A method and device for automatic inspection of high voltage transmission lines

Abstract

The present application discloses a method and equipment for automatic inspection of high-voltage transmission lines, the method comprising: performing image acquisition of the high-voltage transmission line through a camera device with shooting parameters set, obtaining an image containing the conductors in the high-voltage transmission line; determining the inspection end in the image according to the inspection direction contained in the shooting parameters; performing image recognition on the image, identifying and determining the conductor in the image, and confirming the first reference point corresponding to the conductor in the inspection end, and the second reference point corresponding to the entire image; determining the screen offset angle of the conductor in the image according to the first reference point and the second reference point; adjusting the shooting parameters according to the screen offset angle to realize automatic inspection of the high-voltage transmission line. By using the screen offset angle and adaptively adjusting the shooting parameters according to the screen offset angle, problems can be found more frequently and timely compared to drone and robot inspections in traditional solutions.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method and device for automatic inspection of high-voltage transmission lines. Background Art

[0002] Overhead transmission lines have low construction costs, short construction periods, and are easy to inspect and maintain. Therefore, compared with underground transmission lines, they are the main transmission method for the development of the power industry. Overhead transmission lines have large transmission capacity and high working voltage. They are mostly in the form of split conductors and spacer combinations. Multiple conductors are combined into one phase conductor and stretch for thousands of miles. Overhead transmission lines are exposed to the atmosphere for a long time and will be directly affected by meteorological conditions, which may cause dangerous situations such as loose spacers and broken conductors. Therefore, it is necessary to patrol the conductors regularly and check for possible problems with the conductors in a timely manner.

[0003] Currently, most line inspections rely on manual inspections, drones, robots or online device inspections. Manual inspections, drone inspections and robot inspections all require on-site inspections of overhead transmission lines, which have low inspection frequency and efficiency, and are inconvenient to inspect on-site in bad weather conditions. Remote online device inspections require manual inspections of equipment and transmission lines on towers, and manual inspections from each viewing angle, which is time-consuming and laborious, and may lead to omissions due to manual fatigue. Summary of the invention

[0004] In order to solve the above problems, the present application proposes an automatic inspection method for high-voltage transmission lines, comprising: performing image acquisition on the high-voltage transmission line by a camera device with shooting parameters set to obtain an image containing the conductors in the high-voltage transmission line; determining the inspection end in the image according to the inspection direction contained in the shooting parameters; performing image recognition on the image, identifying and determining the conductor in the image, and confirming a first reference point corresponding to the conductor in the inspection end, and a second reference point corresponding to the image as a whole; determining a screen offset angle of the conductor in the image according to the first reference point and the second reference point; adjusting the shooting parameters according to the screen offset angle, and continuing to acquire images of the high-voltage transmission line according to the adjusted shooting parameters, so as to realize automatic inspection of the high-voltage transmission line.

[0005] In one example, performing image recognition on the image and identifying and determining the wire in the image specifically includes: performing edge recognition in the image and performing binarization processing based on the edge recognition result; performing linear fitting on the binarized image and performing cluster analysis on the fitted straight line obtained after the linear fitting to determine several directions with the most line clusters as several wires existing in the image.

[0006] In one example, the linear fitting of the binarized image specifically includes: specifying a plurality of edge points in the binarized image, the edge points being obtained according to the edge recognition result; converting the plurality of edge points from the image coordinate space to the parameter space; determining corresponding straight line parameters according to the commonality of parameters of the converted edge points in the parameter space, and implementing linear fitting according to the straight line parameters.

[0007] In one example, the method of determining corresponding straight line parameters according to the commonality of parameters of the converted edge points in the parameter space, and implementing linear fitting according to the straight line parameters, specifically includes: establishing multiple two-dimensional accumulation arrays A(a, b) corresponding to the parameter space, wherein the range of the first dimension a is determined according to the slope of the straight line of the edge point in the image coordinate space, and the range of the second dimension b is determined according to the intercept of the straight line of the edge point in the image coordinate space; initializing the multiple A(a, b); for each designated edge point in the image coordinate space, determining the corresponding b according to the a corresponding to the edge point after conversion, and increasing the corresponding A(a, b) by a fixed value in an additive manner according to the a and the b; selecting several A(a, b) with the highest peak values ​​according to the peak values ​​corresponding to the accumulated A(a, b), and using the a and the b in the selected A(a, b) as straight line parameters to generate several straight lines in the image coordinate space respectively.

[0008] In one example, determining the first reference point corresponding to the wire at the inspection end and the second reference point corresponding to the entire image specifically includes: determining a first center point (d x ,d y ), and the second center point of the entire image (c x ,c y ), wherein said d x , the y represent the horizontal coordinate and vertical coordinate of the first center point in the image respectively, and the c x 、the c y respectively represent the horizontal coordinate and the vertical coordinate of the second center point in the image; determining the screen offset angle of the wire in the image according to the first reference point and the second reference point specifically includes: determining the width W and the height H of the image, and determining that the field of view FOV of the camera device is horizontal HA and vertical VA respectively; by The screen offset angle of the wire in the image is obtained.

[0009] In one example, before continuing to capture images of the high-voltage transmission line according to the adjusted shooting parameters, the method also includes: determining the pixel diameter corresponding to the wire at the end of the inspection according to the direction with the most wire clusters; and adjusting the lens magnification in the shooting parameters according to the pixel diameter.

[0010] In one example, determining the pixel diameter corresponding to the wire at the end of the inspection based on the direction with the most wire clusters specifically includes: determining the direction Q with the most wire clusters; selecting a wire in the wire cluster and rotating the selected wire in the -Q direction; vertically projecting the rotated wire and counting the number of column vectors greater than 0 in the projection matrix to determine the pixel diameter corresponding to the wire at the end of the inspection.

[0011] In one example, the adjusting the lens magnification in the shooting parameters according to the pixel diameter specifically includes: determining the correspondence between the lens magnification obtained in advance through calibration and the pixel diameter, and adjusting the lens magnification in the shooting parameters according to the correspondence and the pixel diameter, the correspondence including B=P1*r+P2+P0, wherein B is the camera diameter, r is the pixel diameter, P0 is the initial lens magnification, and P1 and P2 are respectively the specified lens magnifications obtained by sampling and linear fitting.

[0012] In one example, the camera device is a pan-tilt camera, and the shooting parameters include at least one of a starting acquisition position, a final acquisition position, a timed patrol cycle, a horizontal rotation angle of the pan-tilt, a vertical rotation angle of the pan-tilt, and a lens magnification.

[0013] On the other hand, the present application also proposes an automatic inspection device for high-voltage transmission lines, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute: performing image acquisition on the high-voltage transmission line by a camera device with shooting parameters set to obtain an image containing the conductors in the high-voltage transmission line; determining the inspection end in the image according to the inspection direction contained in the shooting parameters; performing image recognition on the image, identifying and determining the conductor in the image, and confirming the first reference point corresponding to the conductor in the inspection end, and the second reference point corresponding to the entire image; determining the screen offset angle of the conductor in the image according to the first reference point and the second reference point; adjusting the shooting parameters according to the screen offset angle, and continuing to acquire images of the high-voltage transmission line according to the adjusted shooting parameters to realize automatic inspection of the high-voltage transmission line.

[0014] The automatic inspection method for high-voltage transmission lines proposed in this application can bring the following beneficial effects:

[0015] By identifying and analyzing the collected images, the screen offset angle of the wire in the image can be determined, and the shooting parameters can be adaptively adjusted according to the screen offset angle. Compared with the drone and robot inspection in the traditional solution, problems can be found more frequently and timely. In addition, the solution in this application does not need to pre-set multiple preset position information and then fit to obtain the shooting parameter curve. It only needs to automatically adjust the shooting parameters during the inspection process, which saves the manpower and material resources required for manually setting these preset positions, and can solve the problem of poor fitting effect caused by omissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A schematic diagram of a process flow of an automatic inspection method for high-voltage transmission lines in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of an image containing a wire collected in an embodiment of the present application;

[0019] Figure 3 This is a schematic diagram of an image after being binarized in an embodiment of the present application;

[0020] Figure 4This is a schematic diagram of linear fitting of an image in an embodiment of the present application;

[0021] Figure 5 A schematic diagram of image parameter coordinates and space coordinates in an embodiment of the present application;

[0022] Figure 6 A schematic diagram of the parameter calculation voting results in the embodiment of the present application;

[0023] Figure 7 This is a schematic diagram of the effect of cluster analysis in an embodiment of the present application;

[0024] Figure 8 It is a schematic diagram of the automatic inspection equipment of high-voltage transmission lines in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0026] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0027] like Figure 1 As shown, the embodiment of the present application provides a method for automatic inspection of high-voltage transmission lines, comprising:

[0028] S101: Capturing images of a high-voltage transmission line by using a camera device with set shooting parameters to obtain an image containing conductors in the high-voltage transmission line.

[0029] The camera device usually refers to a pan-tilt camera, in which the pan-tilt has a device that supports the camera to rotate horizontally and vertically. Mounting the camera on the pan-tilt can enable the camera to shoot from multiple angles. The pan-tilt usually has two motors, and the horizontal and vertical rotation angles can be adjusted by limit switches.

[0030] The shooting parameters may include: the starting acquisition position, the final acquisition position, the timed patrol cycle, the horizontal rotation angle of the pan / tilt, the vertical rotation angle of the pan / tilt, the lens magnification, etc.

[0031] When starting the automatic inspection, the camera device can be placed at the starting collection position by drone or manual means, then start recording the video stream, and perform subsequent image processing on the frame images in the video to achieve automatic inspection.

[0032] S102: Determine an inspection end in the image according to the inspection direction included in the shooting parameters.

[0033] The inspection direction can be directly carried in the shooting parameters, or the inspection direction can be determined by the starting acquisition position and the final acquisition position. For example, Figure 2 As shown, when the starting acquisition position is above the image and the final acquisition position is below the image, it can be determined that the inspection direction is from top to bottom. At this time, the end of the inspection is the bottom of the image.

[0034] S103: performing image recognition on the image, identifying and determining the wire in the image, and confirming a first reference point corresponding to the wire at the inspection end, and a second reference point corresponding to the entire image.

[0035] The image is recognized and the position of the wire is determined. At this time, two reference points can be determined. The first reference point corresponds to the wire at the end of the inspection, which can accurately indicate the position of the wire at the end of the inspection, for example, it can be the midpoint of the wire at the end of the inspection, and the second reference point corresponds to the entire image, which can indicate the position of the entire image, for example, it can be a corner point or midpoint of the image.

[0036] S104: Determine a screen offset angle of the wire in the image according to the first reference point and the second reference point.

[0037] S105: adjusting the shooting parameters according to the picture offset angle, and continuing to collect images of the high-voltage transmission line according to the adjusted shooting parameters, so as to realize automatic inspection of the high-voltage transmission line.

[0038] The image offset angle refers to the offset angle of the wire in the image. When the offset angle is too large, it means that the position of the wire at the end of the inspection is very close to the edge of the image. If the image is still acquired according to the current shooting parameters, it is very likely that the wire cannot be clearly acquired in the subsequent image acquisition process, and automatic inspection cannot be achieved.

[0039] Based on this, the shooting parameters are adjusted according to the image offset angle. The larger the image offset angle, the greater the adjustment range of the shooting parameters. Generally speaking, the two parameters that need to be adjusted most at this time are the horizontal rotation angle and the vertical rotation angle of the gimbal.

[0040] By identifying and analyzing the collected images, the screen offset angle of the wire in the image can be determined, and the shooting parameters can be adaptively adjusted according to the screen offset angle. Compared with the drone and robot inspection in the traditional solution, problems can be found more frequently and timely. In addition, the solution in this application does not need to pre-set multiple preset position information and then fit to obtain the shooting parameter curve. It only needs to automatically adjust the shooting parameters during the inspection process, which saves the manpower and material resources required for manually setting these preset positions, and can solve the problem of poor fitting effect caused by omissions.

[0041] In one embodiment, when performing image recognition on an image and determining the wire, edge recognition is first performed in the image, and then binarization is performed based on the edge recognition result.

[0042] Among them, edge detection algorithms are not limited to Canny, Sobel, etc., they can also be deep learning methods, such as pixel convolution differential pidinet. Deep learning methods achieve more robust results than image processing methods. In the early stages of a project, when there is not much data, image processing methods are used to collect data online. When the amount of data accumulated and the diversity are sufficient, the images are annotated and trained using a pixel convolution differential network to obtain a more robust detection effect. The binarized image can be Figure 3 shown.

[0043] Linear fitting is performed on the binarized image, and then cluster analysis is performed on the fitted straight line obtained after fitting. The directions with the most line clusters can be determined as the wires in the image. The image after linear fitting can be Figure 4 shown.

[0044] Specifically, a plurality of edge points may be first specified in the binarized image according to the edge recognition result. The edge points refer to points on the edge line identified in the edge recognition result, which may be selected regularly or randomly by the user according to the needs.

[0045] The corresponding coordinate system xy can be constructed in advance, for example, taking the upper left corner of the image as the far point, to construct a rectangular coordinate system xy. At this time, the image and the edge points are in the image coordinate space xy, and then at least these multiple edge points (or all points in the image) are converted from the image coordinate space xy to the parameter space ab. Figure 5As shown in the figure, each point on the straight line passing through the point in the image coordinate space xy corresponds to a straight line in the parameter space ab. Conversely, all straight lines intersecting at the same point in the parameter space have collinear points corresponding to them in the image coordinate space. Based on this, the corresponding straight line parameters are determined according to the parameter commonality of the converted edge points in the parameter space, and linear fitting is achieved based on the straight line parameters. Among them, the parameter commonality is related to the number of straight lines intersecting at the same point in the parameter space. The more the number, the higher the parameter commonality. At this time, the more edge points have the parameter, the greater the probability of forming a straight line.

[0046] Furthermore, when determining the line parameters according to the commonality of the parameters, the parameter space can be regarded as discrete. In this case, firstly, multiple two-dimensional accumulation arrays A(a,b) are established in the parameter space, wherein the range of the first dimension a is determined according to the line slope of the edge point in the image coordinate space (for example, it can be the possible range of the line slope in the image coordinate space), and the range of the second dimension b is determined according to the line intercept of the edge point in the image coordinate space (for example, it can be the possible range of the line intercept in the image coordinate space), and different A(a,b)s contain different values ​​of the parameter a and / or parameter b.

[0047] Initialize A(a,b) to 0, and then for each edge point (xi,yi) in the image coordinate space, substitute the known discrete value of a in the parameter space into the following formula to calculate the corresponding b value, where the formula is b = -x i a+y i . For each pair (a, b) calculated, a fixed value (for example, 1) is added to the corresponding A(a, b), that is, A(a, b) = A(a, b) + 1.

[0048] After all calculations are completed, the peak values ​​corresponding to each A(a,b) are determined in the parameter calculation voting results, and several A(a0,b0) with the highest peak values ​​are selected, where the corresponding a0 and b0 are the linear parameters of the linear equation with the largest number of collinear points in the original image. For example, the selection can be made according to the maximum peak value, the second peak value, the third peak value, the fourth peak value, etc. At this time, according to the corresponding parameters a0 and b0, the corresponding linear equation can be generated, and the linear equation corresponding to the wire can be obtained, thereby realizing linear fitting. For example, Figure 6 As shown, +2 is selected as the maximum peak and the other +1 is the secondary peak.

[0049] In addition, if Figure 7As shown, cluster analysis can use density-based spatial clustering of noise applications (DBSCAN), which is an unsupervised ML clustering algorithm. Unsupervised means that it does not use pre-labeled targets to cluster data points. Clustering refers to trying to group similar data points into artificially determined groups or clusters. The input of the DBSCAN clustering method is the angle of all wires, the distance radius is set to 2, and the minimum number of points is 10.

[0050] In one embodiment, when determining the first reference point and the second reference point, the center point can be used as the reference point. In this case, the first center point (d x ,d y ), and the second center point of the entire image (c x ,c y ), where d x ,d y Respectively represent the horizontal and vertical coordinates of the first center point in the image, c x 、c y Respectively represent the horizontal and vertical coordinates of the second center point in the image.

[0051] Then determine the width W and height H of the image. Because the wire segments shot during inspection are usually short, they can be considered to be evenly distributed in angle. At this time, assuming that the field of view FOV of the camera device at this magnification is horizontal HA and vertical VA, we can get The screen offset angle of the wire in the image is obtained. The screen offset angle can be adjusted in reverse to display the end of the wire at the center of the screen. During the adjustment process, the horizontal rotation angle and the vertical rotation angle of the camera device need to be adjusted. After the adjustment is completed, reshooting can place the end of the wire at the center of the screen and start the second shooting.

[0052] In one embodiment, in addition to considering the horizontal and vertical angle rotation to ensure that the end of the wire can be in the center of the image, it is also necessary to consider that during the shooting process, the wire being photographed is getting farther and farther away, and at this time, the lens magnification needs to be adjusted. Based on this, according to the direction with the most wire clusters, the pixel diameter corresponding to the wire at the end of the inspection is determined, and then the lens magnification in the shooting parameters is adjusted according to the pixel diameter. Generally speaking, the lower the pixel diameter, the higher the lens magnification that needs to be adjusted.

[0053] Specifically, the pixel diameter needs to be calculated first. At this time, first determine the direction Q with the most line clusters, then select a wire from the line cluster and rotate the selected wire in the -Q direction. Then perform a vertical projection on the rotated wire and count the number of column vectors greater than 0 in the projection matrix. This number can be used as the pixel diameter corresponding to the wire at the end of the inspection.

[0054] After obtaining the pixel diameter, the lens magnification can be adjusted through the correspondence relationship obtained in advance through calibration. Among them, the correspondence relationship between the lens magnification and the pixel diameter is obtained in advance through calibration, B = P1*r+P2+P0, B is the camera diameter, r is the pixel diameter, P0 is the initial lens magnification, and P1 and P2 are the specified lens magnifications obtained by sampling and linear fitting. In this way, the lens magnification can be adjusted while considering whether the end of the wire is in the center of the image, thereby maximizing the shooting efficiency and shortening the shooting interval on the basis of ensuring that the wire is clearly photographed.

[0055] like Figure 8 As shown, the embodiment of the present application also provides an automatic inspection device for high-voltage transmission lines, including:

[0056] at least one processor; and,

[0057] a memory communicatively connected to the at least one processor; wherein,

[0058] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute:

[0059] Capturing images of the high-voltage transmission line by using a camera device with shooting parameters set, to obtain an image containing the conductors in the high-voltage transmission line;

[0060] Determining the inspection end in the image according to the inspection direction included in the shooting parameters;

[0061] Performing image recognition on the image, identifying and determining the wire in the image, and confirming a first reference point corresponding to the wire at the inspection end, and a second reference point corresponding to the entire image;

[0062] Determining a screen offset angle of the wire in the image according to the first reference point and the second reference point;

[0063] The shooting parameters are adjusted according to the picture offset angle, and the image acquisition of the high-voltage transmission line continues according to the adjusted shooting parameters to realize automatic inspection of the high-voltage transmission line.

[0064] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0065] Capturing images of the high-voltage transmission line by using a camera device with shooting parameters set, to obtain an image containing the conductors in the high-voltage transmission line;

[0066] Determining the inspection end in the image according to the inspection direction included in the shooting parameters;

[0067] Performing image recognition on the image, identifying and determining the wire in the image, and confirming a first reference point corresponding to the wire at the inspection end, and a second reference point corresponding to the entire image;

[0068] Determining a screen offset angle of the wire in the image according to the first reference point and the second reference point;

[0069] The shooting parameters are adjusted according to the picture offset angle, and the image acquisition of the high-voltage transmission line continues according to the adjusted shooting parameters to realize automatic inspection of the high-voltage transmission line.

[0070] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0071] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0072] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0073] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0077] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0078] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0079] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0080] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for automatic inspection of high-voltage transmission lines, characterized in that: include: Capturing images of the high-voltage transmission line by using a camera device with shooting parameters set, to obtain an image containing the conductors in the high-voltage transmission line; Determining the inspection end in the image according to the inspection direction included in the shooting parameters; Performing image recognition on the image, identifying and determining the wire in the image, and determining a first reference point corresponding to the wire at the inspection end, and a second reference point corresponding to the entire image; Determining a screen offset angle of the wire in the image according to the first reference point and the second reference point; Adjusting the shooting parameters according to the picture offset angle, and continuing to collect images of the high-voltage transmission line according to the adjusted shooting parameters, so as to realize automatic inspection of the high-voltage transmission line; The determining of the first reference point corresponding to the wire at the inspection end, and the second reference point corresponding to the entire image, specifically includes: Determine the first center point of the wire at the end of the inspection ( , ), and the second center point of the entire image ( , ), wherein the , represent the horizontal coordinate and vertical coordinate of the first center point in the image respectively, , respectively represent the abscissa and ordinate of the second center point in the image; The determining, according to the first reference point and the second reference point, a screen offset angle of the wire in the image specifically includes: Determine the width W and height H of the image, and determine the field of view FOV of the camera device to be horizontal HA and vertical VA respectively; pass , and obtain the screen offset angle of the wire in the image.

2. The method according to claim 1, characterized in that The performing image recognition on the image to identify and determine the wire in the image specifically includes: Performing edge recognition in the image, and performing binarization processing according to the edge recognition result; Linear fitting is performed on the binarized image, and cluster analysis is performed on the fitted straight lines obtained after the linear fitting, so as to determine several directions with the most line clusters as several wires existing in the image.

3. The method according to claim 2, characterized in that The performing linear fitting on the binarized image specifically includes: Specifying a plurality of edge points in the binarized image, wherein the edge points are obtained according to the edge recognition result; Converting the plurality of edge points from the image coordinate space to the parameter space; According to the parameter commonality of the converted edge points in the parameter space, the corresponding straight line parameters are determined, and linear fitting is achieved based on the straight line parameters. The parameter commonality is positively correlated with the number of straight lines intersecting at the same point in the parameter space.

4. The method according to claim 3, characterized in that The step of determining corresponding straight line parameters according to the parameter commonality of the converted edge points in the parameter space, and implementing linear fitting according to the straight line parameters, specifically includes: Establish multiple two-dimensional accumulation arrays A(a, b) corresponding to the parameter space, wherein the range of the first dimension a is determined according to the slope of the straight line of the edge point in the image coordinate space, and the range of the second dimension b is determined according to the intercept of the straight line of the edge point in the image coordinate space; Initialize the multiple A(a,b); For each designated edge point in the image coordinate space, determine the corresponding b according to the a corresponding to the edge point after transformation, and increase the corresponding A(a, b) by a fixed value in an accumulative manner according to a and b; According to the peak values ​​corresponding to the accumulated A(a,b), several A(a,b) with the highest peak values ​​are selected, and the a and the b in the selected A(a,b) are used as line parameters to generate several straight lines in the image coordinate space respectively.

5. The method according to claim 2, characterized in that Before continuing to collect images of the high-voltage transmission line according to the adjusted shooting parameters, the method further includes: Determine the pixel diameter corresponding to the wire at the inspection end according to the direction with the most wire clusters; The lens magnification in the shooting parameters is adjusted according to the pixel diameter.

6. The method according to claim 5, characterized in that Determining the pixel diameter corresponding to the wire at the inspection end according to the direction with the most wire clusters specifically includes: Determine the direction Q with the most line clusters; In the wire cluster, a wire is selected, and the selected wire is rotated in a -Q direction; the -Q direction is the opposite direction of the direction Q; The rotated wire is vertically projected, and the number of column vectors greater than 0 in the projection matrix is ​​counted to determine the pixel diameter corresponding to the wire at the inspection end.

7. The method according to claim 5, characterized in that The adjusting the lens magnification in the shooting parameters according to the pixel diameter specifically includes: Determine the correspondence between the lens magnification obtained in advance through calibration and the pixel diameter, and adjust the lens magnification in the shooting parameters according to the correspondence and the pixel diameter. The correspondence includes , where B is the camera diameter, r is the pixel diameter, is the initial lens magnification, , are the specified lens magnifications obtained by sampling and linear fitting.

8. The method according to any one of claims 1 to 7, characterized in that The camera device is a pan-tilt camera, and the shooting parameters include at least one of a starting acquisition position, a final acquisition position, a timed patrol cycle, a horizontal rotation angle of the pan-tilt, a vertical rotation angle of the pan-tilt, and a lens magnification.

9. An automatic inspection device for high-voltage transmission lines, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute: Capturing images of the high-voltage transmission line by using a camera device with shooting parameters set, to obtain an image containing the conductors in the high-voltage transmission line; Determining the inspection end in the image according to the inspection direction included in the shooting parameters; Performing image recognition on the image, identifying and determining the wire in the image, and determining a first reference point corresponding to the wire at the inspection end, and a second reference point corresponding to the entire image; Determining a screen offset angle of the wire in the image according to the first reference point and the second reference point; Adjusting the shooting parameters according to the picture offset angle, and continuing to collect images of the high-voltage transmission line according to the adjusted shooting parameters, so as to realize automatic inspection of the high-voltage transmission line; The determining of the first reference point corresponding to the wire at the inspection end, and the second reference point corresponding to the entire image, specifically includes: Determine the first center point of the wire at the end of the inspection ( , ), and the second center point of the entire image ( , ), wherein the , represent the horizontal coordinate and vertical coordinate of the first center point in the image respectively, , respectively represent the abscissa and ordinate of the second center point in the image; The determining, according to the first reference point and the second reference point, a screen offset angle of the wire in the image specifically includes: Determine the width W and height H of the image, and determine the field of view FOV of the camera device to be horizontal HA and vertical VA respectively; pass , and obtain the screen offset angle of the wire in the image.

Images