A method and system for dividing a conductor protection zone of a power transmission channel, and a storage medium

Abstract

The present application relates to a kind of transmission channel wire protection zoning method, system and storage medium, it is related to computer vision technical field.The present application will be transmitted channel image by wire segmentation model and be segmented to obtain wire mask chart;From wire mask chart, wire is screened out;From the wire screened out, the wire of left and right sides of camera is extracted;The tower in transmission channel is identified by tower detection model, and the coordinates of tower detection frame output by tower detection model are saved;According to the position of tower detection frame, effective wire is obtained by filtering wire;Select main tower, select the two outermost wires of leftmost and rightmost from all effective wires and match with main tower, and the outermost wire area is projected to obtain wire protection zone.The present application realizes that the image collected by the camera of any tower is used to determine the wire protection zone of the transmission channel where the tower is located, to realize more accurate transmission channel anomaly alarm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer vision, and in particular to a method and system for dividing a conductor protection zone of a power transmission channel and a storage medium. BACKGROUND

[0002] At present, a camera is arranged on a tower of a power transmission channel to monitor the situation in the power transmission channel, so as to realize abnormal and hidden danger inspection of the power transmission channel. The field of view of a general camera is wide enough to cover the power transmission channel where the camera is located. Current hidden danger inspection generally alarms all hidden dangers appearing in the field of view of the power transmission channel camera. However, due to the wide field of view of the camera lens, some hidden dangers appear at a position far from the tower and the conductor. The alarm generated based on such hidden dangers is an invalid alarm. Moreover, the wide field of view of the camera lens covers multiple power transmission channels. When the same hidden danger is captured by different cameras, repeated alarms for the same hidden danger will occur. In order to improve the accuracy of the alarm information, an effective alarm conductor protection zone needs to be set to avoid repeated alarms and invalid alarms for hidden dangers appearing in the zone. SUMMARY

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a method and system for dividing a conductor protection zone of a power transmission channel and a storage medium.

[0004] In a first aspect, the present application provides a method for dividing a conductor protection zone of a power transmission channel, comprising:

[0005] A camera arranged on a tower is used to capture a power transmission channel image. The power transmission channel image is subjected to conductor segmentation by a pre-trained conductor segmentation model to obtain a segmented conductor mask image.

[0006] The conductor is filtered out from the conductor mask image. The conductors on the left and right sides of the camera are extracted from the filtered conductors. The x-axis coordinate of the lowermost point of the left conductor is greater than the x-axis coordinate of the uppermost point, the x-axis coordinate of the lowermost point of the right conductor is less than the x-axis coordinate of the uppermost point, and the non-left and right conductors are deleted.

[0007] A tower detection model is used to identify the towers in the power transmission channel. The coordinates of the tower detection frame output by the tower detection model are saved.

[0008] The conductors are filtered according to the positions of the tower detection frames to obtain effective conductors. The effective conductors meet at least one of the following conditions: the x-axis coordinate of the uppermost point of the left conductor is less than the right boundary of any tower detection frame; the x-axis coordinate of the uppermost point of the right conductor is greater than the left boundary of any tower detection frame; and the extension line of the left and right conductors intersects any tower detection frame.

[0009] Select the main tower, select the matched main tower from all effective conductors and filter out the leftmost and rightmost two outermost conductors, and project the area where the outermost conductors are located to obtain the conductor protection area.

[0010] Further, the filtering of the conductors from the conductor mask image comprises:

[0011] The median filter processing is performed on the conductor mask image, and the dilation processing is performed on the median filtered conductor mask image.

[0012] The connected domain detection is performed on the dilated conductor mask image, the connected domains with an area less than a set area threshold are deleted, and the filtered connected domains are selected as the conductors.

[0013] Further, the selection of the main tower comprises: counting the number of conductors intersecting each tower detection frame, taking the tower with the maximum number of conductor intersections as the main tower, and if there are multiple towers with the maximum number of conductor intersections and equal, taking the tower with the maximum area of the tower detection frame as the main tower.

[0014] Further, the detection of the intersection of the conductor and the area of the main tower detection frame after the amplification of the set multiple is that the conductor matches the main tower.

[0015] Further, the selection of the leftmost and rightmost two outermost conductors from the effective conductors matched with the main tower comprises: taking the conductor with the minimum x-axis coordinate of the uppermost point from the left effective conductor matched with the main tower as the leftmost conductor, and taking the conductor with the maximum x-axis coordinate of the uppermost point from the right effective conductor matched with the main tower as the rightmost conductor.

[0016] Further, the projection of the area where the outermost conductors are located to obtain the conductor protection area comprises:

[0017] The lowermost extension of the leftmost conductor and the rightmost conductor is to the flush position, if the position exceeds the tower detection frame, it is the final conductor position, if it does not exceed, it is extended to the uppermost boundary of the tower detection frame;

[0018] The lowest point of the leftmost conductor and the rightmost conductor is mapped to the tower bottom, the highest point of the leftmost conductor and the rightmost conductor is projected downward with the tower bottom as the axis of symmetry, and the mapping area of the lowest point and the highest point of the leftmost conductor and the rightmost conductor is the conductor protection area; if the side of the conductor protection area exceeds the image boundary, shorten the side of the conductor protection area to the image lower boundary, if it does not reach the image lower boundary, calculate the slope of the mapped conductor protection area side, and extend the conductor protection area side to the image lower boundary.

[0019] Further, when the following exceptions occur, an exception is thrown and the conductor protection area is not set:

[0020] The conductor segmentation model fails to detect the conductor, the tower detection model fails to detect the tower, the conductor detection is abnormal due to that all conductors on one side are filtered, the tower detection is abnormal due to that all towers are filtered, and the conductor and the tower are mismatched due to that the effective conductor and the main tower are not intersected.

[0021] Further, when the following abnormality occurs, an exception is thrown but the conductor protection zone is set:

[0022] The conductor is not in the expanded region after the tower detection frame is enlarged by the first set multiple, but is in the expanded region after the tower detection frame is enlarged by the second set multiple, an exception of possible incomplete conductor is thrown but the conductor protection zone is still set.

[0023] In a second aspect, the present application provides a two-dimensional conductor protection zone division system of a power transmission channel, which implements the conductor protection zone division method of the power transmission channel, and comprises:

[0024] An image acquisition module, which acquires a power transmission channel image;

[0025] A conductor segmentation module, which segments the power transmission channel image through a pre-trained conductor segmentation model to obtain a segmented conductor mask image;

[0026] A conductor screening module, which screens conductors from the conductor mask image;

[0027] A first filtered conductor module, which extracts conductors on the left and right sides of the camera from the screened conductors, wherein the x-axis coordinate of the lowermost point of the left conductor is greater than the x-axis coordinate of the uppermost point, the x-axis coordinate of the lowermost point of the right conductor is less than the x-axis coordinate of the uppermost point, and non-left and right conductors are deleted;

[0028] A tower identification module, which identifies towers in the power transmission channel through a pre-trained tower detection model and saves the coordinates of the tower detection frame output by the tower detection model;

[0029] A second filtered conductor module, which filters the conductors according to the position of the tower detection frame to obtain effective conductors, wherein the effective conductors meet at least one of the following conditions: the x-axis coordinate of the uppermost point of the left conductor is less than the right boundary of any tower detection frame; the x-axis coordinate of the uppermost point of the right conductor is greater than the left boundary of any tower detection frame; and the extension line of the left and right conductors intersects any tower detection frame;

[0030] A conductor protection zone division module, which selects a main tower, selects the two outermost conductors on the left and right sides from all effective conductors that match the main tower, and projects the region where the outermost conductors are located to obtain a conductor protection zone.

[0031] In a third aspect, the present application provides a computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for dividing the conductor protection area of the power transmission channel.

[0032] Compared with the prior art, the above technical solution provided by the embodiments of the present application has the following advantages:

[0033] The power transmission channel image is segmented by the conductor segmentation model to obtain a conductor mask image, and the conductors in the power transmission channel image are extracted using the conductor mask image; the conductors are screened from the conductor mask image to avoid the interference of line noise similar to the conductors; the conductors on the left and right sides of the camera are extracted from the screened conductors; the camera is arranged on the tower, the conductors monitored by the camera are consistent with the visual direction of the camera, and the conductors other than the conductors on the left and right sides are deleted to avoid the influence of the interlaced conductors in the power transmission channel image on the division of the conductor protection area. The towers in the power transmission channel are identified by the tower detection model, and the coordinates of the tower detection frame output by the tower detection model are saved; the effective conductors are obtained by filtering the conductors according to the position of the tower detection frame, and the conductors are further screened according to the positional relationship between the conductors and the towers to avoid the influence of line interference in the power transmission channel image that is not associated with the towers. The main tower is selected, the two outermost conductors on the left and right sides that match the main tower are selected from all the effective conductors, and the conductor protection area is obtained by projecting the area where the outermost conductors are located. The projection of the area where the main tower is associated with the outermost conductors is used as the conductor protection area, which realizes the determination of the conductor protection area of the power transmission channel where the tower is located by using the image collected by the camera of any tower. When an abnormal alarm occurs, only the abnormal alarm in the conductor protection area is realized to achieve more accurate power transmission channel abnormal alarm and avoid repeated alarm and invalid alarm.

[0034] The median filter processing is performed on the conductor mask image, the inflation processing is performed on the conductor mask image after the median filter processing, the connected domain detection is performed on the conductor mask image after the inflation processing, the connected domains with an area less than a set area threshold are deleted, and the filtered connected domains are selected as the conductors. The above process can effectively delete the line interference that is not a conductor. BRIEF DESCRIPTION OF DRAWINGS

[0035] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained from these drawings without any creative labor.

[0037] Figure 1 A flow chart of a method for dividing a wire protection zone of a power transmission channel according to an embodiment of the present application is provided.

[0038] Figure 2 A flow chart of a method for selecting a wire from a wire mask according to an embodiment of the present application is provided.

[0039] Figure 3 A flow chart of a method for selecting a main tower according to an embodiment of the present application is provided.

[0040] Figure 4 A flow chart of a method for projecting a wire protection zone according to an embodiment of the present application is provided.

[0041] Figure 5 An example of a wire protection zone in a power transmission channel image according to an embodiment of the present application is provided.

[0042] Figure 6 An example of wire detection abnormality caused by all wires on one side of a camera being filtered is provided.

[0043] Figure 7 An example of a wire protection zone being set even though a wire may be incomplete is provided.

[0044] Figure 8 A schematic diagram of a two-dimensional wire protection zone division system of a power transmission channel according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0045] In order to make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0046] It should be noted that, in this document, the terms “comprising” and “including” or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles, or devices including a series of elements not only include those elements, but also include other elements not explicitly listed, or further include inherent elements of such processes, methods, articles, or devices. Without more limitations, the element defined by the statement “comprising a” does not exclude the presence of additional identical elements in the process, method, article, or device including the element.

[0047] Embodiment 1

[0048] Reference is made toFigure 1 As shown in the embodiments of the present application, a method for dividing a conductor protection area of a power transmission channel is provided, comprising:

[0049] A camera arranged on a tower is used to collect a power transmission channel image.

[0050] The power transmission channel image is segmented by a pre-trained conductor segmentation model to obtain a segmented conductor mask image; in the specific implementation process, a PointRend segmentation model is trained to obtain the conductor segmentation model.

[0051] The segmented conductor mask image contains line noise similar to the conductor, and the conductor needs to be selected from the conductor mask image; referring to Figure 2 As shown in the embodiments of the present application, the conductor is selected from the conductor mask image, comprising:

[0052] The conductor mask image is subjected to median filtering processing, and the median filtered conductor mask image is subjected to dilation processing; the dilated conductor mask image is subjected to connected component detection, and the connected components with an area smaller than a set area threshold are deleted, and the filtered connected components are selected as the conductor. The selection of the area threshold is based on the pixel of the power transmission channel image and the area occupied by the conductor in the power transmission channel image.

[0053] The left and right conductors of the camera are extracted from the selected conductor, wherein the x-axis coordinate of the lowermost point of the left conductor is greater than the x-axis coordinate of the uppermost point, and the x-axis coordinate of the lowermost point of the right conductor is smaller than the x-axis coordinate of the uppermost point; the non-left and right conductors are deleted; in the camera view arranged on the tower, the conductor monitored by the camera is consistent with the camera view direction, and the distance between the conductors consistent with the camera view direction is close at near distance and wide at far distance, therefore, the x-axis coordinate of the lowermost point of the left conductor of the camera is greater than the x-axis coordinate of the uppermost point, and the x-axis coordinate of the lowermost point of the right conductor of the camera is smaller than the x-axis coordinate of the uppermost point. The non-left and right conductors are deleted to avoid the influence of the power transmission channel image on the division of the conductor protection area.

[0054] A tower detection model is used to identify the tower in the power transmission channel, and the coordinates of the tower detection frame output by the tower detection model are saved; in the specific implementation process, the tower detection model uses a yolo model for identifying a set type of tower, and the tower categories include iron single and double towers and cement single and double towers.

[0055] According to the tower detection frame position, the conductors are filtered to obtain effective conductors, wherein the effective conductors meet at least one of the following conditions: the x-axis coordinate of the uppermost point of the left side conductor is less than the right side boundary of any tower detection frame; the x-axis coordinate of the uppermost point of the right side conductor is greater than the left side boundary of any tower detection frame; the extension line of the left and right side conductors intersects any tower detection frame; after the conductors on the left and right sides of the camera are screened out, the conductors are further screened according to the positional relationship between the conductors and the towers, so as to avoid the influence of the line type in the power transmission channel image that is not associated with the tower.

[0056] The main tower is selected. Generally, the power transmission channel image often contains multiple power transmission channels and multiple towers, and the image collected by the camera at the tower is only used for protection division of the power transmission channel where the tower is located. Therefore, the main tower is selected from the multiple towers to determine the position of the conductor and the tower related to the power transmission channel. Referring to FIGS. 1, 2 and 3, the process of selecting the main tower includes: counting the number of conductors intersecting each tower detection frame, taking the tower with the maximum number of conductors intersecting as the main tower, and if multiple towers have the maximum number of conductors intersecting and are equal, taking the tower with the maximum area of the tower detection frame as the main tower. Figure 3

[0057] The leftmost and rightmost two outermost conductors are selected from the effective conductors matched with the main tower, and the conductor protection area is obtained by projecting the area where the outermost conductors are located.

[0058] After the main tower is determined, it is detected whether the conductor intersects the area of the main tower detection frame after being enlarged by a first set multiple. If yes, the conductor matches the main tower.

[0059] The leftmost and rightmost two outermost conductors are selected from the effective conductors matched with the main tower, and the conductor protection area is obtained by projecting the area where the outermost conductors are located.

[0060] Referring to FIGS. 1, 2 and 3, the leftmost and rightmost two outermost conductors are selected from the effective conductors matched with the main tower, and the conductor protection area is obtained by projecting the area where the outermost conductors are located. Figure 4 Figure 5 The lowermost of the leftmost and rightmost conductors of the main tower is extended in a flush manner, so as to reach at least one tower detection frame boundary.

[0061] The lowermost of the leftmost and rightmost conductors of the main tower is extended in a flush manner, so as to reach at least one tower detection frame boundary.

[0062] ​​The leftmost conductor and the rightmost conductor lowest point is mapped to the tower bottom, the leftmost conductor and the rightmost conductor highest point is projected downward with the tower bottom as the axis of symmetry, and the leftmost conductor and the rightmost conductor lowest point and highest point mapping area is the conductor protection zone; if the conductor protection zone side exceeds the image boundary, the conductor protection zone side is shortened to the image lower boundary, and if it does not reach the image lower boundary, the conductor protection zone side is extended to the image lower boundary according to the slope of the mapped conductor protection zone side.

[0063] During the entire conductor protection zone division process, conductor detection and tower monitoring are the premise of conductor protection zone division. When the following exceptions occur, an exception is thrown and the conductor protection zone is not set:

[0064] The conductor segmentation model does not detect the conductor, and the tower detection model does not detect the tower, such as Figure 6 Conductor detection exception caused by filtering all conductors on one side of the camera, tower detection exception caused by filtering all towers, and conductor and tower mismatch caused by intersection of effective conductors and main towers.

[0065] When the following exceptions occur, an exception is thrown but the conductor protection zone is set:

[0066] The conductor is not in the expanded area after the tower detection box is enlarged by a first set multiple, but is in the expanded area after the tower detection box is enlarged by a second set multiple, an exemplary first set multiple is 1.5 times, and an exemplary second set multiple is 2 times. For example Figure 7 The conductor may be incomplete exception is thrown, but the conductor protection zone is still set.

[0067] Embodiment 2

[0068] Referring to Figure 8 The embodiment of the application provides a two-dimensional conductor protection zone division system of a power transmission channel, and realizes the conductor protection zone division method of the power transmission channel, which comprises:

[0069] An image acquisition module, the image acquisition module acquires a power transmission channel image;

[0070] A conductor segmentation module, the conductor segmentation module segments the conductor in the power transmission channel image through a pre-trained conductor segmentation model to obtain a segmented conductor mask image;

[0071] A conductor screening module, the conductor screening module screens the conductor from the conductor mask image;

[0072] A first filtered conductor module extracts the left and right side conductors of the camera from the screened conductors, wherein the x-axis coordinate of the lowermost point of the left side conductor is greater than the x-axis coordinate of the uppermost point, the x-axis coordinate of the lowermost point of the right side conductor is less than the x-axis coordinate of the uppermost point, and the non-left and right side conductors are deleted;

[0073] A tower identification module identifies the towers in the power transmission channel through a pre-trained tower detection model, and saves the coordinates of the tower detection frame output by the tower detection model;

[0074] A second filtered conductor module filters the conductors according to the tower detection frame position to obtain effective conductors, wherein the effective conductors meet at least one of the following conditions: the x-axis coordinate of the uppermost point of the left side conductor is less than the right side boundary of any tower detection frame; the x-axis coordinate of the uppermost point of the right side conductor is greater than the left side boundary of any tower detection frame; and the extension line of the left and right side conductors intersects any tower detection frame;

[0075] A conductor protection zone division module selects a main tower, selects the leftmost and rightmost two outermost conductors from all effective conductors that match the main tower, and projects the area where the outermost conductors are located to obtain a conductor protection zone.

[0076] Embodiment 3

[0077] The embodiment of the application provides a computer readable storage medium storing a computer program, which, when executed by a processor, implements the conductor protection zone division method of the power transmission channel.

[0078] The method comprises:

[0079] A camera arranged on a tower collects a power transmission channel image, and a pre-trained conductor segmentation model is used for conductor segmentation on the power transmission channel image to obtain a segmented conductor mask image;

[0080] The conductors are screened from the conductor mask image, and the left and right side conductors of the camera are extracted from the screened conductors, wherein the x-axis coordinate of the lowermost point of the left side conductor is greater than the x-axis coordinate of the uppermost point, the x-axis coordinate of the lowermost point of the right side conductor is less than the x-axis coordinate of the uppermost point, and the non-left and right side conductors are deleted;

[0081] A pre-trained tower detection model is used to identify the towers in the power transmission channel, and the coordinates of the tower detection frame output by the tower detection model are saved;

[0082] Filter the conductors according to the tower detection frame position to obtain effective conductors, wherein the effective conductors meet at least one of the following conditions: the x-axis coordinate of the uppermost point of the left conductor is less than the right boundary of any tower detection frame; the x-axis coordinate of the uppermost point of the right conductor is greater than the left boundary of any tower detection frame; the extension line of the left and right conductors intersects any tower detection frame;

[0083] Select a main tower, select the two outermost conductors from all effective conductors that match the main tower and are filtered out, and project the region where the outermost conductors are located to obtain a conductor protection zone.

[0084] Of course, the computer readable storage medium provided by the embodiment of the application stores a computer program, which is not limited to the method operations described above, and can also perform related operations in the conductor protection zone division method of the power transmission channel provided by any embodiment of the application.

[0085] In the embodiments provided by the application, it should be understood that the disclosed structure and method can be implemented in other ways. For example, the structure embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, structures or units, and can be electrical, mechanical or in other forms.

[0086] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0087] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0088] The foregoing is considered as illustrative only of the principles of the application. Numerous modifications and changes will readily occur to those skilled in the art, and it is intended to embrace all such modifications and changes that fall within the scope of the application. Accordingly, the application is not to be restricted in scope to the specific embodiments disclosed herein but is to be accorded the full scope that the principles and novel features request appropriately granted.

Claims

1. A method of dividing a conductor protection zone of a power transmission corridor, characterized in that, The application relates to a method for setting a power line protection area, and belongs to the technical field of power line protection. The method comprises the following steps: collecting a power transmission channel image through a camera arranged on a tower, performing power line segmentation on the power transmission channel image through a pre-trained power line segmentation model, and obtaining a segmented power line mask image; The method further comprises the following steps: screening the power line from the power line mask image, including: performing median filtering on the power line mask image, performing inflation processing on the power line mask image after the median filtering, performing connected domain detection on the power line mask image after the inflation processing, deleting connected domains with an area smaller than a set area threshold, and selecting the filtered connected domains as the power line; extracting the power line on the left and right sides of the camera from the screened power line, wherein the x-axis coordinate of the lowermost point of the left-side power line is greater than the x-axis coordinate of the uppermost point, the x-axis coordinate of the lowermost point of the right-side power line is smaller than the x-axis coordinate of the uppermost point, and the non-left-and-right-side power line is deleted; The method further comprises the following steps: identifying the tower in the power transmission channel through a pre-trained tower detection model, and saving the coordinates of the tower detection frame output by the tower detection model; The method further comprises the following steps: filtering the power line according to the position of the tower detection frame to obtain an effective power line, wherein the effective power line meets at least one of the following conditions: the x-axis coordinate of the uppermost point of the left-side power line is smaller than the right-side boundary of any tower detection frame; the x-axis coordinate of the uppermost point of the right-side power line is greater than the left-side boundary of any tower detection frame; and the extension line of the left-and-right-side power line intersects with any tower detection frame; The method further comprises the following steps: selecting a main tower, including: counting the number of power lines intersecting each tower detection frame, taking the tower with the maximum number of power lines intersecting as the main tower, and taking the tower with the maximum area of the tower detection frame as the main tower if multiple towers have the maximum number of power lines intersecting and are equal; selecting two outermost power lines on the left and right sides from all effective power lines, wherein the power line matches the main tower if the power line intersects with the area of the main tower detection frame after being enlarged by a set multiple; and projecting the area where the outermost power lines are located to obtain a power line protection area.

2. The method of claim 1, wherein, The method further comprises the following steps: selecting the two outermost power lines on the left and right sides from the effective power lines matching the main tower, including: taking the power line with the minimum x-axis coordinate of the uppermost point from the left-side effective power line matching the main tower as the leftmost power line, and taking the power line with the maximum x-axis coordinate of the uppermost point from the right-side effective power line matching the main tower as the rightmost power line.

3. The method of claim 1, wherein, The method further comprises the following steps: projecting the area where the outermost power lines are located to obtain a power line protection area, including: The lowermost extension of the leftmost power line and the rightmost power line is to a flush position, and if the position exceeds the tower detection frame, the position is the final power line position, and if the position does not exceed the tower detection frame, the position is extended to the uppermost boundary of the tower detection frame; The lowest point of the leftmost power line and the rightmost power line is mapped to the bottom of the tower, the highest point of the leftmost power line and the rightmost power line is projected downward with the bottom of the tower as the axis of symmetry, and the mapping area of the lowest point and the highest point of the leftmost power line and the rightmost power line is the power line protection area; if the side of the power line protection area exceeds the image boundary, the side of the power line protection area is shortened to the lower boundary of the image, and if the side of the power line protection area does not reach the lower boundary of the image, the side of the power line protection area is extended to the lower boundary of the image according to the slope of the mapped side of the power line protection area.

4. The method of claim 1, wherein, When the following exceptions occur, an exception is thrown and the power line protection area is not set: The conductor segmentation model fails to detect the conductor, the tower detection model fails to detect the tower, the conductor detection is abnormal due to the filtering of all conductors on one side, the tower detection is abnormal due to the filtering of all towers, and the conductor and the tower are mismatched due to the disintersection of the effective conductor and the main tower.

5. The method of claim 1, wherein, When the following exceptions occur, an exception is thrown, but the conductor protection zone is still set: The conductor is not in the expanded region after the tower detection frame is enlarged by the first set multiple, but is in the expanded region after the tower detection frame is enlarged by the second set multiple, the conductor may be incomplete exception is thrown, but the conductor protection zone is still set.

6. A system for dividing a two-dimensional conductor protection zone of a power transmission corridor, which implements the method for dividing a conductor protection zone of a power transmission corridor according to any one of claims 1 to 5, characterized in that, Comprise: An image acquisition module that acquires a power transmission channel image; A conductor segmentation module that segments the conductor in the power transmission channel image through a pre-trained conductor segmentation model to obtain a segmented conductor mask image; A conductor screening module that screens the conductor from the conductor mask image; A first filtered conductor module that extracts the left and right conductors of the camera from the screened conductors, wherein the x-axis coordinate of the lowermost point of the left conductor is greater than that of the uppermost point, the x-axis coordinate of the lowermost point of the right conductor is less than that of the uppermost point, and the non-left and right conductors are deleted; A tower identification module that identifies the towers in the power transmission channel through a pre-trained tower detection model and saves the coordinates of the tower detection frame output by the tower detection model; A second filtered conductor module that filters the conductors according to the position of the tower detection frame to obtain effective conductors, wherein the effective conductors meet at least one of the following conditions: the x-axis coordinate of the uppermost point of the left conductor is less than the right boundary of any tower detection frame; the x-axis coordinate of the uppermost point of the right conductor is greater than the left boundary of any tower detection frame; and the extension line of the left and right conductors intersects any tower detection frame; A conductor protection zone division module that selects a main tower, selects the two outermost conductors that match the main tower from all effective conductors, and projects the region where the outermost conductors are located to obtain a conductor protection zone.

7. A computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the conductor protection zone division method of the power transmission channel according to any one of claims 1-5. The computer program is executed by the processor to implement the conductor protection zone division method of the power transmission channel according to any one of claims 1-5.

Images