CN116758142A - Defect component positioning method and device for image geographic registration - Google Patents
Defect component positioning method and device for image geographic registration Download PDFInfo
- Publication number
- CN116758142A CN116758142A CN202310548294.0A CN202310548294A CN116758142A CN 116758142 A CN116758142 A CN 116758142A CN 202310548294 A CN202310548294 A CN 202310548294A CN 116758142 A CN116758142 A CN 116758142A
- Authority
- CN
- China
- Prior art keywords
- defect
- string
- base map
- information
- aerial image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 308
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000013507 mapping Methods 0.000 claims abstract description 75
- 230000002950 deficient Effects 0.000 claims description 60
- 230000009466 transformation Effects 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 abstract description 9
- 238000012545 processing Methods 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 6
- 230000004807 localization Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the field of image processing, in particular to a method, a device, equipment and a computer readable storage medium for positioning a defect component of image geographic registration, which are used for acquiring aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information; determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information; determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio; determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information; and determining longitude and latitude information of the defect component according to the mapping defect position information. According to the invention, the aerial image is combined with the power station base map, and the initial area where the defect component exists is rapidly determined on the premise of not involving complex feature point matching, so that the positioning efficiency and the maintenance efficiency of the defect component are improved.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to a method, an apparatus, a device, and a computer readable storage medium for positioning a defective component in image geographic registration.
Background
At present, energy safety and sustainable development become increasingly important problems in various societies, along with continuous progress and continuous reduction of cost of photovoltaic power generation technology, photovoltaic power generation has become one of dominant renewable energy sources, along with continuous increase of clean energy demand, scale of photovoltaic power stations such as number and area of components are also continuously enlarged, and component defect problems of photovoltaic power stations are also increasingly prominent.
In recent years, a scheme of carrying out photovoltaic inspection by adopting an unmanned aerial vehicle is widely applied. Unmanned aerial vehicle can patrol and examine photovoltaic power plant fast, high-efficient, has improved the efficiency of patrolling and examining greatly. Compare traditional manual work and patrol and examine, unmanned aerial vehicle patrol and examine can effectively reduce the human cost, can acquire photovoltaic power plant's operation data and abnormal conditions fast. Through various sensors and the double-light camera that unmanned aerial vehicle carried, can collect a large amount of data of patrolling and examining, these data can conveniently record and analysis to the behavior of photovoltaic power plant is known better. When unmanned aerial vehicle takes photo by plane, generally carry GPS global positioning system to obtain the position and the speed information of aircraft, these geographic information can provide accurate position benchmark for the location of photovoltaic region. Meanwhile, the unmanned aerial vehicle can acquire image information of the photovoltaic area through the camera, and the images can provide information on the position, angle, size, layout and the like of the photovoltaic panel.
At present, most of positioning schemes of power stations only detect whether a defective component exists in an image manually only through a thermal infrared image acquired after inspection of an unmanned aerial vehicle, if the defective component exists, longitude and latitude information of the image is recorded, and the longitude and latitude information of the image is imported into map navigation software to realize maintenance of the defective component when the maintenance is performed manually, but because the positioning information is too wide, maintenance personnel are required to spend a large amount of time to perform large-scale screening on an area covered by the infrared image, and the time and labor consumption are low.
In summary, how to improve the positioning accuracy and the positioning efficiency of the defective component in the inspection process of the photovoltaic power station becomes a problem to be solved in the prior art.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a computer readable storage medium for positioning a defective component in image geographic registration, which are used for solving the problems of poor positioning precision and low positioning efficiency of inspection of a photovoltaic power station in the prior art.
In order to solve the technical problems, the invention provides a defective component positioning method for image geographic registration, comprising the following steps:
acquiring aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information;
Determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information;
determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio;
determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information;
and determining longitude and latitude information of the defect component according to the mapping defect position information.
Optionally, in the method for positioning a defective component in image geographic registration, the method for obtaining a resolution ratio includes:
acquiring a shooting height corresponding to the aerial image;
the resolution ratio s is determined according to the following equation:
wherein H is the shooting height, P is the pixel size of a shooting sensor corresponding to the aerial image, f is the focal length of the shooting sensor, dp M For the spatial resolution of the plant floor.
Optionally, in the method for positioning a defective component in image geographic registration, the determining a base map sub-map according to the photographed pixel coordinates, the aerial photographed image and the resolution ratio includes:
determining the base graph sub-graph M by 1 ：
p＝max(I w *s，I H *s)
Wherein M is x M is the abscissa of the shooting pixel coordinate y P is the side length of the base map sub-graph, I is the ordinate of the shooting pixel coordinate W For the width of the aerial image, I H For the height of the aerial image, s is the resolution ratio, ma:b, c:d]The coordinate system of the power station base map is a rectangular area enclosed by a horizontal axis from a coordinate a to a coordinate b and a vertical axis from a coordinate c to a coordinate d.
Optionally, in the method for positioning a defective component in image geographic registration, the determining the mapping defect position information on the base map sub-map according to the base map sub-map, the aerial image and the defect component position information includes:
extracting photovoltaic string information of the base map subgraph, and extracting aerial string information of the aerial image;
relatively rotating the base map subgraph and the aerial image, and recording the overlapping degree of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map subgraph and the aerial image are in different relative rotation angles;
when the overlapping degree of the string outline corresponding to the photovoltaic string information and the string outline corresponding to the aerial string information is maximum, the relative rotation angle between the base map subgraph and the aerial image is used as an optimal rotation angle;
And determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image, the optimal rotation angle and the defect component position information.
Optionally, in the method for positioning a defective component in image geographic registration, the determining the mapping defect position information on the base map sub-map according to the base map sub-map, the aerial image, the optimal rotation angle and the defective component position information includes:
taking the base map subgraph as a reference image, taking the aerial image as an image to be matched, and carrying out coordinate transformation on the aerial image to obtain mapping defect position information on the base map subgraph by the following steps:
wherein, (x) d ’,y d ') is the mapping defect location information, (x) d ,y d ) For the defective component position information, W is a coordinate transformation matrix, I W For the width of the aerial image, I H For the height of the aerial image, M W For the width of the base graph sub-graph, M H For the height of the base graph sub-graph, s is the resolution ratio, θ best Is the optimal rotation angle.
Optionally, in the method for positioning a defective component in image geographic registration, when the recorded base map subgraph and the aerial image are at different relative rotation angles, the overlapping degree of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information includes:
Recording the intersection ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map subgraph and the aerial image are at different relative rotation angles;
correspondingly, when the overlapping degree of the string outline corresponding to the photovoltaic string information and the string outline corresponding to the aerial string information is maximum, the relative rotation angle between the base map subgraph and the aerial image as the optimal rotation angle comprises:
and when the intersection ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information is maximum, the relative rotation angle between the base map sub-graph and the aerial image is used as the optimal rotation angle.
Optionally, in the method for positioning a defective component in image geographic registration, the determining the mapping defect position information on the base map sub-map according to the base map sub-map, the aerial image and the defect component position information includes:
and determining mapping defect position information on the base map subgraph and defect group strings corresponding to all defects according to the base map subgraph, the aerial image and the defect component position information.
Optionally, in the method for positioning defect components in image geographic registration, the determining process of the defect group string corresponding to each defect includes:
extracting photovoltaic string information of the base map subgraph;
and searching and determining a defect group string corresponding to each defect by utilizing the centroid of the nearest neighbor region according to the mapping defect position information and the group string outline corresponding to the photovoltaic group string information.
Optionally, in the method for positioning a defect component in image geographic registration, determining mapping defect position information on the base map sub-map according to the base map sub-map, the aerial image and the defect component position information, and a defect group string corresponding to each defect includes:
determining to-be-adjusted defect coordinates on the aerial image according to the aerial image, the shooting pixel coordinates and the defect component position information;
extracting photovoltaic string information of the base map subgraph, and extracting aerial string information of the aerial image;
determining a defect string pair corresponding to each defect according to the to-be-adjusted defect coordinates and the photovoltaic string information; the defect group string pair comprises a defect photovoltaic group string corresponding to the defect on the base map subgraph and a defect aerial group string corresponding to the aerial image;
Judging whether the difference between the length of the long axis of the defective photovoltaic group string and the length of the long axis of the defective aerial group string exceeds a preset tolerance threshold;
when the difference between the length of the long axis of the defect photovoltaic group string and the length of the long axis of the defect aerial group string exceeds the tolerance threshold, obtaining the optimal angular point coordinates of the defect photovoltaic group string and the optimal angular point coordinates of the defect aerial group string;
according to the difference between the length of the long axis of the defect photovoltaic string and the length of the long axis of the defect aerial group string, adjusting the optimal angular point coordinates of the defect photovoltaic string along the long axis direction of the defect photovoltaic string to obtain the calibrated optimal angular point coordinates of the defect photovoltaic string;
calculating the optimal angular point coordinates of the defect aerial photographing group string and the relative position difference between the defect coordinates to be adjusted;
and determining mapping defect position information on the base map subgraph according to the relative position difference and the calibration optimal angular point coordinates.
A defective component localization device for image geographic registration, comprising:
the acquisition module is used for acquiring the aerial image, the corresponding shooting longitude and latitude information and the corresponding defect component position information;
the pixel coordinate conversion module is used for determining shooting pixel coordinates according to the prestored power station base map and the shooting longitude and latitude information;
The sub-graph dividing module is used for determining a base graph sub-graph according to the shooting pixel coordinates, the aerial image and the resolution ratio;
the mapping defect module is used for determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information;
and the defect longitude and latitude module is used for determining longitude and latitude information of the defect component according to the mapping defect position information.
According to the defect component positioning method for image geographic registration, aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information are obtained; determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information; determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio; determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information; and determining longitude and latitude information of the defect component according to the mapping defect position information.
According to the invention, the aerial image is combined with the power station base map, the initial area (namely the base map sub-map) where the defect component exists is rapidly determined on the premise that complex characteristic point matching is not involved, so that the positioning efficiency of the defect component is greatly improved, meanwhile, the accuracy and precision of the longitude and latitude information of the defect component on the power station base map can be greatly improved through the aerial image and the corresponding shooting longitude and latitude information, the position of the defect component is conveniently and rapidly confirmed by subsequent inspection personnel, and the maintenance efficiency is improved. The invention also provides a defective component positioning device, equipment and a computer readable storage medium for image geographic registration with the beneficial effects.
Drawings
For a clearer description of embodiments of the invention or of the prior art, the drawings that are used in the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an embodiment of a method for locating defective components for image geographic registration according to the present invention;
FIG. 2 is a schematic diagram of a power station of an embodiment of a method for locating defective components in image geographic registration according to the present invention;
FIG. 3 is a mask image of a base map sub-map of one embodiment of a method for locating defective components for image geographic registration provided by the present invention;
FIG. 4 is a mask image of an aerial image of one embodiment of a defective component localization method for image geographic registration provided by the present invention;
FIG. 5 is a schematic diagram of a base map sub-map versus an aerial image of one embodiment of a method for locating defective components for geographic registration of images provided by the present invention;
FIG. 6 is a schematic structural diagram of an embodiment of a defective component positioning device for image geographic registration according to the present invention.
The drawing comprises a 100-acquisition module, a 200-pixel coordinate conversion module, a 300-sub-image division module, a 400-mapping defect module and a 500-defect longitude and latitude module.
Detailed Description
In order to accurately position defect points on a large-scale power station scene base map by unmanned aerial vehicle inspection, a full-scene power station base map is generated while a single aerial image is acquired, the base map is usually a grid map, the geographic precision of pixel level is achieved, and the defect component positioning method combining aerial image with base map geographic information is not fully utilized at present.
In order to better understand the aspects of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The core of the present invention is to provide a method for positioning a defective component in image geographic registration, wherein a flow diagram of one embodiment is shown in fig. 1, and the method is referred to as embodiment one, and includes:
s101: and acquiring aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information.
In the process of unmanned aerial vehicle patrol shooting of the photovoltaic power station, shooting is usually performed vertically downwards by the sky, so shooting longitude and latitude information in shooting can be regarded as longitude and latitude information of the geometric midpoint of the corresponding aerial image.
S102: and determining shooting pixel coordinates according to the prestored power station base map and the shooting longitude and latitude information.
In this step, the shooting latitude and longitude information may follow the transformation sequence of the geographic coordinate system, the projection coordinate system and the grid pixel coordinate system by means of a spatial coordinate transformation model, so as to obtain the shooting pixel coordinate.
And the shooting pixel coordinates are coordinates of pixel points corresponding to the shooting longitude and latitude information on the power station base map.
Referring to fig. 2, fig. 2 is a schematic diagram of the power station base map in an embodiment, in which all strings of the power station are included.
S103: and determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio.
On the one hand, the resolution ratio in this step is a preset fixed value; on the other hand, the corresponding resolution ratio may also be determined for each of the aerial images by a preset calculation method, and the specific steps include:
a1: and acquiring the shooting height corresponding to the aerial image.
It should be noted that, the shooting height corresponding to the aerial image in this step only needs to be before step A2, and there is no strict sequence between the shooting height and steps S101 and S102, and the shooting height can be adjusted accordingly according to actual needs.
A2: determining the resolution ratio s according to the following formula (1):
wherein H is the shooting height, the unit is meter, P is the pixel size of a shooting sensor corresponding to the aerial image, the unit is micrometers, f is the focal length of the shooting sensor, the unit is millimeter, dp M For the spatial resolution of the plant floor.
The formula (1) starts from the pixel generation principle of the aerial image, determines the proportional relation between each pixel point in the aerial image and the pixel point of the power station base map, and the proportional relation is all hardware fixed value except the shooting height, can be input into a computing system in advance, is easy to calculate and has extremely high accuracy.
Further, the specific process of determining the base graph sub-graph in this step includes:
determining the base map subgraph M by the following formula (2) and formula (3) 1 ：
p＝max(I W *s，I H *s).........................(3)
Wherein M is x M is the abscissa of the shooting pixel coordinate y P is the side length of the base map sub-graph, I is the ordinate of the shooting pixel coordinate W For the width of the aerial image, I H For the height of the aerial image, s is the resolution ratio, ma:b, c:d]The coordinate system of the power station base map is a rectangular area enclosed by a horizontal axis from a coordinate a to a coordinate b and a vertical axis from a coordinate c to a coordinate d.
Turning to equations (2) and (3) in the preferred embodiment, the long axis length (in pixels) of the aerial image is selected multiplied by theResolution ratio, obtaining side length p of the base graph sub-graph, and then obtaining the photographed pixel coordinate (M x ,M y ) And (3) as the midpoint of the base map sub-map, respectively expanding p/2 along the positive and negative directions of the x-axis and the positive and negative directions of the y-axis to obtain the coordinate range of the base map sub-map on the power station base map.
In the preferred embodiment, the base map sub-map is divided into a square with the side length equal to the long axis of the aerial image, so that the aerial image is ensured to be completely covered, the position information of all defect components can be ensured to be mapped onto the base map sub-map, the defect loss condition can not occur, and the stability of system operation is improved.
S104: and determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information.
In addition, in the process of cruising and photographing by the unmanned aerial vehicle, the problem that the coordinate system of the aerial image is inconsistent with the coordinate system of the power station base map may occur, as shown in fig. 3 and 4, fig. 3 and 4 are mask images of the photovoltaic group strings subjected to mask processing, fig. 3 is a mask image of the base map sub-image, fig. 4 is a mask image of the aerial image corresponding to the same position, it is not difficult to see that a certain photographing angle difference exists between the two images, and obviously, the mapping defect position information obtained by directly mapping the coordinate positions in the two images in this case is inaccurate, and for this case, the steps may include:
b1: and extracting the photovoltaic string information of the base map subgraph, and extracting the aerial string information of the aerial image.
And obtaining the photovoltaic string information of the base graph subgraph by a photovoltaic string information extraction method, wherein the photovoltaic string information is an information set comprising all the corresponding information of the photovoltaic string in the base graph subgraph. Each photovoltaic string specified in the photovoltaic string information may include at least one of a string profile coordinate, a width, a height, a center coordinate, an upper left corner coordinate, a lower left corner coordinate, an upper right corner coordinate, and a lower right corner coordinate of the photovoltaic string.
Specifically, any one of an identification model based on image processing or an identification model based on deep learning can be adopted to identify the photovoltaic string region in the image; extracting the contour information of each group of string regions by adopting any region contour extraction method; and calculating at least one of the width, the height, the center point coordinates, the upper left corner coordinates, the lower left corner coordinates, the upper right corner coordinates and the lower right corner coordinates of the minimum circumscribed rectangles of each group of strings.
B2: and relatively rotating the base map subgraph and the aerial image, and recording the overlapping degree of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map subgraph and the aerial image are in different relative rotation angles.
Because the shooting longitude and latitude information when shooting the aerial image is necessarily accurate, the shooting direction is only different from the power station base map, so that the relative rotation of the base map sub-map and the aerial image in the invention refers to rotation taking the shooting pixel coordinates (corresponding to the shooting longitude and latitude information) as the center, and is not repeated.
B3: and when the overlapping degree of the string outline corresponding to the photovoltaic string information and the string outline corresponding to the aerial string information is maximum, the relative rotation angle between the base map subgraph and the aerial image is used as the optimal rotation angle.
Of course, θ= [0 °, 90 °, 180 °, 270 ° may be defined in advance according to the photovoltaic power station unmanned aerial vehicle inspection path plan]Directions of four standard rotation angles, for each rotation angle θ i Can obtain the rotation theta i String overlap degree D between the aerial image and the base image sub-image i In D i θ at maximum i Optimal rotation angle θ of the aerial image with respect to the base map sub-image best 。
B4: and determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image, the optimal rotation angle and the defect component position information.
In this step, the base map sub-map and the aerial image are rotated relatively, and a new coordinate of the rotated aerial image on the base map sub-map is obtained, which is one specific implementation mode, and this step includes:
taking the base map subgraph as a reference image, taking the aerial image as an image to be matched, and carrying out coordinate transformation on the aerial image through the following formula (4) and the formula (5) to obtain mapping defect position information on the base map subgraph:
wherein, (x) d ’,y d ') is the mapping defect location information, (x) d ,y d ) For the defective component position information, W is a coordinate transformation matrix, I W For the width of the aerial image, I H For the height of the aerial image, M W For the width of the base graph sub-graph, M H For the height of the base graph sub-graph, s is the resolution ratio, θ best Is the optimal rotation angle.
The coordinate transformation matrix W is utilized to carry out coordinate transformation of the position information of the defect component, so that the calculation efficiency is high, the calculation accuracy is high, the universality is strong, and the stability is good.
As a specific embodiment, the overlapping degree of the component contours in the two images obtained in the foregoing may be determined according to various criteria, for example, the following steps C1 and C2 may be used instead of the steps B2 and B3 in the foregoing, including:
c1: and recording the intersection ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map subgraph and the aerial image are at different relative rotation angles.
C2: and when the intersection ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information is maximum, the relative rotation angle between the base map sub-graph and the aerial image is used as the optimal rotation angle.
In this embodiment, the step of using the intersection ratio as a criterion for overlapping the photovoltaic strings of the two images may include:
Setting the number of strings in the aerial image as n 1 The number of strings in the base graph is n 2 Rotating theta i Each group string c in the post aerial image ij (j＝1，2，......n 1 ) Calculating each group string m in the base graph sub-graph by the following formulas (6) (7) (8) k (k＝1，2，......n 2 ) Cross ratio p (c) ij ，m k )：
Union_Area＝w c *h c +w m *h m -Overlap_Area............(8)
Wherein, overlay_area is an intersection Area, union_area is a Union Area, w c For group string c ij The width of the smallest circumscribed rectangle of h c For group string c ij The height, w, of the smallest bounding rectangle m For group string m k The width of the smallest circumscribed rectangle of h m For group string m k Is defined by the height of the smallest bounding rectangle.
In addition, (x) 1o ，y 1o ) And (x) ro ，y ro ) Respectively, are group strings c ij Minimum circumscribed rectangle and group string m k The upper left corner coordinates and lower right corner coordinates of the intersection of the minimum bounding rectangle are calculated as follows:
x lo ＝max(x c_min ，x m_min )........................(9)
y lo ＝max(y c_min ，y m_min )...........................(10)
x ro ＝min(x c_max ，x m_max )...........................(11)
y ro ＝min(y c_max ，y m_max )...........................(12)
wherein, (x) c_min ，y c_min ) For group string c ij Upper left corner coordinates of minimum bounding rectangle, (x) c_max ，y c_max ) For group string c ij Lower right corner coordinates of minimum bounding rectangle, (x) m_min ，y m_min ) For group string m k Upper left corner coordinates of minimum bounding rectangle, (x) m_max ，y m_max ) For group string m k The minimum bounding rectangle lower right corner coordinates.
Record P j ＝[p(c ij ，m 1 )，p(c ij ，m 2 )，......，p(c ij ，m n_2 )]Then
In addition, in another specific embodiment of step S104, the method includes:
and determining mapping defect position information on the base map subgraph and defect group strings corresponding to all defects according to the base map subgraph, the aerial image and the defect component position information.
In this embodiment, besides providing the mapping defect position information on the base map subgraph, that is, the specific coordinates of the defects on the base map subgraph, a defect group string corresponding to each defect is also provided, which is equivalent to providing another positioning reference for the defects in the overhauling process by phase change, when the specific positions of the defects cannot be determined, accident points can be checked one by one for the defect group string, so as to avoid the situation of missing the defects.
Further, the determining process of the defect group string corresponding to each defect includes:
d1: and extracting the photovoltaic string information of the base map subgraph.
The extraction of the string information of the photovoltaic group has been performed several times in the foregoing, and will not be described herein again, please refer to the foregoing.
D2: and searching and determining a defect group string corresponding to each defect by utilizing the centroid of the nearest neighbor region according to the mapping defect position information and the group string outline corresponding to the photovoltaic group string information.
The nearest neighbor region centroid searching method has high accuracy and high reliability, is favorable for stable operation of a system, improves the matching precision and the working stability of the defects and the defect group strings, and specifically comprises the following steps:
the centroid of each group string is calculated by the following equation (13) (14):
Wherein, (x) i ,y i ) Coordinates representing the ith point within a set of string profile points (the set of points that make up the corresponding string profile, see above for an explanation of the string profile), N being the size of the set of string profile points, M 00 Is the zero-order moment of the string profile, i.e. the area of the string profile, M 10 And M 01 Is the first moment of the group string profile, represents the weighted average of the x-coordinate and y-coordinate of the group string profile,i.e. the centroid coordinates of the group string.
After the centroid coordinates are obtained, only the group string corresponding to the centroid coordinate closest to the defect is required to be confirmed as the defect group string.
Further, for an embodiment of providing a defect group string corresponding to each defect, the process of obtaining the mapped defect location information includes:
e1: and determining the defect coordinates to be adjusted on the aerial image according to the aerial image, the shooting pixel coordinates and the defect component position information.
In this step, the position information of the defective component is mapped preliminarily, that is, it is assumed that when the image content of the base map sub-image is completely consistent with that of the aerial image, the position information of the defective component is mapped to coordinates on the base map sub-image, that is, the coordinates of the defect to be adjusted.
Of course, this step may be combined with other embodiments in the foregoing, for example, the base map sub-image and the aerial image are rotated relatively to obtain the optimal rotation angle, and then the aerial image is transformed by using the optimal rotation angle to obtain the defect coordinate to be adjusted, and then the subsequent steps are performed.
E2: and extracting the photovoltaic string information of the base map subgraph, and extracting the aerial string information of the aerial image.
The foregoing is not repeated here, and please refer to the foregoing.
E3: determining a defect string pair corresponding to each defect according to the to-be-adjusted defect coordinates and the photovoltaic string information; the defect group string pair comprises a defect photovoltaic group string corresponding to the defect on the base map subgraph and a defect aerial group string corresponding to the aerial image.
In this step, it is further determined which group of strings the defect corresponds to in the aerial image and the base map sub-image, respectively.
E4: judging whether the difference between the length of the long axis of the defective photovoltaic string and the length of the long axis of the defective aerial group string exceeds a preset tolerance threshold.
Referring to fig. 5, in actual operation, the base map sub-map and the content of the aerial image are likely not completely consistent, and as the previous example, taking the length of the long axis of the aerial image as the side length of the square base map sub-map, it is obvious that, in the case that the coordinates of points in the two images are consistent, the edge cutting positions of the images will be different, as shown in fig. 5, the left side of fig. 5 is the aerial image, the defect is represented by +and the right side is the base map sub-map, the calculated defect position is represented by x, and it can be seen that the positions of the group string in fig. 5 cut by the edges of the picture in the left side map and the right side map are different, which may cause misalignment in calculating the defect position.
In order to avoid the above problem, in this step, the lengths of the strings of the same defect in the two images are compared, and if the tolerance threshold is exceeded, it can be basically determined that the positions of the edges of the strings of the defect corresponding to the cut strings in the two images are different, and at this time, the coordinate mapping cannot be directly performed.
E5: and when the difference between the length of the long axis of the defect photovoltaic group string and the length of the long axis of the defect aerial group string exceeds the tolerance threshold, acquiring the optimal angular point coordinates of the defect photovoltaic group string and the optimal angular point coordinates of the defect aerial group string.
The coordinates of the optimal angular points are the coordinates of the angular points of the group strings corresponding to the defects, one group string is provided with four angular points of upper left, lower left, upper right and lower right, the optimal angular points need to be selected in the angular points existing in the graph according to the corresponding group strings, and the lower right angle is preferred because the coordinates of the lower right angle only need to be the maximum value of the horizontal coordinate and the maximum value of the vertical coordinate of the corresponding group strings, and the value and the calculation are convenient.
E6: and adjusting the optimal angular point coordinates of the defect photovoltaic group string along the long axis direction of the defect photovoltaic group string according to the difference between the long axis length of the defect photovoltaic group string and the long axis length of the defect aerial group string, so as to obtain the calibrated optimal angular point coordinates of the defect photovoltaic group string.
For example, let the optimal corner point coordinate be the lower right corner coordinate, and the width of the defective photovoltaic string be w m Height is h m Lower right angular position (x mr ,y mr ) The width of the defect aerial group string is w c Height is h c Lower right angular position (x cr ,y cr )。
Let the initial optimal corner coordinates (x) b ,y b )＝(x mr ,y mr ) Designing the tolerance threshold r according to the size of the component, and calculating the length of the defective photovoltaic group stringThe difference d=max (w m ,h m )-max(w c ,h c )。
If d>r, describing that the difference between the long axis length of the defect photovoltaic group string and the long axis length of the defect aerial group string exceeds the tolerance threshold, adjusting the coordinates (x) of the optimal angular point b ,y b )，
Continuing with the example, if the base graph is taken in accordance with the previous embodiment, the long axis of the aerial image is selected as the edge length of the base graph, it may be concluded that if the long axis lengths of the two strings are not identical, it is certain that the long axis length of the defective photovoltaic string is greater than the long axis length of the defective aerial string, and at this time, if the long axis directions of the two strings are x-axis directions, the adjusted x b_new ＝x b -d; accordingly, if the long axis direction of the two strings is the y axis direction, the y axis coordinates should be adjusted, the adjusted y b_new ＝y b -d, it can be seen that the adjustment direction of the coordinates is determined according to the relative size of the long axis length of the defective photovoltaic string and the long axis length of the defective aerial string. Of course, the adjusted distance may be other parameters than d, which are derived from d.
E7: and calculating the optimal angular point coordinates of the defect aerial photographing group string and the relative position difference between the defect coordinates to be adjusted.
In the previous example, the optimal corner point (x cr ,y cr ) And defect point (x) d ,y d ) The relative position differences of (2) are d respectively x ＝x cr -x d ，d y ＝y cr -y d 。
E8: and determining mapping defect position information on the base map subgraph according to the relative position difference and the calibration optimal angular point coordinates.
In the previous example, the pixel coordinates (x m ,y m ) The method comprises the following steps: x is x m ＝x b +d x ，y m ＝y b +d y 。
In the preferred embodiment, the problem that the aerial image and the base image are inconsistent in cutting of the string edges is further considered, and the universality of the method is further improved while the positioning accuracy of the defects is improved.
S105: and determining longitude and latitude information of the defect component according to the mapping defect position information.
In this step, the pixel coordinates of the defective component in the full-scene power station base map can be obtained according to the position relationship between the base map sub-map and the power station base map, and then the geographic coordinate system, the projection coordinate system and the grid pixel coordinate system are sequentially transformed by means of the spatial coordinate transformation model to obtain the geographic position of the defective component, that is, the longitude and latitude information of the defective component.
According to the defect component positioning method for image geographic registration, aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information are obtained; determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information; determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio; determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information; and determining longitude and latitude information of the defect component according to the mapping defect position information. According to the invention, the aerial image is combined with the power station base map, the initial area (namely the base map sub-map) where the defect component exists is rapidly determined on the premise that complex characteristic point matching is not involved, so that the positioning efficiency of the defect component is greatly improved, meanwhile, the accuracy and precision of the longitude and latitude information of the defect component on the power station base map can be greatly improved through the aerial image and the corresponding shooting longitude and latitude information, the position of the defect component is conveniently and rapidly confirmed by subsequent inspection personnel, and the maintenance efficiency is improved.
In the following, an apparatus for positioning a defective component in image geographic registration provided by an embodiment of the present invention is described, and the apparatus for positioning a defective component in image geographic registration described below and the method for positioning a defective component in image geographic registration described above may be referred to correspondingly with each other.
FIG. 6 is a block diagram of a defective component positioning device for image geographic registration according to an embodiment of the present invention, and referring to FIG. 6, the defective component positioning device for image geographic registration may include:
the acquisition module 100 is used for acquiring aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information;
the pixel coordinate conversion module 200 is used for determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information;
the sub-graph dividing module 300 is configured to determine a base graph sub-graph according to the photographed pixel coordinates, the aerial image and the resolution ratio;
a mapping defect module 400, configured to determine mapping defect location information on the base map sub-map according to the base map sub-map, the aerial image, and the defect component location information;
the defect longitude and latitude module 500 is configured to determine longitude and latitude information of the defective component according to the mapping defect location information.
As a preferred embodiment, the sub-division module 300 includes:
the height acquisition unit is used for acquiring the shooting height corresponding to the aerial image;
a resolution ratio calculation unit for determining the resolution ratio s according to the following formula:
wherein H is the shooting height, P is the pixel size of a shooting sensor corresponding to the aerial image, f is the focal length of the shooting sensor, dp M For the spatial resolution of the plant floor.
As a preferred embodiment, the sub-division module 300 includes:
an arithmetic sub-graph unit for determining the base-graph sub-graph M by 1 ：
p＝max(I W *s，I H *s)
Wherein M is x My is the abscissa of the shooting pixel coordinate, p is the side length of the base map subgraph, and I W For the width of the aerial image, I H For the height of the aerial image, s is the resolution ratio, ma:b, c:d]The coordinate system of the power station base map is a rectangular area enclosed by a horizontal axis from a coordinate a to a coordinate b and a vertical axis from a coordinate c to a coordinate d.
As a preferred embodiment, the mapping defect module 400 includes:
the group string extraction unit is used for extracting photovoltaic group string information of the base map subgraph and extracting aerial group string information of the aerial image;
The rotation unit is used for relatively rotating the base map subgraph and the aerial image and recording the overlapping degree of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial image string information when the base map subgraph and the aerial image are in different relative rotation angles;
the angle determining unit is used for taking the relative rotation angle between the base map subgraph and the aerial image as the optimal rotation angle when the overlapping degree of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information is maximum;
and the rotation mapping unit is used for determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image, the optimal rotation angle and the defect component position information.
As a preferred embodiment, the mapping defect module 400 includes:
the rotation calculation unit is used for taking the base map subgraph as a reference image, taking the aerial image as an image to be matched, and carrying out coordinate transformation on the aerial image to obtain mapping defect position information on the base map subgraph through the following steps:
wherein, (x) d ’,y d ') is the mapping defect location information, (x) d ,y d ) For the defective component position information, W is a coordinate transformation matrix, I W For the width of the aerial image, I H For the height of the aerial image, M W For the width of the base graph sub-graph, M H For the height of the base graph sub-graph, s is the resolution ratio, θ best Is the optimal rotation angle.
As a preferred embodiment, the mapping defect module 400 includes:
the cross-over ratio recording unit is used for recording the cross-over ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map subgraph and the aerial image are at different relative rotation angles;
accordingly, the map defect module 400 includes:
and the optimal merging ratio unit is used for taking the relative rotation angle between the base map subgraph and the aerial image as the optimal rotation angle when the merging ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information is maximum.
As a preferred embodiment, the mapping defect module 400 includes:
and the defect group string additional mapping defect unit is used for determining mapping defect position information on the base map subgraph and defect group strings corresponding to all defects according to the base map subgraph, the aerial image and the defect component position information.
As a preferred embodiment, the mapping defect module 400 includes:
the base graph string extraction unit is used for extracting photovoltaic string information of the base graph subgraph;
and the centroid searching unit is used for searching and determining the defect group strings corresponding to the defects by utilizing the nearest neighbor area centroid according to the mapping defect position information and the group string outline corresponding to the photovoltaic group string information.
As a preferred embodiment, the mapping defect module 400 includes:
the preliminary mapping unit is used for determining to-be-adjusted defect coordinates on the aerial image according to the aerial image, the shooting pixel coordinates and the defect component position information;
the group string extraction unit is used for extracting photovoltaic group string information of the base map subgraph and extracting aerial group string information of the aerial image;
the defect group string pair determining unit is used for determining a defect group string pair corresponding to each defect according to the to-be-adjusted defect coordinates and the photovoltaic group string information; the defect group string pair comprises a defect photovoltaic group string corresponding to the defect on the base map subgraph and a defect aerial group string corresponding to the aerial image;
the long-axis difference judging unit is used for judging whether the difference between the long-axis length of the defect photovoltaic group string and the long-axis length of the defect aerial group string exceeds a preset tolerance threshold;
The optimal angular point obtaining unit is used for obtaining the optimal angular point coordinates of the defect photovoltaic group string and the optimal angular point coordinates of the defect aerial group string when the difference between the length of the long axis of the defect photovoltaic group string and the length of the long axis of the defect aerial group string exceeds the tolerance threshold;
the optimal angular point adjusting unit is used for adjusting the optimal angular point coordinates of the defect photovoltaic group string along the long axis direction of the defect photovoltaic group string according to the difference between the long axis length of the defect photovoltaic group string and the long axis length of the defect aerial group string to obtain the calibrated optimal angular point coordinates of the defect photovoltaic group string;
the relative position difference unit is used for calculating the relative position difference between the optimal angular point coordinates of the defect aerial photographing group string and the defect coordinates to be adjusted;
and the relative position adjusting unit is used for determining mapping defect position information on the base map subgraph according to the relative position difference and the calibration optimal angular point coordinates.
The invention provides a defect component positioning device for image geographic registration, which comprises an acquisition module 100, a detection module and a detection module, wherein the acquisition module is used for acquiring aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information; the pixel coordinate conversion module 200 is used for determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information; the sub-graph dividing module 300 is configured to determine a base graph sub-graph according to the photographed pixel coordinates, the aerial image and the resolution ratio; a mapping defect module 400, configured to determine mapping defect location information on the base map sub-map according to the base map sub-map, the aerial image, and the defect component location information; the defect longitude and latitude module 500 is configured to determine longitude and latitude information of the defective component according to the mapping defect location information. According to the invention, the aerial image is combined with the power station base map, the initial area (namely the base map sub-map) where the defect component exists is rapidly determined on the premise that complex characteristic point matching is not involved, so that the positioning efficiency of the defect component is greatly improved, meanwhile, the accuracy and precision of the longitude and latitude information of the defect component on the power station base map can be greatly improved through the aerial image and the corresponding shooting longitude and latitude information, the position of the defect component is conveniently and rapidly confirmed by subsequent inspection personnel, and the maintenance efficiency is improved.
The defect component positioning device for image geographic registration of the present embodiment is used to implement the foregoing defect component positioning method for image geographic registration, so that the detailed description of the defect component positioning device for image geographic registration can be found in the foregoing example portions of the defect component positioning method for image geographic registration, for example, the acquisition module 100, the pixel coordinate conversion module 200, the sub-division module 300, the mapping defect module 400, and the defect longitude and latitude module 500, which are respectively used to implement steps S101, S102, S103, and S104 in the defect component positioning method for image geographic registration, so that the detailed description of the embodiments of the respective portions will be omitted herein.
The invention also provides a defect component positioning device for image geographic registration, which comprises:
a memory for storing a computer program;
a processor for performing the steps of the defective component localization method of image geographical registration as described in any one of the above when executing the computer program. According to the defect component positioning method for image geographic registration, aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information are obtained; determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information; determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio; determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information; and determining longitude and latitude information of the defect component according to the mapping defect position information. According to the invention, the aerial image is combined with the power station base map, the initial area (namely the base map sub-map) where the defect component exists is rapidly determined on the premise that complex characteristic point matching is not involved, so that the positioning efficiency of the defect component is greatly improved, meanwhile, the accuracy and precision of the longitude and latitude information of the defect component on the power station base map can be greatly improved through the aerial image and the corresponding shooting longitude and latitude information, the position of the defect component is conveniently and rapidly confirmed by subsequent inspection personnel, and the maintenance efficiency is improved.
The present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a defective component localization method of image geo-registration as described in any of the above. According to the defect component positioning method for image geographic registration, aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information are obtained; determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information; determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio; determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information; and determining longitude and latitude information of the defect component according to the mapping defect position information. According to the invention, the aerial image is combined with the power station base map, the initial area (namely the base map sub-map) where the defect component exists is rapidly determined on the premise that complex characteristic point matching is not involved, so that the positioning efficiency of the defect component is greatly improved, meanwhile, the accuracy and precision of the longitude and latitude information of the defect component on the power station base map can be greatly improved through the aerial image and the corresponding shooting longitude and latitude information, the position of the defect component is conveniently and rapidly confirmed by subsequent inspection personnel, and the maintenance efficiency is improved.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It should be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The method, the device, the equipment and the computer readable storage medium for positioning the defective components of the image geographic registration provided by the invention are described in detail above. The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Claims (10)
1. A method of locating defective components for geographic registration of images, comprising:
acquiring aerial images, corresponding shooting longitude and latitude information and corresponding defect component position information;
determining shooting pixel coordinates according to a pre-stored power station base map and the shooting longitude and latitude information;
determining a base map subgraph according to the shooting pixel coordinates, the aerial image and the resolution ratio;
determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information;
and determining longitude and latitude information of the defect component according to the mapping defect position information.
2. The method for locating defective components for image geographical registration of claim 1, wherein the method for obtaining the resolution ratio comprises:
acquiring a shooting height corresponding to the aerial image;
the resolution ratio s is determined according to the following equation:
wherein H is the shooting height, P is the pixel size of a shooting sensor corresponding to the aerial image, f is the focal length of the shooting sensor, dp M For the spatial resolution of the plant floor.
3. The method of claim 1, wherein determining a base map sub-map based on the captured pixel coordinates, the aerial image, and a resolution ratio comprises:
Determining the base graph sub-graph M by 1 ：
p＝max(I W *s，I H *s)
Wherein M is x M is the abscissa of the shooting pixel coordinate y Longitudinal sitting for the shooting pixel coordinatesThe mark, p is the side length of the base graph sub-graph, I W For the width of the aerial image, I H For the height of the aerial image, s is the resolution ratio, ma:b, c:d]The coordinate system of the power station base map is a rectangular area enclosed by a horizontal axis from a coordinate a to a coordinate b and a vertical axis from a coordinate c to a coordinate d.
4. The method of claim 1, wherein determining mapping defect location information on the base map sub-map based on the base map sub-map, the aerial image, and the defect component location information comprises:
extracting photovoltaic string information of the base map subgraph, and extracting aerial string information of the aerial image;
relatively rotating the base map subgraph and the aerial image, and recording the overlapping degree of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map subgraph and the aerial image are in different relative rotation angles;
when the overlapping degree of the string outline corresponding to the photovoltaic string information and the string outline corresponding to the aerial string information is maximum, the relative rotation angle between the base map subgraph and the aerial image is used as an optimal rotation angle;
And determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image, the optimal rotation angle and the defect component position information.
5. The method of claim 4, wherein determining mapping defect location information on the base map sub-map based on the base map sub-map, the aerial image, the optimal rotation angle, and the defect component location information comprises:
taking the base map subgraph as a reference image, taking the aerial image as an image to be matched, and carrying out coordinate transformation on the aerial image to obtain mapping defect position information on the base map subgraph by the following steps:
wherein, (x) d ’,y d ') is the mapping defect location information, (x) d ,y d ) For the defective component position information, W is a coordinate transformation matrix, I W For the width of the aerial image, I H For the height of the aerial image, M W For the width of the base graph sub-graph, M H For the height of the base graph sub-graph, s is the resolution ratio, θ best Is the optimal rotation angle.
6. The method for locating a defective component in image geographic registration according to claim 4, wherein recording the overlapping degree of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map sub-map and the aerial image are at different relative rotation angles comprises:
Recording the intersection ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information when the base map subgraph and the aerial image are at different relative rotation angles;
correspondingly, when the overlapping degree of the string outline corresponding to the photovoltaic string information and the string outline corresponding to the aerial string information is maximum, the relative rotation angle between the base map subgraph and the aerial image as the optimal rotation angle comprises:
and when the intersection ratio of the string profile corresponding to the photovoltaic string information and the string profile corresponding to the aerial string information is maximum, the relative rotation angle between the base map sub-graph and the aerial image is used as the optimal rotation angle.
7. The method of claim 1, wherein determining mapping defect location information on the base map sub-map based on the base map sub-map, the aerial image, and the defect component location information comprises:
and determining mapping defect position information on the base map subgraph and defect group strings corresponding to all defects according to the base map subgraph, the aerial image and the defect component position information.
8. The method for locating defective components in geographical registration of images according to claim 7, wherein the determining of the defect group string corresponding to each defect comprises:
extracting photovoltaic string information of the base map subgraph;
and searching and determining a defect group string corresponding to each defect by utilizing the centroid of the nearest neighbor region according to the mapping defect position information and the group string outline corresponding to the photovoltaic group string information.
9. The method for locating a defective component according to claim 7, wherein determining mapping defect location information on the base map sub-map, the aerial image and the defect component location information, and a defect group string corresponding to each defect comprises:
determining to-be-adjusted defect coordinates on the aerial image according to the aerial image, the shooting pixel coordinates and the defect component position information;
extracting photovoltaic string information of the base map subgraph, and extracting aerial string information of the aerial image;
determining a defect string pair corresponding to each defect according to the to-be-adjusted defect coordinates and the photovoltaic string information; the defect group string pair comprises a defect photovoltaic group string corresponding to the defect on the base map subgraph and a defect aerial group string corresponding to the aerial image;
Judging whether the difference between the length of the long axis of the defective photovoltaic group string and the length of the long axis of the defective aerial group string exceeds a preset tolerance threshold;
when the difference between the length of the long axis of the defect photovoltaic group string and the length of the long axis of the defect aerial group string exceeds the tolerance threshold, obtaining the optimal angular point coordinates of the defect photovoltaic group string and the optimal angular point coordinates of the defect aerial group string;
according to the difference between the length of the long axis of the defect photovoltaic string and the length of the long axis of the defect aerial group string, adjusting the optimal angular point coordinates of the defect photovoltaic string along the long axis direction of the defect photovoltaic string to obtain the calibrated optimal angular point coordinates of the defect photovoltaic string;
calculating the optimal angular point coordinates of the defect aerial photographing group string and the relative position difference between the defect coordinates to be adjusted;
and determining mapping defect position information on the base map subgraph according to the relative position difference and the calibration optimal angular point coordinates.
10. A defective component positioning device for geographic registration of images, comprising:
the acquisition module is used for acquiring the aerial image, the corresponding shooting longitude and latitude information and the corresponding defect component position information;
The pixel coordinate conversion module is used for determining shooting pixel coordinates according to the prestored power station base map and the shooting longitude and latitude information;
the sub-graph dividing module is used for determining a base graph sub-graph according to the shooting pixel coordinates, the aerial image and the resolution ratio;
the mapping defect module is used for determining mapping defect position information on the base map subgraph according to the base map subgraph, the aerial image and the defect component position information;
and the defect longitude and latitude module is used for determining longitude and latitude information of the defect component according to the mapping defect position information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310548294.0A CN116758142A (en) | 2023-05-12 | 2023-05-12 | Defect component positioning method and device for image geographic registration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310548294.0A CN116758142A (en) | 2023-05-12 | 2023-05-12 | Defect component positioning method and device for image geographic registration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116758142A true CN116758142A (en) | 2023-09-15 |
Family
ID=87957979
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310548294.0A Pending CN116758142A (en) | 2023-05-12 | 2023-05-12 | Defect component positioning method and device for image geographic registration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116758142A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117351053A (en) * | 2023-12-04 | 2024-01-05 | 尚特杰电力科技有限公司 | Photovoltaic power station image registration method, storage medium and electronic equipment |
-
2023
- 2023-05-12 CN CN202310548294.0A patent/CN116758142A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117351053A (en) * | 2023-12-04 | 2024-01-05 | 尚特杰电力科技有限公司 | Photovoltaic power station image registration method, storage medium and electronic equipment |
| CN117351053B (en) * | 2023-12-04 | 2024-02-23 | 尚特杰电力科技有限公司 | Photovoltaic power station image registration method, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148169B (en) | Vehicle target three-dimensional information acquisition method based on PTZ (pan/tilt/zoom) pan-tilt camera | |
| CN104200086B (en) | Wide-baseline visible light camera pose estimation method | |
| CN107292927A (en) | A kind of symmetric motion platform's position and pose measuring method based on binocular vision | |
| CN106971408A (en) | A kind of camera marking method based on space-time conversion thought | |
| CN112270320B (en) | Power transmission line tower coordinate calibration method based on satellite image correction | |
| CN116758142A (en) | Defect component positioning method and device for image geographic registration | |
| KR101255461B1 (en) | Position Measuring Method for street facility | |
| CN111476798B (en) | Vehicle space morphology recognition method and system based on contour constraint | |
| CN104180794B (en) | The disposal route in digital orthoimage garland region | |
| CN112446915B (en) | Picture construction method and device based on image group | |
| CN108801225A (en) | A kind of unmanned plane tilts image positioning method, system, medium and equipment | |
| CN109146936A (en) | A kind of image matching method, device, localization method and system | |
| CN111380503B (en) | Monocular camera ranging method adopting laser-assisted calibration | |
| CN116740174B (en) | Method and device for positioning tunnel defect in three-dimensional live-action model and storage medium | |
| CN115690380B (en) | Registration method and system | |
| CN116958218A (en) | Point cloud and image registration method and equipment based on calibration plate corner alignment | |
| CN111968182A (en) | Calibration method for binocular camera nonlinear model parameters | |
| CN116386373A (en) | Vehicle positioning method and device, storage medium and electronic equipment | |
| CN103606321B (en) | Based on video location and the road test judgment method of digital modeling combined technology | |
| CN115457130A (en) | Electric vehicle charging port detection and positioning method based on depth key point regression | |
| CN112767498A (en) | Camera calibration method and device and electronic equipment | |
| CN113192075A (en) | Improved visual ranging method based on Aruco marker | |
| CN112330740A (en) | Pseudo-binocular dynamic distance measurement method based on monocular video | |
| CN117152361B (en) | Remote sensing image visibility estimation method based on attention mechanism | |
| JP7271413B2 (en) | Object detection device and object detection 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 |