Method, device, medium, and program for determining ice thickness on a power line

Abstract

The application discloses a method for determining the ice thickness of a power line and relates to the technical field of power line monitoring, which comprises the following steps: obtaining a power line icing image of the power line, performing binaryzation processing on the power line icing image to obtain a binaryzation image; processing the binaryzation image based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and determining the number of target pixels corresponding to the power line according to the power line mask image, wherein the image processing algorithm at least comprises a straight line detection algorithm and a region growing algorithm; obtaining the number of reference pixels of the power line in an unicing state, and determining the ice thickness of the power line according to the number of reference pixels and the number of target pixels; the number of reference pixels is determined according to a power line reference image of the power line in the unicing state, and the power line reference image and the power line icing image are obtained by the same shooting device. The method can improve the icing monitoring efficiency and the accuracy of the monitoring result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power line monitoring, and in particular to a method, device, medium and program for determining the ice thickness of a power line. BACKGROUND

[0002] With the development of the times, electricity has become an indispensable part of us. In the process of power transmission, power transmission lines are vulnerable to wind, rain, fog, frost, pollution and other natural weather conditions, resulting in line dancing, broken strands, icing, and even tower collapse accidents. When icing occurs on the power transmission line, when the icing reaches a certain thickness, the power line load overload is prone to cause line dancing, line collapse, tower collapse and other accidents.

[0003] In the prior art, the ice thickness of the power line in the area prone to icing is generally monitored by manual monitoring to obtain the icing condition of the power line. However, this manual ice thickness monitoring method is not only time-consuming and labor-intensive, but also has low monitoring efficiency and low accuracy of the detected ice thickness result. SUMMARY

[0004] According to an aspect of the present application, a method for determining the ice thickness of a power line is provided, comprising:

[0005] obtaining a power line icing image of the power line, performing binaryzation processing on the power line icing image to obtain a binaryzation image;

[0006] processing the binaryzation image based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and determining a target pixel number corresponding to the power line according to the power line mask image, wherein the image processing algorithm at least includes a straight line detection algorithm and a region growing algorithm;

[0007] obtaining a reference pixel number of the power line in an uniced state, and determining the ice thickness of the power line according to the reference pixel number and the target pixel number, wherein the reference pixel number is determined according to a power line reference image of the power line in the uniced state, and the power line reference image and the power line icing image are obtained by the same shooting device.

[0008] According to another aspect of the present application, a device for determining the ice thickness of a power line is provided, comprising:

[0009] an image preprocessing module configured to obtain a power line icing image of the power line, perform binaryzation processing on the power line icing image to obtain a binaryzation image;

[0010] An image processing module is configured to process the binary image based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and determine a target pixel number corresponding to the power line according to the power line mask image, wherein the image processing algorithm at least includes a straight line detection algorithm and a region growing algorithm.

[0011] An ice thickness determination module is configured to obtain a reference pixel number of the power line in an un-iced state, and determine the ice thickness of the power line according to the reference pixel number and the target pixel number, wherein the reference pixel number is determined according to a power line reference image of the power line in the un-iced state, and the power line reference image and the power line icing image are obtained by the same shooting device.

[0012] According to another aspect of the present application, an electronic device is provided, which comprises:

[0013] at least one processor; and

[0014] a memory connected to the at least one processor in communication; wherein

[0015] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method for determining the ice thickness of the power line according to any one of the embodiments of the present application.

[0016] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the method for determining the ice thickness of the power line according to any one of the embodiments of the present application when executed by the processor.

[0017] According to another aspect of the present application, a computer program product is provided, which comprises a computer program for implementing the method for determining the ice thickness of the power line according to any one of the embodiments of the present application when executed by a processor.

[0018] The technical scheme of the embodiment of the present application is that the obtained power line icing image is subjected to binaryzation processing to obtain a binaryzation image, the binaryzation image is processed based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and the number of target pixels corresponding to the power line is determined according to the power line mask image. Then, the number of reference pixels of the power line in the non-icing state is obtained, and the icing thickness of the power line is determined according to the number of reference pixels and the number of target pixels. The power line icing image of the power line is processed by the image processing algorithm to obtain the number of target pixels of the power line in the icing state, and the icing thickness corresponding to the power line is determined according to the number of target pixels, which can improve the prediction accuracy of the icing thickness of the power line and improve the timeliness and detection efficiency of the monitoring.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is a flow chart of a method for determining the icing thickness of a power line according to the first embodiment of the present application;

[0022] Figure 2 is a flow chart of another method for determining the icing thickness of a power line according to the second embodiment of the present application;

[0023] Figure 3a is a schematic diagram of a power line icing image photographed by a photographing device according to the second embodiment of the present application;

[0024] Figure 3b is a schematic diagram of a binaryzation image obtained after binaryzation processing of a power line icing image according to the second embodiment of the present application;

[0025] Figure 4a is a schematic diagram of edge data extracted from a binaryzation image according to the second embodiment of the present application;

[0026] Figure 4b is a schematic diagram of straight line data distribution obtained by detecting straight line data in edge data according to the second embodiment of the present application;

[0027] Figure 4cis a schematic diagram of target straight line data obtained by screening blue straight line data according to an embodiment two of the present application;

[0028] Figure 5a is a schematic diagram of a mask image corresponding to a target mask area according to an embodiment two of the present application;

[0029] Figure 5b is a schematic diagram of an initial power line mask image corresponding to an initial image area of a power line according to an embodiment two of the present application;

[0030] Figure 5c is a schematic diagram of a power line mask image after a morphological closing operation according to an embodiment two of the present application;

[0031] Figure 6 is a schematic diagram of a structure of a device for determining an ice thickness of a power line according to an embodiment three of the present application;

[0032] Figure 7 is a schematic diagram of a structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] In order to make the personnel in the art better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without creative labor should belong to the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to include only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0035] Embodiment one

[0036] Figure 1is a flowchart of a method for determining the ice thickness of a power line according to an embodiment of the present application. The embodiment can be applied to determine the ice thickness of a power line based on the processing result of a power line icing image. The method can be executed by a device for determining the ice thickness of a power line, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown in FIG. 1, the method comprises the following steps.

[0037] In S110, a power line icing image of a power line is obtained, and a binaryzation process is performed on the power line icing image to obtain a binaryzation image.

[0038] The power line icing image can be an image of the power line covered with ice layers, which can be obtained by a shooting device. The power line can be a power line in a region where icing is prone to occur. The power line icing image can be used to monitor the state of the power line. In cold weather conditions, the ice layers on the power line can cause power interruption or equipment damage.

[0039] The binaryzation image can be a binaryzation image corresponding to the power line icing image, such as a black-and-white image, which can be obtained by threshold segmentation of the power line icing image by the maximum inter-class variance method. Each pixel in the binaryzation image has only two possible values, such as 0 and 1 or black and white. The binaryzation image can be obtained by simplifying the power line icing image, which can improve the image monitoring efficiency. The binaryzation process of the power line icing image can be implemented by the maximum inter-class variance method.

[0040] Specifically, the power line icing image of the power line in the icing-prone region can be obtained by a shooting device, and the power line icing image can be processed by threshold segmentation by the maximum inter-class variance method to obtain a binaryzation image corresponding to the power line icing image. The power line icing image can be converted into a binaryzation image, which can more efficiently analyze and evaluate the icing condition of the power line.

[0041] In S120, the binaryzation image is processed based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and the number of target pixels corresponding to the power line is determined according to the power line mask image. The image processing algorithm at least includes a straight line detection algorithm and a region growing algorithm.

[0042] The preset image processing algorithm can be an image processing algorithm defined in advance in the process of processing the binary image, and can be used for specific processing or analysis of the binary image. The image processing algorithm can at least include a straight line detection algorithm and a region growing algorithm. The straight line detection algorithm can be an algorithm for detecting straight line structures in an image, such as a Hough straight line detection algorithm. The straight line detection algorithm can identify straight line edge data in the image, and determine the rough position of the power line in the image according to the identified straight line edge data. The region growing algorithm can be an algorithm for collecting pixels with similarities to form a region, and can be used to identify and expand the region related to the power line, thereby generating a power line mask image corresponding to the power line icing image. For example, starting from a group of “seed” pixels, adjacent pixels can be gradually added to the current region according to certain similarity criteria (such as gray value), until the growth stopping condition is met, such as the gray value and color of the adjacent pixels meeting the set growth stopping condition, then the growth is stopped.

[0043] The power line mask image can be determined on the basis of the candidate image region by the region growing algorithm, and is used to represent the mask image after the power line icing. For example, after the binary image is processed by the preset image processing algorithm, the pixel information related to the power line can be retained, and other non-power line related pixels are set to black or transparent image. For example, if the power line icing image is composed of region 1, region 2 and region 3, and after the binary image corresponding to the power line icing image is processed by the preset image processing algorithm, it is determined that the image region after the power line icing is the image corresponding to region 2 of the power line icing image, then the pixels of region 2 of the power line icing image are retained, and the image obtained by setting region 1 and region 3 to black is determined as the power line mask image. The target pixel number can be the total number of pixels in the power line mask image corresponding to the image after the power line icing. The target pixel number can be used to represent the pixel number of the power line after icing.

[0044] Specifically, the straight line edge data in the binary image can be extracted by a straight line detection algorithm, and the approximate position of the power line in the binary image can be framed according to the extracted straight line. After the approximate position of the power line is determined, the region growing algorithm can be used to gradually add the adjacent pixels to the region corresponding to the approximate position of the power line according to the gray value of the approximate position of the power line and the gray value of the adjacent region of the approximate position of the power line in the binary image, so as to obtain the power line mask image. The number of target pixels is determined according to the power line mask image. The power line icing image is processed by the preset image processing algorithm, so as to obtain the mask image of the corresponding region of the power line in the power line icing image, and the number of target pixels corresponding to the power line is determined according to the mask image, which can provide more accurate data basis for the analysis of the power line icing condition, and can improve the monitoring accuracy of the power line icing condition.

[0045] In S130, the reference pixel number of the power line in the non-icing state is obtained, and the icing thickness of the power line is determined according to the reference pixel number and the target pixel number. The reference pixel number is determined according to the power line reference image of the power line in the non-icing state, and the power line reference image and the power line icing image are obtained by the same shooting device.

[0046] The power line reference image can be an image of the power line in the non-icing state, which is used for comparison with the icing image. The power line reference image and the power line icing image can be obtained by the same shooting device, and the power line in the non-icing state and the power line in the icing state can be obtained by the same shooting device, which can reduce the error and ensure the accuracy of the image. The reference pixel number of the power line in the non-icing state can be the pixel number representing the size (such as diameter or width) of the power line in the power line reference image obtained by shooting in the non-icing state of the power line. The reference pixel number can be the total number of pixels corresponding to the image of the power line in the non-icing state. The reference pixel number can be used to represent the pixel number of the non-icing power line. The reference pixel number of the power line can be determined according to the power line reference image of the power line in the non-icing state, and the specific determination method of the reference pixel number of the power line can be the same as that of the target pixel number. The icing thickness of the power line can be determined according to the reference pixel number corresponding to the image of the power line in the non-icing state and the target pixel number corresponding to the image of the power line in the icing state, and can be used to represent the thickness of the power line surface increased due to icing.

[0047] Specifically, the reference pixel quantity and the thickness of the power line in the non-icing state can be obtained, and the power line icing image is processed and analyzed by a preset image processing algorithm to obtain the target pixel quantity of the power line in the icing state. The corresponding relationship between the pixel quantity of the power line and the thickness of the power line is determined according to the reference pixel quantity of the power line in the non-icing state and the thickness of the power line, and the icing thickness of the power line corresponding to the power line icing image is obtained according to the corresponding relationship and the target pixel quantity of the power line in the icing state. The power line icing image of the power line is processed by the image processing algorithm to obtain the target pixel quantity of the power line in the icing state, and the icing thickness corresponding to the power line is determined according to the target pixel quantity, which can improve the prediction accuracy of the icing thickness of the power line and improve the timeliness and detection efficiency of the monitoring.

[0048] The technical scheme of the embodiment of the application obtains a binary image by performing binaryzation processing on the obtained power line icing image, processes the binary image based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and determines a target pixel quantity corresponding to the power line according to the power line mask image. Then, a reference pixel quantity of the power line in a non-icing state is obtained, and the icing thickness of the power line is determined according to the reference pixel quantity and the target pixel quantity. The power line icing image of the power line is processed by the image processing algorithm to obtain the target pixel quantity of the power line in the icing state, and the icing thickness corresponding to the power line is determined according to the target pixel quantity, which can improve the prediction accuracy of the icing thickness of the power line and improve the timeliness and detection efficiency of the monitoring.

[0049] Embodiment Two

[0050] Figure 2 is a flowchart of another method for determining the icing thickness of a power line according to Embodiment Two of the application. Based on the above-mentioned embodiment, the binary image is processed based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, specifically: the binary image is detected by an edge detection algorithm to obtain edge data corresponding to the binary image; straight line data in the edge data is determined by a straight line detection algorithm, and a candidate image region corresponding to the power line is determined according to the straight line data; the target image region corresponding to the power line is determined from the candidate image region by a region growing algorithm to obtain the power line mask image. The reference pixel quantity of the power line in the non-icing state is obtained, and the icing thickness of the power line is determined according to the reference pixel quantity and the target pixel quantity, specifically: the reference pixel quantity of the power line in the non-icing state and the original radius data are obtained, and the icing thickness of the power line is determined according to the original radius data, the reference pixel quantity and the target pixel quantity. The same terms as in the above-mentioned embodiment will not be described here. As shown in Figure 2 The method comprises:

[0051] S210, acquire a power line icing image of the power line, and perform binaryzation processing on the power line icing image to obtain a binaryzation image.

[0052] Specifically, the power line icing image of the power line in the icing-prone area can be acquired by the shooting device, the power line icing image can be converted into a gray-scale image, and a denoising image can be obtained by using Gaussian filtering denoising on the gray-scale image. The binaryzation image corresponding to the power line icing image can be obtained by using OTSU threshold segmentation method on the denoising image. The icing condition of the power line can be more efficiently analyzed and evaluated by converting the power line icing image into the binaryzation image.

[0053] Exemplarily, Figure 3a is a schematic diagram of the power line icing image shot by the shooting device according to the second embodiment of the present application, as shown in Figure 3a , the power line icing image contains the power line with icing and other objects within the shooting direction of the shooting device. Figure 3b is a schematic diagram of the binaryzation image obtained by performing binaryzation processing on the power line icing image according to the second embodiment of the present application, as shown in Figure 3b , the binaryzation image with only two colors can be obtained after performing binaryzation processing on the power line icing image.

[0054] S220, detect the binaryzation image by using an edge detection algorithm to obtain edge data corresponding to the binaryzation image.

[0055] The edge detection algorithm can be a basic technology in image processing and computer vision, and can be used to identify points with obvious brightness change in the binaryzation image. The edge algorithm can include Roberts operator (Roberts operator, a kind of algorithm for finding edges by using local difference operator), Prewitt operator (edge detection operator, which locates edge pixels by calculating the difference of the neighborhood around the center pixel) or Canny operator (a multi-stage edge detection algorithm, which is used to find an optimal edge detection solution or find the position with the strongest gray intensity change in an image. Double threshold technology and hysteresis technology can be used to track the boundary to obtain accurate edge information.) and the like. The edge data can be edge information extracted from the binaryzation image by using the edge detection algorithm. The edge data can be used to represent the boundary of the object in the binaryzation image.

[0056] Specifically, the edge data of the object in the binaryzation image can be extracted by using the preset edge detection algorithm to obtain edge data corresponding to each object in the binaryzation image. Exemplarily, Figure 4a is a schematic diagram of the edge data extracted from the binaryzation image according to the second embodiment of the present application, as shown in Figure 4a , the edge data of each object in the binaryzation image is contained in the diagram.

[0057] S230, determining straight line data in the edge data through a straight line detection algorithm, and determining a candidate image region corresponding to the power line according to the straight line data.

[0058] The straight line data can be straight line information extracted from the edge data through the straight line detection algorithm. The candidate image region can be an image region in the binary image containing the power line, and can be determined according to the straight line data. The candidate image region can be determined by analyzing the spatial distribution and attributes of the straight line data.

[0059] Specifically, the straight line data in the edge data can be extracted through the straight line detection algorithm. The power line usually appears as a straight line or an approximately straight line in the image, so the candidate image region of the power line in the binary image can be framed according to the direction and slope information of the extracted straight line edge data.

[0060] Optionally, determining the candidate image region corresponding to the power line according to the straight line data includes: constructing a straight line set according to the straight line data, wherein the straight line data carries a slope label and an intercept label; determining a slope difference value and an intercept difference value between each straight line data and the remaining straight line data in the straight line set according to the slope label and the intercept label of each straight line data; determining target straight line data in the straight line set according to the slope difference value and the intercept difference value corresponding to each straight line data, and determining the candidate image region corresponding to the power line according to the target straight line data.

[0061] The straight line set can be a set of all straight line data extracted from the edge data. Each straight line data in the straight line set carries a slope label and an intercept label. The slope label is used to represent the slope of the straight line data, and the intercept label is used to represent the position information of the straight line. The slope difference value can be the difference between the slope of a straight line data and the slope of other straight line data in the straight line set, and the slope difference value can be used to represent the difference in inclination between two straight lines. The intercept difference value can be the difference between the intercept of a straight line data and the intercept of other straight line data in the straight line set, and the intercept difference value can be used to measure the position difference between two straight lines.

[0062] The target straight line data can be two straight line data obtained by merging two groups of straight line data with relatively small slope difference values and intercept difference values compared with other straight line data in the straight line set. The two groups of straight line data can be straight line data corresponding to the power line which is relatively consistent and arranged in order in the image.

[0063] Specifically, the slope difference and the intercept difference between each straight line data and other straight line data can be calculated according to the slope label and the intercept label corresponding to each straight line data. Then, a plurality of straight line data satisfying a preset difference condition in the slope difference and the intercept difference can be determined according to the slope difference and the intercept difference between each straight line data and other straight line data, and the plurality of straight line data satisfying the preset difference condition can be merged to obtain a plurality of merged straight line data. Then, a pair of parallel lines closest in slope can be selected as target straight line data from the merged straight line data through the slope information of each merged straight line data and the actual slope information of the power line, and a candidate image region corresponding to the power line can be selected through the parallel line frame. By calculating the slope difference and the intercept difference between each straight line data and other straight line data in the straight line set, the candidate image region corresponding to the position of the power line can be determined from the binary image, so as to determine the candidate image region corresponding to the power line, which can provide a data basis with higher accuracy for calculating the ice thickness of the power line, and thus improve the monitoring accuracy of the ice thickness of the power line.

[0064] Optionally, the target straight line data in the straight line set is determined according to the slope difference and the intercept difference corresponding to each straight line data, including: in a case where the slope difference and the intercept difference of at least two straight line data satisfy a preset merging condition, merging the at least two straight line data to obtain a first candidate straight line data set; obtaining a reference slope of the power line, and screening the straight line data in the first candidate straight line data set through the reference slope and the slope label to obtain a second candidate straight line data set; for each straight line data in the second candidate straight line data set, determining a geometric relationship between the straight line data and the remaining straight line data in the second candidate straight line data set according to the slope information of the straight line data, and determining the target straight line data from the second candidate straight line data set according to the geometric relationship.

[0065] The preset merging condition can be determined based on the slope difference and the intercept difference, and is a preset condition required to be satisfied when merging at least two straight line data in the straight line set. For example, when the slope difference of two straight line data is less than a slope threshold value, and the intercept difference is also less than an intercept threshold value, it can be determined that the two straight line data are close enough, and the two straight line data can be merged into one continuous straight line data. The first candidate straight line data set can be a straight line data set obtained after merging, and the straight line data set includes a plurality of merged candidate straight line data. Each candidate straight line data can be a straight line data obtained after merging a plurality of straight line data.

[0066] The reference slope can be a slope value of the power line in the image, and can be determined by a shooting angle of the camera and position information of the power line in the shooting image. The reference slope can be used to analyze and compare the candidate straight line data in the first candidate straight line data set, and then determine a plurality of straight line data corresponding to the slope of the power line from the first candidate straight line data set. The second candidate straight line data set can be a straight line data set obtained by screening the first candidate straight line data set based on the reference slope. The second candidate straight line data set includes straight line data similar to the slope of the power line.

[0067] The geometric relationship can be a spatial geometric relationship of two straight line data determined according to slope information of a certain straight line data in the second candidate straight line data set and slope information of the remaining straight line data. For example, whether the two straight lines are parallel, whether the slope information of the two straight lines satisfies the parallel condition, and the like.

[0068] Specifically, after obtaining the second candidate straight line data set, because the second candidate straight line data set includes a plurality of straight line data similar to the reference slope of the power line, a group of parallel lines with the closest slope can be screened from the second candidate straight line data set as the straight line data corresponding to the power line, and a region framed by the group of parallel lines is determined as the candidate image region. By determining a group of parallel lines with the closest slope from the second candidate straight line data set and framing the region of the group of parallel lines as the candidate image region, the position region of the power line in the image can be quickly determined, and the monitoring accuracy of the ice thickness of the power line is improved.

[0069] Exemplarily, Figure 4b is a schematic diagram of straight line data distribution obtained by detecting the straight line data in the edge data according to the embodiment two of the present application, as shown in Figure 4b , the blue lines represent all the straight line data extracted from the edge data by the straight line detection algorithm, and the distribution of the straight line data in the power line icing image. Figure 4c is a schematic diagram of target straight line data obtained by screening the blue straight line data according to the embodiment two of the present application, as shown in Figure 4c , the red lines represent the target straight line data obtained by merging and screening the blue straight line data according to the slope and intercept of the straight line data and the reference slope of the power line, and the region framed by the two red lines is the candidate image region corresponding to the power line.

[0070] S240, determining the target image region corresponding to the power line from the candidate image region by a region growing algorithm to obtain a power line mask image.

[0071] Optionally, the target image region corresponding to the power line is determined from the candidate image region by a region growing algorithm, comprising: extracting an initial image region corresponding to the power line from the candidate image region by the region growing algorithm; and performing a morphological closing operation on the initial image region to remove holes in the initial image region, to obtain the target image region corresponding to the power line. The holes in the initial image region are removed by the morphological closing operation, so that an image closer to the image of the power line covered with ice is obtained, thereby improving the accuracy of the ice thickness monitoring of the power line.

[0072] The initial image region can be an image region corresponding to the power line and extracted from the candidate image region by the region growing algorithm. The initial image region can contain some noise, holes or incomplete parts, and thus needs to be further processed to determine the target image region corresponding to the actual icing condition of the power line.

[0073] The morphological closing operation can be a morphological operation for filling small holes or gaps in the initial image while keeping the overall shape of the image unchanged. For example, an inflation operation can be performed on the image first, and then a corrosion operation can be performed on the inflated image, so that the holes in the initial image region are removed, and a more complete and continuous target image region of the power line is obtained.

[0074] Optionally, the power line icing image data can be processed to obtain mask image data corresponding to the icing image data; a target mask region of the power line in the mask image data is determined according to the candidate image region; the target mask region is expanded according to the gray mean value and the gray variance value of the target mask region and the gray value of the mask region outside the target mask region in the mask image data; and if the target mask region satisfies a preset expansion end condition, an initial image region corresponding to the power line is determined according to the expanded target mask region.

[0075] The target mask region can be a mask region in the mask image data corresponding to the candidate image region in the power line icing image. The preset expansion end condition can be determined according to the gray mean value and the gray variance value of the target mask region and the gray value of the mask region outside the target mask region in the mask image data. If the difference between the gray mean value and the gray variance value of the target mask region and the gray value of the mask region outside the target mask region in the mask image data satisfies a certain preset difference value, the expansion is ended.

[0076] For example, Figure 5a is a mask image diagram corresponding to the target mask region provided by the second embodiment of the present application, as Figure 5a shown, the target mask region of the power line in the mask image data can be determined according to the candidate image region. Figure 5bis a schematic view of an initial power line mask image corresponding to an initial image region of a power line provided by Embodiment Two of the present application, as shown in Figure 5b After the mask image corresponding to the candidate image region is expanded by the region growing algorithm, an initial power line mask image corresponding to the initial image region of the power line is obtained, wherein there are noises, holes or incomplete parts, and thus further processing is needed before a target image region corresponding to the actual icing condition of the power line can be determined. Figure 5c is a schematic view of a power line mask image after morphological closure operation provided by Embodiment Two of the present application, as shown in Figure 5c After the holes in the initial image region are removed by the morphological closure operation, an image more similar to the image after the power line is iced can be obtained, and thus the accuracy of the icing thickness monitoring of the power line is improved.

[0077] S250, reference pixel quantity and original radius data of the power line in an uniced state are obtained, and the icing thickness of the power line is determined according to the original radius data, the reference pixel quantity and the target pixel quantity.

[0078] The original radius data can be the radius data of the power line in the uniced state.

[0079] Optionally, the icing thickness of the power line can be determined according to the original radius data, the reference pixel quantity and the target pixel quantity by the following formula:

[0080]

[0081] wherein d is the icing thickness of the power line, S1 is the reference pixel quantity of the power line, S2 is the target pixel quantity of the power line, and d1 is the original radius data of the power line.

[0082] The above formula can be derived by the following process:

[0083] If the pixel quantity of the power line in the uniced state is S1, the diameter is d1, the pixel quantity of the power line after icing is S2, and the diameter is d2, then according to the proportional relationship, the following formula can be obtained: The icing thickness d of the power line can be calculated by Therefore, by solving and the following formula can be obtained:

[0084] The technical scheme of the embodiment of the present application is that the obtained power line icing image is binarized to obtain a binarized image, the binarized image is processed based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and the target pixel quantity corresponding to the power line is determined according to the pixel quantity in the power line mask image. Then, the reference pixel quantity of the power line in the non-icing state is obtained, and the icing thickness of the power line is determined by combining the target pixel quantity and the correlation between the icing thickness and the pixel quantity of the power line according to the correlation between the reference pixel quantity and the original radius data of the power line in the non-icing state. The prediction accuracy of the icing thickness of the power line can be improved, and the timeliness and detection efficiency of monitoring can be improved.

[0085] Embodiment three

[0086] Figure 6 is a structural schematic diagram of a device for determining the icing thickness of a power line according to the third embodiment of the present application. As shown in the figure, the device comprises an image preprocessing module 610, an image processing module 620 and an icing thickness determination module 630. Figure 6

[0087] Further, the image preprocessing module 610 is configured to obtain a power line icing image of the power line, binarize the power line icing image to obtain a binarized image; the image processing module 620 is configured to process the binarized image based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and determine a target pixel quantity corresponding to the power line according to the power line mask image, wherein the image processing algorithm at least comprises a straight line detection algorithm and a region growing algorithm; and the icing thickness determination module 630 is configured to obtain a reference pixel quantity of the power line in a non-icing state, and determine the icing thickness of the power line according to the reference pixel quantity and the target pixel quantity, wherein the reference pixel quantity is determined according to a power line reference image of the power line in the non-icing state, and the power line reference image and the power line icing image are obtained by the same shooting device.

[0088] Further, the image processing module 620 is specifically configured to: detect the binarized image by an edge detection algorithm to obtain edge data corresponding to the binarized image; determine straight line data in the edge data by a straight line detection algorithm, and determine a candidate image region corresponding to the power line according to the straight line data; and determine a target image region corresponding to the power line from the candidate image region by a region growing algorithm to obtain the power line mask image.

[0089] ​Further, the image processing module 620 is further specifically configured to: construct a straight line set according to the straight line data, wherein the straight line data carries a slope label and an intercept label; determine a slope difference value and an intercept difference value between each straight line data and the remaining straight line data in the straight line set according to the slope label and the intercept label of each straight line data in the straight line set; determine target straight line data in the straight line set according to the slope difference value and the intercept difference value corresponding to each straight line data, and determine a candidate image region corresponding to the power line according to the target straight line data.

[0090] Further, the image processing module 620 is further specifically configured to: in a case where the slope difference value and the intercept difference value of at least two straight line data satisfy a preset merging condition, merge the at least two straight line data to obtain a first selected straight line data set; obtain a reference slope of the power line, and screen the straight line data in the first selected straight line data set through the reference slope and the slope label to obtain a second selected straight line data set; for each straight line data in the second selected straight line data set, determine a geometric relationship between the straight line data and the remaining straight line data in the second selected straight line data set according to the slope information of the straight line data, and determine target straight line data from the second selected straight line data set according to the geometric relationship.

[0091] Further, the image processing module 620 is further specifically configured to: extract an initial image region corresponding to the power line from the candidate image region through a region growing algorithm; and perform a morphological closing operation on the initial image region to remove holes in the initial image region, to obtain a target image region corresponding to the power line.

[0092] Further, the ice thickness determination module 630 is specifically configured to: obtain original radius data of the power line, and determine the ice thickness of the power line according to the original radius data, a reference pixel quantity and a target pixel quantity.

[0093] Further, the ice thickness of the power line can be determined according to the original radius data, the reference pixel quantity and the target pixel quantity through the following formula:

[0094]

[0095] wherein d is the ice thickness of the power line, S1 is the reference pixel quantity of the power line, S2 is the target pixel quantity of the power line, and d1 is the original radius data of the power line.

[0096] The ice thickness determination device provided in the embodiment can execute the ice thickness determination method provided in any of the embodiments, and has the corresponding function modules and beneficial effects of the execution method.

[0097] Embodiment four

[0098] Figure 7A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0099] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0100] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0101] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining ice thickness on power lines.

[0102] In some embodiments, the method of determining the ice thickness of a power line can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the method of determining the ice thickness of a power line described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method of determining the ice thickness of a power line by other means, e.g., with the aid of firmware.

[0103] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0104] Computer programs used to implement the processes of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0105] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0106] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0107] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0108] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0109] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0110] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of determining the thickness of ice on a power line, characterized by, The method comprises the following steps: An image of power line icing of a power line is acquired, and the image of power line icing is binarized to obtain a binarized image; The binarized image is processed based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and the number of target pixels corresponding to the power line is determined according to the power line mask image, wherein the image processing algorithm at least includes a straight line detection algorithm and a region growing algorithm; A reference pixel number of the power line in an un-icing state is acquired, and the icing thickness of the power line is determined according to the reference pixel number and the number of target pixels, wherein the reference pixel number is determined according to a power line reference image of the power line in the un-icing state, and the power line reference image and the image of power line icing are acquired by the same shooting device; The binarized image is processed based on a preset image processing algorithm to obtain a power line mask image corresponding to the power line, and the number of target pixels corresponding to the power line is determined according to the power line mask image, wherein the image processing algorithm at least includes a straight line detection algorithm and a region growing algorithm; The binarized image is detected by an edge detection algorithm to obtain edge data corresponding to the binarized image; The straight line data in the edge data is determined by the straight line detection algorithm, and a candidate image region corresponding to the power line is determined according to the straight line data; The target image region corresponding to the power line is determined from the candidate image region by the region growing algorithm to obtain the power line mask image; The candidate image region corresponding to the power line is determined according to the straight line data, comprising: A straight line set is constructed according to the straight line data, wherein the straight line data carries a slope label and an intercept label; The slope difference and the intercept difference between each straight line data and the remaining straight line data in the straight line set are determined according to the slope label and the intercept label of each straight line data in the straight line set; The target straight line data in the straight line set is determined according to the slope difference and the intercept difference corresponding to each straight line data, and the candidate image region corresponding to the power line is determined according to the target straight line data; The target straight line data in the straight line set is determined according to the slope difference and the intercept difference corresponding to each straight line data, comprising: In the case that the slope difference and the intercept difference of at least two straight line data satisfy a preset merging condition, at least two straight line data are merged to obtain a first selected straight line data set; A reference slope of the power line is acquired, and the straight line data in the first selected straight line data set is screened by the reference slope and the slope label to obtain a second selected straight line data set; For each straight line data in the second selected straight line data set, the geometric relationship between the straight line data and the remaining straight line data in the second selected straight line data set is determined according to the slope information of the straight line data, and the target straight line data is determined from the second selected straight line data set according to the geometric relationship.

2. The method of claim 1, wherein, The target image region corresponding to the power line is determined from the candidate image region by the region growing algorithm, comprising: extracting, by the region growing algorithm, an initial image region corresponding to the power line from the candidate image region; performing a morphological closing operation on the initial image region to remove holes in the initial image region, to obtain a target image region corresponding to the power line.

3. The method of claim 1, wherein, The determining the ice thickness of the power line according to the reference pixel quantity and the target pixel quantity comprises: acquiring original radius data of the power line, and determining the ice thickness of the power line according to the original radius data, the reference pixel quantity and the target pixel quantity.

4. The method of claim 3, wherein, The ice thickness of the power line is determined according to the original radius data, the reference pixel quantity and the target pixel quantity by the following formula: wherein, is an ice thickness of the power line, is a reference pixel number of the power line, is a target pixel number of the power line, is original radius data of the power line.

5. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method for determining the ice thickness of the power line according to any one of claims 1-4.

6. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the method for determining the ice thickness of the power line according to any one of claims 1-4 when executed by the processor.

7. A computer program product comprising computer programs / instructions, wherein, The computer program / instructions enable the processor to execute the method for determining the ice thickness of the power line according to any one of claims 1-4 when executed by the processor.

Images