CN117173601B - Photovoltaic power station array hot spot identification method and system - Google Patents
Photovoltaic power station array hot spot identification method and system Download PDFInfo
- Publication number
- CN117173601B CN117173601B CN202311452573.3A CN202311452573A CN117173601B CN 117173601 B CN117173601 B CN 117173601B CN 202311452573 A CN202311452573 A CN 202311452573A CN 117173601 B CN117173601 B CN 117173601B
- Authority
- CN
- China
- Prior art keywords
- image
- visible light
- infrared
- images
- array
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 54
- 230000004927 fusion Effects 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 239000013598 vector Substances 0.000 claims description 13
- 238000003384 imaging method Methods 0.000 claims description 12
- 241000208340 Araliaceae Species 0.000 claims description 10
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 10
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 10
- 235000008434 ginseng Nutrition 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000003068 static effect Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000000926 separation method Methods 0.000 claims description 7
- 241001270131 Agaricus moelleri Species 0.000 claims description 6
- 238000012952 Resampling Methods 0.000 claims description 4
- 238000007667 floating Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 description 15
- 230000006641 stabilisation Effects 0.000 description 8
- 238000011105 stabilization Methods 0.000 description 8
- 238000013507 mapping Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008054 signal transmission Effects 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 Analysis (AREA)
Abstract
The invention relates to the technical field of hot spot position detection of a photovoltaic power station array, and provides a method and a system for identifying hot spots of the photovoltaic power station array, wherein the method comprises the following steps: dividing a photovoltaic power station into a plurality of photovoltaic array detection areas by using unmanned aerial vehicle equipment, and recording a plurality of infrared images and visible light images; aligning and splicing a plurality of infrared images and visible light images to form a large-range image, and finding out mutually corresponding characteristic point pairs in the visible light images and the infrared images in the large-range image so as to enable the visible light images and the infrared image information to be registered; separating a photovoltaic array detection area from a background area in the visible light image and the infrared image; obtaining a fusion image based on the calculation and matching of the gray scale of the visible light image and the infrared image; and finding out the hot spot position in the fused image according to the temperature characteristics of the array hot spots, and identifying and counting the hot spot coordinates. According to the invention, the infrared image is subjected to image fusion operation to obtain the preprocessed image, so that the hot spot position of the array is identified, and false detection caused by reflected light is avoided.
Description
Technical Field
The invention relates to the technical field of hot spot position detection of a photovoltaic power station array, in particular to a method and a system for identifying hot spots of the photovoltaic power station array.
Background
Photovoltaic power generation is a clean energy technology widely applied, and the construction of a photovoltaic power station has a great effect on sustainable development. In the practical application of a photovoltaic power station, a photovoltaic panel can generate hot spot faults, and the generated energy is inconsistent due to the fact that the quality of battery installation and operation and maintenance management can cause the photovoltaic panel to be consumed as a load to generate heat when generating electricity, namely the hot spot effect. The hot spot effect has a serious influence on the performance of the photovoltaic panel, and even a fire disaster can be caused when the hot spot effect is serious, so that the photovoltaic panel needs to be detected.
The traditional mode that adopts artifical inspection scans photovoltaic array with thermal infrared imager, but along with photovoltaic power plant scale expansion, the inefficiency of artifical inspection can't in time discover the problem. In recent years, with the rapid development of unmanned aerial vehicles and artificial intelligence technology, photovoltaic power station hot spot detection methods and devices based on unmanned aerial vehicles and artificial intelligence are widely researched and applied. The unmanned aerial vehicle can carry out efficient large-area inspection, and the artificial intelligence technology can automatically analyze infrared images.
The infrared image can reflect the temperature difference of different objects, a technician can identify the hot spot position by means of image processing by means of the characteristic, but the difference between a mirror reflection area formed by sunlight reflection on the photovoltaic array and the hot spot infrared image is small, the accuracy and the reliability of hot spot detection are reduced, and therefore the accuracy and the reliability of detecting and identifying the hot spot of the photovoltaic power station array by the traditional scheme are lower.
Disclosure of Invention
The invention aims to solve at least one technical problem in the background art and provides a method and a system for identifying hot spots of a photovoltaic power station array.
In order to achieve the above object, the present invention provides a method for identifying hot spots of a photovoltaic power station array, comprising:
dividing a photovoltaic power station into a plurality of photovoltaic array detection areas by using unmanned aerial vehicle equipment, and recording a plurality of infrared images and visible light images;
aligning and splicing a plurality of infrared images and visible light images to form a large-range image, and finding out mutually corresponding characteristic point pairs in the visible light images and the infrared images in the large-range image so as to enable the visible light images and the infrared image information to be registered;
separating a photovoltaic array detection area from a background area in the visible light image and the infrared image;
obtaining a fusion image based on the calculation and matching of the gray scale of the visible light image and the infrared image;
and finding out the position of the hot spot in the fused image according to the temperature characteristics of the array hot spot, and identifying and counting the coordinates of the hot spot.
According to one aspect of the invention, the unmanned aerial vehicle device comprises:
the area dividing module is used for dividing the photovoltaic array detection area according to the flight range of the unmanned aerial vehicle, establishing an array coordinate, constructing a ginseng lamp at four corner coordinate points of the photovoltaic array detection area, and sending a signal when the ginseng lamp is patrolled and examined by the unmanned aerial vehicle;
the two-axis stable cradle head is used for installing a camera and a thermal imager;
the image acquisition module comprises a double-channel camera and a light splitter and is used for acquiring and transmitting infrared images and visible light images.
According to one aspect of the invention, the two-axis swing mode of the two-axis stable cradle head is as follows:
transverse axis: transversely swinging for 5 times in one stroke, standing for 300ms at the imaging moment, and immediately resetting the two-axis stable cradle head after the stroke is finished when each swinging angle is 12.5 degrees and each angle position is static;
pitch axis: and swinging corresponding compensating angular velocity along the opposite direction of a pitching axis in the imaging process of the double-channel camera:
；
wherein ω is pitch axis angular velocity, V is flight velocity, and H is unmanned aerial vehicle height.
According to one aspect of the invention, the method finds mutually corresponding characteristic point pairs in the visible light image and the infrared image in the large-scale image, so that the visible light image and the infrared image information are registered as follows: matching and aligning pixel points corresponding to each other in a visible light image and an infrared image in a large-scale image, wherein the matching and aligning comprises the following steps:
finding out reference lamplight built at four corners of a photovoltaic array detection area in a visible light image and an infrared image, and extracting n SIFT feature vectors from the images to be registered by applying a SIFT algorithm;
the RANSAC algorithm is applied to iteratively extract the n SIFT feature vectors to obtain 4 optimal infrared and visible light image feature vectors, a homography matrix for describing transformation between two images is calculated, and the homography matrix is calculated through an equation established with corresponding pixel point position information:；
wherein x and y respectively represent the abscissa and the ordinate of the visible light image pixel point, and x ', y' respectively represent the abscissa and the ordinate of the infrared image pixel point;
traversing the pixel point coordinates (x, y) of each visible light image, and transforming the pixel point coordinates into new image coordinates: it is expressed as homogeneous coordinates (x ', y', 1) and the new coordinates (xh, yh, wh) are obtained by multiplication with a homography matrix, normalized:
x1=xh/wh，y1=yh/wh；
wherein x1 and y1 are the abscissa and ordinate of the new image floating point number corresponding to the converted visible light image and the infrared image;
and (3) calculating the value of the integer coordinate point by linear interpolation, resampling the transformed visible light image according to the new image coordinate of each pixel point, and registering the visible light image with the infrared image.
According to one aspect of the invention, the separating the photovoltaic array region from the background region in the visible light image and the infrared image comprises:
converting the visible light image and the infrared image into gray images through image preprocessing;
based on the gray level image of the infrared image, identifying a photovoltaic array detection area in the infrared image by using a self-adaptive threshold segmentation algorithm, and segmenting a background area in the infrared image;
cutting the visible light image according to the pixel point positions corresponding to the infrared image, and dividing the background area in the visible light image to obtain the photovoltaic array detection area of the visible light image.
According to one aspect of the invention, the calculation and matching of gray scales based on the visible light image and the infrared image, to obtain a fusion image, includes:
extracting the reflected light features from the gray level histogram, prescribing the gray level histogram of the visible light image with the infrared image as the prescribed image: at [0, 255]Calculating cumulative histograms of the visible light image and the infrared image in a range, and calculating absolute values of differences between gray values of the visible light image and gray values of the infrared image cumulative histogram, wherein the gray value with the smallest absolute value is the mapping gray value:；
wherein P is i For the cumulative probability of gray level i in the cumulative histogram of visible light image, P j，min Accumulating the sum P in the histogram for infrared images i Cumulative probability of least phase difference, j min For the corresponding gray value, P r (k) ，P z (l) The distribution probability that the gray level of the visible light image and the infrared image is k and l respectively, and the T is the mapping relation from the gray level of the visible light image to the gray level of the stipulated result;
calculating gray level difference of each pixel point in the matched visible light image and the infrared image to obtain a fusion image:；
wherein I is x，y Is the gray level difference value of two image pixel points, Y x，y Is the gray value of the infrared image, Y' x，y The gray value of the visible light image is represented by n and m, and the number of the horizontal and vertical pixel points of the image is represented by n and m.
According to one aspect of the invention, the hot spot position is found in the fused image according to the temperature characteristics of the array hot spots, and the coordinates of the hot spots are identified and counted:
and carrying out threshold segmentation on the gray level difference matrix in the fused image by applying an Otsu algorithm to obtain a binary image, identifying hot spot features in the binary image by extracting image features, and recording coordinates of each hot spot.
In order to achieve the above object, the present invention further provides a photovoltaic power station array hot spot identification system, including:
the image acquisition module is used for dividing the photovoltaic power station into a plurality of photovoltaic array detection areas by using unmanned aerial vehicle equipment and recording a plurality of infrared images and visible light images;
the image information registration module is used for aligning and splicing a plurality of infrared images and visible light images to form a large-range image, and finding out mutually corresponding characteristic point pairs in the visible light images and the infrared images in the large-range image so as to register the visible light images and the infrared image information;
the region separation module separates a photovoltaic array detection region from a background region in the visible light image and the infrared image;
the fusion image module is used for obtaining a fusion image based on the calculation and matching of the gray scales of the visible light image and the infrared image;
and the hot spot identification module is used for finding out the hot spot position in the fused image according to the temperature characteristics of the array hot spots and identifying and counting the coordinates of the hot spots.
In order to achieve the above object, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program when executed by the processor implements the method for identifying hot spots of a photovoltaic power plant array as described above.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the photovoltaic power plant array hot spot identification method as described above.
According to the scheme of the invention, the unmanned aerial vehicle is carried with the double-channel camera to obtain the image to be detected, and the image fusion operation is carried out on the infrared image to obtain the preprocessed image, so that the array hot spot position is identified. This approach avoids false detection caused by reflected light; the accuracy of camera image registration is increased through the improvement of the unmanned aerial vehicle holder and the application of the same-optical-axis beam splitter, and the improvement can be adapted under different environmental conditions and has good adaptability to different scenes.
Drawings
FIG. 1 schematically shows a flow chart of a method for identifying hot spots of a photovoltaic power plant array according to the invention;
FIG. 2 schematically illustrates a structural layout of a two-axis stabilization head according to one embodiment of the present invention;
fig. 3 schematically shows a flow chart of a method for identifying hot spots of a photovoltaic power plant array according to an embodiment of the present invention.
Detailed Description
The present disclosure will now be discussed with reference to exemplary embodiments. It should be understood that the embodiments discussed are merely to enable those of ordinary skill in the art to better understand and thus practice the teachings of the present invention and do not imply any limitation on the scope of the invention.
As used herein, the term "comprising" and variants thereof are to be interpreted as meaning "including but not limited to" open-ended terms. The term "based on" is to be interpreted as "based at least in part on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment.
Fig. 1 schematically shows a flow chart of a method for identifying hot spots of a photovoltaic power plant array according to the invention. As shown in fig. 1, in the present embodiment, a method for identifying hot spots of a photovoltaic power plant array includes:
a. dividing a photovoltaic power station into a plurality of photovoltaic array detection areas by using unmanned aerial vehicle equipment, and recording a plurality of infrared images and visible light images;
b. aligning and splicing a plurality of infrared images and visible light images to form a large-range image, and finding out mutually corresponding characteristic point pairs in the visible light images and the infrared images in the large-range image so as to enable the visible light images and the infrared image information to be registered;
c. separating a photovoltaic array detection area from a background area in the visible light image and the infrared image;
d. obtaining a fusion image based on the calculation and matching of the gray scale of the visible light image and the infrared image;
e. and finding out the position of the hot spot in the fused image according to the temperature characteristics of the array hot spot, and identifying and counting the coordinates of the hot spot.
According to the scheme, unmanned aerial vehicle equipment is adopted to acquire the image to be detected, then feature matching alignment is carried out on the visible light image and the infrared image, image fusion processing is carried out on the visible light image and the infrared image, and the hot spot position in the fused image is identified according to the identification temperature feature. This approach avoids false detection caused by reflected light.
Further, fig. 2 schematically shows a structural layout of a two-axis stabilization tripod head according to an embodiment of the present invention. As shown in fig. 2, in the present embodiment, the unmanned aerial vehicle apparatus 1 includes:
the area dividing module is used for dividing a photovoltaic array detection area according to the flight range of the unmanned aerial vehicle, establishing an array coordinate, constructing a ginseng lamp at four corner coordinate points of the photovoltaic array detection area, and sending a signal by the ginseng lamp in the inspection time of the unmanned aerial vehicle;
the two-axis stable cradle head 2 is used for installing a camera and a thermal imager;
the image acquisition module comprises a double-channel camera 3 and a beam splitter 4 and is used for acquiring and transmitting infrared images and visible light images.
Further, as shown in fig. 2, in the present embodiment, the pose stabilization of the dual-channel camera 3 in the unmanned aerial vehicle device 1 is independently completed by the two-axis stabilization tripod head 2, and the tripod head view angle swing and the image acquisition control the two-axis movement and the camera exposure by the program set in advance by the built-in control computer 5, and the two-axis swing mode of the two-axis stabilization tripod head 2 is as follows:
transverse axis: the control computer 5 executes a preset program, the two-axis stable cradle head receives the sent instruction to start swinging, the two-axis stable cradle head transversely swings for 5 times in one stroke, the imaging time is static for 300ms, and the two-channel camera 3 is simultaneously exposed when each angle position of each swinging angle of 12.5 degrees is static. And after the stroke is finished, the two-axis stable cradle head is reset immediately.
Pitch axis: the unmanned aerial vehicle device 1 is provided with a higher-precision position measurement system 6 to acquire the current flight speed in real time, the control computer 5 of the two-axis stable cradle head 2 is used for calculating the unmanned aerial vehicle height and the image shift angle caused by the flight speed, and the pitching axis swings in the opposite direction to the corresponding compensation angular speed in the imaging process of the camera every time:the method comprises the steps of carrying out a first treatment on the surface of the Wherein ω is pitch axis angular velocity, V is flight velocity, and H is unmanned aerial vehicle height.
In this embodiment, the two-axis stable pan-tilt 2 receives the program instructions of the controller to control the four-way movement of the camera view angle through the transverse axis and the pitching axis, the shooting angle is controlled through the program in the control computer 5, and the plurality of unmanned aerial vehicles transmit the image of the region to be detected of the photovoltaic power station back to the terminal of the control computer 5 through the wireless network.
In the embodiment, the transverse shaft swings transversely for 5 times in the stroke of a region to be detected, the angle is from-25 degrees to 25 degrees, the swinging angle is 12.5 degrees each time, the transverse shaft is static for 300ms at the imaging moment, the transverse shaft is reset to-25 degrees immediately after the stroke is finished to enter the next stroke, the flying speed and the height of the unmanned aerial vehicle are set to be 5m/s and 80m, and therefore the pitching shaft starts to compensate at the angular speed of 2 degrees/s when the camera images. By means of the arrangement, clear and accurate infrared images and visible light images can be obtained through unmanned aerial vehicle equipment, and a detection basis is provided for follow-up recognition of hot spots.
Further, fig. 3 schematically shows a flowchart of a method for identifying hot spots of a photovoltaic power plant array according to an embodiment of the present invention. Referring to fig. 3, in the step b, the corresponding feature point pairs in the visible light image and the infrared image in the wide-range image are found, so that the information of the visible light image and the infrared image are registered as follows: matching and aligning pixel points corresponding to each other in a visible light image and an infrared image in a large-scale image, wherein the matching and aligning comprises the following steps:
finding out reference lamplight built at four corners of a photovoltaic array detection area in a visible light image and an infrared image, and extracting n SIFT feature vectors from the images to be registered by applying a SIFT algorithm;
the RANSAC algorithm is applied to iteratively extract the n SIFT feature vectors to obtain 4 optimal infrared and visible light image feature vectors, a homography matrix for describing transformation between two images is calculated, and the homography matrix is calculated through an equation established with corresponding pixel point position information:；
wherein x and y respectively represent the abscissa and the ordinate of the visible light image pixel point, and x ', y' respectively represent the abscissa and the ordinate of the infrared image pixel point;
traversing the pixel point coordinates (x, y) of each visible light image, and transforming the pixel point coordinates into new image coordinates: it is expressed as homogeneous coordinates (x ', y', 1) and the new coordinates (xh, yh, wh) are obtained by multiplication with a homography matrix, normalized:
x1=xh/wh，y1=yh/wh；
wherein x1 and y1 are the abscissa and ordinate of the new image floating point number corresponding to the converted visible light image and the infrared image;
and (3) calculating the value of the integer coordinate point by linear interpolation, resampling the transformed visible light image according to the new image coordinate of each pixel point, and registering the visible light image with the infrared image.
Further, according to an embodiment of the present invention, in the step c, the separation of the photovoltaic array region and the background region in the visible light image and the infrared image includes:
converting the visible light image and the infrared image into gray images through image preprocessing;
based on the gray level image of the infrared image, identifying a photovoltaic array detection area in the infrared image by using a self-adaptive threshold segmentation algorithm, and segmenting a background area in the infrared image;
cutting the visible light image according to the pixel point positions corresponding to the infrared image, and dividing the background area in the visible light image to obtain the photovoltaic array detection area of the visible light image.
In the present embodiment, the gray information of the infrared image is used as a basis for separating the detection area of the photovoltaic array of the visible light image from the background, and in the present embodiment, the gray conversion method is a weighted calculation and matrix data is formed according to the relative position:wherein ω is the weight of the different color channels, ω r =0.299,ω g =0.587,ω b =0.114, m is the color channel matrix extracting the pixel, r, g, b represent red, green, blue channels, respectively.
In this embodiment, whether the detection area is a photovoltaic array detection area is determined according to the gradient change of the gray level of the infrared image, the gradient change of the gray level of the background area is large, and a vertical gradient image is calculated:wherein (1)>Is the gray scale vertical gradient of coordinates (x, y),Yis the gray value on the corresponding coordinates.
In this embodiment, the Otsu algorithm is used to obtain a vertical gradient binary matrix, and the vertical gradient binary matrix is inverted to obtain a judgment coefficient of whether the vertical gradient binary matrix is a reserved area, and the coefficient matrix is multiplied by the grayscale matrix of the infrared image and the visible light image to reserve a photovoltaic array area with a small grayscale difference, and remove a background area with a large grayscale difference.
Further, according to an embodiment of the present invention, in the step d, based on the calculation and matching of the gray scales of the visible light image and the infrared image, a fusion image is obtained, including:
extracting the reflected light features from the gray level histogram, prescribing the gray level histogram of the visible light image with the infrared image as the prescribed image: at [0, 255]Calculating cumulative histograms of the visible light image and the infrared image in a range, and calculating absolute values of differences between gray values of the visible light image and gray values of the infrared image cumulative histogram, wherein the gray value with the smallest absolute value is the mapping gray value:；
wherein P is i For the cumulative probability of gray level i in the cumulative histogram of visible light image, P j，min Accumulating the sum P in the histogram for infrared images i Cumulative probability of least phase difference, j min For the corresponding gray value, P r (k) ，P z (l) The distribution probability that the gray level of the visible light image and the infrared image is k and l respectively, and the T is the mapping relation from the gray level of the visible light image to the gray level of the stipulated result;
calculating gray level difference of each pixel point in the matched visible light image and the infrared image to obtain a fusion image:；
wherein I is x，y Is the gray level difference value of two image pixel points, Y x，y Is the gray value of the infrared image, Y' x，y The gray value of the visible light image is represented by n and m, and the number of the horizontal and vertical pixel points of the image is represented by n and m.
In this embodiment, the gray values of the visible light image and the infrared image in the light reflection area are both larger, and the gray value of the visible light image is not changed due to the temperature of the array surface, so that only the temperature information of the array surface is reserved in the gray difference image of the two images, and the light reflection information is eliminated.
Further, according to an embodiment of the present invention, in the step e, the hot spot position is found in the fused image according to the temperature characteristics of the hot spots of the array, and the coordinates of the hot spots are identified and counted:
and carrying out threshold segmentation on the gray level difference matrix in the fused image by applying an Otsu algorithm to obtain a binary image, identifying hot spot features in the binary image by extracting image features, and recording coordinates of each hot spot.
According to the scheme, false detection caused by reflected light is avoided; the accuracy of camera image registration is improved through the application of the unmanned aerial vehicle holder beam splitter and the ground reference lamp, and the improvement can be adapted under different environmental conditions and has good adaptability to different scenes.
Further, in order to achieve the above object, the present invention further provides a photovoltaic power station array hot spot identification system, including:
the image acquisition module is used for dividing the photovoltaic power station into a plurality of photovoltaic array detection areas by using unmanned aerial vehicle equipment and recording a plurality of infrared images and visible light images;
the image information registration module is used for aligning and splicing a plurality of infrared images and visible light images to form a large-range image, and finding out mutually corresponding characteristic point pairs in the visible light images and the infrared images in the large-range image so as to register the visible light images and the infrared image information;
the region separation module separates a photovoltaic array detection region from a background region in the visible light image and the infrared image;
the fusion image module is used for obtaining a fusion image based on the calculation and matching of the gray scales of the visible light image and the infrared image;
and the hot spot identification module is used for finding out the hot spot position in the fused image according to the temperature characteristics of the array hot spots and identifying and counting the coordinates of the hot spots.
According to the scheme, unmanned aerial vehicle equipment is adopted to acquire the image to be detected, then feature matching alignment is carried out on the visible light image and the infrared image, image fusion processing is carried out on the visible light image and the infrared image, and the hot spot position in the fused image is identified according to the identification temperature feature. This approach avoids false detection caused by reflected light.
Further, as shown in fig. 2, in the present embodiment, the unmanned aerial vehicle apparatus 1 includes:
the area dividing module is used for dividing a photovoltaic array detection area according to the flight range of the unmanned aerial vehicle, establishing an array coordinate, constructing a ginseng lamp at four corner coordinate points of the photovoltaic array detection area, and sending a signal by the ginseng lamp in the inspection time of the unmanned aerial vehicle;
the two-axis stable cradle head 2 is used for installing a camera and a thermal imager;
the image acquisition module comprises a double-channel camera 3 and a beam splitter 4 and is used for acquiring and transmitting infrared images and visible light images.
Further, as shown in fig. 2, in the present embodiment, the pose stabilization of the dual-channel camera 3 in the unmanned aerial vehicle device 1 is independently completed by the two-axis stabilization tripod head 2, and the tripod head view angle swing and the image acquisition control the two-axis movement and the camera exposure by the program set in advance by the built-in control computer 5, and the two-axis swing mode of the two-axis stabilization tripod head 2 is as follows:
transverse axis: the control computer 5 executes a preset program, the two-axis stable cradle head receives the sent instruction to start swinging, the two-axis stable cradle head transversely swings for 5 times in one stroke, the imaging time is static for 300ms, and the two-channel camera 3 is simultaneously exposed when each angle position of each swinging angle of 12.5 degrees is static. And after the stroke is finished, the two-axis stable cradle head is reset immediately.
Pitch axis: the unmanned aerial vehicle device 1 is provided with a higher-precision position measurement system 6 to acquire the current flight speed in real time, and the control computer 5 of the two-axis stable cradle head 2 is used for calculating the image caused by the unmanned aerial vehicle height and the flight speedAngle-shifting, each time the pitching axis swings towards opposite directions during the imaging process of the camera, corresponding compensating angular velocity:;
wherein ω is pitch axis angular velocity, V is flight velocity, and H is unmanned aerial vehicle height.
In this embodiment, the two-axis stable pan-tilt 2 receives the program instructions of the controller to control the four-way movement of the camera view angle through the transverse axis and the pitching axis, the shooting angle is controlled through the program in the control computer 5, and the plurality of unmanned aerial vehicles transmit the image of the region to be detected of the photovoltaic power station back to the terminal of the control computer 5 through the wireless network.
In the embodiment, the transverse shaft swings transversely for 5 times in the stroke of a region to be detected, the angle is from-25 degrees to 25 degrees, the swinging angle is 12.5 degrees each time, the transverse shaft is static for 300ms at the imaging moment, the transverse shaft is reset to-25 degrees immediately after the stroke is finished to enter the next stroke, the flying speed and the height of the unmanned aerial vehicle are set to be 5m/s and 80m, and therefore the pitching shaft starts to compensate at the angular speed of 2 degrees/s when the camera images. By means of the arrangement, clear and accurate infrared images and visible light images can be obtained through unmanned aerial vehicle equipment, and a detection basis is provided for follow-up recognition of hot spots.
Further, as shown in fig. 3, according to an embodiment of the present invention, in the image information registration module, a pair of feature points corresponding to each other in a visible light image and an infrared image in a large-scale image is found, so that the visible light image and the infrared image information are registered as follows: matching and aligning pixel points corresponding to each other in a visible light image and an infrared image in a large-scale image, wherein the matching and aligning comprises the following steps:
finding out reference lamplight built at four corners of a photovoltaic array detection area in a visible light image and an infrared image, and extracting n SIFT feature vectors from the images to be registered by applying a SIFT algorithm;
iterative extraction of the n SIFT feature vectors is carried out on the n SIFT feature vectors by using a RANSAC algorithm, 4 optimal infrared and visible light image feature vectors are extracted, a homography matrix for describing transformation between two images is calculated, and the homography matrix passes through the corresponding relationEquation calculation for establishing pixel point position information:；
wherein x and y respectively represent the abscissa and the ordinate of the visible light image pixel point, and x ', y' respectively represent the abscissa and the ordinate of the infrared image pixel point;
traversing the pixel point coordinates (x, y) of each visible light image, and transforming the pixel point coordinates into new image coordinates: it is expressed as homogeneous coordinates (x ', y', 1) and the new coordinates (xh, yh, wh) are obtained by multiplication with a homography matrix, normalized:
x1=xh/wh，y1=yh/wh；
wherein x1 and y1 are the abscissa and ordinate of the new image floating point number corresponding to the converted visible light image and the infrared image;
and (3) calculating the value of the integer coordinate point by linear interpolation, resampling the transformed visible light image according to the new image coordinate of each pixel point, and registering the visible light image with the infrared image.
Further, according to an embodiment of the present invention, in the above-described region separation module, separating the photovoltaic array region and the background region in the visible light image and the infrared image includes:
converting the visible light image and the infrared image into gray images through image preprocessing;
based on the gray level image of the infrared image, identifying a photovoltaic array detection area in the infrared image by using a self-adaptive threshold segmentation algorithm, and segmenting a background area in the infrared image;
cutting the visible light image according to the pixel point positions corresponding to the infrared image, and dividing the background area in the visible light image to obtain the photovoltaic array detection area of the visible light image.
In the present embodiment, the gray information of the infrared image is used as a basis for separating the detection area of the photovoltaic array of the visible light image from the background, and in the present embodiment, the gray conversion method is a weighted calculation and matrix data is formed according to the relative position:；
wherein ω is the weight of the different color channels, ω r =0.299,ω g =0.587,ω b =0.114, m is the color channel matrix extracting the pixel, r, g, b represent red, green, blue channels, respectively.
In this embodiment, whether the detection area is a photovoltaic array detection area is determined according to the gradient change of the gray level of the infrared image, the gradient change of the gray level of the background area is large, and a vertical gradient image is calculated:；
wherein,is the gray scale vertical gradient of coordinates (x, y),Yis the gray value on the corresponding coordinates.
In this embodiment, the Otsu algorithm is used to obtain a vertical gradient binary matrix, and the vertical gradient binary matrix is inverted to obtain a judgment coefficient of whether the vertical gradient binary matrix is a reserved area, and the coefficient matrix is multiplied by the grayscale matrix of the infrared image and the visible light image to reserve a photovoltaic array area with a small grayscale difference, and remove a background area with a large grayscale difference.
Further, according to an embodiment of the present invention, in the above fused image module, based on calculation and matching of gray scales of a visible light image and an infrared image, a fused image is obtained, including:
extracting the reflected light features from the gray level histogram, prescribing the gray level histogram of the visible light image with the infrared image as the prescribed image: at [0, 255]Calculating cumulative histograms of the visible light image and the infrared image in a range, and calculating absolute values of differences between gray values of the visible light image and gray values of the infrared image cumulative histogram, wherein the gray value with the smallest absolute value is the mapping gray value:；
wherein P is i For the cumulative probability of gray level i in the cumulative histogram of visible light image, P j，min Is an infrared imageAccumulating the sum P in the histogram i Cumulative probability of least phase difference, j min For the corresponding gray value, P r (k) ，P z (l) The distribution probability that the gray level of the visible light image and the infrared image is k and l respectively, and the T is the mapping relation from the gray level of the visible light image to the gray level of the stipulated result;
calculating gray level difference of each pixel point in the matched visible light image and the infrared image to obtain a fusion image:；
wherein I is x，y Is the gray level difference value of two image pixel points, Y x，y Is the gray value of the infrared image, Y' x，y The gray value of the visible light image is represented by n and m, and the number of the horizontal and vertical pixel points of the image is represented by n and m.
In this embodiment, the gray values of the visible light image and the infrared image in the light reflection area are both larger, and the gray value of the visible light image is not changed due to the temperature of the array surface, so that only the temperature information of the array surface is reserved in the gray difference image of the two images, and the light reflection information is eliminated.
Further, according to an embodiment of the present invention, in the above-mentioned hot spot identification module, a hot spot position is found in the fused image according to the temperature characteristics of the array hot spots, and coordinates of the hot spots are identified and counted:
and carrying out threshold segmentation on the gray level difference matrix in the fused image by applying an Otsu algorithm to obtain a binary image, identifying hot spot features in the binary image by extracting image features, and recording coordinates of each hot spot.
According to the scheme, the unmanned aerial vehicle is carried with the double-channel camera to obtain the image to be detected, and the image fusion operation is carried out on the infrared image to obtain the preprocessed image, so that the array hot spot position is identified. This approach avoids false detection caused by reflected light; the accuracy of camera image registration is increased through the improvement of the unmanned aerial vehicle holder and the application of the same-optical-axis beam splitter, and the improvement can be adapted under different environmental conditions and has good adaptability to different scenes.
Further, to achieve the above object, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, where the computer program when executed by the processor implements the method for identifying hot spots of a photovoltaic power plant array as described above.
Further, to achieve the above object, the present invention further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for identifying hot spots of a photovoltaic power plant array as described above.
Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. 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.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and device described above may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment of the invention.
In addition, each functional module in the embodiment of the present invention may be integrated in one processing module, or each module may exist alone physically, or two or more modules may be integrated in one module.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method for energy saving signal transmission/reception of the various embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the invention referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or equivalents thereof is possible without departing from the spirit of the invention. Such as the above-described features and technical features having similar functions (but not limited to) disclosed in the present application are replaced with each other.
It should be understood that, the sequence numbers of the steps in the summary and the embodiments of the present invention do not necessarily mean the order of execution, and the execution order of the processes should be determined by the functions and the internal logic, and should not be construed as limiting the implementation process of the embodiments of the present invention.
Claims (7)
1. The method for identifying the hot spots of the photovoltaic power station array is characterized by comprising the following steps of:
dividing a photovoltaic power station into a plurality of photovoltaic array detection areas by using unmanned aerial vehicle equipment, and recording a plurality of infrared images and visible light images;
aligning and splicing a plurality of infrared images and visible light images to form a large-range image, and finding out mutually corresponding characteristic point pairs in the visible light images and the infrared images in the large-range image so as to enable the visible light images and the infrared image information to be registered;
separating a photovoltaic array detection area from a background area in the visible light image and the infrared image;
obtaining a fusion image based on the calculation and matching of the gray scale of the visible light image and the infrared image; the fusion image is a visible light image and an infrared image after background area separation;
finding out the position of the hot spot in the fused image according to the temperature characteristics of the array hot spot, and identifying and counting the coordinates of the hot spot;
the calculation and matching of gray scale based on visible light image and infrared image, obtaining a fusion image, comprises:
extracting the reflected light features from the gray level histogram, prescribing the gray level histogram of the visible light image with the infrared image as the prescribed image:
calculating gray level difference of each pixel point in the matched visible light image and the infrared image to obtain a fusion image:；
wherein I is x，y Is the gray level difference value of two image pixel points, Y x，y Is the gray value of the infrared image, Y' x，y The gray value of the visible light image is represented by n and m, and the number of the horizontal and vertical pixel points of the image is represented by n and m;
the unmanned aerial vehicle device includes:
the area dividing module is used for dividing the photovoltaic array detection area according to the flight range of the unmanned aerial vehicle, establishing an array coordinate, constructing a ginseng lamp at four corner coordinate points of the photovoltaic array detection area, and sending a signal when the ginseng lamp is patrolled and examined by the unmanned aerial vehicle;
the two-axis stable cradle head is used for installing a camera and a thermal imager;
the image acquisition module comprises a double-channel camera and a beam splitter and is used for acquiring and transmitting infrared images and visible light images;
the two-axis swinging mode of the two-axis stable cradle head is as follows:
transverse axis: transversely swinging for 5 times in one stroke, standing for 300ms at the imaging moment, and immediately resetting the two-axis stable cradle head after the stroke is finished when each swinging angle is 12.5 degrees and each angle position is static;
pitch axis: and swinging corresponding compensating angular velocity along the opposite direction of a pitching axis in the imaging process of the double-channel camera:；
wherein ω is pitch axis angular velocity, V is flight velocity, and H is unmanned aerial vehicle height.
2. The method for identifying hot spots of the photovoltaic power plant array according to claim 1, wherein the finding of the feature point pairs corresponding to each other in the visible light image and the infrared image in the large-scale image registers the information of the visible light image and the infrared image as follows: matching and aligning pixel points corresponding to each other in a visible light image and an infrared image in a large-scale image, wherein the matching and aligning comprises the following steps:
finding out reference lamplight built at four corners of a photovoltaic array detection area in a visible light image and an infrared image, and extracting n SIFT feature vectors from the images to be registered by applying a SIFT algorithm;
the RANSAC algorithm is applied to iteratively extract the n SIFT feature vectors to obtain 4 optimal infrared and visible light image feature vectors, a homography matrix for describing transformation between two images is calculated, and the homography matrix is calculated through an equation established with corresponding pixel point position information:
；
wherein x and y respectively represent the abscissa and the ordinate of the visible light image pixel point, and x ', y' respectively represent the abscissa and the ordinate of the infrared image pixel point;
traversing the pixel point coordinates (x, y) of each visible light image, and transforming the pixel point coordinates into new image coordinates: it is expressed as homogeneous coordinates (x ', y', 1) and the new coordinates (xh, yh, wh) are obtained by multiplication with a homography matrix, normalized:
x1=xh/wh，y1=yh/wh；
wherein x1 and y1 are the abscissa and ordinate of the new image floating point number corresponding to the converted visible light image and the infrared image;
and (3) calculating the value of the integer coordinate point by linear interpolation, resampling the transformed visible light image according to the new image coordinate of each pixel point, and registering the visible light image with the infrared image.
3. The method for identifying hot spots of a photovoltaic power plant array according to claim 1, wherein the separating the photovoltaic array region from the background region in the visible light image and the infrared image comprises:
converting the visible light image and the infrared image into gray images through image preprocessing;
based on the gray level image of the infrared image, identifying a photovoltaic array detection area in the infrared image by using a self-adaptive threshold segmentation algorithm, and segmenting a background area in the infrared image;
cutting the visible light image according to the pixel point positions corresponding to the infrared image, and dividing the background area in the visible light image to obtain the photovoltaic array detection area of the visible light image.
4. A method for identifying hot spots of a photovoltaic power plant array according to any one of claims 1 to 3, wherein the coordinates of the hot spots are identified and counted by finding the hot spot positions in the fused image according to the temperature characteristics of the hot spots of the array:
and carrying out threshold segmentation on the gray level difference matrix in the fused image by applying an Otsu algorithm to obtain a binary image, identifying hot spot features in the binary image by extracting image features, and recording coordinates of each hot spot.
5. A photovoltaic power plant array hot spot identification system, comprising:
the image acquisition module is used for dividing the photovoltaic power station into a plurality of photovoltaic array detection areas by using unmanned aerial vehicle equipment and recording a plurality of infrared images and visible light images;
the image information registration module is used for aligning and splicing a plurality of infrared images and visible light images to form a large-range image, and finding out mutually corresponding characteristic point pairs in the visible light images and the infrared images in the large-range image so as to register the visible light images and the infrared image information;
the region separation module separates a photovoltaic array detection region from a background region in the visible light image and the infrared image;
the fusion image module is used for obtaining a fusion image based on the calculation and matching of the gray scales of the visible light image and the infrared image; the fusion image is a visible light image and an infrared image after background area separation;
the hot spot identification module is used for finding out the hot spot position in the fused image according to the temperature characteristics of the array hot spots and identifying and counting the coordinates of the hot spots;
the calculation and matching of gray scale based on visible light image and infrared image, obtaining a fusion image, comprises:
extracting the reflected light features from the gray level histogram, prescribing the gray level histogram of the visible light image with the infrared image as the prescribed image:
calculating gray level difference of each pixel point in the matched visible light image and the infrared image to obtain a fusion image:；
wherein I is x，y Is the gray level difference value of two image pixel points, Y x，y Is an infrared imageGray value, Y' x，y The gray value of the visible light image is represented by n and m, and the number of the horizontal and vertical pixel points of the image is represented by n and m;
the unmanned aerial vehicle device includes:
the area dividing module is used for dividing the photovoltaic array detection area according to the flight range of the unmanned aerial vehicle, establishing an array coordinate, constructing a ginseng lamp at four corner coordinate points of the photovoltaic array detection area, and sending a signal when the ginseng lamp is patrolled and examined by the unmanned aerial vehicle;
the two-axis stable cradle head is used for installing a camera and a thermal imager;
the image acquisition module comprises a double-channel camera and a beam splitter and is used for acquiring and transmitting infrared images and visible light images;
the two-axis swinging mode of the two-axis stable cradle head is as follows:
transverse axis: transversely swinging for 5 times in one stroke, standing for 300ms at the imaging moment, and immediately resetting the two-axis stable cradle head after the stroke is finished when each swinging angle is 12.5 degrees and each angle position is static;
pitch axis: and swinging corresponding compensating angular velocity along the opposite direction of a pitching axis in the imaging process of the double-channel camera:；
wherein ω is pitch axis angular velocity, V is flight velocity, and H is unmanned aerial vehicle height.
6. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the method of identifying hot spots of a photovoltaic power plant array as claimed in any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the method for identifying hot spots of a photovoltaic power plant array according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311452573.3A CN117173601B (en) | 2023-11-03 | 2023-11-03 | Photovoltaic power station array hot spot identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311452573.3A CN117173601B (en) | 2023-11-03 | 2023-11-03 | Photovoltaic power station array hot spot identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117173601A CN117173601A (en) | 2023-12-05 |
| CN117173601B true CN117173601B (en) | 2024-03-01 |
Family
ID=88932178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311452573.3A Active CN117173601B (en) | 2023-11-03 | 2023-11-03 | Photovoltaic power station array hot spot identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117173601B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117456371B (en) * | 2023-12-26 | 2024-04-12 | 浙江正泰智维能源服务有限公司 | Group string hot spot detection method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815838A (en) * | 2017-01-22 | 2017-06-09 | 晶科电力有限公司 | A kind of method and system of the detection of photovoltaic module hot spot |
| CN108364272A (en) * | 2017-12-30 | 2018-08-03 | 广东金泽润技术有限公司 | A kind of high-performance Infrared-Visible fusion detection method |
| CN115409814A (en) * | 2022-09-02 | 2022-11-29 | 大唐（赤峰）新能源有限公司 | Photovoltaic module hot spot detection method and system based on fusion image |
| CN116385421A (en) * | 2023-04-07 | 2023-07-04 | 哈尔滨工业大学（深圳） | Photovoltaic panel detection method, unmanned aerial vehicle and computer readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110969670B (en) * | 2019-11-22 | 2022-02-15 | 大连理工大学 | Multispectral camera dynamic three-dimensional calibration method based on significant features |
-
2023
- 2023-11-03 CN CN202311452573.3A patent/CN117173601B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815838A (en) * | 2017-01-22 | 2017-06-09 | 晶科电力有限公司 | A kind of method and system of the detection of photovoltaic module hot spot |
| CN108364272A (en) * | 2017-12-30 | 2018-08-03 | 广东金泽润技术有限公司 | A kind of high-performance Infrared-Visible fusion detection method |
| CN115409814A (en) * | 2022-09-02 | 2022-11-29 | 大唐（赤峰）新能源有限公司 | Photovoltaic module hot spot detection method and system based on fusion image |
| CN116385421A (en) * | 2023-04-07 | 2023-07-04 | 哈尔滨工业大学（深圳） | Photovoltaic panel detection method, unmanned aerial vehicle and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 《无人机载可见红外光伏板热斑检测***研究》;洪声艺;《优秀硕士论文》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117173601A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112767391B (en) | Power grid line part defect positioning method integrating three-dimensional point cloud and two-dimensional image | |
| CN111882612B (en) | Vehicle multi-scale positioning method based on three-dimensional laser detection lane line | |
| CN110595476B (en) | Unmanned aerial vehicle landing navigation method and device based on GPS and image visual fusion | |
| CN115439424B (en) | Intelligent detection method for aerial video images of unmanned aerial vehicle | |
| CN117173601B (en) | Photovoltaic power station array hot spot identification method and system | |
| CN107421473A (en) | The two beam laser coaxial degree detection methods based on image procossing | |
| Borrmann et al. | Mutual calibration for 3D thermal mapping | |
| CN111536981B (en) | Embedded binocular non-cooperative target relative pose measurement method | |
| CN110889829A (en) | Monocular distance measurement method based on fisheye lens | |
| CN108362205B (en) | Space distance measuring method based on fringe projection | |
| CN114511014A (en) | Subway tunnel water leakage detection system and method based on image deep learning algorithm | |
| CN109118429A (en) | A kind of medium-wave infrared-visible light multispectral image rapid generation | |
| Mi et al. | A vision-based displacement measurement system for foundation pit | |
| CN113066050B (en) | Method for resolving course attitude of airdrop cargo bed based on vision | |
| CN114399675A (en) | Target detection method and device based on machine vision and laser radar fusion | |
| CN114413958A (en) | Monocular vision distance and speed measurement method of unmanned logistics vehicle | |
| CN112116637B (en) | Automatic power tower detection method and system based on unmanned aerial vehicle 3D laser scanning technology | |
| CN115376028A (en) | Target detection method based on dense feature point splicing and improved YOLOV5 | |
| CN113947724A (en) | Automatic line icing thickness measuring method based on binocular vision | |
| CN113743286A (en) | Target monitoring system and method for multi-source signal fusion | |
| CN115393196B (en) | Infrared multi-sequence image seamless splicing method for unmanned aerial vehicle area array swinging | |
| CN112767459A (en) | Unmanned aerial vehicle laser point cloud and sequence image registration method based on 2D-3D conversion | |
| CN116977806A (en) | Airport target detection method and system based on millimeter wave radar, laser radar and high-definition array camera | |
| CN115375762A (en) | Three-dimensional reconstruction method for power line based on trinocular vision | |
| CN113095324A (en) | Classification and distance measurement method and system for cone barrel |
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 |