Remote scheduling system and method for fire scene

Abstract

The invention provides a remote dispatching system and method for a fire scene, and relates to the technical field of fire dispatching, wavelet transformation is performed on a collected on-site thermal infrared image to obtain an interference-free on-site thermal infrared image, fire node extraction is performed on the interference-free on-site thermal infrared image to obtain all fire nodes in a target fire scene, and the fire nodes in the target fire scene are extracted. Determining a fire behavior spreading coefficient of each fire node in the target fire scene; acquiring fire scene information of the target fire scene, constructing a path topological graph by using corresponding node position parameters of each fire node in the fire scene information and all fire behavior spreading coefficients, and performing path search on the path topological graph according to scene fire behavior characteristics in the fire scene information to obtain a fire-fighting advancing path; the remote dispatching center dispatches the fire-fighting vehicles on the fire scene based on the fire-fighting advancing path, and transmits the state data to the block chain, so that a safe and effective fire-fighting path can be searched in time in a complex fire scene environment, and the efficiency of the remote dispatching system is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fire dispatching, and more specifically, to a remote dispatching system and method for a fire scene. Background Art

[0002] Remote dispatch at the fire scene is a complex and challenging task, which aims to optimize resource allocation and rescue strategies through real-time monitoring and data analysis to effectively respond to sudden fire incidents. Remote dispatch centers usually rely on advanced technical means, such as thermal infrared imaging, drone monitoring and geographic information systems (GIS), to obtain real-time status information of the fire scene, including the development of the fire, the location of trapped people, and changes in the surrounding environment. This information can provide decision makers with an intuitive understanding of the fire scene, enabling them to make scientific and reasonable dispatch decisions in a timely manner.

[0003] However, the unpredictability of fires makes the situation at the fire scene change rapidly. The fire may spread rapidly due to meteorological factors such as wind speed and humidity. The remote dispatch center needs to be able to update data in real time and respond quickly. In addition, the fire environment is complex and changeable. Factors such as terrain, buildings, smoke and high temperature will affect the actions of firefighters and the use of equipment, increasing the difficulty of dispatch. Especially in complex environments such as urban high-rise buildings or forest fires, the path and speed of fire spread are often difficult to predict. The dispatch center needs to use models to predict the development of the fire in order to formulate effective firefighting strategies. Therefore, how to search for safe and effective firefighting paths in a complex fire environment in a timely manner to improve the efficiency of the remote dispatch system is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a remote dispatch system and method for a fire scene, which can timely search for a safe and effective firefighting path in a complex fire scene environment to improve the efficiency of the remote dispatch system.

[0005] In a first aspect, the present application provides a remote dispatching method for a fire scene, the dispatching method comprising the following steps:

[0006] Collect on-site thermal infrared images of the target fire scene;

[0007] Performing wavelet transform on the on-site thermal infrared image to obtain an undisturbed on-site thermal infrared image, extracting fire nodes from the undisturbed on-site thermal infrared image to obtain all fire nodes in the target fire scene, and then determining the fire spread coefficient of each fire node in the target fire scene;

[0008] Obtaining fire scene information of a target fire scene, using the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology map of fire fighting vehicles in the target fire scene, performing a path search on the path topology map according to the on-site fire characteristics in the fire scene information, and obtaining a fire fighting travel path of the fire fighting vehicle in the target fire scene;

[0009] The firefighting path is transmitted to a remote dispatching center using blockchain technology. The remote dispatching center dispatches fire trucks at the fire scene based on the firefighting path, and then transmits the status data of the fire truck dispatching process to the blockchain in real time.

[0010] In this embodiment, a firefighting drone is used to collect on-site thermal infrared images of the target fire scene.

[0011] In this embodiment, performing wavelet transform on the on-site thermal infrared image to obtain the on-site thermal infrared image without interference specifically includes:

[0012] Performing multi-scale two-dimensional wavelet decomposition on the on-site thermal infrared image based on a given wavelet basis to obtain an approximation coefficient and a detail coefficient corresponding to the on-site thermal infrared image;

[0013] Performing adaptive threshold processing on the detail coefficient to obtain the detail coefficient after interference removal;

[0014] An inverse transformation is performed based on the approximation coefficient and the detail coefficient after interference removal to obtain an interference-free on-site thermal infrared image.

[0015] In this embodiment, the fire nodes are extracted from the non-interference on-site thermal infrared image to obtain all the fire nodes in the target fire scene, including:

[0016] Performing morphological operations on the non-interference on-site thermal infrared image to obtain all fire source areas in the target fire scene;

[0017] Extract features from each fire source area respectively to obtain the temperature features corresponding to each fire source area;

[0018] Labels are assigned to each fire source area according to the corresponding temperature characteristics, and then all fire nodes in the target fire scene are obtained.

[0019] In this embodiment, determining the fire spread coefficient of each fire node in the target fire scene specifically includes:

[0020] For each fire node, determine the fire source area corresponding to the fire node in the target fire scene;

[0021] Input the corresponding fire source area into the simulation software for simulation, and obtain the fire spread flow diagram corresponding to the fire node;

[0022] The fire spread coefficient of the fire node is determined according to the fire spread flow diagram, and then the fire spread coefficient of each fire node is obtained.

[0023] In this embodiment, the fire scene information of the target fire scene is obtained through the sensor system carried by the firefighting drone.

[0024] In this embodiment, using the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology diagram of fire fighting vehicles in the target fire scene specifically includes:

[0025] For each fire node, obtaining the node position parameter corresponding to the fire node in the fire scene information;

[0026] Determine the node disaster tolerance of the fire node through the node position parameter, and then obtain the node disaster tolerance of each fire node;

[0027] Based on all fire spread coefficients and node disaster tolerance, topological connections are made between each fire node to obtain the path topology map of the fire trucks in the target fire scene.

[0028] In this embodiment, the path search is performed on the path topology map according to the on-site fire characteristics in the fire scene information to obtain the firefighting travel path of the fire truck at the target fire scene, specifically including:

[0029] Determining the path safety of each travel path in the path topology map according to the on-site fire characteristics in the fire scene information;

[0030] The path safety of each travel path is marked in the path topology map, and then the path topology map after safety marking is obtained.

[0031] The fire scene information and the safety-annotated path topology map are used as inputs for path search, thereby obtaining the firefighting travel path of the fire truck at the target fire scene.

[0032] In this embodiment, the remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path, specifically including:

[0033] The remote dispatch center analyzes the demand for firefighting materials according to the firefighting route and obtains a dispatch plan for the target fire scene;

[0034] Firefighting vehicles at the fire scene are dispatched according to the dispatch plan.

[0035] In a second aspect, the present application provides a remote dispatching system for a fire scene, which is used to execute a remote dispatching method for a fire scene, and the dispatching system includes:

[0036] Fire scene image acquisition module, used to collect on-site thermal infrared images of the target fire scene;

[0037] A fire spread feature extraction module is used to perform wavelet transform on the on-site thermal infrared image to obtain an undisturbed on-site thermal infrared image, extract fire nodes from the undisturbed on-site thermal infrared image to obtain all fire nodes in the target fire scene, and then determine the fire spread coefficient of each fire node in the target fire scene;

[0038] A firefighting path determination module is used to obtain the fire scene information of the target fire scene, use the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology map of the firefighting vehicle in the target fire scene, perform a path search on the path topology map according to the on-site fire characteristics in the fire scene information, and obtain the firefighting travel path of the firefighting vehicle in the target fire scene;

[0039] The fire remote dispatch module is used to use blockchain technology to transmit the fire travel path to the remote dispatch center. The remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path, and then transmits the status data of the fire truck dispatch process to the blockchain in real time.

[0040] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0041] By collecting on-site thermal infrared images of the target fire scene; performing wavelet transform on the on-site thermal infrared images to obtain undisturbed on-site thermal infrared images, performing fire node extraction on the undisturbed on-site thermal infrared images to obtain all fire nodes in the target fire scene, and then determining the fire spread coefficient of each fire node in the target fire scene; obtaining the fire scene information of the target fire scene, using the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology map of the fire truck in the target fire scene, performing path search on the path topology map according to the on-site fire characteristics in the fire scene information, and obtaining the firefighting path of the fire truck in the target fire scene; using blockchain technology to transmit the firefighting path to a remote dispatching center, the remote dispatching center dispatches the fire trucks at the fire scene based on the firefighting path, and then transmitting the status data of the fire truck dispatching process to the blockchain in real time.

[0042] It can be seen that in this application, a safe and effective fire-fighting path can be searched in a complex fire environment in a timely manner; among them, the wavelet transform can effectively remove noise, enhance the details of the on-site thermal infrared image, make the fire source area more obvious, and extract the fire node, which can accurately identify the fire source area and temperature characteristics in the target fire scene. Based on the fire spread coefficient, the spread speed and range of the fire can be dynamically monitored, which helps to quickly plan a safe and effective fire-fighting path; then, the real-time fire information and fire nodes are used to ensure that the decision is based on the actual situation rather than assumptions, thereby improving the accuracy and scientificity of the judgment, and through path search, the optimal travel path can be quickly determined, and a relatively safe travel route can be selected by evaluating and marking the safety of the path; finally, the remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path, effectively improving the efficiency of the remote dispatch system, and by transmitting the status data to the blockchain in real time, all relevant parties can access this data in real time, so as to understand the current status and travel status of the fire trucks. This transparency helps to improve the coordination of emergency response and enable all parties to respond in time.

[0043] In summary, the technical solution adopted in this application can timely search for safe and effective firefighting paths in a complex fire environment to improve the efficiency of the remote dispatch system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 is a flow chart of a remote dispatch method for a fire scene provided by the present application;

[0046] Figure 2 is an exemplary flow chart for determining a fire node according to the present application;

[0047] Figure 3 is an exemplary flow chart of determining a path topology map provided by the present application;

[0048] Figure 4 It is a module structure diagram of a remote dispatch system for fire scenes provided in accordance with the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] The embodiment of the present application provides a remote dispatch system and method for a fire scene, the core of which is to collect the on-site thermal infrared image of the target fire scene; perform wavelet transform on the on-site thermal infrared image to obtain the non-interference on-site thermal infrared image, perform fire node extraction on the non-interference on-site thermal infrared image to obtain all the fire nodes in the target fire scene, and then determine the fire spread coefficient of each fire node in the target fire scene; obtain the fire scene information of the target fire scene, use the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology map of the fire truck in the target fire scene, perform path search on the path topology map according to the on-site fire characteristics in the fire scene information, and obtain the firefighting path of the fire truck in the target fire scene; use blockchain technology to transmit the firefighting path to the remote dispatch center, and the remote dispatch center dispatches the fire trucks at the fire scene based on the firefighting path, and then transmits the status data in the fire truck dispatching process to the blockchain in real time. The above scheme can timely search for safe and effective firefighting paths in complex fire environments to improve the efficiency of the remote dispatching system.

[0051] Embodiment 1

[0052] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG. 1 , this figure is an exemplary flow chart of a remote dispatching method for a fire scene according to this embodiment of the present application, and the dispatching method includes the following steps:

[0053] In step S1, a thermal infrared image of the target fire scene is collected.

[0054] In specific implementation, on-site thermal infrared images of the target fire scene are collected through firefighting drones. First, a firefighting drone suitable for the fire scene is selected, which should be equipped with a high-performance thermal infrared camera. Then, the firefighting drone takes off according to the established flight plan and controls the firefighting drone to fly over the target fire scene. The thermal infrared camera is used to collect thermal infrared images of the fire scene, which can effectively identify the fire source and temperature distribution, and can produce clear images even in smoke or night conditions.

[0055] In step S2, wavelet transform is performed on the on-site thermal infrared image to obtain an undisturbed on-site thermal infrared image, and fire nodes are extracted from the undisturbed on-site thermal infrared image to obtain all fire nodes in the target fire scene, thereby determining the fire spread coefficient of each fire node in the target fire scene.

[0056] In this embodiment, the wavelet transform is performed on the on-site thermal infrared image to obtain the on-site thermal infrared image without interference, which can be specifically carried out in the following manner, namely:

[0057] Performing multi-scale two-dimensional wavelet decomposition on the on-site thermal infrared image based on a given wavelet basis to obtain an approximation coefficient and a detail coefficient corresponding to the on-site thermal infrared image;

[0058] Performing adaptive threshold processing on the detail coefficient to obtain the detail coefficient after interference removal;

[0059] An inverse transformation is performed based on the approximation coefficient and the detail coefficient after interference removal to obtain an interference-free on-site thermal infrared image.

[0060] In the specific implementation, first, a suitable wavelet basis can be selected according to the application requirements and image characteristics. The wavelet basis selected in this application is Haar wavelet, so that the selected wavelet basis is used to perform multi-scale two-dimensional wavelet decomposition on the on-site thermal infrared image. This process decomposes the on-site thermal infrared image into multiple frequency sub-bands, namely, approximation coefficients and detail coefficients corresponding to the on-site thermal infrared image, wherein the approximation coefficient contains the low-frequency information of the on-site thermal infrared image, representing the overall structure and contour of the on-site thermal infrared image, and the detail coefficient contains the high-frequency information of the on-site thermal infrared image, representing the details and noise of the on-site thermal infrared image; then, the detail coefficient is subjected to adaptive threshold processing to obtain the detail coefficient after interference removal. The adaptive threshold can be calculated according to the distribution of detail coefficients. The adaptive threshold can be determined by Bayesian estimation, so as to apply threshold processing to the detail coefficients. The detail coefficients below the adaptive threshold are set to zero, and the detail coefficients above the adaptive threshold are retained to remove noise from the on-site thermal infrared image. Finally, the approximation coefficients and the detail coefficients after interference removal are used for inverse wavelet transform to reconstruct the interference-free on-site thermal infrared image. The inverse transform recombines the denoised frequency information to obtain a clear image. The wavelet reconstruction algorithm (such as Mallat algorithm) is applied to combine the approximation coefficients and the detail coefficients after interference removal to generate the final interference-free on-site thermal infrared image.

[0061] Preferably, in this embodiment, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart of determining fire nodes in an embodiment of the present application. In this embodiment, the fire nodes are extracted from the non-interference on-site thermal infrared image to obtain all the fire nodes in the target fire scene, which can be specifically implemented by the following steps:

[0062] First, in step S21, a morphological operation is performed on the non-interference on-site thermal infrared image to obtain all fire source areas in the target fire scene;

[0063] Then, in step S22, feature extraction is performed on each fire source area to obtain temperature features corresponding to each fire source area;

[0064] Finally, in step S23, labels are assigned to each fire source area according to the corresponding temperature characteristics, thereby obtaining all fire nodes in the target fire scene.

[0065] In specific implementation, first, morphological operations can be performed on the undisturbed on-site thermal infrared image, that is, the undisturbed on-site thermal infrared image is binarized to separate the fire source area from the background, so as to use the opening operation to remove small noise. The opening operation is a process of first corrosion and then expansion, which can effectively clean up small interferences in the image, and the closing operation is applied to fill the small holes in the fire source area to ensure the integrity of each fire source area, so as to mark the connected areas of the undisturbed on-site thermal infrared image, and all independent fire source areas can be identified; then, feature extraction can be performed on each fire source area respectively to obtain the temperature features corresponding to each fire source area, that is, the average temperature in the fire source area is calculated, and the average temperature is used as the temperature feature corresponding to the fire source area; finally, each fire source area is labeled according to the extracted temperature features. For example, a temperature threshold can be set, and only the area whose temperature feature exceeds the set critical value is marked as a fire node. The label may include a category (such as "high temperature fire source", "medium temperature fire source") and a number. All fire nodes in the target fire scene can be obtained in the above manner.

[0066] In this embodiment, the fire spread coefficient of each fire node in the target fire scene can be determined in the following manner, namely:

[0067] For each fire node, determine the fire source area corresponding to the fire node in the target fire scene;

[0068] Input the corresponding fire source area into the simulation software for simulation, and obtain the fire spread flow diagram corresponding to the fire node;

[0069] The fire spread coefficient of the fire node is determined according to the fire spread flow diagram, and then the fire spread coefficient of each fire node is obtained.

[0070] In the specific implementation, first, for each fire node, determine the fire source area corresponding to the fire node in the target fire scene. The fire source area information extracted previously can be used to determine the fire source area corresponding to the fire node in the target fire scene; then, the corresponding fire source area can be input into the simulation software for simulation to obtain the fire spread flow diagram corresponding to the fire node, that is, select the fire spread simulation software (such as FDS, PyroSim, etc.), set the simulation parameters according to the characteristics of the fire source area, including the fire source type, environmental parameters and fire source location, so as to start the simulation, observe the spread process of the fire source area, and generate Fire spread flow diagram, which will show the spread of fire in different time periods; finally, the fire spread coefficient of the fire node can be determined based on the fire spread flow diagram, that is, the generated fire spread flow diagram is analyzed to determine the fire spread characteristics of the fire node, including the spread speed and direction. In actual implementation, the area of ​​the fire source area can be multiplied by the fire spread speed, and the ratio of the result to the unit time can be used as the fire spread coefficient of the fire node. The fire spread coefficient represents the fire growth rate of the fire source area corresponding to the fire node. The fire spread coefficient of each fire node can be obtained in the above way.

[0071] It should be noted that wavelet transform can effectively remove noise, enhance the details of on-site thermal infrared images, make the fire source area more obvious, and extract fire nodes, which can accurately identify the fire source area and temperature characteristics in the target fire scene. Based on the fire spread coefficient, the spread speed and range of the fire can be dynamically monitored, which helps to quickly plan safe and effective firefighting routes, reduce the risks of firefighters, and improve rescue efficiency.

[0072] In step S3, the fire scene information of the target fire scene is obtained, and the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node are used to construct a path topology map of the fire truck in the target fire scene. The path topology map is searched for a path based on the on-site fire characteristics in the fire scene information to obtain the firefighting travel path of the fire truck in the target fire scene.

[0073] In specific implementation, the fire scene information of the target fire scene is obtained through the sensor system carried by the fire-fighting drone; it should be noted that the fire scene information includes the node position parameters of the target fire scene, on-site fire characteristics, humidity, wind speed and wind direction. In this application, the on-site fire characteristics represent the flame height in the target fire scene.

[0074] Preferably, in this embodiment, reference Figure 3As shown, this figure is an exemplary flow chart of determining a path topology map in an embodiment of the present application. In this embodiment, the path topology map of the fire fighting vehicles in the target fire scene is constructed using the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node. The following steps can be used to implement it:

[0075] First, in step S31, for each fire node, the node position parameter corresponding to the fire node in the fire scene information is obtained;

[0076] Then, in step S31, the node disaster tolerance of the fire node is determined by the node position parameter, and then the node disaster tolerance of each fire node is obtained;

[0077] Finally, in step S31, a topological connection is made between each fire node based on all fire spread coefficients and node disaster tolerance, thereby obtaining a path topology map of fire trucks in the target fire scene.

[0078] In specific implementation, first, for each fire node, the node position parameters corresponding to the fire node in the fire scene information are obtained, and the fire scene information previously obtained can be used to extract the specific coordinates of each fire node in the target fire scene; then, the node disaster tolerance of the fire node is determined by the node position parameters, and the node disaster tolerance represents the ability of the fire node to withstand the spread of fire. The ratio of the strength of the combustible material around the fire node to the resistance of the fire node (such as fire prevention facilities, personnel configuration, etc.) can be used as the node disaster tolerance of the fire node. The node disaster tolerance of each fire node can be obtained in the above manner; finally, based on all fire spread coefficients and node disaster tolerance, topological connections are made between each fire node, and a spread threshold and a bearing threshold can be set respectively, so as to screen out fire nodes with a fire spread coefficient lower than the spread threshold and a node disaster tolerance higher than the disaster tolerance threshold, and the screened fire nodes are connected. The path topology map of firefighting vehicles in the target fire scene can be obtained in the above manner, and the path topology map contains all travel paths with low fire risk in the target fire scene.

[0079] In this embodiment, the path search is performed on the path topology map according to the on-site fire characteristics in the fire scene information to obtain the firefighting travel path of the fire truck at the target fire scene, which can be specifically carried out in the following manner, namely:

[0080] Determining the path safety of each travel path in the path topology map according to the on-site fire characteristics in the fire scene information;

[0081] The path safety of each travel path is marked in the path topology map, and then the path topology map after safety marking is obtained.

[0082] The fire scene information and the safety-annotated path topology map are used as inputs for path search, thereby obtaining the firefighting travel path of the fire truck at the target fire scene.

[0083] In specific implementation, first, the path safety of each path in the path topology map can be determined by the on-site fire characteristics in the fire scene information. The path safety is used to indicate the safety degree of the path. In actual implementation, the path safety can be determined according to the following formula:

[0084]

[0085] Among them, α(x) represents the path safety of the travel path x, n represents the total number of fire nodes contained in the travel path x, β(x) represents the on-site fire characteristics on the travel path x, and A i represents the fire spread coefficient of the i-th fire node on the travel path x, B i represents the node disaster tolerance of the i-th fire node on the travel path x. The path safety of each travel path can be obtained by the above method. Then, the path safety of each travel path is marked in the path topology map, that is, each travel path in the path topology map is marked with safety, and different safety levels are represented by colors. For example, the path safety can be divided into multiple levels (such as high, medium, and low), and different colors (green, yellow, and red) are used to distinguish them. In this way, the safety marking information is integrated in the path topology map to obtain a path topology map with safety marking. Finally, the fire scene information and the path topology map with safety marking can be used as the path The input of path search can obtain the firefighting path of the fire truck at the target fire scene. The path search algorithm is used for path planning. The starting point and the end point can be set (usually the starting point of the firefighting resources and the key position of the fire scene). According to the marked path safety and path connection relationship, the feasible path from the starting point to each fire node is evaluated. During the path search process, if it is found that the path safety of some paths is reduced, the path selection can be dynamically adjusted to give priority to the path with high safety. In this way, the optimal firefighting path at the target fire scene is obtained through the path search algorithm, that is, the firefighting path of the fire truck at the target fire scene, ensuring that this path is safe and efficient.

[0086] It should be noted that the use of real-time fire scene information and fire nodes ensures that decisions are based on actual conditions rather than assumptions, thereby improving the accuracy and scientificity of judgments. In addition, through path search, the optimal path can be quickly determined. By evaluating and marking the safety of the path, a relatively safe route can be selected, thereby effectively reducing the risks of fire trucks at the fire scene.

[0087] In step S4, the firefighting path is transmitted to a remote dispatching center using blockchain technology. The remote dispatching center dispatches fire trucks at the fire scene based on the firefighting path, and then transmits the status data of the fire truck dispatching process to the blockchain in real time.

[0088] In specific implementation, blockchain technology can be used to transmit the firefighting route to a remote dispatch center.

[0089] In this embodiment, the remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path in the following manner, namely:

[0090] The remote dispatch center analyzes the demand for firefighting materials according to the firefighting route and obtains a dispatch plan for the target fire scene;

[0091] Firefighting vehicles at the fire scene are dispatched according to the dispatch plan.

[0092] In the specific implementation, first, the remote dispatch center parses the received firefighting route, identifies the key fire nodes in the route, the fire conditions of each fire node and the required response measures, and evaluates the firefighting materials required for each fire node according to the type and severity of the fire node, thereby summarizing the quantity and type of each type of materials to form a detailed material demand list; then, based on the material demand list and combined with the current inventory situation, a detailed firefighting vehicle dispatch plan is formulated. The firefighting vehicle dispatch plan includes the material allocation plan (such as which warehouse to allocate from, the quantity of each type of materials), transportation methods and route planning of firefighting vehicles to ensure that the materials can be delivered to the fire scene in the shortest time, and set priorities for each type of materials according to the urgency of the fire scene and the necessity of the materials to ensure that key materials are dispatched first; finally, according to the formulated dispatch plan, relevant personnel and firefighting vehicles are organized to dispatch and transport materials.

[0093] In addition, in the specific implementation, the status data of the fire truck dispatch process can be transmitted to the blockchain in real time; during the movement of the fire truck, its status is monitored in real time through the onboard sensor system, including location information (GPS), speed, temperature, fuel status and equipment status, etc. These real-time monitoring data are recorded through blockchain technology to ensure that each data point is tamper-proof. This can be achieved by regularly packaging and sending the data to the blockchain to form a timestamp record to ensure the authenticity and transparency of the data; all relevant parties (such as the dispatch center, on-site commanders, logistics support teams, etc.) can access this data in real time to understand the current status and movement of the fire truck. This transparency helps to improve the coordination of emergency response and enable all parties to respond in a timely manner.

[0094] It can be seen that in this application, a safe and effective fire-fighting path can be searched in a complex fire environment in a timely manner; among them, the wavelet transform can effectively remove noise, enhance the details of the on-site thermal infrared image, make the fire source area more obvious, and extract the fire node, which can accurately identify the fire source area and temperature characteristics in the target fire scene. Based on the fire spread coefficient, the spread speed and range of the fire can be dynamically monitored, which helps to quickly plan a safe and effective fire-fighting path; then, the real-time fire information and fire nodes are used to ensure that the decision is based on the actual situation rather than assumptions, thereby improving the accuracy and scientificity of the judgment, and through path search, the optimal travel path can be quickly determined, and a relatively safe travel route can be selected by evaluating and marking the safety of the path; finally, the remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path, effectively improving the efficiency of the remote dispatch system, and by transmitting the status data to the blockchain in real time, all relevant parties can access this data in real time, so as to understand the current status and travel status of the fire trucks. This transparency helps to improve the coordination of emergency response and enable all parties to respond in time.

[0095] In summary, the technical solution adopted in this application can timely search for safe and effective firefighting paths in a complex fire environment to improve the efficiency of the remote dispatch system.

[0096] Embodiment 2

[0097] This application provides a remote dispatch system for fire scene, referring to Figure 4 As shown, this figure is a schematic diagram of a scheduling system according to this embodiment of the present application, and the scheduling system includes:

[0098] The fire scene image acquisition module 100 is used to acquire on-site thermal infrared images of the target fire scene;

[0099] The fire spread feature extraction module 200 is used to perform wavelet transform on the on-site thermal infrared image to obtain an undisturbed on-site thermal infrared image, extract fire nodes from the undisturbed on-site thermal infrared image to obtain all fire nodes in the target fire scene, and then determine the fire spread coefficient of each fire node in the target fire scene;

[0100] The firefighting path determination module 300 is used to obtain the fire scene information of the target fire scene, use the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology map of the firefighting vehicle in the target fire scene, and perform a path search on the path topology map according to the on-site fire characteristics in the fire scene information to obtain the firefighting travel path of the firefighting vehicle in the target fire scene;

[0101] The fire remote dispatch module 400 is used to use blockchain technology to transmit the fire travel path to the remote dispatch center. The remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path, and then transmits the status data of the fire truck dispatch process to the blockchain in real time.

[0102] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0104] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A remote dispatching method for a fire scene, characterized in that: The scheduling method comprises the following steps: Collect on-site thermal infrared images of the target fire scene; Performing wavelet transform on the on-site thermal infrared image to obtain an undisturbed on-site thermal infrared image, extracting fire nodes from the undisturbed on-site thermal infrared image to obtain all fire nodes in the target fire scene, and then determining the fire spread coefficient of each fire node in the target fire scene; Obtaining fire scene information of a target fire scene, using the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology map of fire fighting vehicles in the target fire scene, performing a path search on the path topology map according to the on-site fire characteristics in the fire scene information, and obtaining a fire fighting travel path of the fire fighting vehicle in the target fire scene; The firefighting path is transmitted to a remote dispatching center using blockchain technology. The remote dispatching center dispatches fire trucks at the fire scene based on the firefighting path, and then transmits the status data of the fire truck dispatching process to the blockchain in real time.

2. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: On-site thermal infrared images of the target fire scene are collected by firefighting drones.

3. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: Performing wavelet transform on the on-site thermal infrared image to obtain an interference-free on-site thermal infrared image specifically includes: Performing multi-scale two-dimensional wavelet decomposition on the on-site thermal infrared image based on a given wavelet basis to obtain an approximation coefficient and a detail coefficient corresponding to the on-site thermal infrared image; Performing adaptive threshold processing on the detail coefficient to obtain the detail coefficient after interference removal; An inverse transformation is performed based on the approximation coefficient and the detail coefficient after interference removal to obtain an interference-free on-site thermal infrared image.

4. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: The fire nodes are extracted from the non-interference on-site thermal infrared image to obtain all the fire nodes in the target fire scene, including: Performing morphological operations on the non-interference on-site thermal infrared image to obtain all fire source areas in the target fire scene; Extract features from each fire source area respectively to obtain the temperature features corresponding to each fire source area; Labels are assigned to each fire source area according to the corresponding temperature characteristics, and then all fire nodes in the target fire scene are obtained.

5. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: Determining the fire spread coefficient of each fire node in the target fire scene specifically includes: For each fire node, determine the fire source area corresponding to the fire node in the target fire scene; Input the corresponding fire source area into the simulation software for simulation, and obtain the fire spread flow diagram corresponding to the fire node; The fire spread coefficient of the fire node is determined according to the fire spread flow diagram, and then the fire spread coefficient of each fire node is obtained.

6. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: The fire scene information of the target fire scene is obtained through the sensor system carried by the fire-fighting drone.

7. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: Using the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology diagram of fire fighting vehicles in the target fire scene specifically includes: For each fire node, obtaining the node position parameter corresponding to the fire node in the fire scene information; Determine the node disaster tolerance of the fire node through the node position parameter, and then obtain the node disaster tolerance of each fire node; Based on all fire spread coefficients and node disaster tolerance, topological connections are made between each fire node to obtain the path topology map of the fire trucks in the target fire scene.

8. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: The path search is performed on the path topology map according to the on-site fire characteristics in the fire scene information to obtain the firefighting travel path of the fire truck at the target fire scene, specifically including: Determining the path safety of each travel path in the path topology map according to the on-site fire characteristics in the fire scene information; The path safety of each travel path is marked in the path topology map, and then the path topology map after safety marking is obtained. The fire scene information and the safety-annotated path topology map are used as inputs for path search, thereby obtaining the firefighting travel path of the fire truck at the target fire scene.

9. A remote dispatching method for a fire scene as claimed in claim 1, characterized in that: The remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path, specifically including: The remote dispatch center analyzes the demand for firefighting materials according to the firefighting route and obtains a dispatch plan for the target fire scene; Firefighting vehicles at the fire scene are dispatched according to the dispatch plan.

10. A remote dispatching system for a fire scene, used to execute a remote dispatching method for a fire scene as claimed in any one of claims 1 to 9, characterized in that: The dispatching system comprises: Fire scene image acquisition module, used to collect on-site thermal infrared images of the target fire scene; A fire spread feature extraction module is used to perform wavelet transform on the on-site thermal infrared image to obtain an undisturbed on-site thermal infrared image, extract fire nodes from the undisturbed on-site thermal infrared image to obtain all fire nodes in the target fire scene, and then determine the fire spread coefficient of each fire node in the target fire scene; A firefighting path determination module is used to obtain the fire scene information of the target fire scene, use the node position parameters corresponding to each fire node in the fire scene information and the fire spread coefficient of each fire node to construct a path topology map of the firefighting vehicle in the target fire scene, perform a path search on the path topology map according to the on-site fire characteristics in the fire scene information, and obtain the firefighting travel path of the firefighting vehicle in the target fire scene; The fire remote dispatch module is used to use blockchain technology to transmit the fire travel path to the remote dispatch center. The remote dispatch center dispatches the fire trucks at the fire scene based on the fire travel path, and then transmits the status data of the fire truck dispatch process to the blockchain in real time.

Images