Railway line invasion management system based on radar and video

Abstract

The invention relates to a railway line invasion management system based on radars and videos. The railway line invasion management system is composed of an equipment layer, a network layer and an application layer. The core of the equipment layer is a Raysight all-in-one machine monitoring module and an edge computing terminal which are responsible for collecting and analyzing data along a railway in real time, including associated information among people, animals, trains and the railway. And when potential threats are identified, the edge computing terminal can quickly generate early warning data. And the network layer is responsible for reading and transmitting the key data to ensure the real-time performance and accuracy of the information. And the application layer comprises an intrusion early warning platform and a video monitoring platform which are used for receiving the data from the equipment layer and further processing and displaying the data. Through the system, a railway management department can grasp the conditions along the line in real time and find and deal with potential boundary invasion behaviors in time, so that the safety and smoothness of railway operation are ensured. The system not only improves the efficiency of railway safety management, but also provides powerful technical support for safety protection along the railway.

Description

Technical Field

[0001] The invention relates to the field of railway and information security management, in particular to a railway line intrusion management system based on radar and video. Background Art

[0002] With the development of the times, there are more and more railway layouts, and the problem of railway safety management has become increasingly prominent.

[0003] In the field of railway safety management, the traditional way of managing intrusion along railways mainly relies on manual inspections and video surveillance, but these methods have obvious limitations. Manual inspections are inefficient and difficult to cover all areas; while simple video surveillance can provide real-time images, it lacks intelligent analysis and early warning functions, and does not respond quickly enough to potential intrusions. Summary of the invention

[0004] In view of the above situation, it is necessary to provide a railway line intrusion management system based on radar and video that solves at least one of the above problems, including a device layer, a network layer and an application layer;

[0005] The equipment layer includes a radar-visual integrated machine monitoring module and an edge computing terminal. The radar-visual integrated machine monitoring module is used to collect data along the railway in real time, and transmit the data to the edge computing terminal for analysis, identify and analyze the associated data between people, animals, trains and railways, and generate warning data at the same time, and transmit the warning data to the application layer;

[0006] The network layer is used to read and transmit data from the device layer;

[0007] The application layer includes an intrusion warning platform and a video monitoring platform, and the intrusion warning platform and the comprehensive video monitoring platform are used to receive data from the device layer.

[0008] Preferably, the device layer also includes an edge server, which can run a variety of AI algorithms for intelligent analysis and processing of data collected by cameras and millimeter-wave radars.

[0009] Preferably, the detection distance of the integrated radar and visual monitoring module for people and animals is 230 meters, and the detection distance for vehicles is 300 meters.

[0010] Preferably, the radar detection horizontal angle of the radar-visual integrated monitoring module is 90° within 100 meters and 15° beyond 100 meters.

[0011] Preferably, the edge computing terminal has the function of intelligently analyzing events, including area intrusion detection, boundary crossing detection, area entry detection, area exit detection and audio anomaly detection.

[0012] Preferably, after receiving the data from the integrated radar and vision monitoring module, the edge computing terminal generates warning data and transmits it to the application layer when the overlap area between the identified person, animal or vehicle and the preset safety area exceeds 30%.

[0013] Preferably, when the edge computing terminal is performing audio anomaly detection, it performs logical judgment on the collected audio data. When the audio signal exceeds 80 decibels and lasts for more than 10 seconds, it is determined to be an audio anomaly and generates warning data.

[0014] Preferably, the network layer adopts an encrypted communication protocol.

[0015] Preferably, after receiving the data from the radar-vision integrated monitoring module, the edge computing terminal will perform target identification and classification. When the identified target belongs to a preset threat category (human, animal, unauthorized vehicle) and the target distance from the railway line is less than a preset safety distance threshold, early warning data is generated and transmitted to the application layer. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a flowchart of a railway line intrusion management system based on radar and video according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clear, the following is a further detailed description of the railway line intrusion management system based on radar and video in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] In the description of the present invention, unless otherwise specified, "multiple" means two or more; the terms "center", "longitudinal", "lateral", "up", "down", "left", "right", "inside", "outside", "front end", "rear end", "head", "tail", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third" and the like are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0019] In the description of this utility, it should be noted that, unless otherwise clearly specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this utility can be understood by specific circumstances.

[0020] See also Figure 1 The radar and video-based railway intrusion management system of an embodiment of the present invention includes a device layer, a network layer and an application layer; the device layer includes a radar-vision integrated monitoring module and an edge computing terminal, the radar-vision integrated monitoring module is used to collect data along the railway in real time, and transmit the data to the edge computing terminal for analysis, identify and analyze the related data between people, animals, trains and railways, and generate early warning data at the same time, and transmit the early warning data to the application layer; the network layer is used to read and transmit the data of the device layer; the application layer includes an intrusion warning platform and a video monitoring platform, and the intrusion warning platform and the comprehensive video monitoring platform are used to receive data from the device layer.

[0021] In the above embodiment, its working principle is to collect various data along the railway in real time through the integrated monitoring module of the equipment layer, including the movement trajectory, speed and position of dynamic targets such as personnel, animals, and trains, and transmit these data to the edge computing terminal through the network layer for analysis. The edge computing terminal uses a preset algorithm model to identify, classify and associate the collected data. When a target that may pose a threat to railway safety is identified, early warning data will be generated, and these early warning data will be further transmitted to the intrusion warning platform and video monitoring platform of the application layer. First, the system realizes all-round and all-weather monitoring of the railway line through the integrated monitoring module of the thunder vision machine. Whether it is day or night, regardless of weather conditions, real-time data along the railway line can be effectively collected. This not only greatly improves the coverage and accuracy of monitoring, but also reduces the cost and time consumption caused by manual inspections. Secondly, the system adopts edge computing technology, so that most of the data processing and analysis work can be completed on the device side, rather than relying on a remote data center. This design not only reduces the delay of data transmission and improves the response speed of the system, but also reduces the burden on the network layer, making the entire system more stable and reliable. In addition, the intelligent analysis function of the edge computing terminal can realize the automatic identification and processing of various complex scenarios, greatly improving the intelligence level of the system. In terms of data analysis and early warning, the system uses the preset algorithm model to deeply mine and analyze the collected data, accurately identify targets that may pose a threat to railway safety, such as illegal intruders, animal crossings, etc., and generate corresponding early warning data. These early warning data can not only be pushed to the intrusion warning platform of the application layer in real time to provide timely warning information for managers, but also trigger the video recording and saving function of the video monitoring platform to provide important evidence support for subsequent accident investigation and handling. In addition, the system also has strong scalability and flexibility. With the continuous advancement of technology and the continuous changes in railway safety needs, the system can expand and optimize its functions by upgrading algorithm models, adding monitoring equipment, etc. to meet higher safety monitoring needs. At the same time, the system can also be integrated with other safety management systems to realize information sharing and collaborative work, and further improve the overall efficiency of railway safety management. At the application level, the combined use of the intrusion warning platform and the video monitoring platform provides a comprehensive solution for railway safety management. The intrusion warning platform can receive and analyze the warning data from the edge computing terminal in real time, conduct risk assessment and warning level classification according to preset rules and strategies, and push important warning information to managers in a timely manner so that they can respond quickly and take corresponding measures. The video surveillance platform provides real-time video surveillance images and video playback functions, allowing managers to intuitively understand the actual situation along the railway and further verify and process the warning information.In summary, the railway line intrusion management system based on radar and video in the embodiment of the present invention realizes comprehensive, real-time and efficient safety monitoring of the railway line through integrated radar and video technology, edge computing technology and intelligent early warning and analysis functions. Its working principle embodies a high degree of automation and intelligence, which not only improves the efficiency and accuracy of railway safety management, but also reduces management costs and manpower investment.

[0022] See also Figure 1 In another embodiment, the device layer also includes an edge server, which can run a variety of AI algorithms for intelligently analyzing and processing data collected by cameras and millimeter-wave radars.

[0023] In the above embodiment, the working principle of the edge server is five main steps: data collection, preprocessing, feature extraction, model reasoning, and result output. First, it receives raw data from cameras and millimeter wave radars, which may include video streams, radar point clouds, etc. Next, the server preprocesses the data, such as denoising, format conversion, etc., for subsequent analysis. Subsequently, the server uses AI algorithms to extract useful features from the preprocessed data, which may be the shape, size, speed, etc. of the target. Then, based on these features, the server uses the trained model for reasoning to determine whether the target is a potential threat. Finally, the server outputs the reasoning results as early warning information, which is transmitted to the application layer through the network layer for management personnel to view and respond. It can not only process a large amount of data in real time, but also use AI algorithms to perform in-depth analysis of the data, thereby accurately identifying potential threats. In addition, since data processing and analysis are mainly completed on the device side, the burden on the network layer is greatly reduced and the response speed of the system is improved. The advantages of the edge server in the system are mainly reflected in the following aspects: First, it greatly improves the intelligence level of the system. By integrating multiple AI algorithms, the edge server can deeply analyze and process the collected data to realize automatic identification and classification of targets. This can not only reduce the workload of manual inspections, but also improve the accuracy and efficiency of identification. Secondly, the edge server enhances the real-time and response speed of the system. Since data processing and analysis are mainly completed on the device side, data transmission delays are avoided, allowing the system to identify and warn potential threats at the first time. This is crucial for railway safety management, because timely warnings and responses can greatly reduce the possibility of accidents. In addition, the edge server also improves the stability and reliability of the system. Since data processing and analysis are mainly completed locally and do not rely on remote data centers, the system can still operate normally even in poor network conditions. At the same time, the edge server also has strong scalability and flexibility, and can upgrade and expand functions according to actual needs. Finally, the application of the edge server also reduces the overall cost of the system. By reducing the frequency and intensity of manual inspections, labor costs are reduced; by improving the accuracy of identification and warning, resource waste caused by false alarms and missed alarms is reduced; by optimizing the data processing and analysis process, the system's operating efficiency is improved and operating costs are reduced.

[0024] See also Figure 1 In another embodiment, the detection distance of the integrated radar and visual monitoring module for people and animals is 230 meters, and the detection distance for vehicles is 300 meters.

[0025] In the above embodiment, the integrated monitoring module of the radar vision machine transmits radio waves through its built-in millimeter wave radar system. These waves will be reflected when encountering targets (such as people, animals or vehicles). After receiving these reflected waves, the module can accurately measure the distance, speed and azimuth between the target and the module by calculating the transmission time, phase change and other parameters of the waves. At the same time, the module is also equipped with a high-definition camera, which can capture the video images along the railway in real time, providing managers with an intuitive monitoring perspective. The fusion processing of radar and video data enables the module to more accurately identify the target type, judge its movement trajectory and intention, and thus generate effective early warning information. In terms of detection distance, the integrated monitoring module of the radar vision machine performs well. The detection distance for people and animals reaches 230 meters, which means that in the wide area along the railway, the module can detect potential intruders in time, providing sufficient early warning time for railway safety. At the same time, the detection distance for vehicles reaches 300 meters, which is enough to cover most railway crossings and key areas, ensuring real-time monitoring and early warning of passing vehicles. The integrated monitoring module of the radar vision machine has many significant advantages. First, its highly integrated design makes the module very convenient to install and use, greatly reducing the deployment cost and maintenance difficulty of the system. Second, the module's high-precision detection capability enables railway safety managers to accurately grasp the real-time dynamics along the railway, and promptly discover and deal with potential safety hazards. In addition, the module also has strong anti-interference ability and stability, and can work normally in severe weather and complex environments, ensuring the continuity and reliability of railway safety monitoring.

[0026] See also Figure 1 In another embodiment, the radar detection horizontal angle of the radar-visual integrated monitoring module is 90° within 100 meters and 15° beyond 100 meters.

[0027] In the above embodiment, within a close range of less than 100 meters, the radar's horizontal detection angle reaches 90°, which means that it can cover a fairly wide area and almost achieve all-round monitoring, ensuring that any dynamics within this range can be captured in time. However, at a distance of more than 100 meters, the radar's detection angle is reduced to 15°. This design seems to limit the detection range, but in fact it greatly improves the detection accuracy of long-distance targets. When monitoring at a long distance, by narrowing the detection angle, the radar's "attention" can be focused, clutter interference can be reduced, and specific targets can be locked and tracked more accurately. First, at a close distance, the 90° wide-angle detection enables the module to monitor a wider area, and it is difficult for pedestrians, vehicles or other dynamic targets to escape its monitoring. Because it can detect abnormal situations at the first time and respond in time. Secondly, at a long distance, the 15° narrow-angle detection ensures accurate locking of the target. This design not only improves the radar's anti-interference ability, but also enables monitoring personnel to more accurately grasp the dynamics of the target, providing strong support for subsequent decision-making and actions. In addition to the advantages of angle design, the integrated radar monitoring module also integrates video monitoring functions, combining the images captured by the high-definition camera with radar data to provide users with an intuitive and comprehensive monitoring interface. This double verification method not only improves the accuracy of monitoring, but also enables operators to make judgments and decisions more quickly.

[0028] See also Figure 1 In another embodiment, the edge computing terminal has the function of intelligently analyzing events, including area intrusion detection, boundary crossing detection, area entry detection, area exit detection, and audio anomaly detection.

[0029] In the above embodiment, the edge computing terminal first collects data information of the monitoring area in real time through its built-in sensors, cameras and other hardware devices. These data include video images, audio signals and environmental parameters, which together constitute a comprehensive perception of the monitoring area. Subsequently, these data are transmitted to the processor of the edge computing terminal for real-time analysis and processing. The processor of the edge computing terminal uses a pre-trained algorithm model to extract features and recognize patterns on the collected data, thereby realizing intelligent detection of specific events. Taking regional intrusion detection as an example, the edge computing terminal will monitor the dynamic changes in the area in real time according to the preset monitoring area. Once an object or person enters the area, the edge computing terminal will immediately identify and trigger the alarm mechanism. Similarly, functions such as cross-border detection, entry area detection and exit area detection are also implemented based on similar working principles. Audio anomaly detection is to detect abnormal sounds or noises by analyzing the audio signals in the monitoring area, thereby realizing intelligent identification of audio events. The intelligent analysis event function of the edge computing terminal has significant advantages. First, since data processing and analysis occur on the terminal device, there is no need to upload all data to the cloud for processing, which greatly reduces the delay and bandwidth consumption of data transmission. This enables the edge computing terminal to quickly respond to and process events in scenarios with extremely high real-time requirements. Secondly, the intelligent analysis function of the edge computing terminal enhances the security and privacy protection capabilities of the monitoring system. Since most of the data processing and analysis are completed locally, the risk of data being intercepted or leaked during transmission is reduced. At the same time, through the accurate identification of specific events, the edge computing terminal can also effectively filter out irrelevant information, reduce false positives and false negatives, and improve the accuracy and reliability of the monitoring system. In addition, the intelligent analysis event function of the edge computing terminal also has high flexibility and scalability. According to different application scenarios and requirements, users can easily adjust and optimize the algorithm model to achieve accurate identification and processing of different events. In summary, the intelligent analysis event function of the edge computing terminal provides strong technical support for modern intelligent monitoring systems through its unique working principle and significant advantages. It can not only achieve rapid response and processing of specific events, but also improve the security and privacy protection capabilities of the monitoring system, while having high flexibility and scalability.

[0030] See also Figure 1 In another embodiment, after receiving the data from the integrated radar monitoring module, the edge computing terminal generates warning data and transmits it to the application layer when the overlap area of ​​the identified person, animal or vehicle with the preset safety area exceeds 30%.

[0031] In the above embodiment, once the identified person, animal or vehicle overlaps with the preset safety area, the edge computing terminal will immediately calculate the overlapping area. When the overlapping area exceeds the preset 30% threshold, the edge computing terminal will determine that this is a potential safety risk and immediately generate warning data. The warning data contains the type, position, speed, motion trajectory, etc. of the target, as well as the degree of overlap with the safety area and the potential risk level. This information is crucial for subsequent decision-making and response. After generating the warning data, the edge computing terminal will quickly transmit it to the application layer. As the upper management module of the entire system, the application layer will perform corresponding processing and response according to the preset rules and processes after receiving the warning data. This working principle of the edge computing terminal brings many advantages, making the entire monitoring system more efficient, accurate and reliable. First, the real-time data processing capability of the edge computing terminal ensures the timeliness of the warning. Since data processing and analysis are completed locally at the terminal, there is no need to wait for the cloud response, which greatly reduces the delay time of the warning. This enables the monitoring system to detect and respond to potential safety risks in the first place, effectively preventing the occurrence of safety accidents. Secondly, the precise identification capability of the edge computing terminal improves the accuracy of the warning. Through advanced algorithms and models, edge computing terminals can accurately distinguish different types of targets such as people, animals and vehicles, and accurately calculate the overlapping area between them and the safe area. This precise identification capability avoids security risks caused by misjudgment or missed judgment, and improves the reliability of the entire monitoring system. In addition, the intelligent early warning mechanism of the edge computing terminal also reduces the false alarm rate. By setting a reasonable overlapping area threshold and risk level assessment, the edge computing terminal can effectively filter out irrelevant information while ensuring that there is no missed alarm, reducing the interference of false alarms on system operation. This not only improves the operating efficiency of the monitoring system, but also reduces the workload of operators.

[0032] See also Figure 1 In another embodiment, when the edge computing terminal detects audio anomalies, it performs logical judgment on the collected audio data. When the audio signal exceeds 80 decibels and lasts for more than 10 seconds, it is determined to be an audio anomaly and generates warning data.

[0033] In the above embodiment, this function mainly makes real-time judgment on the collected audio data. Once the audio signal exceeds the preset 80 decibel threshold and this state of exceeding the threshold lasts for more than 10 seconds, the edge computing terminal will quickly determine that the audio is abnormal and immediately generate corresponding warning data. First, through the built-in audio sensor or microphone, the edge computing terminal can capture the sound signal in the monitoring area in real time. Subsequently, these audio data are sent to the processing unit of the edge computing terminal for detailed analysis and judgment. During the processing, the edge computing terminal will digitize the audio signal and extract the key parameter of the volume. By comparing with the preset 80 decibel threshold, the edge computing terminal can determine whether the current audio signal exceeds the normal range. If the volume exceeds this threshold, the edge computing terminal will further calculate the duration of this state. Only when the duration exceeds 10 seconds will the edge computing terminal finally determine that the audio is abnormal. The design of this judgment mechanism fully considers the noise interference and misjudgment problems in actual scenarios. By setting reasonable thresholds and durations, the edge computing terminal can effectively filter out short-term and accidental noise interference while ensuring the accuracy of the warning, avoiding the generation of false alarms. When an audio anomaly is determined, the edge computing terminal will immediately generate warning data. This data not only contains specific information about the audio anomaly, such as volume, duration, etc., but may also include additional information such as the time and location of the anomaly. These warning data are crucial for subsequent decision-making and response, and can help relevant personnel quickly understand the abnormal situation and take corresponding measures. This audio anomaly detection function of the edge computing terminal has many advantages. First, since data processing and analysis are completed at the edge and do not need to be uploaded to the cloud, the response speed of the warning is extremely fast, and real-time monitoring and warning of audio anomalies can be achieved. Secondly, through a reasonable judgment mechanism and threshold setting, the edge computing terminal can accurately identify the real audio anomaly and reduce the false alarm rate. In addition, since the edge computing terminal has powerful data processing capabilities, it can process audio data from multiple monitoring areas at the same time, improving the coverage and efficiency of the monitoring system.

[0034] See also Figure 1 In another embodiment, the network layer adopts an encrypted communication protocol.

[0035] In the above embodiment, the network layer encryption communication protocol ensures the integrity of the data. During the data transmission process, the data may be tampered with or damaged, resulting in the recipient receiving incomplete or erroneous information. The encryption communication protocol can ensure the integrity of the data during the transmission process by adopting a data integrity verification mechanism.

[0036] See also Figure 1In another embodiment, after receiving the data from the radar-vision integrated monitoring module, the edge computing terminal will perform target identification and classification. When the identified target belongs to a preset threat category (human, animal, unauthorized vehicle), and the target distance from the railway line is less than a preset safety distance threshold, early warning data is generated and transmitted to the application layer.

[0037] In the above embodiment, the data collected by the integrated monitoring module of the radar and vision device includes video and radar information, which provides detailed monitoring scene details for the edge computing terminal. By using advanced image recognition and machine learning technology, the edge computing terminal can accurately identify and classify various types of targets in the monitoring screen, such as people, animals and vehicles. After identifying the target, the edge computing terminal will further compare these targets with the preset threat categories. The threat categories are pre-set to identify entities that may pose a potential threat to the railway line. Once the identified target is classified as one of these threat categories, the edge computing terminal will immediately enter the next stage of processing. Next, the edge computing terminal will calculate the actual distance between the identified target and the railway line. This step is crucial because it is directly related to the urgency and severity of the threat. Through an accurate ranging algorithm, the edge computing terminal can quickly determine the distance between the target and the railway line and compare it with the preset safety distance threshold. When the distance between the target and the railway line is less than the preset safety distance threshold, the edge computing terminal will determine that this is an urgent warning situation. At this time, the edge computing terminal will immediately generate warning data. These warning data not only contain key information such as the type, location, and distance of the target, but may also include an assessment of the threat level and recommended countermeasures. After the warning data is generated, the edge computing terminal will quickly transmit it to the application layer. As the core management layer of the entire system, the application layer can receive and process the warning data from the edge computing terminal. Here, the warning data will be further analyzed and the corresponding warning mechanism will be triggered according to the preset rules and processes, such as alarming, notifying relevant personnel, or launching emergency plans. First, the target recognition and classification capabilities of the edge computing terminal enable the system to accurately identify potential threat targets, thereby avoiding false alarms and missed alarms. This greatly improves the accuracy and reliability of the warning, and makes the safety of the railway line more effectively guaranteed. Secondly, by calculating the distance between the target and the railway line in real time and comparing it with the preset safety distance threshold, the edge computing terminal can quickly detect those threat targets approaching the railway line. This real-time nature enables the system to issue a warning before the threat occurs, providing relevant personnel with sufficient response time and reducing the possibility of accidents. In addition, the seamless connection between the edge computing terminal and the application layer enables the warning data to be quickly and accurately conveyed to relevant personnel. This efficient communication mechanism ensures the timeliness and effectiveness of early warning information, providing strong support for the safety management of railway lines. Finally, the superiority of the working principle of edge computing terminals is also reflected in their scalability and flexibility. With the continuous advancement of technology and the changes in railway safety requirements, edge computing terminals can continuously improve their recognition capabilities and early warning accuracy by updating algorithms, optimizing models, etc. At the same time, its flexible architecture also enables the system to adapt to different monitoring scenarios and safety requirements, providing more possibilities for the safety management of railway lines.

[0038] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technician familiar with this profession can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A railway line intrusion management system based on radar and video, characterized in that: Includes device layer, network layer and application layer; The equipment layer includes a radar-visual integrated machine monitoring module and an edge computing terminal. The radar-visual integrated machine monitoring module is used to collect data along the railway in real time, and transmit the data to the edge computing terminal for analysis, identify and analyze the associated data between people, animals, trains and railways, and generate warning data at the same time, and transmit the warning data to the application layer; The network layer is used to read and transmit data from the device layer; The application layer includes an intrusion warning platform and a video monitoring platform, and the intrusion warning platform and the comprehensive video monitoring platform are used to receive data from the device layer.

2. The railway line intrusion management system based on radar and video according to claim 1 is characterized in that: The device layer also includes an edge server that can run a variety of AI algorithms for intelligent analysis and processing of data collected by cameras and millimeter-wave radars.

3. The railway line intrusion management system based on radar and video according to claim 1 is characterized in that: The detection distance of the integrated radar and vision monitoring module for people and animals is 230 meters, and the detection distance for vehicles is 300 meters.

4. The railway line intrusion management system based on radar and video according to claim 1 is characterized in that: The radar detection horizontal angle of the radar-visual integrated monitoring module is 90° within 100 meters and 15° beyond 100 meters.

5. The railway line intrusion management system based on radar and video according to claim 1 is characterized in that: The edge computing terminal has the function of intelligently analyzing events, including area intrusion detection, cross-border detection, area entry detection, area exit detection, and audio anomaly detection.

6. The railway line intrusion management system based on radar and video according to claim 1 is characterized in that: After receiving the data from the integrated radar and vision monitoring module, the edge computing terminal generates warning data and transmits it to the application layer when the overlap area of ​​the identified person, animal or vehicle with the preset safety area exceeds 30%.

7. The railway line intrusion management system based on radar and video according to claim 5 is characterized in that: When performing audio anomaly detection, the edge computing terminal performs logical judgment on the collected audio data. When the audio signal exceeds 80 decibels and lasts for more than 10 seconds, it is determined to be an audio anomaly and generates warning data.

8. The railway line intrusion management system based on radar and video according to claim 1 is characterized in that: The network layer adopts an encrypted communication protocol.

9. The railway line intrusion management system based on radar and video according to claim 1 is characterized in that: After receiving the data from the integrated radar monitoring module, the edge computing terminal will perform target identification and classification. When the identified target belongs to the preset threat category (people, animals, unauthorized vehicles) and the target distance from the railway line is less than the preset safety distance threshold, early warning data is generated and transmitted to the application layer.

Images