Power transmission channel external damage prevention monitoring device and method based on radar and visual monitoring

Abstract

The invention provides a power transmission channel external damage prevention monitoring device and method based on radar and visual monitoring. The power transmission channel external damage prevention monitoring device comprises a millimeter wave radar arranged on an electric tower of a power transmission line, camera shooting equipment and a main control box. When a target object exists in the monitoring area, the millimeter wave radar sends radar monitoring data to the main control box; the main control box determines whether a target object enters a tracking area of the camera equipment according to radar monitoring data, and controls the camera equipment to track and shoot the target object; identifying whether the target object is a to-be-repelled target according to the tracked and shot image; according to the device and the method, radar monitoring is carried out on a monitoring area by combining a millimeter wave radar and camera equipment, a target object is accurately tracked and shot in a tracking area with a small range according to radar monitoring data, blind observation of the camera equipment is avoided, and all-day all-weather real-time monitoring is realized; and meanwhile, the false alarm rate is reduced in combination with the type recognition of the target object.

Description

Technical Field

[0001] The present invention belongs to the technical field of power transmission channel anti-external damage monitoring, and particularly relates to a power transmission channel anti-external damage monitoring device and method based on radar and visual monitoring. Background Art

[0002] A transmission channel, or transmission line corridor, refers to a strip of land extending to a specified width below the high-voltage overhead transmission line along the roadside conductors. Within this area, the public is permitted to enter or engage in basic agricultural and other restricted production activities. However, overhead transmission lines have long been subject to damage from external forces, including human activity. This includes construction and the intrusion of large engineering vehicles into transmission line corridors, all of which threaten the safe operation of the transmission lines. Furthermore, the recent expansion of urban areas and the accelerated implementation of infrastructure projects have led to frequent external line damage accidents, seriously affecting the safety of the power grid and on-site construction workers. External damage has become one of the main factors affecting the safe and reliable operation of transmission lines.

[0003] Currently, external damage still relies primarily on manual inspections, resulting in a lack of detection methods. In terms of monitoring methods, two common measures are employed. The first involves regular line inspections, demarcation of protected areas, hanging safety warning signs, and on-site safety training for operators. This approach presents challenges such as high staff requirements, high labor costs, and a lack of oversight. The second approach involves deploying network video surveillance equipment on-site, transmitting video data in real time to a monitoring center via 3G / 4G / 5G. Staff then use real-time viewing or image processing algorithms to assess external damage incidents. However, this approach is susceptible to weather conditions and, due to the viewing angle of the video surveillance equipment, cannot provide timely warnings of external damage incidents.

[0004] Currently, video surveillance is often used to monitor line failures. However, this method has several drawbacks, including limited monitoring range, significant weather impact, the need for infrared assistance at night, and high power consumption. Therefore, a new technology is urgently needed to address these issues. Summary of the Invention

[0005] To overcome the above-mentioned shortcomings of the prior art, the present invention proposes a power transmission channel anti-external damage monitoring device based on radar and visual monitoring, comprising: a millimeter-wave radar, a camera device, and a main control box installed on a power transmission line tower; the millimeter-wave radar and the camera device are respectively connected to the main control box for communication;

[0006] The millimeter-wave radar is used to monitor the monitoring area around the power transmission line around the clock and in all weather conditions; when a target object exists in the monitoring area, the radar monitoring data of the target object is sent to the main control box;

[0007] The main control box is used to determine whether the target object has entered the tracking area of ​​the camera device based on the radar monitoring data of the target object; if it is determined that the target object has entered the tracking area, control the camera device to track and photograph the target object; and identify whether the target object is a target to be driven away based on the image captured by the camera device during tracking.

[0008] Preferably, the main control box is provided with a radar data calculation module, a coordinate conversion module, a shooting control module and a target recognition module; the radar data calculation module and the shooting control module are both communicatively connected to the millimeter-wave radar, and the shooting control module is communicatively connected to the camera device; the target recognition module is communicatively connected to the millimeter-wave radar and the camera device respectively;

[0009] The radar data solving module is used to determine the coordinates of the target object in the radar polar coordinate system according to the radar monitoring data of the target object monitored by the millimeter wave radar;

[0010] The coordinate conversion module is used to convert the coordinates of the target object in the radar polar coordinate system into the plane coordinates in the camera coordinate system according to the relative position relationship between the millimeter wave radar and the camera device;

[0011] The shooting control module is used to control the start and stop of the camera device according to the radar monitoring data of the target object; and control the camera device to track and shoot the target object entering the tracking area according to the plane coordinates of the target object;

[0012] The target recognition module is used to identify whether the target object is a target to be driven away based on the image captured by the camera device and the radar monitoring data of the target object.

[0013] Preferably, the shooting control module is specifically used to:

[0014] When there are multiple target objects in the tracking area, determining the distance between each target object and the power transmission channel according to the radar monitoring data of each target object;

[0015] According to the distance between each target object and the power transmission channel, the camera device is controlled to track, photograph and identify each target object in sequence according to the rule of from near to far.

[0016] Preferably, the shooting control module is specifically used to:

[0017] If it is determined according to the radar monitoring data that the target object enters the monitoring area, the camera device in a dormant state is controlled to start; if it is determined according to the radar monitoring data that there is no target object in the monitoring area, the camera device is controlled to sleep.

[0018] Preferably, the shooting control module is specifically used to:

[0019] When the camera device is in an activated state, if it is detected that the target object enters the tracking area, the camera device is controlled to turn to the target object according to the plane coordinates of the target object and track and shoot the target object.

[0020] Preferably, the target recognition module is specifically used to:

[0021] Using a feature extraction network to extract features from the image captured by the camera device; classifying the target object in the image based on the extracted image features to determine whether the size of the target object exceeds a preset safety size limit;

[0022] determining, based on the radar monitoring data of the target object, whether the target object is in a moving state;

[0023] The target object whose size exceeds the preset safety size limit and is in a moving state is identified as the target to be driven away.

[0024] Preferably, the apparatus further comprises an alarm device, and the main control box further comprises an alarm control module, wherein the alarm control module is communicatively connected to the alarm device and the millimeter wave radar respectively;

[0025] The alarm control module is used to obtain radar monitoring data of the target object monitored by the millimeter-wave radar. When the target object invades the alarm area of ​​the camera device, the target recognition module obtains the recognition result of the target object; when the recognition result of the target object is the target to be expelled, a signal is sent to the alarm device to control the action of the alarm device, and then the target to be expelled in the alarm area is warned and expelled, and the management end is notified for processing.

[0026] Based on the same inventive concept, the present invention also provides a method for monitoring power transmission channels against external damage based on radar and visual monitoring, which uses the above-mentioned power transmission channel against external damage monitoring device, including:

[0027] The main control box receives radar monitoring data of the target object monitored by the millimeter wave radar in the power transmission channel anti-external damage monitoring device;

[0028] The main control box determines whether the target object has entered the tracking area of ​​the camera equipment in the power transmission channel anti-external damage monitoring device based on the radar monitoring data of the target object; if it is determined that the target object has entered the tracking area, the camera equipment is controlled to track and photograph the target object; and the target object is identified as a target to be driven away based on the image captured by the tracking device.

[0029] Preferably, the main control box determines whether the target object enters the tracking area of ​​the camera device in the power transmission channel anti-external damage monitoring device based on the radar monitoring data of the target object, and the tracking area is included in the monitoring area; if it is determined that the target object enters the tracking area, the camera device is controlled to track and photograph the target object; and the target object is identified as a target to be driven away based on the image captured by the tracking camera device, including:

[0030] determining the coordinates of the target object in a radar polar coordinate system according to radar monitoring data of the target object monitored by the millimeter wave radar;

[0031] Converting the target object's coordinates in the radar's polar coordinate system into planar coordinates in the camera's coordinate system based on the relative positional relationship between the millimeter-wave radar and the camera device;

[0032] Controlling the start and stop of the camera device according to the radar monitoring data of the target object; and controlling the camera device to track and photograph the target object entering the tracking area according to the plane coordinates of the target object;

[0033] According to the images captured by the camera device and the radar monitoring data of the target object, it is identified whether the target object is a target to be driven away.

[0034] Preferably, when there are multiple target objects in the tracking area, controlling the camera device to track and photograph the target objects entering the tracking area includes:

[0035] determining the distance between each target object and the power transmission channel according to the radar monitoring data of each target object;

[0036] According to the distance between each target object and the power transmission channel, the camera device is controlled to track, photograph and identify each target object in sequence according to the rule of from near to far.

[0037] Preferably, controlling the start and stop of the camera device according to the radar monitoring data of the target object includes:

[0038] If it is determined according to the radar monitoring data that the target object enters the monitoring area, the camera device in a dormant state is controlled to start; if it is determined according to the radar monitoring data that there is no target object in the monitoring area, the camera device is controlled to sleep.

[0039] Preferably, controlling the camera device to track and photograph the target object entering the tracking area according to the plane coordinates of the target object includes:

[0040] When the camera device is in an activated state, if it is detected that the target object enters the tracking area, the camera device is controlled to turn to the target object according to the plane coordinates of the target object and track and shoot the target object.

[0041] Preferably, the identifying whether the target object is a target to be driven away based on the image captured by the camera device and the radar monitoring data of the target object includes:

[0042] Using a feature extraction network to extract features from the image captured by the camera device; classifying the target object in the image based on the extracted image features to determine whether the size of the target object exceeds a preset safety size limit;

[0043] determining, based on the radar monitoring data of the target object, whether the target object is in a moving state;

[0044] The target object whose size exceeds the preset safety size limit and is in a moving state is identified as the target to be driven away.

[0045] Preferably, it also includes:

[0046] Acquire radar monitoring data of the target object monitored by the millimeter-wave radar, and when the target object invades the warning area of ​​the camera device, obtain the identification result of the target object; when the identification result of the target object is the target to be expelled, send a signal to the warning device in the power transmission channel anti-external damage monitoring device to control the action of the warning device, and then warn and expel the target to be expelled in the warning area, and notify the management end for processing.

[0047] Compared with the closest prior art, the present invention has the following beneficial effects:

[0048] The present invention provides a transmission channel anti-extradition monitoring device and method based on radar and visual monitoring, comprising a millimeter-wave radar, a camera device and a main control box arranged on a power tower of a transmission line; the millimeter-wave radar and the camera device are respectively connected to the main control box for communication; the millimeter-wave radar is used to monitor the monitoring area around the transmission line around the day and all weather; when a target object exists in the monitoring area, the radar monitoring data of the target object is sent to the main control box; the main control box is used to determine whether the target object has entered the tracking area of ​​the camera device based on the radar monitoring data of the target object; if it is determined that the target object has entered the tracking area, the camera device is controlled to detect the target object; the main control box is used ... The camera device tracks and photographs the target object; and identifies whether the target object is a target to be driven away based on the image tracked and photographed by the camera device; the device and method combine the advantages of millimeter-wave radar and camera equipment, and utilize the advantages of millimeter-wave radar that is less affected by the environment and can detect the target position at high frequency, to monitor a larger monitoring area, and control the camera device to accurately photograph the target object in a smaller tracking area based on radar monitoring data, thereby avoiding blind observation of the camera device, reducing the power consumption of the device and realizing real-time monitoring around the clock; at the same time, combined with the main control box to identify the type of target object, avoid warnings for non-destructive target objects that do not need to be driven away, and reduce the false alarm rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a structural block diagram of a power transmission channel anti-extrinsic damage monitoring device based on radar and visual monitoring provided by the present invention;

[0050] Figure 2 A block diagram of the device structure of an embodiment of a power transmission channel anti-external damage monitoring device based on radar and visual monitoring provided by the present invention;

[0051] Figure 3 Installation diagram of a power transmission channel anti-extradition monitoring device based on radar and visual monitoring provided by the present invention Figure 1 ;

[0052] Figure 4 Installation diagram of a power transmission channel anti-extradition monitoring device based on radar and visual monitoring provided by the present invention Figure 2 ;

[0053] Figure 5 A schematic diagram of the radar polar coordinate system provided by the present invention;

[0054] Figure 6 A schematic flow chart of a method for monitoring power transmission channels against external damage based on radar and visual monitoring provided by the present invention. DETAILED DESCRIPTION

[0055] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0056] Example 1:

[0057] This invention aims to meet the all-weather perception and detection needs of large machinery around transmission lines and transmission towers, and focuses on reducing data transmission volume and energy consumption. It combines the latest millimeter-wave radar technology, video processing technology, and deep learning technology, and integrates the advantages of radar and vision to provide a transmission channel anti-external damage monitoring device based on radar and visual monitoring, such as Figure 1 As shown, it includes: a millimeter wave radar, a camera device and a main control box arranged on a power tower of a power transmission line; the millimeter wave radar and the camera device are respectively connected to the main control box for communication;

[0058] The millimeter-wave radar is used to monitor the monitoring area around the power transmission line around the clock and in all weather conditions; when a target object exists in the monitoring area, the radar monitoring data of the target object is sent to the main control box;

[0059] The main control box is used to determine whether the target object has entered the tracking area of ​​the camera device based on the radar monitoring data of the target object; if it is determined that the target object has entered the tracking area, control the camera device to track and photograph the target object; and identify whether the target object is a target to be driven away based on the image captured by the camera device during tracking.

[0060] The device further includes an alarm device, and the main control box further includes an alarm control module, wherein the alarm control module is communicatively connected to the alarm device and the millimeter wave radar respectively;

[0061] The alarm control module is used to obtain radar monitoring data of the target object monitored by the millimeter-wave radar, and when the target object invades the alarm area of ​​the camera device, obtain the identification result of the target object; when the identification result of the target object is the target to be expelled, send a signal to the alarm device to control the action of the alarm device, and then issue an alarm to expel the target to be expelled in the alarm area, and notify the management end for processing.

[0062] When this device is installed, the number of millimeter-wave radars installed can be expanded and the monitoring area can be increased.

[0063] In this embodiment, the tracking area is included in the monitoring area, and the warning area is included in the tracking area.

[0064] In this embodiment, Figure 2As shown, the main control box is connected to a power supply module, which supplies power to the millimeter wave radar, the camera equipment and the main control box. The visual camera is the main body of the camera equipment, and the loudspeaker is the warning device.

[0065] In this embodiment, Figure 3 and Figure 4 As shown, the batteries and solar panels on the tower form a power supply module.

[0066] In this embodiment, the shooting pitch angle of the camera device is set according to the tracking area so that the shooting range of the camera device covers the tracking area;

[0067] Or the shooting pitch angle of the camera device is controlled and adjusted according to the real-time angle between the target object and the camera device, so that the tracking effect is better and the image of the target object obtained by shooting is clearer.

[0068] In addition to the visual camera, the camera device also includes an electric pan-tilt platform, which is fixed on the power tower. The horizontal rotation angle of the electric pan-tilt platform is 360 degrees. The control signal output by the main control box controls the electric pan-tilt platform to drive the visual camera to rotate, thereby achieving positioning and shooting of the target;

[0069] The millimeter-wave radar has a resolution of meters, but has a large field of view with 360° omnidirectional coverage, which is used to locate target objects and provide direction for the camera equipment to turn, track and shoot. It also has strong environmental adaptability, especially in adverse weather conditions such as rain, snow, and fog. It is not restricted by weather conditions. When the camera equipment cannot clearly capture the target photo for target identification, it can also indiscriminately warn targets that invade the warning area of ​​the transmission channel, thereby protecting the transmission channel in all directions around the clock and preventing the transmission channel from being invaded and damaged by foreign objects.

[0070] The visualization camera can optionally be equipped with a zoom camera device. The focal length of the visualization camera is determined according to the real-time position, distance and speed of the target object identified by the millimeter-wave radar, so as to capture a clearer image of the target to be identified, further improving the accuracy of subsequent image recognition results, thereby reducing the false alarm rate, reducing the review workload of management personnel, and avoiding management personnel from being complacent due to frequent false alarms, thereby ensuring the effectiveness of monitoring, driving away real targets and preventing external damage.

[0071] The main control box is equipped with a radar data calculation module, a coordinate conversion module, a shooting control module and a target recognition module; the radar data calculation module and the shooting control module are both connected to the millimeter wave radar in communication, and the shooting control module is connected to the camera device in communication; the target recognition module is connected to the millimeter wave radar and the camera device in communication, respectively;

[0072] The radar data solving module is used to determine the coordinates of the target object in the radar polar coordinate system according to the radar monitoring data of the target object monitored by the millimeter wave radar;

[0073] The coordinate conversion module is used to convert the coordinates of the target object in the radar polar coordinate system into the plane coordinates in the camera coordinate system according to the relative position relationship between the millimeter wave radar and the camera device;

[0074] The shooting control module is used to control the start and stop of the camera device according to the radar monitoring data of the target object; and control the camera device to track and shoot the target object entering the tracking area according to the plane coordinates of the target object;

[0075] The target recognition module is used to identify whether the target object is a target to be driven away based on the image captured by the camera device and the radar monitoring data of the target object.

[0076] The millimeter-wave radar detects the presence of intruding target objects in the monitoring area around the power transmission line. When an intruding target object exists in the monitoring area, it quickly detects and calculates its position (polar coordinate system), distance (distance from the intruding target object to the radar), speed (travel speed), and other information. The target object's position (radar polar coordinate system), distance (distance from the intruding target object to the radar), and speed (travel speed) are the radar monitoring data, including the distance and angle between the target object and the millimeter-wave radar in the radar polar coordinate system.

[0077] The camera equipment is guided by the millimeter wave radar. After the millimeter wave radar detects the target object, it will calculate the direction, distance and speed of the target object in the radar polar coordinate system. The radar polar coordinate system is as follows: Figure 5 As shown in the figure, after detecting the target object, the millimeter wave radar outputs the angle angle and distance range of the target object in the polar coordinate system, and the calculated coordinates xL, yL of the target object in the radar polar coordinate system, which are expressed as:

[0078] The main control box converts the radar coordinate system information into the camera coordinate system based on the positional relationship between the millimeter-wave radar and the camera, sends it to the camera, controls the camera to rotate to the target direction, and takes photos at a fixed point.

[0079] like Figure 3 As shown, the millimeter-wave radar and the camera equipment are both installed on the tower beam, and the horizontal distance between them is l. Then, the plane coordinates xS and yS of the target object in the camera coordinate system can be determined according to the different left and right positions of the camera equipment with respect to the millimeter-wave radar, where xS = xL ± l and yS = yL ± l.

[0080] In this embodiment, the radar data solution module, coordinate conversion module, and shooting control module constitute the control module in the main control box, which controls the operation logic of the control device, receives data from the millimeter-wave radar, converts the radar polar coordinate system information into the camera coordinate system according to the installation position of the millimeter-wave radar and the camera device, sends it to the camera device, controls the camera device to rotate to the target orientation, and takes fixed-point photos.

[0081] The main control box is also provided with a communication module for communicating with the millimeter wave radar and the camera equipment.

[0082] The shooting control module is specifically used for:

[0083] When there are multiple target objects in the tracking area, determining the distance between each target object and the power transmission channel according to the radar monitoring data of each target object;

[0084] According to the distance between each target object and the power transmission channel, the camera device is controlled to track, photograph and identify each target object in sequence according to the rule of from near to far.

[0085] The shooting control module is specifically used for:

[0086] If it is determined according to the radar monitoring data that the target object enters the monitoring area, the camera device in a dormant state is controlled to start; if it is determined according to the radar monitoring data that there is no target object in the monitoring area, the camera device is controlled to sleep.

[0087] When the camera device is in an activated state, if it is detected that the target object enters the tracking area, the camera device is controlled to turn to the target object according to the plane coordinates of the target object and track and shoot the target object.

[0088] In this embodiment, the high stability, high reliability, and low power consumption of millimeter-wave radar can be used to detect dynamic target objects, providing 24-hour, non-contact, and low-blind-angle monitoring of the area around the power transmission line. When a target object such as a vehicle or machinery enters within 300 meters of the power transmission line, a risk warning message is issued: "Line ahead, drive safely." (Blue warning); a signal is simultaneously sent to the main control box, which activates the camera device; the 300-meter area centered on the power transmission line is the monitoring area;

[0089] Millimeter-wave radar and camera data are used to comprehensively monitor the type of target object. When the target object enters the 150m range of the transmission line, a second risk warning is issued: "Line ahead, maintain a safe distance." (Red alert). At the same time, the target object's position and speed relative to the radar polar coordinate system are sent to the main control box. The main control box controls the camera and controls the camera to rotate and focus to the target position based on the target position and speed information, allowing for precise capture. The 150m area centered on the transmission line is the tracking area.

[0090] The millimeter-wave radar detects the target object's position in real time and sends it to the main control box. The main control box controls the camera equipment to track it in real time. When the target object crosses the safe distance, that is, invades the warning area, the loudspeaker is activated to play a voice to drive the target away; the main control box transmits the radar monitoring data and tracking images or videos back to the background management end and mobile end through 3G / 4G / 5G and other wireless signals. The management personnel review and perform relevant processing; the camera equipment automatically sleeps and waits for the next wake-up to shoot.

[0091] The target recognition module is specifically used for:

[0092] Using a feature extraction network to extract features from the image captured by the camera device; classifying the target object in the image based on the extracted image features to determine whether the size of the target object exceeds a preset safety size limit;

[0093] determining, based on the radar monitoring data of the target object, whether the target object is in a moving state;

[0094] The target object whose size exceeds the preset safety size limit and is in a moving state is identified as the target to be driven away.

[0095] The targets to be driven away are mechanical equipment whose size exceeds the preset safety size limit and can cause external force damage to the transmission channel, that is, large machinery that is sensitive to transmission lines, including but not limited to truck cranes, tower cranes, excavators, dump trucks, forklifts, pile drivers, and sand dredging ships. Other small vehicles are not sensitive.

[0096] The target recognition module's AI algorithm for identifying large machinery and other small vehicles uses a two-stream architecture: one stream processes tracking image data (CNN), and the other processes radar monitoring data (LSTM). For image data, ResNet-50 or InceptionV3 are used as pre-trained models. These models have been trained on large datasets (such as ImageNet) and can effectively extract image features. For radar monitoring data, no pre-trained models are required; customized RNN or LSTM networks are used to process time series data.

[0097] Radar monitoring data is preprocessed by standardization and noise reduction, while image data is preprocessed by scaling, cropping, and normalization. ResNet-50 or InceptionV3 is then used to extract target features from the image data. An LSTM network is used to process radar time series data to capture vehicle dynamics. Data fusion is then performed to combine image and radar features at the feature level. For example, this can be achieved through simple concatenation or by combining the two features through a fully connected layer. Attention mechanisms, such as the SENet (Squeeze-and-Excitation Networks) module, are also added to the network to improve the network's focus on key features of large vehicles.

[0098] The Yolo model can also be used to process the image data captured by tracking. Yolo is a widely used artificial intelligence model that acts as an end-to-end detection network and completes the tasks of target detection and classification in the same network. For the input image, Yolo uses a convolutional neural network based on a pre-set anchor box to extract the features of the image at three different scales, and predicts the four-dimensional offset between the detection box and the anchor box coordinates, as well as the confidence and classification score of the target in the box. Finally, the non-maximum suppression method is used to deduplicate and denoise the prediction results with low confidence and large overlapping areas to obtain the final detection results. Since the above operations are implemented in a neural network, the detection speed is greatly improved compared to traditional detection networks. The multi-scale prediction method enhances the network's ability to detect targets of different sizes, especially significantly improving the detection accuracy of small targets.

[0099] Example 2:

[0100] Based on the same inventive concept, the present invention also provides a method for monitoring the power transmission channel against external damage based on radar and visual monitoring, using the above-mentioned power transmission channel against external damage monitoring device, such as Figure 6 As shown, including:

[0101] S1. The main control box receives radar monitoring data of a target object monitored by the millimeter-wave radar in the power transmission channel anti-external damage monitoring device;

[0102] S2. The main control box determines whether the target object enters the tracking area of ​​the camera device in the power transmission channel anti-external damage monitoring device based on the radar monitoring data of the target object;

[0103] S3. If it is determined that the target object enters the tracking area, control the camera device to track and photograph the target object; and identify whether the target object is a target to be driven away based on the image photographed by the camera device.

[0104] Step S2 includes:

[0105] Determine the coordinates of the target object in the radar polar coordinate system based on the radar monitoring data of the target object monitored by the millimeter-wave radar; obtain the distance between the target object and the millimeter-wave radar, and determine whether the target object has entered the tracking area of ​​the camera device in the power transmission channel anti-external damage monitoring device;

[0106] Step S3 includes:

[0107] Converting the target object's coordinates in the radar's polar coordinate system into planar coordinates in the camera's coordinate system based on the relative positional relationship between the millimeter-wave radar and the camera device;

[0108] Controlling the start and stop of the camera device according to the radar monitoring data of the target object; and controlling the camera device to track and photograph the target object entering the tracking area according to the plane coordinates of the target object;

[0109] According to the images captured by the camera device and the radar monitoring data of the target object, it is identified whether the target object is a target to be driven away.

[0110] When there are multiple target objects in the tracking area, controlling the camera device to track and photograph the target objects entering the tracking area includes:

[0111] determining the distance between each target object and the power transmission channel according to the radar monitoring data of each target object;

[0112] According to the distance between each target object and the power transmission channel, the camera device is controlled to track, photograph and identify each target object in sequence according to the rule of from near to far.

[0113] The controlling the start and stop of the camera device according to the radar monitoring data of the target object includes:

[0114] If it is determined according to the radar monitoring data that the target object enters the monitoring area, the camera device in a dormant state is controlled to start; if it is determined according to the radar monitoring data that there is no target object in the monitoring area, the camera device is controlled to sleep.

[0115] The controlling the camera device to track and photograph the target object entering the tracking area according to the plane coordinates of the target object includes:

[0116] When the camera device is in an activated state, if it is detected that the target object enters the tracking area, the camera device is controlled to turn to the target object according to the plane coordinates of the target object and track and shoot the target object.

[0117] The step of identifying whether the target object is a target to be driven away based on the image captured by the camera and the radar monitoring data of the target object includes:

[0118] Using a feature extraction network to extract features from the image captured by the camera device; classifying the target object in the image based on the extracted image features to determine whether the size of the target object exceeds a preset safety size limit;

[0119] determining, based on the radar monitoring data of the target object, whether the target object is in a moving state;

[0120] The target object whose size exceeds the preset safety size limit and is in a moving state is identified as the target to be driven away.

[0121] Also includes:

[0122] Acquire radar monitoring data of the target object monitored by the millimeter-wave radar, and when the target object invades the warning area of ​​the camera device, obtain the identification result of the target object; when the identification result of the target object is the target to be expelled, send a signal to the warning device in the power transmission channel anti-external damage monitoring device to control the action of the warning device, and then warn and expel the target to be expelled in the warning area, and notify the management end for processing.

[0123] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0124] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. 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.

[0125] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that after reading the present invention, those skilled in the art may still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the scope of protection of the claims of the present invention.

Claims

1. A power transmission channel anti-external damage monitoring device based on radar and visual monitoring, characterized in that: include: A millimeter-wave radar, a camera, and a main control box are installed on a power tower of a power transmission line; the millimeter-wave radar and the camera are respectively connected to the main control box for communication; The millimeter-wave radar is used to monitor the monitoring area around the power transmission line around the clock and in all weather conditions; when a target object exists in the monitoring area, the radar monitoring data of the target object is sent to the main control box; The main control box is used to determine whether the target object has entered the tracking area of ​​the camera device based on the radar monitoring data of the target object; if it is determined that the target object has entered the tracking area, control the camera device to track and photograph the target object; and identify whether the target object is a target to be driven away based on the image captured by the camera device during tracking.

2. The device according to claim 1, wherein The main control box is equipped with a radar data calculation module, a coordinate conversion module, a shooting control module and a target recognition module; the radar data calculation module and the shooting control module are both connected to the millimeter wave radar in communication, and the shooting control module is connected to the camera device in communication; the target recognition module is connected to the millimeter wave radar and the camera device in communication, respectively; The radar data solving module is used to determine the coordinates of the target object in the radar polar coordinate system according to the radar monitoring data of the target object monitored by the millimeter wave radar; The coordinate conversion module is used to convert the coordinates of the target object in the radar polar coordinate system into the plane coordinates in the camera coordinate system according to the relative position relationship between the millimeter wave radar and the camera device; The shooting control module is used to control the start and stop of the camera device according to the radar monitoring data of the target object; and control the camera device to track and shoot the target object entering the tracking area according to the plane coordinates of the target object; The target recognition module is used to identify whether the target object is a target to be driven away based on the image captured by the camera device and the radar monitoring data of the target object.

3. The device according to claim 2, wherein The shooting control module is specifically used for: When there are multiple target objects in the tracking area, determining the distance between each target object and the power transmission channel according to the radar monitoring data of each target object; According to the distance between each target object and the power transmission channel, the camera device is controlled to track, photograph and identify each target object in sequence according to the rule of from near to far.

4. The device according to claim 2, wherein The shooting control module is specifically used for: If it is determined according to the radar monitoring data that the target object enters the monitoring area, the camera device in a dormant state is controlled to start; if it is determined according to the radar monitoring data that there is no target object in the monitoring area, the camera device is controlled to sleep.

5. The device according to claim 2, wherein The shooting control module is specifically used for: When the camera device is in an activated state, if it is detected that the target object enters the tracking area, the camera device is controlled to turn to the target object according to the plane coordinates of the target object and track and shoot the target object.

6. The device according to claim 2, wherein The target recognition module is specifically used for: Using a feature extraction network to extract features from the image captured by the camera device; classifying the target object in the image based on the extracted image features to determine whether the size of the target object exceeds a preset safety size limit; determining, based on the radar monitoring data of the target object, whether the target object is in a moving state; The target object whose size exceeds the preset safety size limit and is in a moving state is identified as the target to be driven away.

7. The device according to claim 2, wherein The device further includes an alarm device, and the main control box further includes an alarm control module, wherein the alarm control module is communicatively connected to the alarm device and the millimeter wave radar respectively; The alarm control module is used to obtain radar monitoring data of the target object monitored by the millimeter-wave radar. When the target object invades the alarm area of ​​the camera device, the target recognition module obtains the recognition result of the target object; when the recognition result of the target object is the target to be expelled, a signal is sent to the alarm device to control the action of the alarm device, and then the target to be expelled in the alarm area is warned and expelled, and the management end is notified for processing.

8. A method for monitoring power transmission channels against external damage based on radar and visual monitoring, using the power transmission channel against external damage monitoring device according to any one of claims 1 to 7, characterized in that: include: The main control box receives radar monitoring data of the target object monitored by the millimeter wave radar in the power transmission channel anti-external damage monitoring device; The main control box determines whether the target object enters the tracking area of ​​the camera device in the power transmission channel anti-external damage monitoring device based on the radar monitoring data of the target object; If it is determined that the target object enters the tracking area, the camera device is controlled to track and photograph the target object; and whether the target object is a target to be driven away is identified based on the image photographed by the camera device during tracking.

9. The method according to claim 8, wherein The main control box determines, based on the radar monitoring data of the target object, whether the target object has entered a tracking area of ​​a camera device in the power transmission channel anti-external damage monitoring device, and the tracking area is included in the monitoring area; if it is determined that the target object has entered the tracking area, the main control box controls the camera device to track and photograph the target object; and identifying whether the target object is a target to be driven away based on the image captured by the camera device, including: determining the coordinates of the target object in a radar polar coordinate system according to radar monitoring data of the target object monitored by the millimeter wave radar; Converting the target object's coordinates in the radar's polar coordinate system into planar coordinates in the camera's coordinate system based on the relative positional relationship between the millimeter-wave radar and the camera device; Controlling the start and stop of the camera device according to the radar monitoring data of the target object; and controlling the camera device to track and photograph the target object entering the tracking area according to the plane coordinates of the target object; According to the images captured by the camera device and the radar monitoring data of the target object, it is identified whether the target object is a target to be driven away.

10. The method according to claim 9, wherein When there are multiple target objects in the tracking area, controlling the camera device to track and photograph the target objects entering the tracking area includes: determining the distance between each target object and the power transmission channel according to the radar monitoring data of each target object; According to the distance between each target object and the power transmission channel, the camera device is controlled to track, photograph and identify each target object in sequence according to the rule of from near to far.

11. The method according to claim 9, wherein The controlling the start and stop of the camera device according to the radar monitoring data of the target object includes: If it is determined according to the radar monitoring data that the target object enters the monitoring area, the camera device in a dormant state is controlled to start; if it is determined according to the radar monitoring data that there is no target object in the monitoring area, the camera device is controlled to sleep.

12. The method according to claim 9, wherein The controlling the camera device to track and photograph the target object entering the tracking area according to the plane coordinates of the target object includes: When the camera device is in an activated state, if it is detected that the target object enters the tracking area, the camera device is controlled to turn to the target object according to the plane coordinates of the target object and track and shoot the target object.

13. The method according to claim 9, wherein The step of identifying whether the target object is a target to be driven away based on the image captured by the camera and the radar monitoring data of the target object includes: Using a feature extraction network to extract features from the image captured by the camera device; classifying the target object in the image based on the extracted image features to determine whether the size of the target object exceeds a preset safety size limit; determining, based on the radar monitoring data of the target object, whether the target object is in a moving state; The target object whose size exceeds the preset safety size limit and is in a moving state is identified as the target to be driven away.

14. The method according to claim 8, wherein Also includes: Acquire radar monitoring data of the target object monitored by the millimeter-wave radar, and when the target object invades the warning area of ​​the camera device, obtain the identification result of the target object; when the identification result of the target object is the target to be expelled, send a signal to the warning device in the power transmission channel anti-external damage monitoring device to control the action of the warning device, and then warn and expel the target to be expelled in the warning area, and notify the management end for processing.

Images