Emergency command rescue system and method for mountain rail transit station

Abstract

The invention discloses an emergency command and rescue system and method for a mountain rail transit station. The emergency command and rescue system comprises the emergency command and rescue system for the mountain rail transit station and the emergency command and rescue method for the mountain rail transit station. The system comprises a command center and n mobile rescue subsystems which are carried by rescue workers during rescue implementation, and further comprises emergency navigation positioning subsystems, emergency monitoring subsystems based on image recognition and emergency voice recognition and dialogue subsystems which are arranged in s mountain track traffic stations and communicate with the command center in real time. The method comprises the steps of direct positioning, image positioning and analysis, sound positioning and analysis, trapped person indication in a scene model, rescue path indication, real-time monitoring and rescue and the like. According to the invention, when an emergency occurs, rescue workers can more conveniently and intuitively know the on-site condition, and the rescue efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field related to transportation station rescue, and in particular to an emergency command and rescue system and method for a mountain rail transit station. Background Art

[0002] Mountain rail transit is a new type of rail transit suitable for mountain characteristics, with the advantages of small footprint, large capacity, comfort and convenience. Since mountain rail transit stations are relatively closed and narrow spaces, a large number of passengers gather here in a short period of time during daily operations, especially during peak hours. Once an emergency occurs, the closed and narrow space will cause casualties, property losses, and negative social impacts.

[0003] However, the rescue method of the existing technology requires personnel to manually collect the location and situation information of all trapped persons on site, which results in a long time difference for the department in charge of the rescue work to formulate a rescue plan and low rescue efficiency. In addition, when the rescue route is blocked due to local building collapse or other situations on site, it is impossible to notify the rescue personnel in time, resulting in the failure to carry out rescue in time through the appropriate rescue route. Summary of the invention

[0004] In view of the above-mentioned defects, the present invention provides a mountain rail transit station emergency command and rescue system and method, which can enable rescue personnel to understand the on-site situation more conveniently and intuitively when an emergency occurs, thereby improving rescue efficiency.

[0005] In order to achieve the purpose of the present invention, the following technologies are proposed: A mountain rail transit station emergency command and rescue system, comprising: The command center includes a control host and a command display module. The control host stores scene models of s mountain rail transit stations. n mobile rescue subsystems carried by rescuers during rescue operations, the mobile rescue subsystems comprising a mobile camera module and a mobile display module; The emergency command and rescue system also includes the following facilities that are set up at each of the mountain rail transit stations for real-time communication with the command center: The emergency navigation and positioning subsystem includes multiple indoor direct positioning modules. Each mountain rail transit station includes multiple areas, and each area is equipped with at least one indoor direct positioning module. An emergency monitoring subsystem based on image recognition, the emergency monitoring subsystem based on image recognition includes a plurality of fixed camera modules, and each area of ​​a mountain rail transit station is provided with an image recognition array including at least two fixed camera modules; The emergency speech recognition and dialogue subsystem includes a plurality of sound receiving modules. Part or all of the areas of the mountain rail transit station are respectively provided with a sound receiving array including at least two sound receiving modules.

[0006] Furthermore, the command center also includes an editing interface, a command communication module, and the scenario model includes a map of the corresponding mountain rail transit station; The mobile rescue subsystem also includes a mobile communication module; Each emergency navigation and positioning subsystem also includes a first transceiver module; Each image recognition-based emergency monitoring subsystem also includes a second transceiver module; Each emergency speech recognition and dialogue subsystem also includes a third transceiver module.

[0007] Furthermore, the emergency navigation and positioning subsystem also includes a plurality of emergency channel control modules, and each emergency channel control module of the mountain rail transit station is used to control an emergency channel respectively.

[0008] A mountain rail transit station emergency command and rescue method using a mountain rail transit station emergency command and rescue system comprises the following steps: S100: When an emergency occurs in a mountain rail transit station, the mountain rail transit station collects the positions of trapped persons through each indoor direct positioning module of the emergency navigation and positioning subsystem, and sends the collected direct positioning coordinates of each trapped person in each area to the command center, and then the command center generates each trapped person instance in the scene model of the mountain rail transit station, and the trapped person instance includes the following variables: trapped person ID, location area, and positioning coordinates; S200: In the image recognition-based emergency monitoring subsystem of the mountain rail transit station where an emergency occurs, the image recognition array of each area identifies the trapped persons in the area, adds trapped person instances in the scene model for the trapped persons not found in step S100 in each area, and determines the criticality level of each trapped person; S300: In the emergency speech recognition and dialogue subsystem of the mountain rail transit station where an emergency occurs, each sound receiving array collects the voices of the trapped persons in the area where it is located, and separates the voices into separate sound sources of several trapped persons, and then locates the sound sources respectively. In each area, for the trapped persons who are not found through step S100 and step S200, the trapped persons instances are added to the scene model, and the criticality level of each trapped person is judged; S400: The command center displays the scene model of the mountain rail transit station where an emergency occurs on the command display module, and displays each trapped person instance at each predetermined position on the command display module according to the positioning coordinates of each trapped person; S500: The command center receives a group of rescue path instructions, each group of rescue path instructions respectively including multiple rescue paths for instructing rescue personnel to rescue trapped persons in one of the a areas of the mountain rail transit station in S400; S600: The command center displays all rescue paths described in S500 on the command display module, and the command center communicates with all mobile rescue subsystems. When each rescuer arrives at the mountain rail transit station described in S400, the mobile rescue subsystem sends entry feedback to the command center respectively. The command center adds a rescuer instance to the scene model. The rescuer instance includes the rescuer ID, the area where the rescuer is located, and the positioning coordinates. At the same time, the mobile camera module is started, and the video is recorded in real time and transmitted to the command center. When the rescuer enters the scene, the command center synchronously communicates the display content of the command display module to the mobile display module of the mobile rescue subsystem. S700: After the rescuer selects the area for rescue, if it is found that each rescue path in the area has obstacles during the rescue, then after the rescuer reports to the command center, the command center adds an obstacle removal mark at the obstacle position of the rescue path selected by the rescuer, and displays the obstacle removal mark on the command display module and the mobile display modules of all mobile rescue subsystems. When the obstacle is removed, the command center and the mobile rescue subsystem delete the obstacle removal mark, and then execute S800. If it is found that at least one rescue path in the area is unobstructed during the rescue, S800 is directly executed; S800: In a mountain rail transit station where an emergency occurs, S700 is executed multiple times. After all the trapped persons who can be rescued in the mountain rail transit station are rescued and leave the mountain rail transit station, the command center determines that the rescue is completed.

[0009] Furthermore, S200 includes: S210: Obtain the area number a of mountain rail transit stations where an emergency occurs; S220: set i=1; S230: The image recognition array of the i-th area acquires an image in the area and sends it to the command center; S240: The command center separates multiple images corresponding to each trapped person from the acquired images, and calculates the image positioning coordinates of b trapped persons by identifying the position of each trapped person in the images taken by multiple fixed camera modules; S250: traverse and compare the image positioning coordinates of the b trapped persons with the positioning coordinates of the p trapped person instances in the i-th area in the scene model of the mountain rail transit station described in S210, and generate a number of new trapped person instances for the trapped persons identified in S240 whose positioning coordinates do not exist in the trapped person instances matching the image positioning coordinates; S260: Determine whether i=a. If so, execute S270. If not, i=i+1 and execute S230 again. S270: After supplementation, q trapped person instances are included in the scene model, and the command center calculates the criticality level through the image of each trapped person corresponding to the trapped person instance, and adds the criticality level to the trapped person instance.

[0010] Further, the S250 includes: S251: Obtain the number p of trapped persons instances existing in the i-th area in the scene model of the mountain rail transit station described in S210; S252: set j=1; S253: Determine whether there is a trapped person instance among the existing p trapped person instances whose distance from the image positioning coordinates of the jth trapped person identified in S240 is less than a preset error w. If so, directly execute S255; if not, execute S254 first and then execute S255; S254: generating a new trapped person instance in the scene model, wherein the positioning coordinates of the trapped person instance adopt the image positioning coordinates; S255: Determine whether j=b. If so, S250 ends. If not, j=j+1 and S253 is executed again.

[0011] Furthermore, S300 includes: S310: Obtain the number c of areas with sound receiving arrays in a mountain rail transit station where an emergency occurs; S320: set x=1; S330: The sound receiving array in the x-th area obtains a sound clip in the area and sends it to the command center; S340: the command center separates the acquired sound fragments to obtain individual sound sources corresponding to a number of trapped persons, identifies each individual sound source, locates the sound source of each trapped person, and calculates the sound location coordinates of d trapped persons; S350: traverse and compare the sound positioning coordinates of the d trapped persons with the positioning coordinates of the q trapped person instances in the xth area in the scene model of the mountain rail transit station described in S310, and generate several new trapped person instances for the trapped persons whose positioning coordinates are not matched with the sound positioning coordinates identified in S340; S360: Determine whether x=c. If so, execute S370. If not, determine x=x+1 and execute S330 again. S370: After supplementation, k trapped person instances are included in the scene model.

[0012] Further, the S350 includes: S351: Obtain the number q of trapped persons instances existing in the x-th area in the scene model of the mountain rail transit station described in S310; S352: Set y=1; S353: Determine whether there is a trapped person instance among the existing q trapped person instances whose distance from the sound positioning coordinates of the yth trapped person identified in S340 is less than the preset error w. If so, directly execute S355; if not, execute S354 first and then execute S355; S354: generating a new trapped person instance in the scene model, wherein the positioning coordinates of the trapped person instance adopt the sound positioning coordinates; S355: Determine whether y=d. If so, S350 ends. If not, y=y+1 and S353 is executed again.

[0013] Furthermore, when executing S600 to S700, the following steps are also executed simultaneously: The command center sends a status feedback command to the mobile rescue subsystem of all rescuers at a preset time interval t, requiring each rescuer to send a normal status feedback through the mobile rescue subsystem; The one or more rescuers are determined to be trapped when at least one of the following two situations occurs: the command center receives trapped information actively sent by the mobile rescue subsystem of the one or more rescuers, or the command center does not receive normal status feedback sent by the mobile rescue subsystem of the one or more rescuers within a time interval t of a predetermined number of times m; In the scenario model of a mountain rail transit station where an emergency occurs, the control host of the command center converts the rescuer instance corresponding to each trapped rescuer into a trapped person instance, deletes the rescuer ID, and generates a trapped person ID. At the same time, the command center stops sending status feedback instructions to the mobile rescue subsystem of the trapped rescuer; For each trapped person instance converted from the rescuer instance, the area where each trapped rescuer is located is obtained through the area variable contained in the trapped person instance, and the image is obtained through the image recognition array of the area. Then, the emergency monitoring subsystem based on image recognition sends the image to the command center. The control host of the command center finds the trapped rescuer through the positioning coordinates of the trapped rescuer, separates the image of the trapped rescuer, calculates the criticality level, and adds the criticality level to the trapped person instance.

[0014] The beneficial effects of this technical solution are: 1. Through the scenario model and each instance of trapped persons detected therein, combined with the rescue path indicated by the command center, rescuers can make on-site rescue decisions more accurately and intuitively, thereby improving rescue efficiency and success rate.

[0015] 2. Detect trapped persons in mountain rail transit stations through multiple dimensions. First, people carrying communication tools such as mobile phones can be located through direct positioning. For the elderly, children and other people who cannot be directly located because they do not carry relevant equipment, they are first positioned and supplemented with detection through the image recognition array. At the same time, the critical level of the trapped persons detected in these two steps is determined. The critical level can be used for reference by rescue personnel, such as rescuing people in the principle of rescuing people from the easy to the difficult. In some on-site situations, due to obstruction of vision or conditions such as smoke, image recognition is still limited, so positioning and supplementary detection are performed through the sound receiving array, which further improves the accuracy of identifying people in need of rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The overall architecture diagram of the mountain rail transit station emergency command and rescue system of the embodiment of the present application is shown.

[0017] Figure 2 The overall flow chart of the emergency command and rescue method for a mountain rail transit station according to an embodiment of the present application is shown.

[0018] Figure 3 A flow chart of step S200 of the mountain rail transit station emergency command and rescue method according to an embodiment of the present application is shown.

[0019] Figure 4 A flow chart of step S250 of the mountain rail transit station emergency command and rescue method according to an embodiment of the present application is shown.

[0020] Figure 5 A flow chart of step S300 of the mountain rail transit station emergency command and rescue method according to an embodiment of the present application is shown.

[0021] Figure 6A flow chart of step S350 of the mountain rail transit station emergency command and rescue method according to an embodiment of the present application is shown.

[0022] Figure 7 A partial flow chart of a preferred implementation method of an emergency command and rescue method for a mountain rail transit station in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] The present application is further described below in conjunction with the accompanying drawings and embodiments.

[0024] like Figure 1 The shown example is an emergency command and rescue system for a mountain rail transit station, comprising a command center, n mobile rescue subsystems carried by rescue personnel during rescue operations, and the emergency command and rescue system further comprising emergency navigation and positioning subsystems, an emergency monitoring subsystem based on image recognition, and an emergency voice recognition and dialogue subsystem, each of which is respectively provided at s mountain rail transit stations that communicate with the command center in real time.

[0025] The command center includes a control host, an editing interface, a command display module, and a command communication module. The control host stores scene models of s mountain rail transit stations. The scene model includes a map of the corresponding mountain rail transit station. Specifically, the map is a two-dimensional map or a three-dimensional map.

[0026] The n mobile rescue subsystems are respectively carried by rescuers when carrying out rescue work. The mobile rescue subsystems include a mobile camera module, a mobile display module, and a mobile communication module.

[0027] The emergency navigation and positioning subsystem includes multiple indoor direct positioning modules, several emergency channel control modules, and a first transceiver module. Each mountain rail transit station includes multiple areas. Specifically, each area corresponds to the range of a room, or the range of an independent space. Each area is equipped with at least one indoor direct positioning module. Each emergency channel control module of the mountain rail transit station is used to control an emergency channel respectively.

[0028] Specifically, the indoor direct positioning module adopts a positioning method that mainly uses WIFI positioning and Bluetooth positioning, and is supplemented by RFID (radio frequency identification) positioning. WIFI and Bluetooth positioning are common and relatively mature positioning methods with high accuracy indoors. If the personnel do not turn on Bluetooth or WIFI, positioning can also be achieved by implanting RFID chips in tickets or work permits.

[0029] The emergency monitoring subsystem based on image recognition includes multiple fixed camera modules. Specifically, both the fixed camera module and the mobile camera module have thermal imaging functions, which are used to assist in insufficient light. The emergency monitoring subsystem based on image recognition also includes a second transceiver module. Each area of ​​the mountain rail transit station is provided with an image recognition array including at least two fixed camera modules.

[0030] The emergency voice recognition and dialogue subsystem includes multiple sound receiving modules, multiple broadcast alarm modules, and a third transceiver module. Part or all of the areas of the mountain rail transit station are respectively provided with a sound receiving array including at least two sound receiving modules. Preferably, part or all of the areas of the mountain rail transit station are respectively provided with a broadcast alarm module, for the command center to communicate with the trapped persons, calm their emotions, teach them self-rescue measures, and guide the trapped persons who are still able to move to leave the mountain rail transit station through the nearest emergency passage.

[0031] like Figure 2~Figure 7 As shown, a mountain rail transit station emergency command and rescue method using a mountain rail transit station emergency command and rescue system is operated in the following steps: S100: When an emergency occurs in a mountain rail transit station, the mountain rail transit station collects the positions of trapped persons through each indoor direct positioning module of the emergency navigation and positioning subsystem, and sends the collected direct positioning coordinates of each trapped person in each area to the command center, specifically, sending through the first transceiver module, receiving through the command communication module, and then controlling the host to parse the direct positioning coordinates of each trapped person, and generating each trapped person instance in the scene model of the mountain rail transit station, wherein the trapped person instance includes the following variables: trapped person ID, area, positioning coordinates, wherein the trapped person ID is an automatically generated positive integer, and in this embodiment, the trapped person ID is counted sequentially starting from 1; S200: In the image recognition-based emergency monitoring subsystem of the mountain rail transit station where an emergency occurs, the image recognition array of each area identifies the trapped persons in the area, adds trapped person instances to the scene model for the trapped persons not found in step S100 in each area, and determines the criticality level of each trapped person, including: S210: Acquire the area number a of the mountain rail transit station where the emergency occurs. Specifically, the area number a is pre-stored in the control host of the command center; S220: set i=1; S230: The image recognition array of the i-th area acquires an image in the area and sends it to the command center, specifically, sending it through the second transceiver module and receiving it through the command communication module; S240: The command center separates multiple images corresponding to each trapped person from the acquired image, and calculates the image positioning coordinates of b trapped persons by identifying the position of each trapped person in the image taken by multiple fixed camera modules. Specifically, multiple fixed camera modules of the image recognition array simultaneously capture the images of objects in space from different angles, and calculate the spatial position of the trapped person by comparing and analyzing the common features in these images and using algorithms such as triangulation. This is a common existing method of positioning through multiple images. S250: traverse and compare the image positioning coordinates of the b trapped persons with the positioning coordinates of the p trapped person instances in the i-th area in the scene model of the mountain rail transit station described in S210, and generate several new trapped person instances for the trapped persons whose positioning coordinates are identified in S240 and do not exist in the trapped person instances matching the image positioning coordinates. S250 includes: S251: Obtain the number p of trapped persons instances existing in the i-th area in the scene model of the mountain rail transit station described in S210; S252: set j=1; S253: Determine whether there is a trapped person instance among the existing p trapped person instances whose distance from the image positioning coordinates of the jth trapped person identified in S240 is less than a preset error w. If so, directly execute S255; if not, execute S254 first and then execute S255; S254: generating a new trapped person instance in the scene model, wherein the positioning coordinates of the trapped person instance adopt the image positioning coordinates; S255: Determine whether j=b. If so, S250 ends. If not, j=j+1 and S253 is executed again. S260: Determine whether i=a. If so, execute S270. If not, i=i+1 and execute S230 again. S270: After supplementation, the scene model includes q trapped person instances. The command center calculates the criticality level through the image of each trapped person corresponding to the trapped person instance, and adds the criticality level to the trapped person instance. Specifically, the criticality level visual judgment model is first trained on the control host. In this embodiment, the criticality level visual judgment model is a model obtained by training using a YOLO framework with millions of personnel feature images as a training set. The model is used to divide the criticality levels of trapped persons into three levels: unable to act, needing assistance to act, and unable to act. The trapped persons who are judged to be unable to move are the fallen wounded, the trapped persons who are judged to be in need of assistance are the elderly, children, and pregnant women, and the other trapped persons are judged to be in a critical level and can move on their own. For example, in a certain rescue operation, there are a number of trapped persons of these three critical levels in the station. The trapped persons who can move on their own leave by themselves through the prompt of the broadcast alarm module. For the other two types of trapped persons, the rescuers follow the principle of easy first and difficult later, first rescuing the trapped persons who need assistance, and then rescuing the trapped persons who are unable to move; S300: In the emergency speech recognition and dialogue subsystem of the mountain rail transit station where an emergency occurs, each sound receiving array collects the voices of the trapped persons in the area, separates the voices into separate sound sources of several trapped persons, and then locates the sound sources respectively. In each area, the trapped persons who are not found in step S100 and step S200 are added to the scene model as trapped persons, and the criticality level of each trapped person is judged, including: S310: Acquire the number c of areas with a sound receiving array in a mountain rail transit station where an emergency occurs. Specifically, the number c of areas with a sound receiving array is pre-stored in a control host of a command center; S320: Set x=1; S330: The sound receiving array of the x-th area obtains the sound clip in the area and sends it to the command center, specifically, sending it through the third transceiver module and receiving it through the command communication module; S340: The command center separates the acquired sound fragments to obtain individual sound sources corresponding to several trapped persons, and locates the sound source of each trapped person by identifying each individual sound source, and calculates the sound location coordinates of d trapped persons. Specifically, through the multiple sound receiving modules of the sound receiving array, for sound source separation, existing speech models, such as models based on deep learning (such as Wave-U-Net, Conv-TasNet, etc.), can be trained using a large number of labeled data sets, so as to have the ability to separate different sound sources from mixed signals. These models can identify and separate multiple superimposed sounds, providing a basis for subsequent sound source location. For sound source location, mature technologies such as multiple signal classification and signal parameter estimation based on rotation invariant technology are used. By decomposing the covariance matrix of the array received signal and constructing a spatial spectrum, the direction of the sound source is determined. These methods are suitable for multiple sound sources and have high direction finding accuracy and resolution. S350: traverse and compare the sound location coordinates of the d trapped persons with the location coordinates of the q trapped person instances in the xth area in the scene model of the mountain rail transit station described in S310, and generate several new trapped person instances for the trapped persons whose location coordinates are not matched with the sound location coordinates in the trapped person instances identified in S340. S350 includes: S351: Obtain the number q of trapped persons instances existing in the x-th area in the scene model of the mountain rail transit station described in S310; S352: Set y=1; S353: Determine whether there is a trapped person instance among the existing q trapped person instances whose distance from the sound positioning coordinates of the yth trapped person identified in S340 is less than the preset error w. If so, directly execute S355; if not, execute S354 first and then execute S355; S354: generating a new trapped person instance in the scene model, wherein the positioning coordinates of the trapped person instance adopt the sound positioning coordinates; S355: Determine whether y=d. If so, S350 ends. If not, y=y+1, and S353 is executed again. S360: Determine whether x=c. If so, execute S370. If not, determine x=x+1 and execute S330 again. S370: After supplementation, the scene model includes k trapped person instances. Specifically, the critical level variables of the (kq) trapped person instances supplemented in S350 are temporarily empty. After the rescuers arrive, the critical levels of the (kq) trapped persons are determined through images through the mobile camera module of the mobile rescue subsystem carried by the rescuers. The image recognition method is the same as the specific method described in S270. S400: The control host of the command center converts the scene model of the mountain rail transit station where the emergency occurs into visual data, displays it on the command display module, and converts each trapped person instance into visual data through the positioning coordinates of each trapped person, and displays it at each predetermined position on the command display module; S500: The command center receives a group of rescue path instructions, each group of rescue path instructions respectively includes multiple rescue paths for instructing rescue personnel to rescue trapped persons in one of the a areas of the mountain rail transit station described in S400. In this embodiment, three rescue paths are provided for each area. Specifically, the receiving of the rescue path instruction referred to in this step is for the command personnel to edit the rescue path through the editing interface; S600: The control host of the command center converts all the rescue paths described in S500 into visual data and displays them on the command display module. The command center communicates with all mobile rescue subsystems. When each rescuer arrives at the mountain rail transit station described in S400, the mobile rescue subsystem sends entry feedback to the command center respectively. The command center adds a rescuer instance to the scene model. The rescuer instance includes the rescuer ID, the area where the rescuer is located, and the positioning coordinates. The rescuer ID is an automatically generated positive integer. The rescuer has a locator, so the area where the rescuer is located and the positioning coordinates can be directly obtained and updated in real time and synchronized to the command center. At the same time, the mobile camera module is started, and the video is recorded in real time and transmitted to the command center. When the rescuer enters the scene, the command center synchronously communicates the display content of the command display module to the mobile display module of the mobile rescue subsystem. Specifically, communication is performed through the command communication module and the mobile communication module. S700: After the rescuers select the area for rescue, if it is found during the rescue that each rescue path in the area has obstacles, such as collapsed objects, making it impossible to pass, then after the rescuers report to the command center, the control host of the command center adds an obstacle removal mark at the obstacle position of the rescue path selected by the rescuers, and displays the obstacle removal mark on the command display module and the mobile display modules of all mobile rescue subsystems. When the obstacle is removed, the command center and the mobile rescue subsystem delete the obstacle removal mark, and then execute S800. If it is found during the rescue that at least one rescue path in the area is unobstructed, S800 is directly executed; S800: In a mountain rail transit station where an emergency occurs, S700 is executed multiple times by multiple rescue workers until all the trapped persons who can be rescued in the mountain rail transit station are rescued and leave the mountain rail transit station, and the command center determines that the rescue is completed. Specifically, the trapped persons who can be rescued in this step exclude those who have been confirmed dead by the rescue workers. The bodies of the people are not within the scope of rescue and generally need to wait for the subsequent special body handling team to handle them.

[0032] Preferably, in S100 to S300, there may still be trapped persons who have not been detected by the methods in these steps. In this case, during the execution of S700, the rescuers report to the command center on their own.

[0033] Further preferably, since the rescuers themselves may be trapped during the rescue, when executing S600 to S700, the following steps are also executed simultaneously: The command center sends a status feedback command to the mobile rescue subsystem of all rescuers at a preset time interval t, requiring each rescuer to send a normal status feedback through the mobile rescue subsystem; The one or more rescuers are determined to be trapped when at least one of the following two situations occurs: the command center receives trapped information actively sent by the mobile rescue subsystem of the one or more rescuers, or the command center does not receive normal status feedback sent by the mobile rescue subsystem of the one or more rescuers within a time interval t of a predetermined number of times m; In the scenario model of a mountain rail transit station where an emergency occurs, the control host of the command center converts the rescuer instance corresponding to each trapped rescuer into a trapped person instance, deletes the rescuer ID, and generates a trapped person ID. At the same time, the command center stops sending status feedback instructions to the mobile rescue subsystem of the trapped rescuer; For each trapped person instance converted from the rescuer instance, the area where each trapped rescuer is located is obtained through the area variable contained in the trapped person instance, and the image is obtained through the image recognition array of the area. Then, the emergency monitoring subsystem based on image recognition sends the image to the command center. The control host of the command center finds the trapped rescuer through the positioning coordinates of the trapped rescuer, separates the image of the trapped rescuer, calculates the criticality level, and adds the criticality level to the trapped person instance.

[0034] The above are only some of the embodiments listed in this application and are not intended to limit this application.

Claims

1. A mountain rail transit station emergency command and rescue system, characterized in that: include: The command center includes a control host and a command display module. The control host stores scene models of s mountain rail transit stations. n mobile rescue subsystems respectively carried by rescuers when carrying out rescue operations, the mobile rescue subsystems comprising a mobile camera module and a mobile display module; The emergency command and rescue system also includes s mountain rail transit stations that communicate with the command center in real time and are respectively provided with: The emergency navigation and positioning subsystem includes multiple indoor direct positioning modules. Each mountain rail transit station includes multiple areas, and each area is equipped with at least one indoor direct positioning module. An emergency monitoring subsystem based on image recognition, the emergency monitoring subsystem based on image recognition includes a plurality of fixed camera modules, and each area of ​​a mountain rail transit station is provided with an image recognition array including at least two fixed camera modules; The emergency speech recognition and dialogue subsystem includes a plurality of sound receiving modules. Part or all of the areas of the mountain rail transit station are respectively provided with a sound receiving array including at least two sound receiving modules.

2. The mountain rail transit station emergency command and rescue system according to claim 1 is characterized by: The command center also includes an editing interface and a command communication module, and the scenario model includes a map of the corresponding mountain rail transit station; The mobile rescue subsystem also includes a mobile communication module; Each emergency navigation and positioning subsystem also includes a first transceiver module; Each image recognition-based emergency monitoring subsystem also includes a second transceiver module; Each emergency speech recognition and dialogue subsystem also includes a third transceiver module.

3. The mountain rail transit station emergency command and rescue system according to claim 1 is characterized by: The emergency navigation and positioning subsystem also includes a plurality of emergency channel control modules, and each emergency channel control module of the mountain rail transit station is used to control an emergency channel respectively.

4. A mountain rail transit station emergency command and rescue method, characterized in that: The mountain rail transit station emergency command and rescue system according to claim 1 comprises the following steps: S100: When an emergency occurs in a mountain rail transit station, the mountain rail transit station collects the positions of trapped persons through each indoor direct positioning module of the emergency navigation and positioning subsystem, and sends the collected direct positioning coordinates of each trapped person in each area to the command center, and then the command center generates each trapped person instance in the scene model of the mountain rail transit station, and the trapped person instance includes the following variables: trapped person ID, location area, and positioning coordinates; S200: In the image recognition-based emergency monitoring subsystem of the mountain rail transit station where an emergency occurs, the image recognition array of each area identifies the trapped persons in the area, adds trapped person instances in the scene model for the trapped persons not found in step S100 in each area, and determines the criticality level of each trapped person; S300: In the emergency speech recognition and dialogue subsystem of the mountain rail transit station where an emergency occurs, each sound receiving array collects the voices of the trapped persons in the area where it is located, and separates the voices into separate sound sources of several trapped persons, and then locates the sound sources respectively. In each area, for the trapped persons who are not found through step S100 and step S200, the trapped persons instances are added to the scene model, and the criticality level of each trapped person is judged; S400: The command center displays the scene model of the mountain rail transit station where an emergency occurs on the command display module, and displays each trapped person instance at each predetermined position on the command display module according to the positioning coordinates of each trapped person; S500: The command center receives a group of rescue path instructions, each group of rescue path instructions respectively including multiple rescue paths for instructing rescue personnel to rescue trapped persons in one of the a areas of the mountain rail transit station in S400; S600: The command center displays all rescue paths described in S500 on the command display module, and the command center communicates with all mobile rescue subsystems. When each rescuer arrives at the mountain rail transit station described in S400, the mobile rescue subsystem sends entry feedback to the command center respectively. The command center adds a rescuer instance to the scene model. The rescuer instance includes the rescuer ID, the area where the rescuer is located, and the positioning coordinates. At the same time, the mobile camera module is started, and the video is recorded in real time and transmitted to the command center. When the rescuer enters the scene, the command center synchronously communicates the display content of the command display module to the mobile display module of the mobile rescue subsystem. S700: After the rescuer selects the area for rescue, if it is found that each rescue path in the area has obstacles during the rescue, then after the rescuer reports to the command center, the command center adds an obstacle removal mark at the obstacle position of the rescue path selected by the rescuer, and displays the obstacle removal mark on the command display module and the mobile display modules of all mobile rescue subsystems. When the obstacle is removed, the command center and the mobile rescue subsystem delete the obstacle removal mark, and then execute S800. If it is found that at least one rescue path in the area is unobstructed during the rescue, S800 is directly executed; S800: In a mountain rail transit station where an emergency occurs, S700 is executed multiple times. After all the trapped persons who can be rescued in the mountain rail transit station are rescued and leave the mountain rail transit station, the command center determines that the rescue is completed.

5. The mountain rail transit station emergency command and rescue method according to claim 4, characterized in that: S200 includes: S210: Obtaining the area number a of mountain rail transit stations where an emergency occurs; S220: set i=1; S230: The image recognition array of the i-th area acquires an image in the area and sends it to the command center; S240: The command center separates multiple images corresponding to each trapped person from the acquired images, and calculates the image positioning coordinates of b trapped persons by identifying the position of each trapped person in the images taken by multiple fixed camera modules; S250: traverse and compare the image positioning coordinates of the b trapped persons with the positioning coordinates of the p trapped person instances in the i-th area in the scene model of the mountain rail transit station described in S210, and generate a number of new trapped person instances for the trapped persons identified in S240 whose positioning coordinates do not exist in the trapped person instances matching the image positioning coordinates; S260: Determine whether i=a. If so, execute S270. If not, i=i+1 and execute S230 again. S270: After supplementation, q trapped person instances are included in the scene model, and the command center calculates the criticality level through the image of each trapped person corresponding to the trapped person instance, and adds the criticality level to the trapped person instance.

6. The mountain rail transit station emergency command and rescue method according to claim 5, characterized in that: S250 includes: S251: Obtain the number p of trapped persons instances existing in the i-th area in the scene model of the mountain rail transit station described in S210; S252: set j=1; S253: Determine whether there is a trapped person instance among the existing p trapped person instances whose distance from the image positioning coordinates of the jth trapped person identified in S240 is less than a preset error w. If so, directly execute S255; if not, execute S254 first and then execute S255; S254: generating a new trapped person instance in the scene model, wherein the positioning coordinates of the trapped person instance adopt the image positioning coordinates; S255: Determine whether j=b. If so, S250 ends. If not, j=j+1 and S253 is executed again.

7. The mountain rail transit station emergency command and rescue method according to claim 4, characterized in that: S300 includes: S310: Obtain the number c of areas with sound receiving arrays in a mountain rail transit station where an emergency occurs; S320: Set x=1; S330: The sound receiving array in the x-th area obtains a sound clip in the area and sends it to the command center; S340: the command center separates the acquired sound fragments to obtain individual sound sources corresponding to a number of trapped persons, identifies each individual sound source, locates the sound source of each trapped person, and calculates the sound location coordinates of d trapped persons; S350: traverse and compare the sound positioning coordinates of the d trapped persons with the positioning coordinates of the q trapped person instances in the xth area in the scene model of the mountain rail transit station described in S310, and generate several new trapped person instances for the trapped persons whose positioning coordinates are not matched with the sound positioning coordinates identified in S340; S360: Determine whether x=c. If so, execute S370. If not, determine x=x+1 and execute S330 again. S370: After supplementation, k trapped person instances are included in the scene model. The command center calculates the criticality level for each individual sound source of each trapped person corresponding to the (kq) trapped person instances supplemented in S350, and adds the criticality level to the (kq) trapped person instances.

8. The mountain rail transit station emergency command and rescue method according to claim 7, characterized in that: S350 includes: S351: Obtain the number q of trapped persons instances existing in the x-th area in the scene model of the mountain rail transit station described in S310; S352: Set y=1; S353: Determine whether there is a trapped person instance among the existing q trapped person instances whose distance from the sound positioning coordinates of the yth trapped person identified in S340 is less than the preset error w. If so, directly execute S355; if not, execute S354 first and then execute S355; S354: generating a new trapped person instance in the scene model, wherein the positioning coordinates of the trapped person instance adopt the sound positioning coordinates; S355: Determine whether y=d. If so, S350 ends. If not, y=y+1 and S353 is executed again.

9. The mountain rail transit station emergency command and rescue method according to claim 4, characterized in that: When executing S600~S700, the following steps are also executed at the same time: The command center sends a status feedback command to the mobile rescue subsystem of all rescuers at a preset time interval t, requiring each rescuer to send a normal status feedback through the mobile rescue subsystem; The one or more rescuers are determined to be trapped when at least one of the following two situations occurs: the command center receives trapped information actively sent by the mobile rescue subsystem of the one or more rescuers, or the command center does not receive normal status feedback sent by the mobile rescue subsystem of the one or more rescuers within a time interval t of a predetermined number of times m; In the scenario model of a mountain rail transit station where an emergency occurs, the control host of the command center converts the rescuer instance corresponding to each trapped rescuer into a trapped person instance, deletes the rescuer ID, and generates a trapped person ID. At the same time, the command center stops sending status feedback instructions to the mobile rescue subsystem of the trapped rescuer; For each trapped person instance converted from the rescuer instance, the area where each trapped rescuer is located is obtained through the area variable contained in the trapped person instance, and the image is obtained through the image recognition array of the area. Then, the emergency monitoring subsystem based on image recognition sends the image to the command center. The control host of the command center finds the trapped rescuer through the positioning coordinates of the trapped rescuer, separates the image of the trapped rescuer, calculates the criticality level, and adds the criticality level to the trapped person instance.

Images