, the first distance and the inclination angle of the photovoltaic group string.
7. The method of claim 1, wherein the group string segmentation of the picture of the photovoltaic power plant is performed by a trained segmentation model to obtain a plurality of initial group strings, wherein the training of the segmentation model comprises:
acquiring an orthoimage and a digital surface model of a photovoltaic power station;
determining a minimum altitude of the photovoltaic power plant through the digital surface model;
obtaining a surface model of the relative elevation of the photovoltaic power station from all elevations on the digital surface model and the minimum altitude;
extracting a first RGB three-channel image of the surface model with the relative elevation and a second RGB three-channel image of the orthographic image;
and processing the first RGB three-channel image and the second RGB three-channel image into four-channel images, and inputting the four-channel images into a depth network for training to obtain the segmentation model.
8. The method of claim 1, wherein dividing the plurality of standard strings into a plurality of regions according to the number of strings comprises:
acquiring coordinates of a plurality of standard group strings and sequencing the coordinates to obtain the sequence of each standard group string;
respectively carrying out differential processing on the coordinates of every two standard group strings adjacent to each other in the sequence in the plurality of standard group strings based on the sequence of each standard group string to obtain a plurality of differential results;
dividing the plurality of standard group strings into lines according to the plurality of difference results to obtain a plurality of lines of standard group strings;
the plurality of rows of standard set strings are divided into a plurality of regions according to the number of sets of serial columns.
9. An electronic device comprising a memory and a processor, the memory having stored thereon computer instructions, wherein the computer instructions, when executed by the processor, cause the method of any of claims 1 to 8 to be performed.
10. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, causes the method of any of claims 1 to 8 to be performed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211087071.0A CN115311587B (en) | 2022-09-07 | 2022-09-07 | Intelligent generation method for photovoltaic power station inspection waypoints |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211087071.0A CN115311587B (en) | 2022-09-07 | 2022-09-07 | Intelligent generation method for photovoltaic power station inspection waypoints |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115311587A true CN115311587A (en) | 2022-11-08 |
CN115311587B CN115311587B (en) | 2024-05-31 |
Family
ID=83866135
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211087071.0A Active CN115311587B (en) | 2022-09-07 | 2022-09-07 | Intelligent generation method for photovoltaic power station inspection waypoints |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115311587B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117132419A (en) * | 2023-10-26 | 2023-11-28 | 北京图知天下科技有限责任公司 | Numbering method of photovoltaic module |
CN117968705A (en) * | 2024-04-02 | 2024-05-03 | 广东电网有限责任公司佛山供电局 | Cable line inspection method and device, readable storage medium and processor |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170192418A1 (en) * | 2015-12-30 | 2017-07-06 | Unmanned Innovation, Inc. | Unmanned aerial vehicle inspection system |
CN109636787A (en) * | 2018-12-11 | 2019-04-16 | 哈尔滨工业大学 | Battery point quality automatic testing method when a kind of high-precision real based on deep learning |
CN110244766A (en) * | 2019-07-03 | 2019-09-17 | 王峰 | A kind of method and system for planning in photovoltaic plant unmanned plane inspection course line |
CN112034878A (en) * | 2020-11-05 | 2020-12-04 | 北京云圣智能科技有限责任公司 | Unmanned aerial vehicle-based power inspection method and device and electronic equipment |
CN113311861A (en) * | 2021-05-14 | 2021-08-27 | 国家电投集团青海光伏产业创新中心有限公司 | Automatic detection method and system for photovoltaic module subfissure characteristics |
CN113591729A (en) * | 2021-08-03 | 2021-11-02 | 浙江农林大学 | Urban forest single-tree crown detection method combining RGB-DSM image and deep learning |
CN114758002A (en) * | 2022-06-15 | 2022-07-15 | 南开大学 | Photovoltaic string position determining method and system based on aerial image |
CN114935942A (en) * | 2022-05-20 | 2022-08-23 | 无锡海纳智能科技有限公司 | Method for determining inspection route of distributed photovoltaic power station and electronic equipment |
-
2022
- 2022-09-07 CN CN202211087071.0A patent/CN115311587B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170192418A1 (en) * | 2015-12-30 | 2017-07-06 | Unmanned Innovation, Inc. | Unmanned aerial vehicle inspection system |
CN109636787A (en) * | 2018-12-11 | 2019-04-16 | 哈尔滨工业大学 | Battery point quality automatic testing method when a kind of high-precision real based on deep learning |
CN110244766A (en) * | 2019-07-03 | 2019-09-17 | 王峰 | A kind of method and system for planning in photovoltaic plant unmanned plane inspection course line |
CN112034878A (en) * | 2020-11-05 | 2020-12-04 | 北京云圣智能科技有限责任公司 | Unmanned aerial vehicle-based power inspection method and device and electronic equipment |
CN113311861A (en) * | 2021-05-14 | 2021-08-27 | 国家电投集团青海光伏产业创新中心有限公司 | Automatic detection method and system for photovoltaic module subfissure characteristics |
CN113591729A (en) * | 2021-08-03 | 2021-11-02 | 浙江农林大学 | Urban forest single-tree crown detection method combining RGB-DSM image and deep learning |
CN114935942A (en) * | 2022-05-20 | 2022-08-23 | 无锡海纳智能科技有限公司 | Method for determining inspection route of distributed photovoltaic power station and electronic equipment |
CN114758002A (en) * | 2022-06-15 | 2022-07-15 | 南开大学 | Photovoltaic string position determining method and system based on aerial image |
Non-Patent Citations (2)
Title |
---|
LIPING SHI ET AL.: "Inspection Path Planning for Aerial Vehicles via Sampling-based Sequential Optimization", 2021 INTERNATIONAL CONFERENCE ON UNMANNED AIRCRAFT SYSTEMS (ICUAS), pages 679 - 687 * |
张欢: "基于React的输电线路智能机巡系统的设计与实现", 万方数据, pages 1 - 89 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117132419A (en) * | 2023-10-26 | 2023-11-28 | 北京图知天下科技有限责任公司 | Numbering method of photovoltaic module |
CN117132419B (en) * | 2023-10-26 | 2024-01-23 | 北京图知天下科技有限责任公司 | Numbering method of photovoltaic module |
CN117968705A (en) * | 2024-04-02 | 2024-05-03 | 广东电网有限责任公司佛山供电局 | Cable line inspection method and device, readable storage medium and processor |
Also Published As
Publication number | Publication date |
---|---|
CN115311587B (en) | 2024-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115311587A (en) | Intelligent generation method for photovoltaic power station inspection waypoints | |
CN110363861B (en) | Laser radar point cloud-based field crop three-dimensional reconstruction method | |
CN103218817B (en) | The dividing method of plant organ point cloud and system | |
CN107014827A (en) | Transmission line of electricity defect analysis method based on image processing, device and system | |
CN109002048B (en) | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method | |
CN113269791B (en) | Point cloud segmentation method based on edge judgment and region growth | |
CN114419085A (en) | Automatic building contour line extraction method and device, terminal device and storage medium | |
CN113400460B (en) | Binding method and binding device for reinforcing steel bars | |
CN113296543B (en) | Method and system for planning aerial route | |
CN111581711B (en) | Tower modeling method and device, terminal equipment and computer readable storage medium | |
CN113632035B (en) | System and method for surface feature detection and traversal | |
CN111582156B (en) | High and large vegetation extraction method based on oblique photography urban three-dimensional model | |
CN111895907B (en) | Electricity tower point cloud extraction method, system and equipment | |
CN115187803A (en) | Positioning method for picking process of tender shoots of famous tea | |
WO2021051268A1 (en) | Machine vision-based tree type identification method and apparatus | |
CN113470017B (en) | Power transmission line safety early warning detection method, device and equipment based on artificial intelligence | |
CN113298768B (en) | Cotton detection, segmentation and counting method and system | |
CN112651390B (en) | Method and device for counting picture human heads based on convolutional neural network | |
CN114066910A (en) | Automatic extraction method and system for model effective area of unmanned aerial vehicle photogrammetry | |
JP6874987B2 (en) | Feature shape extraction device, feature shape extraction method, and program | |
CN115937466B (en) | GIS-fused three-dimensional model generation method, system and storage medium | |
CN116482700A (en) | Robust unmanned plane laser radar line-imitating tower recognition method and device | |
CN112991303B (en) | Automatic extraction method of electric tower insulator string based on three-dimensional point cloud | |
CN114625166B (en) | Intelligent positioning method for shooting position of unmanned aerial vehicle | |
CN115721296A (en) | Wild animal identification system based on PaddleDeprotection |
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 |