Power transmission line inspection method with prediction function, equipment and medium
By performing frame extraction analysis and point cloud ranging on the inspection video, predicting the three-dimensional action range of the hidden danger target and generating alarm information, the problem of inaccurate prediction of the degree of hidden danger and early warning in the existing technology is solved, and the inspection of transmission lines is improved efficiency and safety.
Patent Information
- Application Number
- CN202410959291.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-12
AI Technical Summary
The existing transmission line inspection methods cannot accurately predict the degree of harm to the transmission line by hidden danger targets, and cannot be warned in advance, resulting in large inspection workloads, undetected hidden dangers in time, and may even lead to power outages.
By performing frame extraction analysis on the inspection video, the best image of the hidden danger target is determined, and three-dimensional ranging is used to measure the point cloud mapping relationship, determining the three-dimensional action range of the hidden danger target within the preset time period, generating alarm information and inspection distance Images to achieve predictive monitoring of hidden danger targets.
It improves the efficiency of hidden danger target identification, reduces the workload of staff to check, can be early warning, reduces the risk of power outages, and enhances the safety of transmission lines.
Smart Images

Figure CN118942169A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of online monitoring, and specifically to a transmission line inspection method, equipment and medium with a prediction function. Background Art
[0002] In recent years, with the development of communication technology and artificial intelligence, intelligent inspection devices for power transmission lines have been promoted and applied on a large scale. Compared with traditional manual inspection methods, the inspection efficiency has been greatly improved. These inspection devices generate thousands of inspection pictures every day. After identification and filtering by the front-end intelligent analysis module, the number of alarm pictures is greatly reduced, which improves the inspection efficiency of power transmission hazards.
[0003] In order to further improve the recognition efficiency of hidden danger targets, the laser point cloud and visualization device are combined. Through fusion calibration, the hidden danger targets in the image have the three-dimensional characteristics of the laser point cloud, and the quantitative detection of hidden dangers to the wires is realized. The shortest distance from the hidden danger vehicle to the wires is output, and the number of warning pictures is further reduced through early warning classification management, which improves the inspection efficiency.
[0004] The above method can meet the needs of transmission channel field detection to a certain extent and quantify the distance from the hidden danger target to the conductor of the transmission line, but it still has shortcomings, as follows:
[0005] During the early warning, the distance from the hidden danger target to the wire is the hidden danger distance measurement at the time of taking the photo. When the hidden danger target is not stretched out, the measured distance may not be within the designated early warning range, resulting in missed detection of the hidden danger target, leaving hidden dangers for the transmission line. The measured hidden danger image distance measurement information only indicates the current hidden danger status, and has no predictive value for the subsequent window period or subsequent time of the hidden danger target, and cannot evaluate the degree of harm of the hidden danger target to the transmission line.
[0006] This has greatly increased the work pressure of the inspection personnel. The degree of hidden dangers cannot be accurately determined through image detection, and future hidden dangers cannot be predicted through laser point cloud quantitative detection. If real-time video monitoring is turned on, the power consumption is too high and early warning cannot be provided. There are many warning images for transmission lines, and the inspection workload is large. Failure to inspect in time will cause huge hidden dangers to the transmission lines, and in serious cases, it will cause power outages. Summary of the invention
[0007] In order to solve the above problems, the present application proposes a transmission line inspection method, device and medium with a prediction function, wherein the method includes:
[0008] By performing frame sampling analysis on the inspection video, the best hidden danger images corresponding to all hidden danger targets in the inspection video are determined; using the mapping relationship between the best hidden danger image and the point cloud, three-dimensional distance measurement is performed on the hidden danger target to obtain the distance measurement information corresponding to the hidden danger target; based on the distance measurement information, the three-dimensional movement range of the hidden danger target within a preset time period is determined; based on the three-dimensional movement range, alarm information and inspection distance images are generated.
[0009] In one example, the frame sampling analysis of the inspection video is performed to determine the best hidden danger images corresponding to all hidden danger targets in the inspection video, which specifically includes: sampling the inspection video to obtain multiple inspection video frames; performing image recognition on the multiple inspection video frames to determine whether there is a specified view of a preset recognition object in the inspection video frame; if there is a specified view of the preset recognition object in the inspection video frame, the inspection video frame is the best hidden danger image; the preset recognition object includes at least one of a boom and an excavator; and the specified view is a side view.
[0010] In one example, the distance measurement information includes at least one of the vehicle height of the hidden danger target, the length of each joint mechanical arm, and the wheel spacing.
[0011] In one example, determining the three-dimensional motion range of the hidden danger target within a preset time period based on the ranging information specifically includes: determining the extended motion range of the hidden danger target at different time points based on the ranging information; determining the predicted movement range of the hidden danger target based on the inspection video; and determining the three-dimensional motion range of the hidden danger target within a preset time period based on the extended motion range and the predicted movement range.
[0012] In one example, determining the extension movement range of the hidden danger target at different time points based on the ranging information specifically includes: determining the number of extended mechanical arms and the number of unextended mechanical arms of the hidden danger target based on the optimal hidden danger image; determining the extension movement range of the hidden danger target based on the number of extended mechanical arms, the number of unextended mechanical arms, the mechanical lengths of each joint, and the vehicle body height.
[0013] In one example, determining the three-dimensional motion range of the hidden danger target within a preset time period based on the stretching motion range and the predicted moving range specifically includes: determining the displacement information of the hidden danger target based on the inspection video, the displacement information including moving direction, moving speed, and moving acceleration information; determining the predicted moving range of the hidden danger target within the preset time period based on the displacement information; determining the three-dimensional motion range of the hidden danger target within the preset time period with the vertical coordinate of each point in the predicted moving range as the center and the stretching motion range corresponding to the hidden danger target at different heights as the radius.
[0014] In one example, the generating of alarm information and inspection distance image based on the three-dimensional motion range specifically includes: if there is an overlapping part between the three-dimensional motion range and the preset alarm range, generating alarm information and sending the alarm information to the staff; if there is no overlapping part between the three-dimensional motion range and the preset alarm range, determining the inspection distance between the hidden danger target in the optimal hidden danger image and the preset alarm target; generating the inspection distance image based on the inspection distance and the optimal hidden danger image.
[0015] In one example, the method is applied to a radar monitoring device, which includes an intelligent control module, a charging management module, a rechargeable battery, a gimbal, a lidar, a visible light camera, a temperature and humidity sensor, and an IMU tilt sensor.
[0016] The present application also provides a power transmission line inspection device with a prediction function, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute: determining the best hidden danger images corresponding to all hidden danger targets in the inspection video by performing frame analysis on the inspection video; performing three-dimensional ranging on the hidden danger targets by utilizing the mapping relationship between the best hidden danger image and the point cloud to obtain ranging information corresponding to the hidden danger targets; determining the three-dimensional motion range of the hidden danger targets within a preset time period based on the ranging information; and generating alarm information and an inspection distance image based on the three-dimensional motion range.
[0017] The present application also provides a non-volatile computer storage medium storing computer executable instructions, characterized in that the computer executable instructions are configured to: determine the best hidden danger images corresponding to all hidden danger targets in the inspection video by performing frame analysis on the inspection video; perform three-dimensional ranging on the hidden danger targets by utilizing the mapping relationship between the best hidden danger images and the point cloud to obtain ranging information corresponding to the hidden danger targets; determine the three-dimensional motion range of the hidden danger targets within a preset time period based on the ranging information; and generate alarm information and an inspection distance image based on the three-dimensional motion range.
[0018] The method proposed in this application can bring the following beneficial effects: BRIEF DESCRIPTION OF THE DRAWINGS
[0019] 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:
[0020] Figure 1 A schematic diagram of a flow chart of a power transmission line inspection method with a prediction function in an embodiment of the present application;
[0021] Figure 2 This is a schematic diagram of the structure of a radar monitoring device in an embodiment of the present application;
[0022] Figure 3 This is a schematic diagram of an inspection distance image in an embodiment of the present application;
[0023] Figure 4 It is a structural schematic diagram of a power transmission line inspection device with a prediction function in an embodiment of the present application. DETAILED DESCRIPTION
[0024] 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.
[0025] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0026] Figure 1A flow chart of a transmission line inspection method with a prediction function provided for one or more embodiments of this specification. The method can be applied to inspect potential targets (such as cranes, excavators) in the construction area. When inspecting, it is necessary to determine the distance between the potential target and the transmission line. If the distance is close, a construction hazard may occur and an early warning is required. The process can be executed by a computing device in the construction area, and some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.
[0027] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.
[0028] It should be noted that the server can be a single device or a system composed of multiple devices, that is, a distributed server, and this application does not make any specific limitations on this.
[0029] like Figure 1 As shown, the embodiment of the present application provides a transmission line inspection method with a prediction function, comprising:
[0030] S101: Determine the best hidden danger images corresponding to all hidden danger targets in the inspection video by performing frame sampling analysis on the inspection video.
[0031] Through Figure 2 The radar monitoring device shown obtains inspection videos. The radar monitoring device here is mainly composed of an intelligent control module, a charging management module, a rechargeable battery, a gimbal, a laser radar, a visible light camera, a temperature and humidity sensor, and an IMU tilt sensor.
[0032] Among them, the intelligent control module has powerful computing power, can perform front-end intelligent analysis, identify hidden danger data in the image, and process point cloud data to realize the analysis and ranging functions of three-dimensional point cloud data, realize conventional external hidden danger inspection and line ice inspection tasks, and the processing results are transmitted to the control center via 4G / 5G. The rechargeable battery is charged and the system is powered by solar panels, with overcurrent, overvoltage and lightning protection functions. The temperature and humidity sensor realizes the temperature and humidity collection function in the environment. At low temperatures, the heating function is triggered to keep the battery active. At low temperatures and high humidity, the lens heating function can be turned on to prevent the lens from fogging. The visible light camera collects images of the transmission line channel and the body. When hidden dangers are found through intelligent identification, the radar scan is triggered to realize three-dimensional measurement of hidden danger targets. There are visible light cameras, radars and IMU attitude acquisition modules on the gimbal. When the gimbal rotates, the IMU can record the angle of rotation of the gimbal. When the point cloud moves and scans, the IMU provides attitude information to splice and synthesize the point cloud. The visible light camera and radar lens sides have heating defogging and ice melting functions to prevent the lenses from fogging and icing. The heating device power is 5W.
[0033] Before the equipment starts working, it is necessary to carry out identification training for hidden danger targets. The training is carried out using a neural network algorithm to complete the training of the characteristics of the hidden danger targets, the joints of the boom, the vehicle body, and the joints of the mechanical arm. After the training is completed, the inspection operation is started; before the inspection begins, the internal and external parameters of the camera need to be calibrated, and the relative position relationship of the image point cloud needs to be calibrated; when the inspection starts, the inspection video is firstly extracted to obtain multiple inspection video frames, and then image recognition is performed on the multiple inspection video frames to determine whether there is a specified view of the preset identification object in the inspection video frame; if there is a specified view of the preset identification object in the inspection video frame, the inspection video frame is the best hidden danger image; the best hidden danger image point is generally the side view of the hidden danger vehicle such as the boom and excavator.
[0034] S102: Perform three-dimensional distance measurement on the hidden danger target by using the mapping relationship between the optimal hidden danger image and the point cloud to obtain distance measurement information corresponding to the hidden danger target.
[0035] For the best hidden danger image obtained, the mapping relationship between the image and the point cloud is used to perform three-dimensional distance measurement of the hidden danger target, so as to obtain the distance measurement information corresponding to the hidden danger target. The distance measurement information here includes the vehicle height of the hidden danger target, the length of each joint mechanical arm, the wheel spacing and other information.
[0036] S103: Determine the three-dimensional motion range of the hidden danger target within a preset time period based on the distance measurement information.
[0037] By using information such as the vehicle height and the length of each joint robot arm in the ranging information, the maximum construction action range of the hidden danger target is predicted, that is, the three-dimensional action range of the hidden danger target within the preset time period is predicted.
[0038] Specifically, when determining the three-dimensional motion range, first determine the extended motion range of the hidden danger target at different time points through the distance measurement information; and determine the predicted movement range of the hidden danger target based on the inspection video. The three-dimensional motion range of the hidden danger target within the preset time period can be determined through the extended motion range and the predicted movement range.
[0039] Furthermore, when determining the extension range, it is necessary to determine the number of extended mechanical arms and the number of unextended mechanical arms of the hidden danger target in the best hidden danger image based on the best hidden danger image, and then determine the extension range of the hidden danger target based on the number of extended mechanical arms, the number of unextended mechanical arms, the mechanical length of each joint, and the vehicle height. In addition to the above methods, the extension range can also be calculated by querying and matching the corresponding vehicle information from the special vehicle registration website through the wheel spacing of the hidden danger target. Or by identifying the nameplate logo of the hidden danger target, extracting the corresponding product information, checking the vehicle registration information from the Internet, and calculating the extension range through the vehicle height and arm raising information.
[0040] When determining the predicted movement range, it is necessary to determine the displacement information of the hidden danger target based on the inspection video, including the movement direction, movement speed, movement acceleration information, etc., and then a simple prediction of the predicted movement range of the hidden danger target within the preset time period can be made based on the displacement information. After obtaining the predicted movement range and the stretching range, it is necessary to determine the three-dimensional movement range of the hidden danger target within the preset time period with the vertical coordinate of each point in the predicted movement range as the center and the stretching range of the hidden danger target at different heights as the radius.
[0041] S104: Generate warning information and inspection distance image based on the three-dimensional action range.
[0042] After determining the three-dimensional motion range of the hidden danger target, alarm information and inspection distance images can be generated based on the three-dimensional motion range. By sending the alarm information and inspection distance images to the staff, the staff's investigation work can be reduced and the inspection efficiency can be improved.
[0043] Specifically, if there is an overlap between the three-dimensional motion range and the preset alarm range, an alarm message is generated and sent to the staff. When the maximum value of the hidden danger target construction action is less than the set value, the distance measurement image information and high-level alarm information are output to the platform or the mobile phone of the relevant responsible person. This operation is likely to face the risk of electric shock of construction vehicles. First, it may cause life safety issues for construction workers, and second, it may cause power outages and affect the reliability of power supply. The preset alarm range here refers to the area close to the transmission line. The set value is generally the safe discharge distance of the transmission line of the corresponding level plus a certain threshold. For example, for a 220kV line, the preset alarm range is the area within 4 meters of the transmission line. If there is no overlap between the three-dimensional motion range and the preset alarm range, the inspection distance between the hidden danger target and the preset alarm target in the best hidden danger image is determined. Based on the inspection distance and the best hidden danger image, the following can be generated. Figure 3 The inspection distance image shown. When the inspection distance image is uploaded to the platform, it will not trigger an alarm signal or a low-level alarm, so users can ignore it or pay little attention to it.
[0044] It should be noted that for hidden danger targets at a long distance, the data collected by the radar and the laser point cloud data collected by the drone can be fused to achieve three-dimensional measurement of the hidden danger targets, thereby calculating the three-dimensional movement range of the hidden danger targets.
[0045] like Figure 4 As shown, the embodiment of the present application further provides a power transmission line inspection device with a prediction function, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can:
[0046] By performing frame sampling analysis on the inspection video, the best hidden danger images corresponding to all hidden danger targets in the inspection video are determined; using the mapping relationship between the best hidden danger image and the point cloud, three-dimensional distance measurement is performed on the hidden danger target to obtain the distance measurement information corresponding to the hidden danger target; based on the distance measurement information, the three-dimensional movement range of the hidden danger target within a preset time period is determined; based on the three-dimensional movement range, alarm information and inspection distance images are generated.
[0047] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:
[0048] By performing frame sampling analysis on the inspection video, the best hidden danger images corresponding to all hidden danger targets in the inspection video are determined; using the mapping relationship between the best hidden danger image and the point cloud, three-dimensional distance measurement is performed on the hidden danger target to obtain the distance measurement information corresponding to the hidden danger target; based on the distance measurement information, the three-dimensional movement range of the hidden danger target within a preset time period is determined; based on the three-dimensional movement range, alarm information and inspection distance images are generated.
[0049] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0050] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
[0051] 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.
[0052] 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.
[0053] 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.
[0054] 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.
[0055] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0056] 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.
[0057] 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 transitory media such as modulated data signals and carrier waves.
[0058] 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.
[0059] 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 transmission line inspection method with prediction function, It is characterized in that include: By performing frame extraction analysis on the inspection video, the best hidden danger images corresponding to all hidden danger targets in the inspection video are determined; Using the mapping relationship between the optimal hidden danger image and the point cloud, three-dimensional distance measurement is performed on the hidden danger target to obtain distance measurement information corresponding to the hidden danger target; Based on the distance measurement information, determine the three-dimensional motion range of the hidden danger target within a preset time period; Alarm information and an inspection distance image are generated based on the three-dimensional action range.
2. The method according to claim 1, It is characterized in that The step of performing frame extraction analysis on the inspection video to determine the best hidden danger images corresponding to all hidden danger targets in the inspection video includes: Extracting frames of the inspection video to obtain multiple inspection video frames; Performing image recognition on the multiple inspection video frames to determine whether a specified view of a preset recognition object exists in the inspection video frames; If the designated view of the preset recognition object exists in the inspection video frame, the inspection video frame is the optimal hidden danger image; The preset identification object includes at least one of a boom and an excavator; The designated view is a side view.
3. The method according to claim 1, It is characterized in that The distance measurement information includes at least one of the vehicle height of the hidden danger target, the length of each joint mechanical arm, and the wheel spacing.
4. The method according to claim 3, It is characterized in that The determining, based on the distance measurement information, the three-dimensional motion range of the hidden danger target within a preset time period specifically includes: Based on the distance measurement information, determining the extension range of the hidden danger target at different time points; Based on the inspection video, determining the predicted movement range of the hidden danger target; Based on the stretching motion range and the predicted movement range, a three-dimensional motion range of the hidden danger target within a preset time period is determined.
5. The method according to claim 4, It is characterized in that The step of determining the extension range of the hidden danger target at different time points based on the distance measurement information specifically includes: Based on the optimal hidden danger image, determining the number of extended mechanical arms and the number of unextended mechanical arms of the hidden danger target; The extension range of the hidden danger target is determined based on the number of extended mechanical arms, the number of unextended mechanical arms, the mechanical lengths of the joints, and the height of the vehicle body.
6. The method according to claim 5, It is characterized in that The determining, based on the stretching motion range and the predicted movement range, the three-dimensional motion range of the hidden danger target within a preset time period specifically includes: Based on the inspection video, determine the displacement information of the hidden danger target, wherein the displacement information includes moving direction, moving speed, and moving acceleration information; Based on the displacement information, determining the predicted movement range of the hidden danger target within the preset time period; Taking the vertical coordinates of each point in the predicted moving range as the center and the extending movement ranges corresponding to the hidden danger target at different heights as the radius, the three-dimensional movement range of the hidden danger target within the preset time period is determined.
7. The method according to claim 1, It is characterized in that The generating of the warning information and the inspection distance image based on the three-dimensional action range specifically includes: If the three-dimensional motion range overlaps with the preset alarm range, an alarm message is generated and sent to the staff; If the three-dimensional action range does not overlap with the preset warning range, determining the inspection distance between the hidden danger target and the preset warning target in the optimal hidden danger image; The inspection distance image is generated based on the inspection distance and the optimal hidden danger image.
8. The method according to claim 1, It is characterized in that The method is applied to a radar monitoring device, which includes an intelligent control module, a charging management module, a rechargeable battery, a gimbal, a laser radar, a visible light camera, a temperature and humidity sensor, and an IMU tilt sensor.
9. A transmission line inspection device with prediction function, It is characterized in that include: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute: By performing frame extraction analysis on the inspection video, the best hidden danger images corresponding to all hidden danger targets in the inspection video are determined; Using the mapping relationship between the optimal hidden danger image and the point cloud, three-dimensional distance measurement is performed on the hidden danger target to obtain distance measurement information corresponding to the hidden danger target; Based on the distance measurement information, determine the three-dimensional motion range of the hidden danger target within a preset time period; Alarm information and an inspection distance image are generated based on the three-dimensional action range.
10. A non-volatile computer storage medium storing computer executable instructions, It is characterized in that The computer executable instructions are configured to: By performing frame extraction analysis on the inspection video, the best hidden danger images corresponding to all hidden danger targets in the inspection video are determined; Using the mapping relationship between the optimal hidden danger image and the point cloud, three-dimensional distance measurement is performed on the hidden danger target to obtain distance measurement information corresponding to the hidden danger target; Based on the distance measurement information, determine the three-dimensional motion range of the hidden danger target within a preset time period; Alarm information and an inspection distance image are generated based on the three-dimensional action range.
Citation Information
Patent Citations
Construction machinery early warning method and device for overhead power transmission line and medium
CN113869116A
Identification and alarm method and system for external force damage of power transmission line
CN114863357A
Payment method and device based on biological characteristics, equipment and computer storage medium
CN115204884A
Method and device for detecting construction hidden danger around power transmission line and computer equipment
CN116597390A
Power transmission line hidden danger distance measurement method, device, equipment and medium
CN117008138A
Cited By
Power transmission and transformation hidden danger laser point cloud intrusion detection method
CN121074521A
