A construction machinery early warning method, device and medium for overhead power transmission lines

Abstract

The present application discloses a construction machinery early warning method and system for overhead power transmission lines, which is used to solve the technical problem that the existing overhead power transmission line early warning method cannot give early warning of hidden dangers of external damage of overhead power transmission lines caused by construction machinery. The method includes: analyzing the picture of the overhead power transmission line to be analyzed acquired by the image acquisition device through a preset target detection model to determine whether there is construction machinery in the picture of the overhead power transmission line to be analyzed; when it is determined that there is construction machinery in the picture of the overhead power transmission line to be analyzed, starting the image acquisition device to record a video of the overhead power transmission line to be analyzed for a preset time, and analyzing the state of the construction machinery in the video of the overhead power transmission line to be analyzed; based on the state of the construction machinery in the video of the overhead power transmission line to be analyzed, determining the alarm level, and giving an alarm based on the alarm level. The present application realizes early warning of hidden dangers of external damage of construction machinery through the above method.

Description

Technical Field

[0001] The present application relates to the field of power transmission technology, and in particular to a construction machinery early warning method, device and medium for overhead power transmission lines. Background Art

[0002] In the power grid industry, the safety of overhead transmission lines is always of vital importance. Whether the overhead transmission lines are safe is of great significance to the safe and reliable operation of the power grid, so it is very important to monitor the operating status of overhead transmission lines. However, with the accelerated progress of science and technology, construction machinery can gradually extend into the channels of overhead transmission lines, which seriously threatens the safe operation of overhead transmission lines and creates huge safety hazards for overhead transmission lines.

[0003] The hidden dangers of external damage to overhead transmission lines often occur in a very short time window. The current early warning method of taking a single image at a fixed time for front-end or back-end analysis generally cannot generate an alarm in time before the accident occurs, and thus cannot prevent the construction machinery from touching high voltage electricity and causing tripping accidents in advance. Therefore, there is an urgent need for an early warning solution that can effectively analyze the safety hazards caused by construction machinery to overhead transmission lines. Summary of the invention

[0004] The embodiments of the present application provide a construction machinery early warning method, device and medium for overhead power transmission lines, which are used to solve the technical problem that the existing overhead power transmission line early warning method cannot provide early warning of the hidden danger of external damage of overhead power transmission lines caused by construction machinery.

[0005] In a first aspect, an embodiment of the present application provides a construction machinery early warning method for overhead transmission lines, characterized in that the method comprises: analyzing the picture of the overhead transmission line to be analyzed acquired by an image acquisition device through a preset target detection model to determine whether there is construction machinery in the picture of the overhead transmission line to be analyzed; when it is determined that there is construction machinery in the picture of the overhead transmission line to be analyzed, starting the image acquisition device to record a video of the overhead transmission line to be analyzed for a preset time, and analyzing the state of the construction machinery in the video of the overhead transmission line to be analyzed; wherein the state of the construction machinery includes the movement state of the construction machinery, the state of the construction machinery includes the working state of the construction machinery, and the position of the construction machinery; based on the state of the construction machinery in the video of the overhead transmission line to be analyzed, determining the alarm level, and issuing an alarm based on the alarm level.

[0006] The embodiment of the present application provides a construction machinery early warning method for overhead power transmission lines. First, the image of the overhead power transmission line to be analyzed obtained by the image acquisition device is analyzed to determine whether there is construction machinery in the image of the overhead power transmission line to be analyzed. When it is determined that there is construction machinery in the image of the overhead power transmission line to be analyzed, the state of the construction machinery is further analyzed by recording video, thereby achieving early warning and prevention of hidden dangers of external damage of construction machinery, avoiding the occurrence of tripping accidents and personal injury accidents caused by the construction machinery touching the wires. In addition, the above method can avoid the monitoring center personnel from viewing a large number of warning images.

[0007] In one implementation of the present application, before starting the image acquisition device to record a video of the overhead transmission line to be analyzed for a preset time and analyzing the state of the construction machinery in the video of the overhead transmission line to be analyzed, the method also includes: determining the mapping line of the lowest layer of transmission wires in the overhead transmission line image to be analyzed on the ground based on a preset wire detection model and a preset sky segmentation model; wherein the lowest layer of transmission wires is the layer of overhead transmission lines closest to the ground in the overhead transmission line image to be analyzed; based on the lowest layer of transmission wires and the mapping line, determining the overhead transmission line protection channel in the overhead transmission line image to be analyzed.

[0008] In one implementation of the present application, based on a preset wire detection model and a preset sky segmentation model, a mapping line of the lowest layer of transmission wires in an overhead transmission line image to be analyzed on the ground is determined, specifically including: determining the lowest layer of transmission wires in the overhead transmission line image to be analyzed through a preset wire detection model, and determining a first angle of the lowest layer of transmission wires in the overhead transmission line image to be analyzed relative to the horizontal direction; processing the overhead transmission line image to be analyzed through a preset sky segmentation model to determine a second angle at which the image acquisition device rotates relative to the ground; based on the first angle and the second angle, determining a third angle of the mapping line in the overhead transmission line image to be analyzed relative to the horizontal direction to determine the mapping line.

[0009] In one implementation of the present application, the state of construction machinery in the overhead transmission line video to be analyzed is analyzed, specifically including: determining the overhead transmission line protection channel in the overhead transmission line video to be analyzed; analyzing the motion state of the construction machinery through a preset target detection model, and analyzing whether the construction machinery is in the overhead transmission line protection channel; analyzing the aspect ratio of the construction machinery through a preset target edge detection model to determine the working state of the construction machinery; wherein the working state includes an operating state and a non-operating state.

[0010] In one implementation of the present application, the motion state of the construction machinery is analyzed through a preset target detection model, specifically including: extracting a frame of the overhead transmission line video to be analyzed as a video image to be analyzed every preset number of frames, and determining the position of the construction machinery in the video image to be analyzed through the target detection model; determining the motion state of the construction machinery based on the position change of the construction machinery in several extracted video images to be analyzed; wherein the motion state of the construction machinery includes being stationary, close to the overhead transmission line protection channel, and far away from the overhead transmission line protection channel.

[0011] In one implementation of the present application, the alarm level is determined based on the state of the construction machinery in the overhead transmission line video to be analyzed, specifically including: when the construction machinery is in the protection channel of the overhead transmission line and the working state is the operating state, the alarm level is determined to be a first-level alarm; when the construction machinery is in the protection channel of the overhead transmission line and the working state is the non-operating state, the alarm level is determined to be a second-level alarm; when the construction machinery is outside the protection channel of the overhead transmission line and the working state is the operating state, the alarm level is determined to be a second-level alarm; When the machinery is outside the protection channel of the overhead transmission line, and its working state is non-operating, and its moving state is close to the protection channel of the overhead transmission line, the alarm level is determined to be level 2 alarm; when the construction machinery is outside the protection channel of the overhead transmission line, and its working state is non-operating, and its moving state is away from the protection channel of the overhead transmission line, the alarm level is determined to be level 3 alarm; when the construction machinery is outside the protection channel of the overhead transmission line, and its working state is non-operating, and its moving state is stationary, the alarm level is determined to be level 3 alarm.

[0012] In one implementation of the present application, a picture of an overhead transmission line to be analyzed acquired by an image acquisition device is analyzed by a preset target detection model to determine whether there is construction machinery in the picture of the overhead transmission line to be analyzed, specifically including: inputting the picture of the overhead transmission line to be analyzed into a first target detection model preset in the image acquisition device to determine whether there is construction machinery in the picture of the overhead transmission line to be analyzed; wherein the first target detection model is a target detection model; and / or inputting the picture of the overhead transmission line to be analyzed into a second target detection model preset in the server to determine whether there is construction machinery in the picture of the overhead transmission line to be analyzed; wherein the second target detection model is a target detection model.

[0013] In one implementation of the present application, before analyzing the image of the overhead transmission line to be analyzed acquired by the image acquisition device through a preset target detection model, the method also includes: training the preset target detection algorithm based on several first sample images stored in the database to obtain a converged target detection model; wherein the first sample image is a picture containing construction machinery information.

[0014] In a second aspect, an embodiment of the present application also provides a construction machinery early warning device for overhead transmission lines, characterized in that the device includes: a processor; and a memory on which executable code is stored, and when the executable code is executed, the processor executes a method as described in any one of claims 1-8.

[0015] In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium for construction machinery early warning of overhead transmission lines, storing computer executable instructions, characterized in that the computer executable instructions are configured to: analyze the picture of the overhead transmission line to be analyzed acquired by the image acquisition device through a preset target detection model to determine whether there is construction machinery in the picture of the overhead transmission line to be analyzed; when it is determined that there is construction machinery in the picture of the overhead transmission line to be analyzed, start the image acquisition device to record a video of the overhead transmission line to be analyzed for a preset time, and analyze the state of the construction machinery in the video of the overhead transmission line to be analyzed; wherein the state of the construction machinery includes the movement state of the construction machinery, the state of the construction machinery includes the working state of the construction machinery, and the position of the construction machinery; based on the state of the construction machinery in the video of the overhead transmission line to be analyzed, determine the alarm level, and issue an alarm based on the alarm level. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 A flow chart of a construction machinery early warning method for overhead power transmission lines provided in an embodiment of the present application;

[0018] Figure 2 An overhead power transmission line image to be analyzed is processed by a preset sky segmentation model provided in an embodiment of the present application;

[0019] Figure 3 A schematic diagram for describing an overhead transmission line picture to be analyzed provided in an embodiment of the present application;

[0020] Figure 4 An overhead transmission line picture to be analyzed containing overhead transmission line protection channel information provided in an embodiment of the present application;

[0021] Figure 5 A schematic structural diagram of a construction machinery early warning device for overhead power transmission lines provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0023] The existing construction machinery early warning method for overhead power transmission lines uses a warning method of regularly taking a single image for front-end or back-end analysis, which generally cannot generate an alarm in time before an accident occurs, and thus cannot prevent the construction machinery from touching high voltage electricity and causing a tripping accident in advance. For example, in the invention patent application with application number CN110705414A, it adopts a warning method of regularly taking a single image for back-end analysis, so it only identifies the construction machinery within the power transmission line channel. This method not only brings a large number of tasks for the monitoring center personnel to view the warning images, but also cannot identify the different operating states of the construction machinery and make corresponding alarms.

[0024] The embodiments of the present application provide a construction machinery early warning method, device and medium for overhead power transmission lines, which are used to solve the technical problem that the existing overhead power transmission line early warning method cannot provide early warning of the hidden danger of external damage of overhead power transmission lines caused by construction machinery.

[0025] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0026] Figure 1 A flowchart of a construction machinery early warning method for overhead power lines provided in an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a construction machinery early warning method for overhead power transmission lines, which specifically includes the following steps:

[0027] Step 101: Analyze the image of the overhead power transmission line to be analyzed acquired by the image acquisition device through a preset target detection model to determine whether there is construction machinery in the image of the overhead power transmission line to be analyzed.

[0028] In one embodiment of the present application, construction machinery includes but is not limited to cranes, cement pump trucks, dump trucks, excavators, bulldozers, forklifts, pile drivers, etc. Therefore, before analyzing the overhead power line image to be analyzed acquired by the image acquisition device through a preset target detection model, the embodiment of the present application should also train the target detection algorithm based on a number of first sample images stored in the database to obtain a converged target detection model; wherein the first sample image is an image containing construction machinery information, and the obtained converged target detection model is used to detect the overhead power line image to be analyzed to determine whether the overhead power line image to be analyzed contains construction machinery information.

[0029] It should be noted that, in one embodiment of the present application, target detection models are preset on both the image acquisition device and the server; wherein, the image acquisition device corresponds to the preset first target detection model, and the server corresponds to the preset second target detection model. The overhead power transmission line image to be analyzed can be directly analyzed in the first target detection model of the image acquisition device to improve the analysis efficiency, or the overhead power transmission line image to be analyzed can be input into the second target detection model of the server for analysis to improve the accuracy of the analysis. The target detection algorithm corresponding to the first target detection model includes but is not limited to the YOLO algorithm, the SSD algorithm, etc., which can be selected according to the specific situation, and the present application does not limit it here. The target detection algorithm corresponding to the second target detection model includes but is not limited to the Faster RCNN algorithm, the Cascade RCNN algorithm, etc., which can be selected according to the specific situation, and the present application does not limit it here. It can be understood that the image acquisition device has higher real-time recognition, but due to limited computing power, it cannot use a model with too complex calculations, so the model accuracy index is not as high as the server-side index; the server analysis has a high accuracy index, but when analyzing the overhead power transmission line image to be analyzed, it needs to be transmitted through the network and forwarded to the server for analysis, so the real-time performance is not as good as the image acquisition device. By combining the image acquisition device with server analysis, we can not only ensure the analysis accuracy index, but also solve the problem of real-time analysis.

[0030] In one embodiment of the present application, the image acquisition device acquires an image of an overhead power transmission line to be analyzed at a preset time interval, and inputs the acquired image of the overhead power transmission line to be analyzed into a preset first target detection model for analysis to determine whether there is construction machinery in the image of the overhead power transmission line to be analyzed; in addition, the image acquisition device also extracts an image of the overhead power transmission line to be analyzed at a preset value of images of the overhead power transmission line to be analyzed, and inputs the image into a preset second target detection model in the server for analysis to determine whether there is construction machinery in the image of the overhead power transmission line to be analyzed. The above-mentioned preset time interval and preset value can be determined according to the specific use environment, and the present application does not limit them here.

[0031] Step 102: when it is determined that there is construction machinery in the overhead transmission line image to be analyzed, start the image acquisition device to record a video of the overhead transmission line to be analyzed for a preset time, and analyze the status of the construction machinery in the video of the overhead transmission line to be analyzed.

[0032] It is understandable that different states of construction machinery will bring different degrees of safety hazards to overhead transmission lines. For example, a crane in operation within the protection channel of an overhead transmission line and a crane in non-operation outside the protection channel of an overhead transmission line will bring completely different degrees of safety hazards. Therefore, when it is determined that there are construction machinery in the overhead transmission line image to be analyzed, the overhead transmission line protection channel in the overhead transmission line image to be analyzed should also be determined.

[0033] In one embodiment of the present application, to determine the overhead transmission line protection channel in the overhead transmission line image to be analyzed, first, based on a preset wire detection model and a preset sky segmentation model, the mapping line of the lowest layer of transmission wires in the overhead transmission line image to be analyzed on the ground should be determined.

[0034] Specifically, first, a preset wire detection model is used to determine the bottom layer of transmission wires in the overhead transmission line image to be analyzed, and a first angle of the bottom layer of transmission wires in the overhead transmission line image to be analyzed relative to the horizontal direction is determined; and the overhead transmission line image to be analyzed is processed through a preset sky segmentation model to determine a second angle of rotation of the image acquisition device relative to the ground. Figure 2 An overhead transmission line image to be analyzed is provided in an embodiment of the present application and processed by a preset sky segmentation model, such as Figure 2 As shown, the sky and the ground in the overhead transmission line image to be analyzed are separated by a preset sky segmentation model, so as to determine the angle ε of the ground relative to the horizontal direction in the overhead transmission line image to be analyzed. Figure 2 As shown, it can be understood that the angle of rotation of the image acquisition device relative to the ground is the angle of rotation of its lens in a clockwise or counterclockwise direction with the center point of the lens as the center of the circle, and the image acquisition device as a whole is displayed as an angle of rotation relative to the ground; because the image acquisition device obtains the picture at the current rotation angle relative to the ground, and the horizontal direction of the ground is the only constant, the angle of the ground in the picture of the overhead transmission line to be analyzed relative to the horizontal direction of the picture is equal to the second angle of rotation of the image acquisition device relative to the ground.

[0035] After the first angle and the second angle are determined, a third angle of the mapping line relative to the horizontal direction in the overhead transmission line image to be analyzed is determined based on the first angle and the second angle. Figure 3A schematic diagram of describing an overhead transmission line image to be analyzed provided in an embodiment of the present application, such as Figure 3 As shown, the first angle of the bottom transmission wire relative to the horizontal direction in the overhead transmission line image to be analyzed is θ, the second angle of the image acquisition device relative to the ground is ε, and the third angle of the mapping line relative to the horizontal direction in the overhead transmission line image to be analyzed is α. It can be understood that Figure 3 In a rectangular coordinate system with the horizontal direction as the x-axis, the vertical direction as the y-axis, and the right semi-axis as the positive direction of the x-axis, the relationship among the first angle θ, the second angle ε, and the third angle α is α=-θ+ε.

[0036] After determining the third angle, the position of the transmission tower supporting the transmission line is identified by the wire detection model, and the mapping line of the lowest layer of the transmission line on the ground in the overhead transmission line image to be analyzed is determined.

[0037] In one embodiment of the present application, after determining the mapping line of the lowest layer of transmission wires on the ground in the overhead transmission line image to be analyzed, the overhead transmission line protection channel in the overhead transmission line image to be analyzed is determined based on the lowest layer of transmission wires and the mapping line. Figure 4 An overhead transmission line image to be analyzed containing overhead transmission line protection channel information is provided in an embodiment of the present application, such as Figure 4 As shown, in the overhead transmission line image to be analyzed, an overhead transmission line protection channel is formed by two bottom-layer transmission wires and two mapping lines on the ground.

[0038] It should be noted that before determining the mapping line of the lowest layer of transmission wires on the ground in the overhead transmission line image to be analyzed based on the preset wire detection model and the preset sky segmentation model, the wire detection algorithm should also be trained based on several second sample images stored in the database to obtain a converged wire detection model; wherein the second sample image is an image containing overhead transmission wire information; the wire detection algorithm corresponding to the wire detection model includes but is not limited to hough transform, which can be selected according to specific circumstances, and this application does not limit it here. And based on several third sample images stored in the database, the sky segmentation algorithm is trained to obtain a converged sky segmentation model; wherein the third sample image is an image containing both sky information and ground information; the sky segmentation algorithm corresponding to the sky segmentation model includes but is not limited to segmentation algorithms such as deeplabv3, which can be selected according to specific circumstances, and this application does not limit it here.

[0039] In one embodiment of the present application, when it is determined that there is construction machinery in the image of the overhead transmission line to be analyzed, the image acquisition device is also started to record a video of the overhead transmission line to be analyzed for a preset time, and the state of the construction machinery in the video of the overhead transmission line to be analyzed is analyzed. It should be noted that the preset time can be determined according to the specific situation, and this application does not limit it here.

[0040] Specifically, first determine the overhead transmission line protection channel in the overhead transmission line video to be analyzed. It can be understood that the position where the image acquisition device acquires the overhead transmission line image to be analyzed is the same as the position where the overhead transmission line video to be analyzed is acquired. Therefore, the overhead transmission line protection channel determined based on the overhead transmission line image to be analyzed can be directly applied to the overhead transmission line video to be analyzed without the need to perform the process of determining the protection channel again.

[0041] Then, the motion state of the construction machinery is analyzed through the preset target detection model, and whether the construction machinery is in the overhead transmission line protection channel is analyzed. When analyzing the motion state of the construction machinery, a frame of the overhead transmission line video to be analyzed is extracted every preset number of frames as the video picture to be analyzed, and the position of the construction machinery in the video picture to be analyzed is determined through the target detection model; based on the position change of the construction machinery in the extracted video pictures to be analyzed, the motion state of the construction machinery is determined; wherein, the motion state of the construction machinery includes being stationary, close to the overhead transmission line protection channel, and away from the overhead transmission line protection channel. It should be noted that the preset number of frames can be determined according to the specific situation, and this application does not limit it here. When analyzing whether the construction machinery is in the overhead transmission line protection channel, by judging whether the detection frame corresponding to the construction machinery determined by the target detection model overlaps with the overhead transmission line protection channel, it is judged whether the construction machinery is in the overhead transmission line protection channel.

[0042] In addition, the aspect ratio of the construction machinery is analyzed through a preset target edge detection model to determine the working state of the construction machinery; wherein the working state includes an operating state and a non-operating state. When it is determined that the height of the construction machinery is greater than a preset multiple of the width, the working state of the construction machinery is determined to be an operating state; when it is determined that the height of the construction machinery is less than a preset multiple of the width, the working state of the construction machinery is determined to be a non-operating state. It should be noted that the preset multiple can be determined according to the specific situation, and this application does not limit it here.

[0043] It is understandable that the construction machinery information analyzed by the target edge detection model is obtained based on the target detection model analysis. It should also be noted that before analyzing the aspect ratio of the construction machinery through the preset target edge detection model, the target edge detection algorithm should be trained based on several fourth sample images stored in the database to obtain a converged target edge detection model; wherein the fourth sample image is a picture containing sky information and ground information; the target edge detection algorithm corresponding to the target edge detection model includes but is not limited to the yolov3 target detection algorithm, which can be selected according to the specific situation, and this application does not limit it here.

[0044] It should be noted that the image acquisition device in the embodiment of the present application can analyze the state of the construction machinery in the overhead power line video to be analyzed simultaneously with the recording process to ensure the real-time nature of the early warning.

[0045] Step 103: Determine an alarm level based on the state of the construction machinery in the overhead power line video to be analyzed, and issue an alarm based on the alarm level.

[0046] In one embodiment of the present application, after determining the state of the construction machinery in the overhead transmission line video to be analyzed, the position of the construction machinery is first judged to determine whether the construction machinery is in a protection channel. When it is determined that the construction machinery is in the protection channel, the working state of the construction machinery is then judged, and the alarm level is determined according to the working state of the construction machinery; when it is determined that the construction machinery is outside the protection channel, the working state of the construction machinery is judged. If the working state of the construction machinery is determined to be an operating state, the corresponding alarm level is directly determined; if the working state of the construction machinery is determined to be a non-operating state, the alarm level is further determined according to the movement state of the construction machinery.

[0047] Specifically: when the construction machinery is in the protection channel of the overhead transmission line and the working state is the operating state, the alarm level is determined to be the first-level alarm; when the construction machinery is in the protection channel of the overhead transmission line and the working state is the non-operating state, the alarm level is determined to be the second-level alarm; when the construction machinery is outside the protection channel of the overhead transmission line and the working state is the operating state, the alarm level is determined to be the second-level alarm; when the construction machinery is outside the protection channel of the overhead transmission line and the working state is the non-operating state, and the movement state is close to the protection channel of the overhead transmission line, the alarm level is determined to be the second-level alarm; when the construction machinery is outside the protection channel of the overhead transmission line and the working state is the non-operating state, and the movement state is away from the protection channel of the overhead transmission line, the alarm level is determined to be the third-level alarm; when the construction machinery is outside the protection channel of the overhead transmission line, the working state is the non-operating state, and the movement state is stationary, the alarm level is determined to be the third-level alarm.

[0048] In one embodiment of the present application, after the alarm level is determined, a corresponding alarm is sent to a monitoring center or a device terminal according to different alarm levels.

[0049] Based on the same inventive concept, the present application also provides a construction machinery warning device for overhead power transmission lines, the structural diagram of which is shown in FIG. Figure 5 shown.

[0050] Figure 5 This is a schematic diagram of the structure of a construction machinery warning device for overhead power lines provided in an embodiment of the present application. Figure 5 As shown, a construction machinery early warning device 500 for overhead power transmission lines provided in an embodiment of the present application includes: a processor 501; a memory 502, on which executable instructions are stored. When the executable instructions are executed, the processor 501 executes a construction machinery early warning method for overhead power transmission lines as described above.

[0051] In one embodiment of the present application, the processor 501 is used to analyze the image of the overhead transmission line to be analyzed acquired by the image acquisition device through a preset target detection model to determine whether there is construction machinery in the image of the overhead transmission line to be analyzed; it is also used to start the image acquisition device to record a video of the overhead transmission line to be analyzed for a preset time when it is determined that there is construction machinery in the image of the overhead transmission line to be analyzed, and analyze the state of the construction machinery in the video of the overhead transmission line to be analyzed; it is also used to determine the alarm level based on the state of the construction machinery in the video of the overhead transmission line to be analyzed, and to issue an alarm based on the alarm level.

[0052] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for early warning of construction machinery of overhead power transmission lines stores computer executable instructions, wherein the computer executable instructions are set as follows:

[0053] The image of the overhead transmission line to be analyzed acquired by the image acquisition device is analyzed by using a preset target detection model to determine whether there is construction machinery in the image of the overhead transmission line to be analyzed;

[0054] When it is determined that there is construction machinery in the image of the overhead transmission line to be analyzed, the image acquisition device is started to record a video of the overhead transmission line to be analyzed for a preset time, and the state of the construction machinery in the video of the overhead transmission line to be analyzed is analyzed;

[0055] Based on the state of the construction machinery in the overhead power line video to be analyzed, an alarm level is determined, and an alarm is issued based on the alarm level.

[0056] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0057] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0058] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0059] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0060] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0062] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0063] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0064] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0065] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0066] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A construction machinery early warning method for overhead power transmission lines, characterized in that: The method comprises: Analyzing the overhead transmission line image to be analyzed acquired by the image acquisition device through a preset target detection model to determine whether there is construction machinery in the overhead transmission line image to be analyzed; When it is determined that there is a construction machine in the overhead transmission line image to be analyzed, the image acquisition device is started to record a video of the overhead transmission line to be analyzed for a preset time, and the state of the construction machine in the video of the overhead transmission line to be analyzed is analyzed; wherein the state of the construction machine includes the movement state of the construction machine, the state of the construction machine includes the working state of the construction machine, and the position of the construction machine; Determining an alarm level based on the state of the construction machinery in the overhead power transmission line video to be analyzed, and issuing an alarm based on the alarm level; Before starting the image acquisition device to record a video of the overhead power transmission line to be analyzed for a preset time and analyzing the state of the construction machinery in the video of the overhead power transmission line to be analyzed, the method further includes: Based on a preset wire detection model and a preset sky segmentation model, a mapping line of the lowest layer of transmission wires in the overhead transmission line image to be analyzed on the ground is determined; wherein the lowest layer of transmission wires is a layer of overhead transmission lines that is closest to the ground in the overhead transmission line image to be analyzed; Determining an overhead transmission line protection channel in the overhead transmission line image to be analyzed based on the bottom layer transmission wire and the mapping line; Based on the preset wire detection model and the preset sky segmentation model, the mapping line of the lowest layer of transmission wires in the overhead transmission line image to be analyzed on the ground is determined, specifically including: Determine the lowest layer of transmission wires in the overhead transmission line image to be analyzed by using a preset wire detection model, and determine a first angle of the lowest layer of transmission wires relative to the horizontal direction in the overhead transmission line image to be analyzed; Processing the overhead power line image to be analyzed by a preset sky segmentation model to determine a second angle at which the image acquisition device rotates relative to the ground; Based on the first angle and the second angle, a third angle of the mapping line relative to the horizontal direction in the overhead transmission line image to be analyzed is determined to determine the mapping line.

2. A construction machinery early warning method for overhead power transmission lines according to claim 1, characterized in that: Analyzing the state of the construction machinery in the overhead transmission line video to be analyzed, specifically including: Determining the overhead power transmission line protection channel in the overhead power transmission line video to be analyzed; Analyzing the motion state of the construction machinery and analyzing whether the construction machinery is within the overhead power line protection channel through a preset target detection model; The aspect ratio of the construction machinery is analyzed through a preset target edge detection model to determine the working state of the construction machinery; wherein the working state includes an operating state and a non-operating state.

3. A construction machinery early warning method for overhead power transmission lines according to claim 2, characterized in that: The motion state of the construction machinery is analyzed by a preset target detection model, specifically including: Extracting a frame of the overhead transmission line video to be analyzed as a video picture to be analyzed every preset number of frames, and determining the position of the construction machinery in the video picture to be analyzed by using the target detection model; Based on the position changes of the construction machinery in several extracted video images to be analyzed, the motion state of the construction machinery is determined; wherein the motion state of the construction machinery includes being stationary, close to the overhead transmission line protection channel, and far away from the overhead transmission line protection channel.

4. A construction machinery early warning method for overhead power transmission lines according to claim 3, characterized in that: Based on the state of the construction machinery in the overhead transmission line video to be analyzed, the alarm level is determined, specifically including: When the construction machinery is in the overhead power transmission line protection channel and the working state is the operation state, determining the alarm level to be a first-level alarm; When the construction machinery is in the overhead power transmission line protection channel and the working state is a non-operating state, determining the alarm level to be a level 2 alarm; When the construction machinery is outside the overhead power transmission line protection channel and the working state is an operation state, determining the alarm level to be a level 2 alarm; When the construction machinery is outside the overhead transmission line protection channel, the working state is a non-operating state, and the moving state is close to the overhead transmission line protection channel, the alarm level is determined to be a level 2 alarm; When the construction machinery is outside the overhead transmission line protection channel, the working state is a non-operating state, and the moving state is far away from the overhead transmission line protection channel, the alarm level is determined to be a level 3 alarm; When the construction machinery is outside the protection channel of the overhead power transmission line, the working state is a non-operating state, and the moving state is stationary, the alarm level is determined to be a level three alarm.

5. The construction machinery early warning method for overhead power transmission lines according to claim 1, characterized in that: The image of the overhead transmission line to be analyzed acquired by the image acquisition device is analyzed by using a preset target detection model to determine whether there is construction machinery in the image of the overhead transmission line to be analyzed, specifically including: Inputting the overhead transmission line image to be analyzed into a first target detection model preset in the image acquisition device to determine whether there is construction machinery in the overhead transmission line image to be analyzed; wherein the first target detection model is a target detection model; and / or The overhead transmission line image to be analyzed is input into a second target detection model preset in the server to determine whether there is construction machinery in the overhead transmission line image to be analyzed; wherein the second target detection model is a target detection model.

6. The construction machinery early warning method for overhead power transmission lines according to claim 1, characterized in that: Before analyzing the overhead transmission line image to be analyzed acquired by the image acquisition device through the preset target detection model, the method further includes: Based on a number of first sample images stored in a database, a preset target detection algorithm is trained to obtain a converged target detection model; wherein the first sample images are images containing construction machinery information.

7. A construction machinery early warning device for overhead power transmission lines, characterized in that: The device comprises: processor; and a memory having executable codes stored thereon, which, when the executable codes are executed, enable the processor to execute a method as described in any one of claims 1 to 6.

8. A non-volatile computer storage medium for early warning of construction machinery for overhead power transmission lines, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Analyzing the overhead transmission line image to be analyzed acquired by the image acquisition device through a preset target detection model to determine whether there is construction machinery in the overhead transmission line image to be analyzed; When it is determined that there is a construction machine in the overhead transmission line image to be analyzed, the image acquisition device is started to record a video of the overhead transmission line to be analyzed for a preset time, and the state of the construction machine in the video of the overhead transmission line to be analyzed is analyzed; wherein the state of the construction machine includes the movement state of the construction machine, the state of the construction machine includes the working state of the construction machine, and the position of the construction machine; Determining an alarm level based on the state of the construction machinery in the overhead power transmission line video to be analyzed, and issuing an alarm based on the alarm level; Before starting the image acquisition device to record a video of the overhead power transmission line to be analyzed for a preset time and analyzing the state of the construction machinery in the video of the overhead power transmission line to be analyzed, the method further includes: Based on a preset wire detection model and a preset sky segmentation model, a mapping line of the lowest layer of transmission wires in the overhead transmission line image to be analyzed on the ground is determined; wherein the lowest layer of transmission wires is a layer of overhead transmission lines that is closest to the ground in the overhead transmission line image to be analyzed; Determining an overhead transmission line protection channel in the overhead transmission line image to be analyzed based on the bottom layer transmission wire and the mapping line; Based on the preset wire detection model and the preset sky segmentation model, the mapping line of the lowest layer of transmission wires in the overhead transmission line image to be analyzed on the ground is determined, specifically including: Determine the lowest layer of transmission wires in the overhead transmission line image to be analyzed by using a preset wire detection model, and determine a first angle of the lowest layer of transmission wires relative to the horizontal direction in the overhead transmission line image to be analyzed; Processing the overhead power line image to be analyzed by a preset sky segmentation model to determine a second angle at which the image acquisition device rotates relative to the ground; Based on the first angle and the second angle, a third angle of the mapping line relative to the horizontal direction in the overhead transmission line image to be analyzed is determined to determine the mapping line.

Images