CN115223081A

CN115223081A - Intelligent safety monitoring method, system equipment and medium for subway tunnel

Info

Publication number: CN115223081A
Application number: CN202210834889.8A
Authority: CN
Inventors: 王恒; 程远; 李晓毛
Original assignee: Individual
Current assignee: Individual
Priority date: 2022-07-16
Filing date: 2022-07-16
Publication date: 2022-10-21

Abstract

The invention provides an intelligent safety monitoring method, system equipment and medium for a subway tunnel, and relates to the technical field of tunnel safety. Establishing a three-dimensional model about a tunnel environment; arranging a plurality of cameras in the tunnel, and marking the position of any camera in the tunnel on the three-dimensional model; acquiring a video frame image by using a camera; constructing a flame color deep learning model; carrying out flame identification on the video frame image; if the recognition result reaches a threshold value, marking the flame position in the image, storing and uploading the image to a background terminal, determining the fire alarm position according to the three-dimensional model, and sending fire alarm information to the mobile terminal; if the flame position is overlapped with the cable position, the movement direction and speed of the fire are judged, when the movement speed of the fire reaches a preset value, the background terminal remotely stops power supply in the tunnel, and all cables in the preset area of the cable on fire are cut off. The fire monitoring system can prevent fire monitoring from being influenced by the environment, and improves safety.

Description

Intelligent safety monitoring method, system equipment and medium for subway tunnel

Technical Field

The invention relates to the technical field of tunnel safety, in particular to an intelligent safety monitoring method, system equipment and medium for a subway tunnel.

Background

In the tunnel construction and the tunnel use process, fire safety is very important. At present, monitoring of tunnel fire is mainly completed by means of various sensors arranged in the tunnel, such as smoke sensors, temperature sensors and the like, and whether fire occurs in the tunnel or not is judged by analyzing temperature and smoke.

At the initial moment of fire in the tunnel, because various sensors have dispersibility in the distribution of spatial positions, the smoke volume of the fire or the size and the distribution area of the flame temperature are likely to not meet the requirements of triggering various sensors, so that the monitoring at the initial stage of the fire has great uncertainty and great defects. Therefore, an intelligent safety monitoring method for a subway tunnel is needed.

Disclosure of Invention

The invention aims to provide an intelligent safety monitoring method for a subway tunnel, which can prevent fire monitoring from being influenced by environment and improve safety.

The embodiment of the invention is realized by the following steps:

in a first aspect, an embodiment of the present application provides an intelligent safety monitoring method for a subway tunnel, which includes acquiring environmental information of the tunnel; establishing a three-dimensional model about the tunnel environment based on the environment information of the tunnel; arranging a plurality of visible light cameras and infrared cameras in the tunnel, and marking the positions of any visible light camera and any infrared camera in the tunnel on the three-dimensional model; simultaneously, marking the cable position in the tunnel in a three-dimensional model, wherein the monitoring area of a plurality of visible light cameras and infrared cameras covers the cable installation position in the tunnel; acquiring a video frame image by using a visible light camera and an infrared camera, and preprocessing the video frame image; constructing a flame color deep learning model by using a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through a flame color deep learning model; if the recognition result reaches a threshold value, judging that the flame is a flame, marking the flame position in the image, storing the image and uploading the image to a background terminal, determining the fire alarm position according to the three-dimensional model by the background terminal, and sending fire alarm information to a preset mobile terminal; if the flame position is overlapped with the cable position, the image containing the flame is directly subtracted from two adjacent frames to obtain the change of the pixel value in the image, the fire motion direction is judged, the fire motion speed is calculated, when the fire motion speed reaches a preset value, the background terminal remotely stops power supply in the tunnel, and all cables in a preset area of the cable on fire are cut off.

In some embodiments of the present invention, the step of isolating all cables in the predetermined area of the cable in which a fire is occurring comprises: arranging cable fire isolators on cables at preset intervals, and disconnecting the cables by using the cable fire isolators after remotely stopping power supply in the tunnel at the background terminal; the cable fire barrier comprises a metal shell, a cutting tool arranged in the metal shell and a hydraulic cylinder connected with the cutting tool, wherein the cutting tool is connected with the metal shell in a sliding manner.

In some embodiments of the present invention, the metal shell is provided with a placement hole for passing the cable therethrough, and the cutting edge of the cutting tool has a length greater than the diameter of the placement hole.

In some embodiments of the invention, the step of building a three-dimensional model about the tunnel environment comprises: and establishing a BIM building information three-dimensional model related to the tunnel environment.

In some embodiments of the present invention, if the recognition result does not reach the threshold, the thermal imaging monitoring is performed on the monitored area by the infrared camera, and if the thermal imaging analysis result indicates that some areas exceed the preset temperature, the overload information is sent to the preset mobile terminal.

In some embodiments of the present invention, the step of sending the fire alarm information to the preset mobile terminal includes: and the background terminal controls the ventilation system to start a ventilation mode to ventilate the tunnel.

In some embodiments of the invention, the step of performing a pretreatment comprises: and converting the image into a unified format preset by the deep learning model, and carrying out normalized dimensionless processing.

In a second aspect, an embodiment of the present application provides an intelligent safety monitoring system for a subway tunnel, which includes a picture obtaining module, configured to obtain environment information of the tunnel; the model establishing module is used for establishing a three-dimensional model related to the tunnel environment based on the environment information of the tunnel; the monitoring module is used for arranging a plurality of visible light cameras and infrared cameras in the tunnel, and the positions of any visible light camera and any infrared camera in the tunnel are marked on the three-dimensional model; simultaneously, marking the cable position in the tunnel in the three-dimensional model, wherein a plurality of visible light camera and infrared camera monitoring areas cover the cable installation position in the tunnel; the preprocessing module is used for acquiring a video frame image by using the visible light camera and the infrared camera and carrying out preprocessing; the deep learning module is used for constructing a flame color deep learning model by utilizing a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through a flame color deep learning model; the judging module is used for judging whether the flame position in the image is a flame or not if the recognition result reaches a threshold value, marking the flame position in the image, storing and uploading the image to the background terminal, determining the fire alarm position by the background terminal according to the three-dimensional model, and sending fire alarm information to a preset mobile terminal; and the execution module is used for obtaining the change of pixel values in the image by directly subtracting two adjacent frames of the image containing the flame if the flame position is overlapped with the cable position, judging the movement direction of the fire, calculating the movement rate of the fire, remotely stopping power supply in the tunnel by the background terminal when the movement rate of the fire reaches a preset value, and cutting off all cables in the preset area of the cable on fire.

In a third aspect, an embodiment of the present application provides an electronic device, including at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete mutual communication through a data bus; the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the intelligent safety monitoring method for the subway tunnel.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement a method for intelligently monitoring safety of a subway tunnel.

Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:

to prior art's problem, as long as it is less to lie in the detection area of sensor, and sensor quantity uses too much its cost too high again, so this design utilizes image recognition technology to carry out flame and judges, its advantage lies in, the camera can the detection area wide, and because be the monitoring flame, even so the condition that light is relatively poor, because of the luminance and the shape of flame self also can in time be discover by the camera to cooperate infrared camera to make fire monitoring can not receive other influences of environment, improved the security.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

FIG. 1 is a flow chart of an intelligent safety monitoring method for a subway tunnel according to the present invention;

FIG. 2 is another flow chart of an intelligent safety monitoring method for a subway tunnel according to the present invention;

FIG. 3 is a schematic view of the cable fire isolator of the present invention in use;

FIG. 4 is a schematic structural diagram of an intelligent safety monitoring system for a subway tunnel according to the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to the present invention.

An icon: 1. a picture acquisition module; 2. a model building module; 3. a monitoring module; 4. a preprocessing module; 5. a deep learning module; 6. a judgment module; 7. an execution module; 8. a processor; 9. a memory; 10. a data bus; 11. a cable fire isolator; 12. a metal housing; 13. a hydraulic cylinder; 14. cutting a cutter; 15. placing the holes.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings or orientations or positional relationships conventionally placed when products of the application are used, and are only used for convenience of description and simplification of the description, but do not indicate or imply that the devices or elements referred to must have specific orientations, be constructed in specific orientations, and be operated, and thus, should not be construed as limiting the present application.

In the description of the present application, it is also to be noted that, unless otherwise explicitly specified or limited, the terms "disposed" and "connected" are to be interpreted broadly, e.g., as being either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments and features of the embodiments described below can be combined with one another without conflict.

Example 1

Referring to fig. 1, for the intelligent safety monitoring method for the subway tunnel provided in the embodiment of the present application, for the problems in the prior art, as long as the detection area of the sensor is small and the cost of the sensor is too high due to excessive use, the present design utilizes the image recognition technology to perform flame determination, and has the advantages that the detection area of the camera is wide, and even if the light is poor, the brightness and the shape of the flame can be timely found by the camera, and the fire monitoring cannot be affected by other environments by matching with the infrared camera, thereby improving the safety.

S1: acquiring environment information of a tunnel;

for the intelligent monitoring of the tunnel, the ring shape in the tunnel needs to be grasped in advance, and thus, the environmental information of the tunnel, for example, the size information of each part in the tunnel needs to be acquired.

S2: establishing a three-dimensional model about the tunnel environment based on the environment information of the tunnel;

in order to remotely master the position of the emergency in the tunnel as far as possible, a three-dimensional model is established, so that maintenance personnel can quickly reach the designated position, and the maintenance efficiency is improved.

S3: arranging a plurality of visible light cameras and infrared cameras in the tunnel, and marking the positions of any visible light camera and any infrared camera in the tunnel on the three-dimensional model; simultaneously, marking the cable position in the tunnel in a three-dimensional model, wherein the monitoring area of a plurality of visible light cameras and infrared cameras covers the cable installation position in the tunnel;

and to the judgement of accurate position, then can mark the position of camera in advance to can confirm according to camera monitoring area, and because after the vehicle takes place the fire disaster in the tunnel, can not self conflagration can not spread, and the cable is then different, and it can burn along the cable very certainly, need monitor the cable equally from this, avoid tunnel equipment further loss.

S4: acquiring a video frame image by using a visible light camera and an infrared camera, and preprocessing the video frame image;

s5: constructing a flame color deep learning model by using a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through a flame color deep learning model;

for the identification of the flame, a K nearest neighbor classification algorithm and a naive Bayes method are adopted to construct a flame color deep learning model, so that AI is trained, and the flame is identified.

S6: if the recognition result reaches a threshold value, judging that the flame is a flame, marking the flame position in the image, storing the image and uploading the image to a background terminal, determining the fire alarm position according to the three-dimensional model by the background terminal, and sending fire alarm information to a preset mobile terminal;

and after the fire is found, the background terminal firstly receives the signal and then sends a fire alarm to a maintainer with a preset mobile terminal in the form of text information, voice information or telephone.

S7: if the flame position is overlapped with the cable position, the image containing the flame is directly subtracted from two adjacent frames to obtain the change of the pixel value in the image, the fire motion direction is judged, the fire motion speed is calculated, when the fire motion speed reaches a preset value, the background terminal remotely stops power supply in the tunnel, and all cables in a preset area of the cable which is on fire are cut off.

And aiming at the burning with the cable, the fire is extremely easy to continue to spread along the cable, so that in order to slow down the spread, the power supply in the tunnel is remotely stopped for the station terminal, and all the cables in the preset area of the cable on fire are cut off, thereby reducing further loss.

Referring to fig. 3, in some embodiments of the present invention, the step of isolating all cables in a predetermined area of a cable having a fire comprises: arranging cable fire isolators 11 on cables at preset intervals, and disconnecting the cables by using the cable fire isolators 11 after remotely stopping power supply in the tunnel at the background terminal; the cable fire isolator 11 comprises a metal shell 12, a cutting tool 14 arranged in the metal shell 12 and a hydraulic cylinder 13 connected with the cutting tool 14, wherein the cutting tool 14 is connected with the metal shell 12 in a sliding manner.

To the cable after the outage, it can slow down the intensity of a fire to a certain extent and spread, but to ageing cable, the fire-retardant material in it is out of order possibly, is judging from this behind the intensity of a fire motion direction, and this embodiment adopts direct physics to cut off, utilizes the cutting tool 14 of cable fire separator 11 to cut the cable promptly to avoid the intensity of a fire to spread, reduced the loss.

Referring to fig. 3, in some embodiments of the present invention, the metal shell 12 is provided with a placing hole 15 for passing a cable, and the length of the cutting edge of the cutting tool 14 is greater than the diameter of the placing hole 15.

In some embodiments of the present invention, when the fire is strong, although the cutting is performed, there is a possibility that a flame or spark is sputtered into the preventing hole of the cable fire isolator 11, thereby setting the length of the cutting edge of the cutting blade 14 to be larger than the diameter of the placing hole 15, and directly covering the placing hole 15 with the metal cutting blade 14, which improves safety.

In some embodiments of the invention, the step of building a three-dimensional model about the tunnel environment comprises: and establishing a BIM building information three-dimensional model about the tunnel environment.

In some embodiments of the present invention, the BIM three-dimensional model has light weight, visualization and simulation features compared to other three-dimensional models, and not only is a simple modeling but also can simulate a fire and provide simulation data for tunnel safety.

Referring to fig. 2, in some embodiments of the invention, S8: and if the identification result does not reach the threshold value, carrying out thermal imaging monitoring on the monitored area through the infrared camera, and if the thermal imaging analysis result shows that the area exceeds the preset temperature, sending overload information to a preset mobile terminal.

In some embodiments of the invention, the cable is first warmed up during combustion, thereby being monitored by an infrared camera. In addition, in order to avoid recognition errors of a common camera, the infrared camera can also carry out verification, and the accuracy is improved.

In some embodiments of the present invention, in case of a fire with a vehicle accident in the tunnel or a fire with a large area burning, the background terminal controls the ventilation system to start the ventilation mode to ventilate the tunnel, because the generated smoke is more harmful to people than the fire, so that the ventilation can effectively discharge the smoke and improve the survival rate of people.

Example 2

Referring to fig. 4, the intelligent safety monitoring system for a subway tunnel provided by the present invention includes a picture obtaining module 1, configured to obtain environment information of the tunnel; the model building module 2 is used for building a three-dimensional model related to the tunnel environment based on the environment information of the tunnel; the monitoring module 3 is used for arranging a plurality of visible light cameras and infrared cameras in the tunnel, and the positions of any visible light camera and any infrared camera in the tunnel are marked on the three-dimensional model; simultaneously, marking the cable position in the tunnel in a three-dimensional model, wherein the monitoring area of a plurality of visible light cameras and infrared cameras covers the cable installation position in the tunnel; the preprocessing module 4 is used for acquiring a video frame image by using a visible light camera and an infrared camera and carrying out preprocessing; the deep learning module 5 is used for constructing a flame color deep learning model by utilizing a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through a flame color deep learning model; the judging module 6 is used for judging that the flame is generated if the recognition result reaches a threshold value, marking the position of the flame in the image, storing the image and uploading the image to a background terminal, determining the position of a fire alarm by the background terminal according to the three-dimensional model, and sending fire alarm information to a preset mobile terminal; and the execution module 7 is used for obtaining the change of pixel values in the image by directly subtracting two adjacent frames of the image containing the flame if the flame position is overlapped with the cable position, judging the movement direction of the fire, calculating the movement rate of the fire, remotely stopping power supply in the tunnel by the background terminal when the movement rate of the fire reaches a preset value, and cutting off all cables in the preset area of the cable on fire.

Example 3

Referring to fig. 5, an electronic device according to the present invention includes at least one processor 8, at least one memory 9, and a data bus 10; wherein: the processor 8 and the memory 9 are communicated with each other through a data bus 10; the memory 9 stores program instructions executable by the processor 8, and the processor 8 calls the program instructions to execute a subway tunnel intelligent safety monitoring method. For example, to realize:

acquiring environment information of a tunnel; establishing a three-dimensional model about the tunnel environment based on the environment information of the tunnel; arranging a plurality of visible light cameras and infrared cameras in the tunnel, and marking the positions of any visible light camera and any infrared camera in the tunnel on the three-dimensional model; simultaneously, marking the cable position in the tunnel in a three-dimensional model, wherein the monitoring area of a plurality of visible light cameras and infrared cameras covers the cable installation position in the tunnel; acquiring a video frame image by using a visible light camera and an infrared camera, and preprocessing the video frame image; constructing a flame color deep learning model by using a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through a flame color deep learning model; if the recognition result reaches a threshold value, judging that the flame exists, marking the position of the flame in the image, storing the image and uploading the image to a background terminal, determining the position of a fire alarm by the background terminal according to the three-dimensional model, and sending fire alarm information to a preset mobile terminal; if the flame position is overlapped with the cable position, the image containing the flame is directly subtracted from two adjacent frames to obtain the change of the pixel value in the image, the fire motion direction is judged, the fire motion speed is calculated, when the fire motion speed reaches a preset value, the background terminal remotely stops power supply in the tunnel, and all cables in a preset area of the cable which is on fire are cut off.

The MEMORY 9 may be, but is not limited to, RANDOM ACCESS MEMORY (RAM), READ ONLY MEMORY (READ ONLY MEMORY, ROM), PROGRAMMABLE READ ONLY MEMORY (PROM), ERASABLE READ ONLY MEMORY (EPROM), electrically ERASABLE READ ONLY MEMORY (EEPROM), and the like.

The processor 8 may be an integrated circuit chip having signal processing capabilities. The PROCESSOR 8 may be a general-purpose PROCESSOR including a CENTRAL PROCESSING UNIT (CPU), a NETWORK PROCESSOR (NP), etc.; but also DIGITAL SIGNAL Processors (DSPs), APPLICATION SPECIFIC INTEGRATED CIRCUITs (ASICs), FIELD PROGRAMMABLE GATE ARRAYs (FPGAs) or other PROGRAMMABLE logic devices, discrete GATEs or transistor logic devices, discrete hardware components.

Example 4

The present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor 8, implements a method for intelligent safety monitoring of a subway tunnel. For example, the following steps are realized:

acquiring environment information of a tunnel; establishing a three-dimensional model about the tunnel environment based on the environment information of the tunnel; arranging a plurality of visible light cameras and infrared cameras in the tunnel, and marking the positions of any visible light camera and any infrared camera in the tunnel on the three-dimensional model; simultaneously, marking the cable position in the tunnel in a three-dimensional model, wherein the monitoring area of a plurality of visible light cameras and infrared cameras covers the cable installation position in the tunnel; acquiring a video frame image by using a visible light camera and an infrared camera, and preprocessing the video frame image; constructing a flame color deep learning model by using a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through a flame color deep learning model; if the recognition result reaches a threshold value, judging that the flame is a flame, marking the flame position in the image, storing the image and uploading the image to a background terminal, determining the fire alarm position according to the three-dimensional model by the background terminal, and sending fire alarm information to a preset mobile terminal; if the flame position is overlapped with the cable position, the image containing the flame is directly subtracted from two adjacent frames to obtain the change of the pixel value in the image, the fire motion direction is judged, the fire motion speed is calculated, when the fire motion speed reaches a preset value, the background terminal remotely stops power supply in the tunnel, and all cables in a preset area of the cable which is on fire are cut off.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a READ-ONLY MEMORY (ROM), a RANDOM ACCESS MEMORY (RAM), a magnetic disk or an optical disk, and the like.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims

1. An intelligent safety monitoring method for a subway tunnel is characterized by comprising the following steps:

acquiring environment information of a tunnel;

establishing a three-dimensional model about the tunnel environment based on the environment information of the tunnel;

arranging a plurality of visible light cameras and infrared cameras in the tunnel, wherein the positions of any visible light camera and any infrared camera in the tunnel are marked on the three-dimensional model; simultaneously marking the cable position in the tunnel in the three-dimensional model, wherein the monitoring areas of the plurality of visible light cameras and the infrared cameras cover the cable installation position in the tunnel;

acquiring a video frame image by using the visible light camera and the infrared camera, and preprocessing the video frame image;

constructing a flame color deep learning model by using a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through the flame color deep learning model;

if the recognition result reaches a threshold value, determining that the flame is a flame, labeling the position of the flame in the image, storing the image and uploading the image to a background terminal, determining the position of the fire according to the three-dimensional model by the background terminal, and sending fire information to a preset mobile terminal;

if the flame position is overlapped with the cable position, the image containing the flame is directly subtracted from two adjacent frames to obtain the change of the pixel value in the image, the fire motion direction is judged, the fire motion speed is calculated, when the fire motion speed reaches a preset value, the background terminal remotely stops power supply in the tunnel, and all cables in a preset area of the cable which is on fire are cut off.

2. The intelligent safety monitoring method for the subway tunnel according to claim 1, wherein the step of isolating all the cables in the preset area of the cable in fire comprises:

arranging cable fire isolators on cables at preset intervals, and disconnecting the cables by using the cable fire isolators after the background terminal remotely stops supplying power in the tunnel;

the cable fire barrier comprises a metal shell, a cutting tool arranged in the metal shell and a hydraulic cylinder connected with the cutting tool, wherein the cutting tool is connected with the metal shell in a sliding manner.

3. The intelligent safety monitoring method for the subway tunnel according to claim 2, wherein said metal casing is provided with a placing hole for passing a cable therethrough, and the length of the cutting edge of said cutting tool is greater than the diameter of said placing hole.

4. The intelligent safety monitoring method for a subway tunnel according to claim 1, wherein the step of establishing a three-dimensional model about said tunnel environment comprises: and establishing a BIM building information three-dimensional model of the tunnel environment.

5. The intelligent safety monitoring method for the subway tunnel according to claim 1, wherein if the recognition result does not reach the threshold, the thermal imaging monitoring is performed on the monitored area through the infrared camera, and if the thermal imaging analysis result shows that some areas exceed the preset temperature, the overload information is sent to the preset mobile terminal.

6. The intelligent safety monitoring method for the subway tunnel according to claim 1, wherein the step of sending the fire alarm information to the preset mobile terminal comprises: and the background terminal controls a ventilation system to start a ventilation mode to ventilate the tunnel.

7. The intelligent safety monitoring method for the subway tunnel according to claim 1, wherein the preprocessing step comprises:

and converting the image into a unified format preset by the deep learning model, and carrying out normalized dimensionless processing.

8. An intelligent safety monitoring system for a subway tunnel is characterized by comprising

The image acquisition module is used for acquiring the environment information of the tunnel;

the model establishing module is used for establishing a three-dimensional model related to the tunnel environment based on the environment information of the tunnel;

the monitoring module is used for arranging a plurality of visible light cameras and infrared cameras in the tunnel, and the positions of any visible light camera and any infrared camera in the tunnel are marked on the three-dimensional model; simultaneously marking the cable position in the tunnel in the three-dimensional model, wherein a plurality of visible light camera and infrared camera monitoring areas cover the cable installation position in the tunnel;

the preprocessing module is used for acquiring a video frame image by using the visible light camera and the infrared camera and carrying out preprocessing;

the deep learning module is used for constructing a flame color deep learning model by utilizing a K nearest classification algorithm and a naive Bayes method; performing flame identification on the video frame image through the flame color deep learning model;

the judging module is used for judging that the images are flames if the recognition result reaches a threshold value, labeling the positions of the flames in the images, storing and uploading the images to a background terminal, determining the positions of the fire alarms by the background terminal according to the three-dimensional model, and sending fire alarm information to a preset mobile terminal;

and the execution module is used for obtaining the change of a pixel value in an image by directly subtracting two adjacent frames of the image containing the flame if the flame position is overlapped with the cable position, judging the movement direction of the fire, calculating the movement rate of the fire, remotely stopping power supply in the tunnel by the background terminal when the movement rate of the fire reaches a preset value, and cutting off all cables in a preset area of the cable on fire.

9. An electronic device comprising at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete mutual communication through the data bus; the memory stores program instructions executable by the processor, the processor calling the program instructions to perform the method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.