Power line category determination method and apparatus

Abstract

The application discloses a kind of electric power line kind determination method and device. It relates to electric power line information technical field, the method includes: obtaining the target video frame obtained by video acquisition to electric power line, and gray video frame;Gray video frame is carried out regional segmentation processing, obtains the multiple first sub-regions corresponding to gray video frame;Determine the light-dark degree disturbance of multiple first sub-regions;Multiple first sub-regions are carried out luminance key point extraction, obtain the luminance key point corresponding to multiple first sub-regions respectively;Based on the luminance key point and light-dark disturbance corresponding to multiple first sub-regions respectively, obtain the target adaptation between gray video frame and preset video frame Quantity;According to target adaptation, determine the kind of electric power line included in target video frame. The application solves the technical problem of low accuracy of electric power line identification caused by the fact that the related art does not consider all factors when determining the type of electric power line.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power line information, in particular to a power line type determination method and device. BACKGROUND

[0002] The power line refers to a line used for transmitting electric energy between a power plant, a substation and a power user. It is an important component of a power supply system and is responsible for the task of transmitting and distributing electric energy.

[0003] In the related art, a camera is arranged on each tower of a line erection device. One tower is provided with one power line. The camera takes a video frame of the power line on the corresponding tower in real time and transmits the video frame to a controller. The controller extracts key point values of the video frame of the power line by taking the video frame of each power line in advance, stores the key point values in an information table, identifies the type of the power line by taking the key point values of the video frame of the power line and executing adaptation with the key point values stored in the information table, and thus completes the identification process of the controller.

[0004] However, in the extraction process of the key points of the line body of the power line, the video frame is often affected by the brightness of the environment, so that the adaptation amount between the extracted key point values of the video frame of the power line and the key point values of the power line in the information table is not high, thereby causing the accuracy of the identification of the power line to be not high.

[0005] At present, no effective solution has been proposed for the above problems. SUMMARY

[0006] The embodiments of the present application provide a power line type determination method and device to at least solve the technical problem of low accuracy of power line identification caused by the fact that the factors are not comprehensive in the related art when determining the type of the power line.

[0007] According to an aspect of the embodiments of the present application, there is provided a power line type determination method, comprising: obtaining a target video frame obtained by video capturing on a power line, and a gray video frame corresponding to the target video frame, wherein the gray video frame is obtained by desaturation processing on the target video frame according to a predetermined spatial scale; performing region segmentation processing on the gray video frame to obtain a plurality of first sub-regions corresponding to the gray video frame; determining a light-dark degree disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the light-dark degree disturbance quantity is used to indicate a degree of change in brightness and darkness of the corresponding sub-region; performing brightness key point extraction on each of the plurality of first sub-regions to obtain a brightness key point corresponding to each of the plurality of first sub-regions; obtaining a target adaptation quantity between the gray video frame and a preset video frame based on the brightness key point corresponding to each of the plurality of first sub-regions and the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the target adaptation quantity is used to indicate a matching degree between the gray video frame and the preset video frame; and determining a type of the power line included in the target video frame according to the target adaptation quantity between the gray video frame and the preset video frame.

[0008] According to another aspect of the embodiments of the present application, there is also provided a power line type determination apparatus, comprising: an obtaining module configured to obtain a target video frame obtained by video capturing on a power line, and a gray video frame corresponding to the target video frame, wherein the gray video frame is obtained by desaturation processing on the target video frame according to a predetermined spatial scale; a region segmentation module configured to perform region segmentation processing on the gray video frame to obtain a plurality of first sub-regions corresponding to the gray video frame; a light-dark degree disturbance quantity module configured to determine a light-dark degree disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the light-dark degree disturbance quantity is used to indicate a degree of change in brightness and darkness of the corresponding sub-region; a brightness key point extraction module configured to perform brightness key point extraction on each of the plurality of first sub-regions to obtain a brightness key point corresponding to each of the plurality of first sub-regions; a target adaptation quantity determination module configured to obtain a target adaptation quantity between the gray video frame and a preset video frame based on the brightness key point corresponding to each of the plurality of first sub-regions and the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the target adaptation quantity is used to indicate a matching degree between the gray video frame and the preset video frame; and a power line type determination module configured to determine a type of the power line included in the target video frame according to the target adaptation quantity between the gray video frame and the preset video frame.

[0009] In the embodiment of the present application, a target video frame obtained by video acquisition on a power line and a corresponding gray video frame of the target video frame are acquired, wherein the gray video frame is obtained by desaturation processing on the target video frame according to a predetermined spatial scale; the gray video frame is subjected to region segmentation processing to obtain a plurality of first sub-regions corresponding to the gray video frame; a light-dark disturbance quantity corresponding to each of the plurality of first sub-regions is determined, wherein the light-dark disturbance quantity is used to indicate the degree of change in brightness and darkness of the corresponding sub-region; the plurality of first sub-regions are subjected to brightness key point extraction respectively to obtain a brightness key point corresponding to each of the plurality of first sub-regions; based on the brightness key point corresponding to each of the plurality of first sub-regions and the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, a target adaptation quantity between the gray video frame and a preset video frame is obtained, wherein the target adaptation quantity is used to indicate the matching degree between the gray video frame and the preset video frame; and the type of the power line included in the target video frame is determined according to the target adaptation quantity between the gray video frame and the preset video frame. The purpose of considering the influence of environmental light-darkness on power line identification is achieved, thereby realizing the technical effect of improving the accuracy of power line identification, and further solving the technical problem of low accuracy of power line identification caused by the fact that the determination of the type of the power line in the related art does not consider comprehensive factors. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0011] Figure 1 is a flowchart of a power line type determination method according to an embodiment of the present application;

[0012] Figure 2 is a flowchart of an optional power line type determination method according to an embodiment of the present application;

[0013] Figure 3 is a schematic diagram of a power line type determination device according to an embodiment of the present application;

[0014] Figure 4 is a structural schematic diagram of a power line type determination platform according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort should fall within the protection scope of the present application.

[0016] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or 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 need not be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0017] First, for the convenience of understanding the embodiments of the present application, the following will explain some terms or nouns involved in the present application:

[0018] Key points refer to specific positions with important significance in brightness in images, which are usually key feature points of human faces (such as eyes, nose, mouth, etc.) or key parts of objects (such as edges, corner points, etc.).

[0019] Resolution refers to the fineness of a display device or an image, which is usually represented by pixels. In a digital image, the higher the resolution means the clearer and more detailed the image. In a display device, the resolution is usually represented by the number of horizontal pixels and the number of vertical pixels, for example, 1920x1080 represents 1920 horizontal pixels and 1080 vertical pixels. In a printing device, the resolution is usually represented by the number of pixels per inch (dpi).

[0020] According to the embodiments of the present application, a method for power line type determination is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in a different order.

[0021] Figure 1 is a flowchart of the power line type determination method according to the embodiments of the present application, as shown in Figure 1 The method comprises the following steps:

[0022] In step S102, a target video frame obtained by video acquisition of the power line and a corresponding gray video frame of the target video frame are acquired, wherein the gray video frame is obtained by desaturation processing of the target video frame according to a predetermined spatial scale.

[0023] Optionally, a camera is arranged on each tower of the line tower, and one power line is stored on each tower. The target video frame of the power line captured by the corresponding camera on each tower within a predetermined time is acquired, and the target video frame is desaturated by a floating-point algorithm to obtain a gray video frame.

[0024] Optionally, each pixel point in the target video frame is acquired, the basic color value (RGB color value) corresponding to each pixel point is converted into a floating-point value, and the brightness value of each pixel is calculated based on the floating-point value. The specific calculation formula is as follows:

[0025] Y = 0.299 * R + 0.587 * G + 0.114 * B

[0026] Wherein Y is the brightness value, R is the floating-point value corresponding to the red color in the RGB color value, G is the floating-point value corresponding to the green color in the RGB color value, and B is the floating-point value corresponding to the blue color in the RGB color value.

[0027] The RGB color value in the corresponding pixel point is replaced by the brightness value to obtain the desaturated gray video frame.

[0028] In step S104, the gray video frame is subjected to region segmentation processing to obtain a plurality of first sub-regions corresponding to the gray video frame.

[0029] Optionally, the gray video frame is subjected to region segmentation processing according to a predetermined size. For example, the predetermined size is set to an area size of 3*3, i.e., each first sub-region is a square. It should be noted that the predetermined size can be set arbitrarily, and the area of the predetermined size is not limited to a square, but can also be a triangle, a pentagon, a hexagon or other shapes.

[0030] Optionally, after the gray video frame is subjected to region segmentation processing, any one of the plurality of first sub-regions is acquired, the first midpoint region is determined, the sub-regions adjacent to the first midpoint region are determined as the first adjacent regions, and the sub-regions adjacent to the first adjacent regions are determined as the first adjacent regions. The above 3*3 square area is taken as an example for division, and the first midpoint region has four sub-regions adjacent thereto, which are determined as the first adjacent regions, and the first adjacent regions have eight sub-regions adjacent thereto, which are determined as the first adjacent regions.

[0031] In step S106, the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions is determined, wherein the light-dark disturbance quantity is used to indicate the degree of change in brightness and darkness of the corresponding sub-region.

[0032] Optionally, due to the effect of the environmental light-dark, the fitting amount between the key point value of the target video frame of the extracted power line and the key point value of the power line in the information table in the power line identification process is not high, so that the accuracy of the power line identification is not high, and therefore the influence of the environmental light-dark on the power line identification needs to be considered, the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions is determined, and the identification of the power line is adjusted based on the light-dark disturbance quantity, so as to achieve the purpose of considering the influence of the environmental light-dark on the power line identification, thereby realizing the technical effect of improving the accuracy of the power line identification, and further solving the technical problem of low accuracy of the power line identification caused by the fact that the related art does not comprehensively consider the factors in determining the type of the power line.

[0033] In an optional embodiment, determining the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions comprises: determining a target brightness change variable corresponding to each of the plurality of first sub-regions and a target brightness change direction corresponding to each of the plurality of first sub-regions, wherein the target brightness change variable is used to indicate the brightness change state of the corresponding sub-region in the corresponding direction, and the target brightness change direction is used to indicate the brightness change direction of the corresponding sub-region; and determining the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions based on the target brightness change variable corresponding to each of the plurality of first sub-regions and the target brightness change direction corresponding to each of the plurality of first sub-regions.

[0034] Optionally, the color points corresponding to the plurality of sub-regions are obtained, and since the plurality of sub-regions are obtained by dividing the desaturated video frame, the color points corresponding to the plurality of sub-regions have become brightness values, i.e., representing the brightness in the plurality of sub-regions. A line is drawn from the first midpoint region to the first adjacent region, and the line passes through the plurality of color points, thereby obtaining a plurality of lines with different directions. The line passes through the color points in each sub-region, thereby obtaining a line with brightness changes of the color points in the plurality of sub-regions. The direction indicated by the plurality of lines is the brightness change direction of the color points in the corresponding sub-region, and the direction indicated by the plurality of lines is determined as the target brightness change direction. Based on the above-mentioned preset size setting of 3*3, the plurality of lines are respectively drawn from the first midpoint region to the first adjacent region, which has eight regions in four directions, i.e., four lines are drawn from the first midpoint region to the four different directions with an angle of 0, and The direction indicated by the four lines is the target brightness change direction.

[0035] Optionally, each of the plurality of target luminance variation orientations comprises a plurality of color points, and the luminance variation of the plurality of color points is determined based on the plurality of color points comprised in each of the plurality of target luminance variation orientations, and the target luminance variation quantity is obtained according to the luminance variation of the plurality of color points.

[0036] In an optional embodiment, the target luminance variation quantity corresponding to each of the plurality of first sub-regions and the target luminance variation orientation corresponding to each of the plurality of first sub-regions are determined by: obtaining a plurality of contrast video frames corresponding to the target video frame, wherein the plurality of contrast video frames are obtained by down-sampling the grayscale video frame according to a plurality of different layer groups; performing region segmentation processing on each of the plurality of contrast video frames to obtain a plurality of second sub-regions corresponding to each of the plurality of contrast video frames, wherein the plurality of second sub-regions correspond to the plurality of first sub-regions one by one; determining an initial luminance variation quantity corresponding to each of the plurality of second sub-regions of each of the plurality of contrast video frames, wherein the initial luminance variation quantity is used to indicate a luminance variation degree from the second sub-region to a first adjacent region within a corresponding predetermined neighborhood range in a corresponding line direction; obtaining the target luminance variation quantity corresponding to each of the plurality of first sub-regions based on the initial luminance variation quantity corresponding to each of the plurality of second sub-regions of each of the plurality of contrast video frames; and obtaining the target luminance variation orientation corresponding to each of the plurality of first sub-regions based on the target luminance variation quantity corresponding to each of the plurality of first sub-regions.

[0037] Optionally, the down-sampling processing of the grayscale video frame is performed according to a pyrDown function, and the contrast video frame is obtained by the down-sampling processing. The down-sampling processing is performed by using the pyrDown function on the grayscale video frame according to a plurality of different scaling ratios, and a plurality of layer groups are obtained by performing the down-sampling processing on the grayscale video frame. The contrast video frame is obtained by dividing the grayscale video frame into the plurality of different layer groups. It should be noted that one grayscale video frame is divided into a plurality of layer groups, and a plurality of contrast video frames are obtained.

[0038] Optionally, the plurality of second sub-regions are obtained by performing region segmentation on the plurality of contrast video frames according to the manner of obtaining the first sub-region from the grayscale video frame, and the initial luminance variation quantity is determined based on the luminance value of the color point passing through the plurality of lines corresponding to the contrast video frame. The contrast video frame has a plurality of lines corresponding to the initial luminance variation quantity, and each line has an initial luminance variation quantity corresponding to the contrast video frame.

[0039] In an alternative embodiment, the multiple reference video frames corresponding to the target video frame are obtained by: performing down-sampling on the grayscale video frame according to multiple different layer groups to obtain multiple first video frames; and performing supplementary processing on the multiple first video frames to obtain the multiple reference video frames, wherein the multiple reference video frames have the same resolution as the grayscale video frame.

[0040] Alternatively, since the multiple reference video frames are obtained by down-sampling the grayscale video frame, the resolutions of the reference video frames and the grayscale video frame can be different, which can result in the number of color points in each second sub-region being different after the reference video frames are divided by region. Resolution refers to the fineness of a display device or an image, which is usually represented by pixels. When the resolutions are different, the pixel sizes are different, and the number of color points is different when the pixel sizes are different. Therefore, the second sub-region needs to have the same number of color points as the first sub-region, and the reference video frames need to be supplemented to make the resolutions of the multiple reference video frames the same as the resolution of the grayscale video frame. The reference video frames are supplemented by the minimum curvature method, and the specific method is as follows:

[0041] The multiple pixel points in the reference video frame are obtained, and the curvature of the reference video frame is obtained based on the multiple pixel points. The curvature can be used to describe the shape characteristics of the edges or curves in the image. The region with smaller curvature in the reference video frame is determined, and the region that needs to be supplemented in resolution is determined. The difference between the region with smaller curvature and the adjacent other region is calculated to obtain a difference result. The region with smaller curvature is supplemented based on the difference result, and the supplemented reference video frame is obtained. The resolutions of the supplemented reference video frame and the desaturated video frame are the same, thereby ensuring that the number of color points in the multiple second sub-regions is the same as and one-to-one corresponds to the number of color points in the multiple first sub-regions.

[0042] In an alternative embodiment, the initial brightness gradient of each second sub-region corresponding to each reference video frame is determined by: regarding each second sub-region corresponding to each reference video frame as a third sub-region, and obtaining the initial brightness gradient of each second sub-region corresponding to each reference video frame by: determining the adjacent region of the third sub-region in the adjacent interval; drawing lines through the color points corresponding to the midpoint position of the third sub-region along multiple predetermined directions to obtain multiple lines, wherein the multiple predetermined directions and the multiple lines are one-to-one corresponding; and determining the initial brightness gradient of the third sub-region along the multiple predetermined directions based on the change characteristics of the color point brightness levels of the third sub-region and the adjacent region on the multiple lines.

[0043] Optionally, following the method of determining multiple lines for the first sub-region, multiple lines are determined for multiple second sub-regions corresponding to multiple reference video frames. First, any third sub-region within the multiple second sub-regions is obtained and determined as the second midpoint region. The third sub-region adjacent to the second midpoint region is determined as the second adjacent region, and the third sub-region adjacent to the second adjacent region is determined as the second adjacent region.

[0044] Optionally, multiple color points corresponding to each of the third sub-regions are obtained. Taking the second midpoint region as the center, lines are drawn to the second adjacent region, passing through multiple color points, resulting in multiple lines with different orientations. These lines connect the color points within each of the third sub-regions they pass through, thus obtaining lines with brightness variations of the color points within multiple third sub-regions. That is, the orientation indicated by these multiple lines is the brightness variation orientation of the color points within the corresponding second sub-region. The orientation indicated by these multiple lines is determined as the initial brightness variation orientation. Based on the multiple color points included in each initial brightness variation orientation, the brightness variations of the multiple color points are determined, and the initial brightness variation is obtained based on the brightness variations of the multiple color points.

[0045] In one optional embodiment, based on the variation characteristics of the brightness levels of color points in the third sub-region and adjacent regions on multiple lines, the initial brightness of the third sub-region along multiple predetermined directions is determined by a variable, including: taking the multiple predetermined directions as target directions, and obtaining the initial brightness of the third sub-region along the multiple predetermined directions by a variable in the following manner: determining multiple color points in the third sub-region and adjacent regions on the lines corresponding to the target directions; determining color point clusters corresponding to the multiple color points, wherein each color point cluster includes the corresponding color point and a predetermined number of adjacent color points; for each color point cluster corresponding to the multiple color points, for each color point... The brightness levels of two adjacent color points within a cluster are subtracted to obtain multiple brightness subtractions for each color point cluster. These multiple brightness subtractions are then multiplied to obtain a confirmation index for each color point cluster. The confirmation index for each color point cluster is then binarized to obtain a progressive index. The progressive index is set to a first value when the confirmation index is greater than or equal to a predetermined value, and a second value when the confirmation index is less than the predetermined value. The first value is greater than the second value. Finally, the progressive index for each color point cluster is standardized to obtain the initial brightness progressive value for the target direction.

[0046] Optionally, the color points of the third sub-region and the second adjacent region on the same line are defined as the target color points. That is, the set of all color points on a line is the target color point. If there are multiple lines in the second region, there are multiple target color points. Take any one of the target color points and perform the following operation to obtain the corresponding confirmation index, as follows:

[0047] Any adjacent three color points in the target color point are determined as a target color point cluster; two adjacent color points in the target color point cluster are subtracted to obtain a brightness subtraction amount, and the above process is repeated to obtain all brightness subtraction amounts in the target color point cluster; and all brightness subtraction amounts in the target color point cluster are multiplied to obtain a confirmation index.

[0048] Optionally, the confirmation index is binarized to determine a gradual change index, specifically, the confirmation index is compared with a predetermined value, and the predetermined value is set to 0. If the confirmation index is not less than 0, i.e., greater than or equal to 0, it indicates that the brightness levels of the target color points in the target color point cluster are the same or similar, and a first preset value is determined as the gradual change index. If the confirmation index is less than 0, i.e., the confirmation index is less than 0, it indicates that the brightness levels of the target color points in the target color point cluster are different, and a second preset value is determined as the gradual change index. It should be noted that the first value is strictly greater than the second value.

[0049] Optionally, the confirmation index corresponds to any one target color point, and multiple target color points can confirm multiple confirmation indexes, and then multiple target color points confirm multiple gradual change indexes. In addition, one line corresponds to one target color point, and one line corresponds to one gradual change index. The second sub-region includes multiple lines, and the second sub-region includes multiple gradual change indexes. The total amount is obtained by totaling the multiple gradual change indexes. In the case of a higher total amount, it indicates that the brightness of the second sub-region is more affected by the light and shade of the environment. Based on the gradual change index, the initial brightness gradual change amount of the second sub-region is larger. At this time, in order to avoid the difficulty of analyzing the initial brightness gradual change amount, the initial brightness gradual change amount needs to be constrained in the interval [0, 1] for subsequent evaluation and analysis. Therefore, after obtaining the gradual change indexes corresponding to the multiple lines, the multiple gradual change indexes are standardized to obtain the initial brightness gradual change amount of the multiple lines in the second sub-region, so as to constrain the initial brightness gradual change amount in the interval [0, 1]. Among them, multiple lines correspond to multiple initial brightness gradual change directions, and the initial brightness gradual change amount corresponding to different initial brightness gradual change directions in the second sub-region is determined according to the multiple gradual change indexes.

[0050] Optionally, in the process of standardizing the multiple gradual change indexes to obtain the initial brightness gradual change amount of the multiple lines in the second sub-region, the standardization adopts z-score standardization. Specifically, the mean and standard deviation of the multiple gradual change indexes are calculated, each gradual change index is subtracted from the mean and divided by the standard deviation, so as to obtain standardized data with a mean of 0 and a standard deviation of 1, i.e., the initial brightness gradual change amount. In order to constrain the initial brightness gradual change amount in the interval and facilitate subsequent evaluation and analysis, the total amount is standardized to obtain the initial brightness gradual change amount.

[0051] It should be noted that all the standardization processing in the present application adopts z-score standardization processing mode.

[0052] Optionally, the specific calculation of the initial brightness variable is as follows:

[0053]

[0054] Ea,j,k= BZ (Ea,j,k), k = 1, 2, …, K (1) (a,j,k) Ea,j,k= BZ (Ea,j,k), k = 1, 2, …, K (1) l is the variable of the lth target color point cluster on the same line; P is the total number of target color points on the same line, and P-2 is the number of target color point clusters; is the brightness level of the target color point at the end of the three target color points in the lth target color point cluster; is the brightness level of the target color point at the end of the three target color points in the lth target color point cluster; is the brightness level of the target color point at the end of the three target color points in the lth target color point cluster; φ1 is a first preset value, φ2 is a second preset value, and φ1>φ2 is required; BZ() is the z-score standardization processing. It should be noted that φ1 is set to 1 and φ2 is set to 0 in the present application.

[0055] In an optional embodiment, based on the initial brightness variable corresponding to each second sub-region of each reference video frame, the target brightness variable corresponding to each first sub-region is obtained, including: determining the layer group level corresponding to each reference video frame, wherein the layer group level is the layer group level corresponding to the down-sampling processing of the gray video frame; performing standardization processing on the layer group level corresponding to each reference video frame to obtain the layer group key corresponding to each reference video frame; and performing weighted calculation based on the layer group key corresponding to each reference video frame and the initial brightness variable corresponding to each second sub-region of each reference video frame to obtain the target brightness variable corresponding to each first sub-region.

[0056] Optionally, since the reference video frames at different layer levels are obtained through downsampling using the pyrDown function, the layer levels corresponding to multiple reference video frames are different. After performing different layer level processing on grayscale video frames, the effect of ambient brightness on reference video frames at different layer levels varies. Reference video frames with higher layer levels exhibit greater smoothness and higher contrast performance. Therefore, based on the corresponding layer levels of multiple reference video frames, the initial brightness at corresponding positions within the lines of multiple reference video frames can be standardized variable-wise to obtain the layer keyness corresponding to each reference video frame. Based on the layer keyness corresponding to each reference video frame, and the initial brightness variable-wise corresponding to multiple second sub-regions of each reference video frame, a weighted calculation is performed to obtain the target brightness variable-wise of the first sub-region at the target brightness variable-wise orientation. The target brightness variable-wise can more accurately reflect the effect of ambient brightness on the brightness of color points in the first sub-region at multiple target brightness variable-wise orientations.

[0057] Optionally, the specific calculation of the target brightness for each variable is as follows:

[0058]

[0059] Among them, E' (j,k) E represents the target brightness variation at the k-th target brightness variation position of the j-th sub-region in any comparison video frame; (a,j,k) The variable represents the initial brightness of the j-th second sub-region within the reference video frame of the a-th layer group at the k-th initial brightness variable orientation; a is the a-th layer group level; n is the total number of layer group levels; γ is a preset coefficient, which can be set to 1 in this embodiment. This represents the layer criticality of the reference video frame in the a-th layer group.

[0060] It should be noted that the grayscale video frames in this embodiment are the same as the reference video frames of the 0th group level after downsampling by the pyrDown function.

[0061] In an alternative embodiment, the determination of the light-dark degree disturbance quantity corresponding to each of the first sub-regions based on the target lightness variable corresponding to each of the first sub-regions and the target lightness variable corresponding to each of the first sub-regions comprises: taking each of the first sub-regions as a fourth sub-region, and obtaining the light-dark degree disturbance quantity corresponding to each of the first sub-regions by the following method: determining the orientation difference quantity between the lightness variable corresponding to the fourth sub-region and the lightness variable corresponding to the adjacent region of the fourth sub-region, to obtain a plurality of orientation difference quantities corresponding to the fourth sub-region, wherein the adjacent region is a plurality of regions, and the plurality of adjacent regions and the plurality of orientation difference quantities correspond to each other in a one-to-one manner; performing summation processing on the plurality of orientation difference quantities corresponding to the fourth sub-region to obtain a total quantity of the plurality of orientation difference quantities corresponding to the fourth sub-region; performing standardization processing on the total quantity of the plurality of orientation difference quantities corresponding to the fourth sub-region to obtain a standard orientation difference quantity corresponding to the fourth sub-region; and performing multiplication operation on the standard orientation difference quantity corresponding to the fourth sub-region and the target lightness variable corresponding to the fourth sub-region to obtain the light-dark degree disturbance quantity corresponding to the fourth sub-region.

[0062] Optionally, based on the target lightness variable of the first sub-region in the plurality of target lightness variables, the influence degree of the environment light-dark degree on the plurality of first sub-regions is analyzed. Since the higher the target lightness variable is, the higher the influence degree of the environment light-dark degree on the corresponding target lightness variable is. However, the influence range of the environment light-dark degree is large, and the difference quantity between the target lightness variables of the adjacent regions in the first sub-region is large after the influence of the environment light-dark degree. Therefore, directly determining the highest quantity of the target lightness variable as the key quantity of the influence of the environment light-dark degree on the first sub-region may cause the selected key quantity to be unable to well represent the lightness change characteristics of each of the adjacent regions. Therefore, the light-dark degree disturbance quantity of the first sub-region can be obtained according to the difference quantity between the target lightness variables of the adjacent regions in the first sub-region and the target lightness variable of the first sub-region, that is, the light-dark degree disturbance quantity is determined as the key quantity of the influence of the environment light-dark degree on the first sub-region, and the influence degree of the environment light-dark degree on the first sub-region is reflected according to the light-dark degree disturbance quantity.

[0063] Optionally, the light-dark degree disturbance quantity is calculated as follows:

[0064]

[0065] TEj=∑i=1n(TEi-TEj)2 j TEj is the light-dark degree disturbance quantity of the jth first sub-region of an arbitrary gray video frame, that is, the light-dark degree disturbance quantity of the fourth sub-region; TEj is the target lightness variable corresponding to the jth first sub-region; The target luminance gradient of the i-th first adjacent region of the j-th first sub-region is denoted as Tj,i, and the target luminance gradient of the j-th first sub-region is denoted as Tj. The number of the first adjacent regions is denoted as I, and in the present embodiment, the 3*3 square area is taken as an example for division, so that there are eight first adjacent regions, and I = 8. The target luminance gradient of the j-th first sub-region is denoted as Tj, and the target luminance gradient corresponding to the j-th first sub-region in the target luminance gradient direction is denoted as Tj. The Euler number is denoted as e, and is used for inverse proportional standardization processing. The target luminance gradient of the j-th first sub-region is denoted as Tj, and the target luminance gradient corresponding to the j-th first sub-region in the target luminance gradient direction is denoted as Tj. The Euler number is denoted as e, and is used for inverse proportional standardization processing.

[0066] Optionally, the lower the orientation difference quantity corresponding to the fourth sub-region is, the more similar the luminance gradient of the fourth sub-region and the luminance gradient of the first adjacent region are, and therefore the higher the degree of influence of the ambient light intensity on the fourth sub-region is, and the higher the light intensity disturbance quantity TE is. Based on the above inference, the total quantity is obtained by summing the plurality of orientation difference quantities, the inverse proportional standardization processing is performed on the total quantity, the first disturbance index is obtained, and the light intensity disturbance quantity TE is obtained. j The target luminance gradient of the j-th first sub-region is denoted as Tj, and the target luminance gradient corresponding to the j-th first sub-region in the target luminance gradient direction is denoted as Tj. The Euler number is denoted as e, and is used for inverse proportional standardization processing.

[0067] In step S108, the luminance key points of the plurality of first sub-regions are extracted respectively to obtain the luminance key points corresponding to the plurality of first sub-regions respectively.

[0068] Optionally, in the power line identification process, the scale feature transformation operator (SIFT operator) is used to extract the luminance key points of the gray video frame, and the luminance key point value corresponding to the luminance key point is calculated. Specifically, the SIFT operator value corresponding to the first sub-region is obtained according to the difference quantity between the luminance value of the color point of the first midpoint region in the first sub-region and the luminance value of the color point in the first adjacent region, and the luminance key point value of the first sub-region is taken as the luminance key point value of the first sub-region.

[0069] In step S110, based on the luminance key points corresponding to the plurality of first sub-regions respectively and the light intensity disturbance quantity corresponding to the plurality of first sub-regions respectively, the target adaptation quantity between the gray video frame and the preset video frame is obtained, wherein the target adaptation quantity is used to indicate the matching degree between the gray video frame and the preset video frame. ​

[0070] Optionally, the light-dark disturbance quantity only represents the degree of influence of the environment light-dark degree on the gray video frame. In the power line identification process, the influence of the environment light-dark degree needs to be considered. Therefore, the identified power line type needs to be adapted based on the light-dark disturbance quantity. In the adaptation process, the brightness key points in the gray video frame and the key points in the preset video frame need to be adapted to reduce the influence of the environment light-dark degree on the extraction of the brightness key points in the gray video frame during the extraction of the key points, thereby effectively ensuring the accuracy of the adaptation of the gray video frame and the preset video frame, and improving the accuracy of the power line identification.

[0071] In an optional embodiment, based on the brightness key points corresponding to the plurality of first sub-regions and the light-dark disturbance quantities corresponding to the plurality of first sub-regions, the target adaptation quantity between the gray video frame and the preset video frame is obtained, including: calculating the brightness difference between the brightness key points corresponding to the plurality of first sub-regions and the corresponding brightness key points in the preset video frame; based on the brightness difference between the brightness key points corresponding to the plurality of first sub-regions and the corresponding brightness key points in the preset video frame, obtaining the initial adaptation quantity corresponding to the plurality of first sub-regions; and based on the initial adaptation quantity corresponding to the plurality of first sub-regions and the light-dark disturbance quantity corresponding to the plurality of first sub-regions, obtaining the target adaptation quantity.

[0072] Optionally, the preset video frame is first regionally divided to obtain a plurality of fifth sub-regions. The brightness key point values corresponding to the plurality of first sub-regions in the gray video frame are obtained in the above manner, wherein the brightness key point value is used to indicate the brightness value at the key point. Based on the brightness key point values corresponding to the plurality of first sub-regions and the brightness key point values in the fifth sub-regions corresponding to the preset video frame of the power line in the preset information table, the difference quantity between the two is obtained. The initial adaptation quantity between the first sub-region and the fifth sub-region is obtained according to the difference quantity, and the specific calculation is as follows:

[0073]

[0074] wherein g j is the initial adaptation quantity of the jth first sub-region in the gray video frame; χ j is the brightness key point value obtained in the jth first sub-region in the gray video frame; χ j is the preset brightness key point value of the jth fifth sub-region in the preset video frame of the power line in the information table; and e is Euler number, which is used for inverse proportional standardization.

[0075] Optionally, during the obtaining of the initial adaptation quantity between the first sub-region and the fifth sub-region, |χ j -χ’ j| is the modulus of the quantity obtained by subtracting the corresponding luminance key point values of the two, | χ j -χ’ j | The higher, the higher the difference between the luminance key points of the first sub-region in the grayscale video frame and the fifth sub-region in the same position of the preset video frame of the power line stored in the information table, the lower the initial adaptation amount between the first sub-region and the fifth sub-region, so the | χ j -χ’ j | The higher, the higher the difference between the luminance key points of the first sub-region in the grayscale video frame and the fifth sub-region in the same position of the preset video frame of the power line stored in the information table, the lower the initial adaptation amount between the first sub-region and the fifth sub-region, so the | χ j .

[0076] Optionally, since the initial adaptation amount of the first sub-region and the fifth sub-region is not high due to the effect of the lightness, the accuracy of the power line identification may be affected, so the initial adaptation amount is corrected according to the lightness disturbance amount of the first sub-region in the grayscale video frame, and the target adaptation amount of the power line is obtained, so as to reduce the influence of the environmental lightness on the power line identification, and improve the accuracy of the power line identification. The target adaptation amount is calculated as follows:

[0077]

[0078]

[0079] Wherein, G is the final adaptation amount of the grayscale video frame; TE j is the lightness disturbance amount of the jth first sub-region in the grayscale video frame; g j is the initial adaptation amount of the jth first sub-region in the grayscale video frame; N is the number of first sub-regions in the grayscale video frame.

[0080] Optionally, in the process of obtaining the target adaptation amount of the power line, 1-TE j is the credibility of the jth first sub-region, where TE j is the lightness disturbance amount of the jth first sub-region, and the lower the lightness disturbance amount, the lower the degree of influence of the first sub-region by the environmental lightness, and the higher the credibility of the luminance key points extracted from the first sub-region. Set 0≤TE j ≤1, the credibility can be regarded as the key degree of the initial adaptation amount of the corresponding first sub-region, and the total key degrees of a plurality of first sub-regions are combined to obtain the target adaptation amount of the grayscale video frame, so as to reduce the influence of the environmental lightness on the power line identification.

[0081] Step S112, according to the target adaptation amount between the grayscale video frame and the preset video frame, determine the type of the power line included in the target video frame.

[0082] ​Optionally, the adaptation amount threshold value is set as four fifths. Based on the identification of the power line gray scale video frame according to the adaptation amount threshold value, if the target adaptation amount is higher than or equal to the adaptation amount threshold value, it is determined that the type of the power line in the gray scale video frame is the same as the type of the power line stored in the information table, and thus the preset video frame corresponding number integer variable of the power line stored in the information table is increased by one. If the target adaptation amount is lower than the adaptation amount threshold value, it is determined that the type of the power line in the gray scale video frame is different from the type of the power line stored in the information table, and thus the type of the power line stored in the information table is updated according to the type of the power line in the gray scale video frame. Therefore, the type of the power line on the line erection device is identified.

[0083] Through the above steps S102 to S112, the influence of the environment brightness on the identification of the power line is considered, thereby achieving the technical effect of improving the accuracy of the identification of the power line, and further solving the technical problem of low accuracy of the identification of the power line caused by the incomplete consideration of factors in the related art when determining the type of the power line.

[0084] Based on the above embodiment and optional embodiment, the present application provides an optional implementation, Figure 2 is a flow chart of an optional power line type determination method according to an embodiment of the present application, as shown in Figure 2 , the method comprises:

[0085] S1, obtaining an initial video frame of a power line captured by a corresponding camera on a line erection device;

[0086] S2, performing color removal processing on the initial video frame of the power line to obtain a gray scale video frame, and performing a plurality of layer group processing on the gray scale video frame to obtain a plurality of comparison video frames with the same size at different layer group levels, wherein the comparison video frames include the gray scale video frame;

[0087] S3, performing region segmentation processing on the gray scale video frame and the comparison video frame to obtain a plurality of first sub-regions corresponding to the gray scale video frame and a plurality of second sub-regions corresponding to the comparison video frame, setting any sub-region in the first sub-region as a first midpoint region, setting a sub-region adjacent to the midpoint region as a first adjacent region, and setting a sub-region adjacent to the first adjacent region as a first adjacent region. Draw a line in different directions by drawing a color point at the midpoint region in the first sub-region to a color point in the first adjacent region. According to the change of the color point brightness level of the first midpoint region to the first adjacent region on the same line, the initial brightness change variable of the first sub-region in each direction is obtained.

[0088] S4, according to the corresponding layer group level of the plurality of contrast video frames, the initial brightness of the second sub-region of the same site in the plurality of contrast video frames is performed by variable calibration processing, since the contrast video frames are processed by several layer groups of gray video frames, the initial brightness of the second sub-region is calibrated by variable, and the target brightness variable of the first sub-region is obtained; the target brightness variable of the first sub-region is obtained according to the target brightness variable; the target brightness variable of the first sub-region is obtained according to the difference between the target brightness variable and the target brightness variable of the first sub-region;

[0089] S5, the brightness key point extraction processing is performed on the first sub-region of the gray video frame, and the brightness key point value of the first sub-region is obtained; the target adaptation amount of the gray video frame is obtained according to the brightness key point value and the brightness key point value of the first sub-region; the power line is identified according to the target adaptation amount.

[0090] The present application is aimed at the problem that the SIFT operator is susceptible to the influence of the environment brightness when performing brightness key point extraction on the power line, first, the gray video frame of the power line is processed by several layer groups, the image is analyzed on different layer group levels, so as to obtain the corresponding brightness disturbance of the gray video frame, the target adaptation amount of the gray video frame is obtained by combining the corresponding brightness disturbance of the gray video frame and the brightness key point value of the gray video frame, and the identification of the power line is achieved according to the target adaptation amount, which reduces the influence of the environment brightness on the identification of the power line, improves the correctness of the identification of the power line, and improves the achievement rate of the identification of the power line.

[0091] In the embodiment, a power line type determination device is also provided, which is used to realize the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" "device" can be a combination of software and / or hardware that realizes a predetermined function. Although the device described in the following embodiments is preferably realized in software, hardware, or a combination of software and hardware is also possible and is conceived.

[0092] According to the embodiment of the present application, a device embodiment for implementing the above-mentioned power line type determination method is also provided, Figure 3 is a structural schematic diagram of a power line type determination device according to the embodiment of the present application, as Figure 3 shown, the above-mentioned power line type determination device comprises: an acquisition module 700, a region division module 702, a brightness disturbance module 704, a brightness key point extraction module 706, a target adaptation amount determination module 708, and a power line type determination module 710, wherein:

[0093] The acquisition module 700 is configured to acquire a target video frame obtained by video collection on a power line and a gray video frame corresponding to the target video frame, wherein the gray video frame is obtained by desaturation processing on the target video frame according to a predetermined spatial scale.

[0094] The region segmentation module 702 is connected to the acquisition module 700 and configured to perform region segmentation processing on the gray video frame to obtain a plurality of first sub-regions corresponding to the gray video frame.

[0095] The light-dark disturbance quantity module 704 is connected to the region segmentation module 702 and configured to determine light-dark disturbance quantities corresponding to the plurality of first sub-regions, respectively, wherein the light-dark disturbance quantity is used to indicate the degree of change in brightness and darkness of the corresponding sub-region.

[0096] The brightness key point extraction module 706 is connected to the light-dark disturbance quantity module 704 and configured to extract brightness key points from the plurality of first sub-regions, respectively, to obtain brightness key points corresponding to the plurality of first sub-regions, respectively.

[0097] The target adaptation quantity determination module 708 is connected to the brightness key point extraction module 706 and configured to determine a target adaptation quantity between the gray video frame and a preset video frame based on the brightness key points corresponding to the plurality of first sub-regions, respectively, and the light-dark disturbance quantities corresponding to the plurality of first sub-regions, respectively, wherein the target adaptation quantity is used to indicate the matching degree between the gray video frame and the preset video frame.

[0098] The power line type determination module 710 is connected to the target adaptation quantity determination module 708 and configured to determine the type of the power line included in the target video frame according to the target adaptation quantity between the gray video frame and the preset video frame.

[0099] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, the above modules can be located in the same processor or in different processors in any combination.

[0100] It should be noted that the above acquisition module 700, region segmentation module 702, light-dark disturbance quantity module 704, brightness key point extraction module 706, target adaptation quantity determination module 708, and power line type determination module 710 correspond to steps S102 to S112 in the embodiments, and the above modules have the same instances and application scenarios as the corresponding steps, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can run in a computer terminal.

[0101] It should be noted that the optional or preferred embodiments of the present embodiment can refer to the related description in the embodiments, which will not be repeated here.

[0102] The embodiment also provides a power line category determination platform for implementing the above-mentioned embodiment and preferred implementation, which will not be repeated here. Figure 4 Fig. 1 is a structural schematic diagram of a power line category determination platform according to an embodiment of the present application, as shown in the figure, the power line category determination platform comprises a obtaining module 802, a cutting module 804, a correcting module 806 and a determining module 808, wherein: Figure 4 The obtaining module 802 obtains initial video frames of the power line shot by the corresponding camera on the line erection device, performs color removal processing on the initial video frames of the power line to obtain gray video frames, performs a number of group processing on the gray video frames to obtain comparison video frames of the same size at different group levels, wherein the comparison video frames contain the gray video frames.

[0103] The cutting module 804 is connected to the obtaining module 802, performs area cutting processing on the gray video frames and the comparison video frames to obtain a first sub-area corresponding to the gray video frames and a second sub-area corresponding to the comparison video frames, sets any sub-area in the first sub-area as a first midpoint area, sets a sub-area adjacent to the midpoint area as a first adjacent area, and sets a sub-area adjacent to the first adjacent area as a first adjacent area. Draw a line of different orientations from a color point at the midpoint area in the first sub-area to a color point in the first adjacent area, and obtain the initial brightness variation of the first sub-area in each orientation according to the variation of the color point brightness level of the first midpoint area to the first adjacent area on the same line.

[0104] The correcting module 806 is connected to the cutting module 804, performs correction processing on the initial brightness variation of the second sub-area at the same position in a plurality of comparison video frames according to the corresponding group level of the plurality of comparison video frames, since the comparison video frames are processed by a number of group processing on the gray video frames, the initial brightness variation of the second sub-area is corrected to obtain the target brightness variation of the first sub-area in each orientation; obtain the target brightness variation direction of the first sub-area according to the target brightness variation; and obtain the lightness disturbance amount of the first sub-area according to the difference between the target brightness variation directions and the target brightness variation of the first sub-area.

[0105] The determining module 808 is connected to the correcting module 806, performs brightness key point extraction processing on the first sub-area of the gray video frames to obtain the brightness key point value of the first sub-area; obtains the target adaptation amount of the gray video frames according to the brightness key point value and the lightness disturbance amount of the first sub-area; and performs determination on the power line according to the target adaptation amount.

[0106]

[0107] ​It should be noted that the controller can be an industrial computer or a computer, and the time interval of the timing can be 1 second, which can guarantee real-time identification of the type and number of power lines.

[0108] The power line type determination apparatus described above can further include a processor and a memory, and the acquisition module 700, the region segmentation module 702, the lightness disturbance module 704, the brightness key point extraction module 706, the target adaptation amount determination module 708, and the power line type determination module 710 are all stored in the memory as program modules, and the processor executes the program modules stored in the memory to realize the corresponding functions.

[0109] The processor includes a core, and the core retrieves the corresponding program modules from the memory. The core can be one or more. The memory can include a non-permanent memory in a computer readable medium, a random access memory (RAM), and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM), and the memory includes at least one memory chip.

[0110] According to the embodiments of the present application, an embodiment of a non-volatile storage medium is also provided. Optionally, in the present embodiment, the non-volatile storage medium includes a stored program, wherein when the program runs, the device in which the non-volatile storage medium is located executes any of the power line type determination methods described above.

[0111] Optionally, in the present embodiment, the non-volatile storage medium can be located in any one of a group of computer terminals in a computer network, or in any one of a group of mobile terminals, and the non-volatile storage medium includes a stored program.

[0112] Optionally, the program running time controls the device where the nonvolatile storage medium is located to perform the following functions: obtaining a target video frame obtained by video acquisition on the power line and a gray video frame corresponding to the target video frame, wherein the gray video frame is obtained by desaturation processing on the target video frame according to a predetermined spatial scale; performing regional segmentation processing on the gray video frame to obtain a plurality of first sub-regions corresponding to the gray video frame; determining a light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the light-dark disturbance quantity is used to indicate the degree of change in brightness and darkness of the corresponding sub-region; performing brightness key point extraction on each of the plurality of first sub-regions to obtain a brightness key point corresponding to each of the plurality of first sub-regions; obtaining a target adaptation quantity between the gray video frame and a preset video frame based on the brightness key point corresponding to each of the plurality of first sub-regions and the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the target adaptation quantity is used to indicate the matching degree between the gray video frame and the preset video frame; and determining the type of the power line included in the target video frame according to the target adaptation quantity between the gray video frame and the preset video frame.

[0113] According to the embodiments of the present application, an embodiment of a processor is further provided. Optionally, in the embodiment, the processor is used to run a program, and the program is used to perform any of the power line type determination methods when running.

[0114] According to the embodiments of the present application, an embodiment of a computer program product is further provided. Optionally, in the embodiment, the computer program product includes a computer program, and the computer program is used to perform the steps of any of the power line type determination methods when executed by a processor.

[0115] Optionally, the computer program product, when executed on a data processing device, is adapted to perform the program initialized with the following method steps: obtaining a target video frame obtained by video acquisition on the power line and a gray video frame corresponding to the target video frame, wherein the gray video frame is obtained by desaturation processing on the target video frame according to a predetermined spatial scale; performing regional segmentation processing on the gray video frame to obtain a plurality of first sub-regions corresponding to the gray video frame; determining a light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the light-dark disturbance quantity is used to indicate the degree of change in brightness and darkness of the corresponding sub-region; performing brightness key point extraction on each of the plurality of first sub-regions to obtain a brightness key point corresponding to each of the plurality of first sub-regions; obtaining a target adaptation quantity between the gray video frame and a preset video frame based on the brightness key point corresponding to each of the plurality of first sub-regions and the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the target adaptation quantity is used to indicate the matching degree between the gray video frame and the preset video frame; and determining the type of the power line included in the target video frame according to the target adaptation quantity between the gray video frame and the preset video frame.

[0116] An electronic device is provided, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining a target video frame obtained by video acquisition on a power line, and a gray video frame corresponding to the target video frame, wherein the gray video frame is obtained by desaturation processing on the target video frame according to a predetermined spatial scale; performing region segmentation processing on the gray video frame to obtain a plurality of first sub-regions corresponding to the gray video frame; determining a light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the light-dark disturbance quantity is used to indicate the degree of change in brightness and darkness of the corresponding sub-region; performing brightness key point extraction on each of the plurality of first sub-regions to obtain a brightness key point corresponding to each of the plurality of first sub-regions; obtaining a target adaptation quantity between the gray video frame and a preset video frame based on the brightness key point corresponding to each of the plurality of first sub-regions and the light-dark disturbance quantity corresponding to each of the plurality of first sub-regions, wherein the target adaptation quantity is used to indicate the matching degree between the gray video frame and the preset video frame; and determining the type of the power line included in the target video frame according to the target adaptation quantity between the gray video frame and the preset video frame.

[0117] The sequence of the above embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments.

[0118] In the above embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0119] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the above-mentioned modules can be a logical function division, and actual implementation can have another division way, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between modules or modules, which can be electrical or other forms.

[0120] The above-mentioned modules described as separate components can be or can not be physically separated, and the components shown as modules can be or can not be physical modules, that is, they can be located in one place, or can be distributed to multiple modules. According to the actual needs, some or all of the modules can be selected to achieve the purpose of the present embodiment scheme.

[0121] In addition, each function module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically independently, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0122] When the integrated module is realized in the form of a software function module and sold or used as an independent product, the module can be stored in a computer readable nonvolatile storage medium. Based on this understanding, the technical solutions of the present application or the part of the prior art that contributes essentially or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a nonvolatile storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned nonvolatile storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk and various media that can store program codes.

[0123] The above is only the preferred embodiment of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for determining the type of power line, characterized in that, include: Acquire a target video frame obtained by video capture of a power line, and a grayscale video frame corresponding to the target video frame, wherein the grayscale video frame is obtained by desaturating the target video frame according to a predetermined spatial scale; The grayscale video frame is subjected to region segmentation processing to obtain multiple first sub-regions corresponding to the grayscale video frame; Determining the brightness disturbance amount corresponding to the plurality of first sub-regions includes: acquiring a plurality of reference video frames corresponding to the target video frame, wherein the plurality of reference video frames are obtained by downsampling the grayscale video frame according to a plurality of different layer groups; for each of the plurality of reference video frames, performing region segmentation processing on each reference video frame to obtain a plurality of second sub-regions corresponding to each reference video frame, wherein the plurality of second sub-regions correspond one-to-one with the plurality of first sub-regions; determining the initial brightness variation of the plurality of second sub-regions corresponding to each reference video frame, wherein the initial brightness variation is used to indicate the degree of brightness change from the second sub-region to the adjacent region within the corresponding predetermined neighborhood range at the corresponding line position; based on each The initial brightness of multiple second sub-regions corresponding to a reference video frame is used to obtain the target brightness of the multiple first sub-regions. Based on the target brightness of the multiple first sub-regions, the target brightness direction of the multiple first sub-regions is obtained, wherein the target brightness variable indicates the brightness change state of the corresponding sub-region in the corresponding direction, and the target brightness direction indicates the brightness change direction of the corresponding sub-region. Based on the target brightness variable and the target brightness direction of the multiple first sub-regions, the brightness disturbance amount of the multiple first sub-regions is determined, wherein the brightness disturbance amount indicates the degree of change in the brightness and darkness of the corresponding sub-regions. Brightness key points are extracted from the plurality of first sub-regions respectively to obtain the brightness key points corresponding to the plurality of first sub-regions respectively; Based on the brightness key points corresponding to the plurality of first sub-regions respectively, and the brightness and darkness disturbance amounts corresponding to the plurality of first sub-regions respectively, the target adaptation amount between the grayscale video frame and the preset video frame is obtained, wherein the target adaptation amount is used to indicate the degree of matching between the grayscale video frame and the preset video frame. The type of power line included in the target video frame is determined based on the target adaptation amount between the grayscale video frame and the preset video frame.

2. The method according to claim 1, characterized in that, The step of obtaining multiple reference video frames corresponding to the target video frame includes: The grayscale video frames are downsampled according to multiple different layer groups to obtain multiple first video frames; The plurality of first video frames are supplemented to obtain the plurality of reference video frames, wherein the plurality of reference video frames have the same resolution as the grayscale video frames.

3. The method according to claim 1, characterized in that, The step of determining the initial brightness variable corresponding to each of the multiple second sub-regions for each reference video frame includes: Each of the multiple second sub-regions corresponding to each reference video frame is taken as a third sub-region, and the initial brightness of each of the multiple second sub-regions corresponding to each reference video frame is obtained by the following method: Determine the adjacent regions of the third sub-region within the adjacent interval; By drawing a colored dot at the midpoint of the third sub-region, lines are drawn along multiple predetermined directions to the third sub-region and the adjacent region, resulting in multiple lines, wherein the multiple predetermined directions and the multiple lines correspond one-to-one. Based on the variation characteristics of the color point brightness levels of the third sub-region and the adjacent regions on the multiple lines, the initial brightness of the third sub-region along the multiple predetermined directions is determined by a variable.

4. The method according to claim 3, characterized in that, The step of determining the initial brightness of the third sub-region along the multiple predetermined directions based on the variation characteristics of the color point brightness levels of the third sub-region and the adjacent regions on the multiple lines includes: Using the multiple predetermined orientations as target directions, the initial brightness of the third sub-region along the multiple predetermined orientations is obtained variable by variable as follows: Determine multiple color points located on the lines corresponding to the target direction in the third sub-region and the adjacent regions; Determine the color point clusters corresponding to the plurality of color points respectively, wherein the color point cluster includes the corresponding color point and a predetermined number of adjacent color points of the corresponding color point; For each color point cluster corresponding to the plurality of color points, a subtraction operation is performed on the brightness level between two adjacent color points in each color point cluster to obtain a plurality of brightness subtraction amounts corresponding to each color point cluster. Multiply the multiple brightness subtractions corresponding to each color point cluster to obtain the confirmation index corresponding to each color point cluster. The confirmation index corresponding to each color dot cluster is binarized to obtain the progressive index corresponding to each color dot cluster. When the confirmation index is greater than or equal to a predetermined value, the progressive index is a first value. When the confirmation index is less than the predetermined value, the progressive index is a second value. The first value is greater than the second value. The variable index corresponding to each color point cluster is standardized to obtain the initial brightness variable of the target direction.

5. The method according to claim 2, characterized in that, The step of obtaining the target brightness variable corresponding to each of the multiple first sub-regions based on the initial brightness variable corresponding to each of the multiple second sub-regions corresponding to each of the reference video frames includes: Determine the layer group level corresponding to each reference video frame, wherein the layer group level is the layer group level corresponding to the downsampling process performed on the grayscale video frame; The layer group hierarchy corresponding to each reference video frame is standardized to obtain the keyness of the layer group corresponding to each reference video frame. Based on the layer group criticality corresponding to each reference video frame and the initial brightness of the multiple second sub-regions corresponding to each reference video frame, a weighted calculation is performed to obtain the target brightness of the multiple first sub-regions.

6. The method according to claim 1, characterized in that, The step of determining the brightness disturbance amount corresponding to each of the plurality of first sub-regions based on the target brightness variable corresponding to each of the plurality of first sub-regions and the target brightness variable orientation corresponding to each of the plurality of first sub-regions includes: Each of the plurality of first sub-regions is taken as a fourth sub-region, and the brightness disturbance amount corresponding to each of the plurality of first sub-regions is obtained in the following manner: Determine the azimuth difference between the brightness-changing azimuth of the fourth sub-region and the brightness-changing azimuth of the corresponding adjacent region, and obtain multiple azimuth difference values ​​corresponding to the fourth sub-region, wherein there are multiple adjacent regions, and the multiple adjacent regions and the multiple azimuth difference values ​​correspond one-to-one. The multiple azimuth differences corresponding to the fourth sub-region are summed to obtain the total quantity of the multiple azimuth differences corresponding to the fourth sub-region; The total measurement of multiple azimuth differences corresponding to the fourth sub-region is standardized to obtain the standard azimuth difference corresponding to the fourth sub-region. The standard orientation difference value corresponding to the fourth sub-region and the target brightness change orientation corresponding to the fourth sub-region are multiplied together to obtain the brightness disturbance value corresponding to the fourth sub-region.

7. The method according to any one of claims 1 to 6, characterized in that, The step of obtaining the target adaptation amount between the grayscale video frame and the preset video frame based on the brightness key points corresponding to the plurality of first sub-regions and the brightness disturbance amount corresponding to the plurality of first sub-regions includes: Calculate the brightness difference between the brightness key points corresponding to the plurality of first sub-regions and the corresponding brightness key points in the preset video frame; Based on the brightness difference between the brightness key points corresponding to the plurality of first sub-regions and the corresponding brightness key points in the preset video frame, the initial adaptation amount corresponding to the plurality of first sub-regions is obtained. The target adaptation value is obtained based on the initial adaptation values ​​corresponding to the plurality of first sub-regions and the brightness / darkness disturbance values ​​corresponding to the plurality of first sub-regions.

8. A device for determining the type of power line, characterized in that, include: The acquisition module is used to acquire a target video frame obtained by video capture of a power line, and a grayscale video frame corresponding to the target video frame, wherein the grayscale video frame is obtained by desaturating the target video frame according to a predetermined spatial scale. The region segmentation module is used to perform region segmentation processing on the grayscale video frame to obtain multiple first sub-regions corresponding to the grayscale video frame; The brightness perturbation module is used to determine the brightness perturbation amount corresponding to the plurality of first sub-regions, including: acquiring a plurality of reference video frames corresponding to the target video frame, wherein the plurality of reference video frames are obtained by downsampling the grayscale video frame according to a plurality of different layer groups; for each of the plurality of reference video frames, performing region segmentation processing on each reference video frame to obtain a plurality of second sub-regions corresponding to each reference video frame, wherein the plurality of second sub-regions correspond one-to-one with the plurality of first sub-regions; determining the initial brightness pervariate corresponding to each of the plurality of second sub-regions corresponding to each reference video frame, wherein the initial brightness pervariate is used to indicate the degree of brightness change from the second sub-region to the adjacent region within the corresponding predetermined neighborhood range at the corresponding line position. Based on the initial brightness variables corresponding to the multiple second sub-regions of each reference video frame, the target brightness variables corresponding to the multiple first sub-regions are obtained; based on the target brightness variables corresponding to the multiple first sub-regions, the target brightness direction corresponding to the multiple first sub-regions is obtained, wherein the target brightness variables are used to indicate the brightness variation state of the corresponding sub-region in the corresponding direction, and the target brightness direction indicates the brightness change direction of the corresponding sub-region; based on the target brightness variables and the target brightness direction corresponding to the multiple first sub-regions, the brightness disturbance amount corresponding to the multiple first sub-regions is determined, wherein the brightness disturbance amount indicates the degree of change in the brightness and darkness of the corresponding sub-regions; A brightness key point extraction module is used to extract brightness key points from the plurality of first sub-regions respectively, and obtain the brightness key points corresponding to the plurality of first sub-regions respectively. The target adaptation amount determination module is used to obtain the target adaptation amount between the grayscale video frame and the preset video frame based on the brightness key points corresponding to the plurality of first sub-regions and the brightness and darkness disturbance amounts corresponding to the plurality of first sub-regions, wherein the target adaptation amount is used to indicate the degree of matching between the grayscale video frame and the preset video frame. The power line type determination module is used to determine the type of power line included in the target video frame based on the target adaptation amount between the grayscale video frame and the preset video frame.

Images