Intelligent monitoring device for railway tunnel protective door

Abstract

The invention relates to the technical field of railway safety protection monitoring, in particular to an intelligent monitoring device for a railway tunnel protective door. According to the method, the characteristic that piston wind is generated when a train passes through a tunnel, so that air pressure changes remarkably is utilized, the air pressure transmitter collects the air pressure in real time and transmits the air pressure value to the edge calculation unit, the train passing state is detected, and under the condition that the air pressure changes remarkably after the train passes, the train passing state is detected. The image acquisition device is triggered to execute the photographing function with the flash lamp, the safety of the train is not influenced, the method is simple and easy to implement, convenient and reliable, the problem that the driving safety is influenced when a conventional monitoring device works is solved, 24-hour uninterrupted photographing and image recognition are not needed, and the dependence on network data transmission and network server hardware equipment is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of railway safety protection monitoring, in particular to an intelligent monitoring device for railway tunnel protection doors. Background Art

[0002] With the vigorous development of high-speed railway construction in recent years, newly built railways are characterized by many tunnels and long tunnels. Among them, tunnel disaster prevention doors are the objects that need to be monitored. Due to the huge piston wind effect in the tunnel, it will cause abnormalities in the protective door, causing its constituent materials to invade the main line, which has caused many safety accidents. This risk source has posed a severe challenge to railway driving safety. At present, the existing intelligent protective door monitoring solution is to monitor the status of the protective door in real time. It is necessary to continuously transmit a large amount of image data to the network server in order to observe the passing status of the train in real time and monitor the status of the protective door body. The image recognition data volume is large, the network server resource consumption is large, and high-performance server (cluster) support is required. The power consumption is large, the network bandwidth requirement is high, and the cost is high. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent monitoring device for railway tunnel protective doors in order to solve the problems that the existing intelligent protective door monitoring solution needs to continuously transmit a large amount of image data to a network server in order to monitor the status of the protective door in real time, so as to observe the passing status of the train in real time and monitor the status of the protective door body, the image recognition data volume is large, the network server resources are consumed a lot, and the cost is high.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is: A tunnel protection door monitoring device comprises an air pressure transmitter, an image acquisition device and an edge computing unit, wherein the edge computing unit is respectively connected to the air pressure transmitter and the image acquisition device for communication; The air pressure transmitter is used to collect air pressure values ​​and transmit them to the edge computing unit; The image acquisition device is used to collect photos of the door status and transmit them to the edge computing unit; The edge computing unit is used to control the image acquisition device to acquire image data according to changes in air pressure. At the same time, the edge computing unit is used to receive the image data acquired by the image acquisition device and analyze and process the image data.

[0005] This solution integrates the air pressure transmitter, image acquisition device and edge computing unit ECU. The air pressure transmitter collects the air pressure value and transmits it to the edge computing unit. The image acquisition device collects the appearance of the protective door and transmits the image data to the edge computing unit. The edge computing unit is used as a data processing and data output unit to process and analyze the air pressure value and photo image data and output the protective door warning signal. By adopting this solution, the train can pass through the tunnel by using the characteristics of piston wind causing significant changes in air pressure, and the train can pass through the tunnel by using the characteristics of significant decreases in air pressure. After the train passes, photos of the door state can be collected again. There is no need to take photos and perform image recognition 24 hours a day. The image recognition data volume is small, which reduces the dependence on network data transmission and network and server hardware equipment, which is conducive to reducing resource consumption and saving costs. In addition, this solution adopts an edge computing unit, which can deploy computing resources on the spot near the air transmitter and image acquisition device to communicate with the air transmitter and image acquisition device, which can reduce the delay of data transmission, improve network efficiency, further reduce the dependence on the network and server, and reduce the network bandwidth requirements and power consumption requirements.

[0006] As a preferred solution of the present invention, the image acquisition device is arranged corresponding to the tunnel protection door, and the image acquisition is intuitive. The image acquisition device can be arranged on the opposite side of the protection door, or above or to the side of the protection door.

[0007] As a preferred solution of the present invention, the image acquisition device includes a flash module, which is used to provide lighting while acquiring images and automatically turn off the lighting after image acquisition. It is suitable for realizing protective door monitoring in insufficient light in the tunnel, which is beneficial to driving safety.

[0008] In the prior art, in order to monitor the status of the protective door in real time, it is necessary to maintain the tunnel illumination for a long time so as to take photos of the door status in real time. The protective door monitoring cannot be realized when the light in the tunnel is insufficient, the cost is high, and the excessive light intensity will affect the driving safety. However, by adopting this solution, the air pressure transmitter can be used to monitor the air pressure change in real time to judge the timing of the train passing, and the characteristic of the significant drop in air pressure after the train passes can be used to control the image acquisition device to take photos with flash after the train passes, so as to realize image acquisition without affecting the safety of the train. It is simple, easy, convenient and reliable, and solves the problem that the conventional monitoring device needs long-term lighting when working and the excessive light affects the driving safety.

[0009] As another possible implementation method, a light lighting device may be provided and connected to the edge computing unit for communication. The edge computing unit determines the timing of a train passing according to changes in air pressure, thereby reasonably controlling the lighting time of the light lighting device, which is not limited to the above examples.

[0010] The present invention also provides a monitoring method for tunnel protection doors, which uses any of the above-mentioned tunnel protection door monitoring devices to monitor the status of tunnel protection doors, including the following steps: Initialize the data of the edge computing unit, and load the normal air pressure value f1, the train piston wind pressure value f2, and the pressure error threshold f3; Real-time collect the air pressure value f through the air pressure transmitter, and compare the air pressure value f with the train piston wind pressure value f2; When |f - f2| < f3, start the image acquisition device to enter the photo preparation state; When the air pressure value f drops and returns to the normal air pressure value f1, that is, f = f1, control the image acquisition device to execute the photo-taking command.

[0011] Among them, the above-mentioned normal air pressure value f1 refers to the air pressure value when there is no train passing through the protection door. The train piston wind pressure value f2 refers to the air pressure of the piston wind generated by the train passing through the tunnel on the protection door. The pressure error threshold f3 refers to the maximum change difference when the real-time collected air pressure value f triggers the image acquisition device to enter the shooting preparation state. The specific values of f1, f2, and f3 can be reasonably selected according to the pressure change law. For example, the pressure error threshold f3 can be taken as half or two-thirds of the difference between the train piston wind pressure value f2 and the normal air pressure value f1, leaving a certain time for the image acquisition device to change from the preparation state to the execution of the photo-taking command state.

[0012] Generally, 0 < f3 ≤ |f2 - f1|, f1 ≤ f ≤ f2.

[0013] As a preferred solution of the present invention, the above method further includes the steps: the image acquisition device transmits the collected image data to the edge computing unit. The edge computing unit pre-loads the normal protection door photo data. The edge computing unit performs image recognition processing on the received image data using the RepViT network convolutional neural network model, and compares based on the normal protection door photo data and the received image data to give an image classification recognition result of the protection door status.

[0014] As a preferred solution of the present invention, the image classification recognition result is any one of closed, open, loose, damaged, and collapsed.

[0015] As a preferred solution of the present invention, the above method further includes the step of alarming according to the recognition result.

[0016] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: The present invention utilizes the characteristic that when a train passes through a tunnel, piston wind is generated, causing a significant change in air pressure. An air pressure transmitter is used to collect air pressure in real time, and the air pressure value is transmitted to an edge computing unit to judge the train passing status. When the air pressure changes significantly after the train passes, the image acquisition device is triggered to perform the image acquisition function. There is no need for 24-hour uninterrupted shooting and image recognition. The amount of image recognition data is small, which reduces the dependence on network data transmission and network and server hardware equipment, and is conducive to reducing resource consumption and saving costs. In addition, this solution further reduces the dependence on network data transmission and network and server hardware equipment by using an edge computing unit for related data processing and logic control. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the structural composition of a tunnel protection door monitoring device in Example 1; Figure 2 It is the working flow chart of the tunnel protection door monitoring device; Figure 3 It is the timing diagram of air pressure change; Figure 4 It is a schematic diagram of the principle of edge computing unit using RepViT image classification network for image recognition.

[0018] Icon: 1-edge computing unit; 2-air pressure transmitter; 3-image acquisition device. DETAILED DESCRIPTION

[0019] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0020] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below 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.

[0021] Example 1 A tunnel protection door monitoring device, such as Figure 1As shown, it includes an air pressure transmitter 2, an image acquisition device 3 and an edge computing unit 1 (Edge Computing Unit, referred to as ECU), and the air pressure transmitter 2 and the image acquisition device 3 are both connected to the edge computing unit 1 in communication. Among them, the air pressure transmitter 2 is used to collect air pressure values ​​and transmit the air pressure values ​​to the edge computing unit 1; the image acquisition device 3 is set corresponding to the tunnel protection door, and the image acquisition device 3 includes a flash module. The image acquisition device 3 is used to collect the appearance photos of the door body of the protection door and transmit the image data to the edge computing unit 1. The flash module is used to provide lighting while collecting images, and automatically turn off the lighting after the image is collected to reduce the impact on the passage of the next vehicle. The lighting time of the flash module can be customized; the edge computing unit 1 serves as a data processing and data output unit, receives air pressure values ​​and image data and performs processing and analysis, controls the image acquisition device 3 to collect images according to the air pressure changes, and outputs the protection door warning signal after analyzing and processing the image data. The air pressure transmitter 2, the image acquisition device 3 and the edge computing unit 1 are organically integrated through the data interface line. In this embodiment, the image acquisition device 3 preferably adopts a digital camera with a built-in flash function.

[0022] The use of the above-mentioned tunnel protective door monitoring device for tunnel protective door monitoring can solve three types of problems existing in the prior art: First, the protective door monitoring and early warning are not timely enough. The device detects immediately after the protective door is subjected to the action of piston wind, which can ensure the timeliness of the early warning; second, the conventional solution needs to ensure that the tunnel is well lit at all times, which may affect the normal operation of the train, while the device can work after the train passes without affecting driving safety; third, the traditional image analysis algorithm has a large data volume and computing resource requirements and cannot be deployed in a distributed manner on edge devices; fourth, the conventional solution is highly dependent on the network and server. The conventional solution is based on a protective door monitoring system (device) with centralized image recognition technology, which requires the use of a camera or camera to work continuously for 24 hours and continuously perform image analysis and processing on a high-computing power server (cluster).

[0023] The methods for solving these three types of problems in this solution are described in detail as follows.

[0024] 1. Image recognition timing problem This solution utilizes the characteristic that when a train passes through a tunnel, piston wind is generated, causing a significant change in air pressure. It can trigger the photo-taking action at the falling edge of the air pressure, perform precise image recognition, and capture the state changes of the protective door in the first place, thus solving the problem that conventional solutions require 24-hour uninterrupted image recognition.

[0025] 2. Issues where system (device) operation affects driving safety Railway tunnels are dimly lit or completely dark. Conventional solutions cannot work in total darkness. When the main line lighting is on, the illumination of the protective door may not be enough to accurately recognize the image. Even if the infrared camera function is enabled, accurate image recognition may not be possible. If a special protective door illumination light is set up, in addition to the high cost, it may also affect the safety of train driving. This solution uses the flash module of the image acquisition device to take pictures under short lighting, and it is carried out after the train passes. It does not affect the safety of the train and is simple, easy to use, convenient and reliable.

[0026] 3. High network bandwidth requirements and high power consumption Conventional solutions use remote servers to complete image processing, which requires uninterrupted transmission of large amounts of image data to the server through the network, requiring large-capacity network bandwidth support; at the same time, the amount of concurrent image recognition data is large, which consumes a lot of network server resources and requires high-performance server (cluster) support. This device uses an edge computing unit, and data and control logic can be calculated and processed on-site, greatly reducing network data transmission and dependence on network and server hardware equipment, reducing server-side resource consumption, and saving a lot of costs.

[0027] Example 2 Based on Example 1, this embodiment provides a tunnel protection door monitoring method, using the above-mentioned tunnel protection door monitoring device to monitor the status of the tunnel protection door, such as Figure 2 , 3 As shown, the action process steps and working principle of the device are described in detail as follows.

[0028] The first step is to define the opening and closing state and health state of the protective door. The opening and closing state is a Boolean value, and the value range is open and closed; the health state is an enumeration value, and the value range is normal, loose, damaged, and collapsed. The above device is powered on and started, the edge computing unit 1ECU data is initialized, and the normal air pressure value f1, the train piston wind pressure value f2, the pressure error threshold f3 and the normal protective door photo data are loaded. At this time, the image acquisition device 3 is in standby mode.

[0029] In the second step, the air pressure transmitter 2 records the air pressure f in real time and transmits the pressure data to the edge computing unit 1. The edge computing unit 1 collects the air pressure value in real time and compares it with the train piston wind pressure value f2.

[0030] In the third step, when the train passes through the main line next to the tunnel protection door, when the ECU calculates that the absolute value of the difference between the current air pressure f and the train piston wind pressure value f2 is less than the pressure error threshold f3, the ECU recognizes that the train has passed and enters the shooting preparation state.

[0031] That is, the calculation formula for judging whether a train has passed is: |f-f2| <f3。

[0032] In the fourth step, after the train passes, the air pressure value f drops and returns to the normal air pressure value f1, that is, when f=f1, the ECU recognizes that the train has left and sends a control instruction to the image acquisition device 3 to take a photo.

[0033] In the fifth step, the image acquisition device 3 automatically determines whether the flash needs to be turned on according to the control instruction, and then takes a picture of the appearance of the protective door.

[0034] Step 6: Use the RepViT network convolutional neural network model for image recognition.

[0035] The network structure of RepViT is as follows Figure 4 As shown in the figure, it includes 1 Stem module, 4 Stage modules, 3 Downsample modules, and 1 FC module. The Stem module is mainly used to extract the underlying image features from the 3-channel input RGB image, the Stage module is used to extract the middle and high-level semantic features in the image, and the Downsample module replaces the traditional Pooling module to reduce the dimension of the features. The Stage module and the Downsample module are composed of multiple submodules, and the FC module is used to classify and output the final recognition results. In this railway tunnel protective door image recognition task, a training set is established by annotating the protective door images of various states collected in the early stage, and then the training of the RepViT network is completed on the central computer. Finally, the trained RepViT network is deployed in batches to the edge computing units of each monitoring point, so that the local processing of the captured railway tunnel protective door images can be realized, and the classification and recognition results of the images are given in real time. Only the recognition results of the images and a single abnormal state image need to be transmitted.

[0036] The specific implementation is that the ECU delays for a few seconds, reads the latest photo from the image acquisition device, and compares it with the normal protective door photo in the first step, and analyzes it according to the RepViT algorithm. The open and closed state and the healthy state of the protective door are analyzed respectively. Determine which of the two states the protective door is in.

[0037] Step 7: Give an alarm based on the recognition result. If the opening and closing state of the protective door is open, the ECU will send a protective door open alarm signal; if the health state of the protective door is loose, damaged, or collapsed, the ECU will send a protective door health alarm signal. More specifically, it will give an enumeration value of the health state of the protective door. The action process is completed.

[0038] Step 8. Repeat steps 2 to 7.

[0039] This solution uses the changing characteristics of the air pressure in the tunnel when the train passes to timely capture the impact of the piston wind on the protective door, and immediately judge whether the protective door is in an abnormal state and whether it needs repair and maintenance, which solves the shortcomings of the conventional solution that is poor in timeliness and cannot work normally in dimly lit tunnels. At the same time, when the device is used to monitor the status of the protective door, it mainly acts after the train passes, and the network transmission object is a photo. Compared with the conventional technical solution of using a camera to transmit video, it has the advantages of low power consumption, safety and reliability, and saving network bandwidth.

[0040] In addition, this solution can solve the problem of large computing resource requirements of traditional image recognition algorithms by using the RepViT network convolutional neural network model for image recognition. Traditional image recognition algorithms mainly rely on manually designed feature extractors and classifiers, such as edge detection algorithms, corner detection algorithms, SVM classifiers (Support Vector Machine, also known as support vector machines), etc., which have the disadvantages of cumbersome preprocessing steps, low recognition accuracy, and poor generalization ability, which limits their further development and application in the field of image recognition. With the continuous enhancement of computer computing power and the rise and continuous development of deep learning technology, the image recognition algorithm based on deep learning, the Deep Convolutional Neural Network (DCNN), has gradually replaced the traditional algorithm and become the mainstream technology in the field of image recognition. Although the early deep convolutional neural network has the advantages of automatic feature extraction, robustness and strong generalization ability, it has the disadvantages of large data volume requirements, many model parameters, and large computing resource requirements, which is not conducive to deployment on devices with low computing power such as edge computing units ECU and mobile computing devices.

[0041] The RepViT network used in this solution is a lightweight convolutional neural network model that combines the advantages of CNN (Convolutional Neural Networks) and ViT (Vision Transformer). It can be deployed in edge computing units, mobile devices, and embedded systems, and applied to real-time visual tasks such as image recognition, face recognition, and object detection. Experimental results show that the performance of the RepViT network is better than the existing most advanced lightweight ViTs network and lightweight convolutional neural network, and has lower test latency. This solution uses the RepViT network for network identification in the edge computing unit, which is conducive to improving the operating efficiency and performance of the convolutional neural network model in resource-constrained environments such as mobile devices and embedded systems.

[0042] Example 3 Based on Embodiment 2, this embodiment provides an electronic device, which includes a memory and at least one processor, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the above method.

[0043] Specifically, the processor may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the present application. Among them, the memory may include a large-capacity memory for data or instructions. For example, but not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory may be inside or outside the data processing device. In a specific embodiment, the memory is a non-volatile memory. In a specific embodiment, the memory includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (ErasableProgrammable Read-Only Memory, FPROM for short), an electrically erasable PROM (ElectricallyErasableProgrammable Read-Only Memory, EFPROM for short), an electrically alterable ROM (ElectricallyAlterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of the above.Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0044] The memory may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor.

[0045] The processor implements any of the methods in the above embodiments by reading and executing the computer program instructions stored in the memory. In some of the embodiments, the electronic device may further include a communication interface and a bus. The processor, the memory, and the communication interface are connected via a bus and communicate with each other.

[0046] The bus includes hardware, software or both, and couples the components of the computer device to each other. The bus includes but is not limited to at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0047] Example 4 Based on Embodiment 2, this embodiment provides a computer-readable storage medium, on which a computer program is stored, and the computer program implements the above method when executed.

[0048] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiment are executed. When the above-mentioned integrated unit of the present invention is implemented in the form of a software functional unit and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the method described in Example 2 of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A tunnel protection door monitoring device, characterized in that: It includes an air pressure transmitter (2), an image acquisition device (3) and an edge computing unit (1), and the edge computing unit (1) is communicatively connected to the air pressure transmitter (2) and the image acquisition device (3) respectively; The air pressure transmitter (2) is used to collect air pressure values and transmit them to the edge computing unit (1); The image acquisition device (3) is used to collect photos of the door state and transmit them to the edge computing unit (1); The edge computing unit (1) is used to control the image acquisition device (3) to obtain image data according to air pressure changes. At the same time, the edge computing unit (1) is used to receive the image data collected by the image acquisition device (3) and analyze and process it.

2. A tunnel protection door monitoring device according to claim 1, characterized in that: The image acquisition device (3) is arranged corresponding to the tunnel protection door.

3. A tunnel protection door monitoring device according to claim 1, characterized in that: Both between the edge computing unit (1) and the air pressure transmitter (2), and between the edge computing unit (1) and the image acquisition device (3) are electrically connected through data interface lines.

4. A tunnel protection door monitoring device according to any one of claims 1 to 3, characterized in that: The image acquisition device (3) includes a flash module, and the flash module is used to provide illumination while collecting images and automatically turn off the illumination after image acquisition; the image acquisition device (3) uses a camera with a flash function.

5. A tunnel protection door monitoring method, characterized in that: Using the tunnel protection door monitoring device according to any one of claims 1-4 to monitor the state of the tunnel protection door, including the following steps: Initialize the data of the edge computing unit (1) and load the normal air pressure value f1, the train piston wind pressure value f2 and the pressure error threshold f3; Real-time collect the air pressure value f through the air pressure transmitter (2) and compare the air pressure value f with the train piston wind pressure value f2; When |f - f2| < f3, start the image acquisition device (3) to enter the photo-taking preparation state; When the air pressure value f drops and returns to the normal air pressure value f1, that is, f = f1, control the image acquisition device (3) to execute the photo-taking instruction.

6. A tunnel protection door monitoring method according to claim 5, characterized in that: It also includes the steps: the image acquisition device (3) transmits the collected image data to the edge computing unit (1), the edge computing unit (1) pre-loads normal protection door photo data, and the edge computing unit (1) uses the RepViT network convolutional neural network model to perform image recognition processing on the received image data, and based on the normal protection door photo data and the received image data for comparison, gives an image classification recognition result of the protection door state.

7. A tunnel protection door monitoring method according to claim 6, characterized in that: The image classification recognition result is any one of closed, open, loose, damaged and collapsed.

8. A tunnel protection door monitoring method according to any one of claims 5 to 7, characterized in that: It also includes the step of alarming according to the recognition result.

9. An electronic device, characterized in that: The electronic device includes a memory and at least one processor, the memory stores a computer program, and the processor is used to execute the computer program to implement the tunnel protection door monitoring method according to any one of claims 5-8.

10. A computer-readable storage medium, characterized in that: A computer program is stored on the computer-readable storage medium, and when the computer program is executed, it implements the tunnel protection door monitoring method according to any one of claims 5-8 above.

Images