Fire scene fire monitoring method and system based on 3D laser scanning technology

Abstract

The present invention discloses a fire monitoring method and system based on three-dimensional laser scanning technology, which relates to the field of fire monitoring technology, including collecting a fire scene structure diagram for path planning, deploying sensors on a robot for real-time path navigation and obstacle avoidance; performing three-dimensional laser scanning and collecting data after reaching the target point, processing the collected data and performing three-dimensional modeling. The present invention combines three-dimensional laser scanning technology with a robot intelligent navigation system, utilizes high-precision three-dimensional point cloud data and sensor fusion technology, realizes comprehensive monitoring of the fire scene, and through the robot's autonomous path planning and obstacle avoidance, can dynamically collect data at the fire scene and perform three-dimensional modeling, analyze heat source distribution and smoke diffusion trajectory, and then predict the fire spread path, and generate a real-time updated three-dimensional fire scene map, which can provide efficient and accurate fire information in a complex environment, and provide an important basis for decision support and emergency rescue at the fire scene.

Description

Technical Field

[0001] The present invention relates to the technical field of fire monitoring, and in particular to a method and system for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology. Background Art

[0002] With the continuous development of fire rescue technology, traditional fire scene monitoring methods have been unable to cope with increasingly complex fire environments. In recent years, 3D laser scanning technology, as an accurate and efficient data acquisition technology, has been widely used in the fields of building structural analysis, post-disaster assessment and fire safety. 3D laser scanning technology can quickly collect high-density and high-precision spatial point cloud data through the laser radar system to generate detailed 3D models, providing strong data support for fire analysis, smoke diffusion prediction and rescue decision-making at the fire scene. In addition, with the development of robotics technology, more and more firefighting robots have begun to be used in real-time monitoring and rescue work at the fire scene. By deploying sensors such as laser radar and infrared thermal imagers, robots can perform path planning, navigation, obstacle avoidance, data collection and real-time feedback at the fire scene, improving the monitoring efficiency and safety of the fire scene. However, the existing fire scene fire monitoring methods have certain limitations, which are mainly reflected in several aspects. First, most traditional fire monitoring methods rely on manual or static equipment and cannot provide real-time and dynamic fire scene data. Especially in complex building structures or smoke environments, traditional methods often cannot accurately identify the source of fire and its spread. Secondly, although the existing robot navigation technology can achieve basic obstacle avoidance and path planning, it mostly relies on simple sensor information and does not fully utilize the advantages of 3D laser scanning and multi-sensor fusion, resulting in limited autonomous decision-making and fire spread prediction capabilities of robots in complex environments. In addition, existing smoke diffusion models often ignore the dynamic input of real-time data and fail to effectively integrate the changes in fire source location, temperature distribution, and smoke diffusion, resulting in low accuracy in fire spread path prediction. Therefore, traditional fire monitoring methods and existing robot applications have not yet been able to fully solve the problems of efficient collection of fire scene information, fire source analysis, spread prediction, and emergency rescue path planning. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing fire scene fire monitoring method and system based on three-dimensional laser scanning technology, the present invention is proposed.

[0004] Therefore, the present invention provides a fire scene fire monitoring method and system based on three-dimensional laser scanning technology to solve the problems that traditional fire monitoring methods and existing robot applications have not been able to comprehensively solve, such as efficient collection of fire scene information, fire source analysis, fire spread prediction, and emergency rescue path planning.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology, which includes collecting a structural diagram of the fire scene for path planning, and deploying sensors on a robot for real-time path navigation and obstacle avoidance;

[0007] After reaching the target point, three-dimensional laser scanning is performed and data is collected, and the collected data is processed and three-dimensional modeling is performed;

[0008] Based on 3D modeling, the heat source distribution is calibrated and the smoke diffusion trajectory and speed are analyzed to predict the fire spread path. Based on the analysis results, a 3D fire scene map is generated.

[0009] As a preferred solution of the fire scene fire monitoring method based on three-dimensional laser scanning technology of the present invention, wherein: the collecting of the fire scene structure diagram for path planning refers to collecting the building structure diagram of the fire scene, and the user imports the floor plan and elevation diagram of the building through the operation interface;

[0010] The fire scene area is abstracted into a network, where each node represents a location, the lines between nodes represent feasible paths, and the cost of each node consists of the actual cost and the estimated cost;

[0011] The actual cost refers to the actual path cost from the starting point to the current node, which represents the time and resources required for the robot to move from the starting point to the current position;

[0012] The estimated cost refers to the estimated cost from the current node to the target node, which is calculated using a heuristic function;

[0013] All feasible paths are evaluated through the A* algorithm, and the path with the smallest total cost is selected as the best route for the robot and the target point is determined.

[0014] As a preferred solution of the fire scene fire monitoring method based on three-dimensional laser scanning technology described in the present invention, wherein: the deployment of sensors on the robot for real-time path navigation and obstacle avoidance refers to deploying a laser radar and an infrared thermal imager on the robot, the robot scans the surrounding environment through the laser radar to obtain real-time environmental point cloud data, measures the distance to obstacles in all directions through the laser radar, monitors the heat source distribution of the fire scene in real time through the infrared thermal imager, generates thermal map data, marks high temperature areas according to the thermal map data, and fuses the measurement data of the laser radar and the infrared thermal imager through Kalman filtering to form a comprehensive environmental model;

[0015] Define the dynamic window according to the robot's speed, direction and environmental data in the environment model during driving, calculate the obstacle position of the robot at different speeds and steering angles, and calculate the safe distance between the robot and the obstacle and the length of the obstacle-free free path;

[0016] The optimal obstacle avoidance path is calculated using the DWA formula based on the robot's forward speed, steering angle, safety distance, and free path length;

[0017] After the obstacle avoidance path is confirmed, the robot performs path adjustment to avoid obstacles and adjust the motion trajectory in real time.

[0018] As a preferred solution of the fire scene fire monitoring method based on three-dimensional laser scanning technology described in the present invention, the three-dimensional laser scanning and data collection after reaching the target point refers to starting the laser radar scanner after the robot reaches the target point, collecting three-dimensional point cloud data of the fire scene, generating a spatial model, detecting the thermal radiation image of the target point through an infrared thermal imager, calibrating the high-temperature area of ​​the fire source in real time and generating a thermal map.

[0019] As a preferred solution of the fire scene fire monitoring method based on three-dimensional laser scanning technology described in the present invention, the processing of collected data and three-dimensional modeling refers to pre-processing the point cloud data and using a translation transformation algorithm to transform the coordinate system of the laser radar point cloud data and the robot coordinate system, using the ICP algorithm to splice multiple point cloud data after the coordinate system conversion, based on the merged point cloud data, using the Delaunay triangulation algorithm to convert the point cloud into a three-dimensional model, superimposing the heat source distribution map and temperature data on the three-dimensional model, mapping the temperature information to the surface of the three-dimensional model, and forming a three-dimensional thermal map of the heat source area.

[0020] As a preferred solution of the fire scene fire monitoring method based on three-dimensional laser scanning technology described in the present invention, wherein: the heat source distribution is calibrated based on three-dimensional modeling and the smoke diffusion trajectory and speed are analyzed, and the fire spread path is predicted, which means extracting the temperature data of each point from the three-dimensional model and confirming the heat source distribution of the target point based on the three-dimensional thermal map data, using the SVM model to classify the heat source data, classifying the heat source data of the target point into fire source points and non-fire source points, and identifying the fire source position in the three-dimensional space through SVM classification;

[0021] Collect wind speed and direction data at the fire scene and build a CFD model based on the fire source location and temperature distribution. Enter this data into the CFD software and set initial boundary conditions and physical parameters.

[0022] Solve the fluid dynamics equations through numerical methods, output the concentration distribution and diffusion speed of smoke at different time points according to the CFD simulation results, simulate its spreading path, speed and staying area, and generate the smoke diffusion map through the CFD simulation results;

[0023] The smoke diffusion map includes the change of smoke concentration at each moment, and indicates the area with the thickest smoke and the direction of spread;

[0024] Combined with the building structure diagram, analyze the flow path of smoke between different rooms and floors to assess the risk of fire spread;

[0025] During a fire, as the fire source changes and smoke spreads dynamically, new environmental data is continuously input for simulation updates.

[0026] As a preferred solution of the fire scene fire monitoring method based on the three-dimensional laser scanning technology of the present invention, wherein: the generation of a three-dimensional fire scene map based on the analysis result refers to using Kalman filtering to fuse the fire source location data, temperature data, smoke concentration distribution and diffusion path, and generating a three-dimensional fire scene map with the fused fire source location, smoke diffusion path and temperature data through a graphical tool;

[0027] The three-dimensional fire scene map includes the location of the fire source, the distribution of smoke concentration and the building structure;

[0028] The fire intelligence map is output to the on-site commanders to formulate real-time fire rescue plans.

[0029] In a second aspect, the present invention provides a fire scene fire monitoring system based on three-dimensional laser scanning technology, which comprises:

[0030] Path planning module, used to collect fire scene structure diagrams for path planning;

[0031] Navigation and obstacle avoidance module, which is used to deploy sensors on the robot for real-time path navigation and obstacle avoidance;

[0032] A 3D modeling module is used to perform 3D laser scanning and collect data after reaching the target point, process the collected data and perform 3D modeling;

[0033] The simulation and prediction module is used to build a CFD model to simulate smoke diffusion and predict the path and risk area of ​​fire spread;

[0034] The real-time monitoring module is used to generate a three-dimensional fire scene map based on the analysis results, and output the fire intelligence map to the on-site commanders for the formulation of real-time fire rescue plans.

[0035] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the fire scene fire monitoring method based on three-dimensional laser scanning technology as described in the first aspect of the present invention is implemented.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the fire scene fire monitoring method based on three-dimensional laser scanning technology as described in the first aspect of the present invention.

[0037] The beneficial effects of the present invention are as follows: the present invention combines three-dimensional laser scanning technology with a robot intelligent navigation system, utilizes high-precision three-dimensional point cloud data and sensor fusion technology to achieve comprehensive monitoring of the fire scene, and through the robot's autonomous path planning and obstacle avoidance, can dynamically collect data at the fire scene and perform three-dimensional modeling, analyze heat source distribution and smoke diffusion trajectory, and then predict the fire spread path, and generate a real-time updated three-dimensional fire scene map, which can provide efficient and accurate fire information in a complex environment, and provide an important basis for decision support and emergency rescue at the fire scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0039] Figure 1 Schematic diagram of the process of fire scene fire monitoring method based on three-dimensional laser scanning technology in Example 1.

[0040] Figure 2 This is a schematic diagram of the structure of the fire scene fire monitoring system based on three-dimensional laser scanning technology in Example 1. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a fire scene fire monitoring method based on three-dimensional laser scanning technology. The fire scene fire monitoring method based on three-dimensional laser scanning technology includes the following steps:

[0045] S1, collect the structural diagram of the fire scene for path planning, and deploy sensors on the robot for real-time path navigation and obstacle avoidance;

[0046] Specifically, collecting the fire scene structure diagram for path planning refers to collecting the building structure diagram at the fire scene, and the user imports the floor plan and elevation of the building through the operation interface;

[0047] The fire scene area is abstracted into a network, where each node represents a location, the lines between nodes represent feasible paths, and the cost of each node consists of the actual cost and the estimated cost;

[0048] The actual cost refers to the actual path cost from the starting point to the current node, which represents the time and resources required for the robot to move from the starting point to the current position;

[0049] The estimated cost refers to the estimated cost from the current node to the target node, which is calculated using a heuristic function;

[0050] All feasible paths are evaluated through the A* algorithm, and the path with the smallest total cost is selected as the best route for the robot and the target point is determined.

[0051] Collecting the fire scene structure diagram for path planning enables the robot to perform intelligent path planning based on the actual building structure information. By collecting the floor plan and elevation of the fire scene, users can understand the layout of the building, the location of doors and windows, and possible obstacles in advance, providing basic data for path planning. This process can help the robot avoid entering dangerous areas during the fire, and provide more accurate positioning support for rescue work at the fire scene. Accurate modeling of building structures is also a prerequisite for the successful execution of subsequent tasks such as fire spread prediction and smoke analysis. By abstracting the fire scene into a network model, each node represents a location and the connection represents a feasible path. This approach effectively transforms complex physical space into a computable network structure. Through such an abstract model, the path planning algorithm can handle the path search problem more efficiently, enabling the robot to make quick decisions in a complex and dynamic fire environment. At the same time, the setting of nodes also provides an operational reference point for subsequent environmental perception and monitoring, and provides a guarantee for improving the positioning and navigation accuracy of the robot. In path planning, by comprehensively evaluating the actual cost and estimated cost of each node, the robot can choose the optimal route. The actual cost reflects the resource consumption (such as time, energy, etc.) that the robot has already traveled on the current path, while the estimated cost infers the possible cost from the current node to the target node through a heuristic function. Combining the two, the robot can optimize the path in real time during the exploration process, avoid unnecessary detours or stagnation, and reduce the time and energy waste caused by misjudgment of the path. The A* algorithm can effectively find the path with the minimum total cost by combining the actual cost and the estimated cost, thereby providing the robot with the optimal route.

[0052] Furthermore, deploying sensors on the robot for real-time path navigation and obstacle avoidance means deploying a laser radar and an infrared thermal imager on the robot. The robot scans the surrounding environment through the laser radar to obtain real-time environmental point cloud data, measures the distance to obstacles in all directions through the laser radar, and monitors the heat source distribution at the fire scene in real time through the infrared thermal imager to generate thermal map data. High-temperature areas are marked according to the thermal map data, and the measurement data of the laser radar and the infrared thermal imager are fused through Kalman filtering to form a comprehensive environmental model.

[0053] Define the dynamic window according to the robot's speed, direction and environmental data in the environment model during driving, calculate the obstacle position of the robot at different speeds and steering angles, and calculate the safe distance between the robot and the obstacle and the length of the obstacle-free free path;

[0054] The optimal obstacle avoidance path is calculated using the DWA formula based on the robot's forward speed, steering angle, safety distance, and free path length;

[0055] After the obstacle avoidance path is confirmed, the robot performs path adjustment to avoid obstacles and adjust the motion trajectory in real time.

[0056] By deploying laser radar and infrared thermal imager on the robot, the data of the surrounding environment can be scanned and analyzed in real time. The environmental point cloud data generated by the laser radar helps the robot to accurately understand the location and shape of the surrounding obstacles, while the thermal image data of the infrared thermal imager provides key information for the rapid location of the fire source and the identification of the high-temperature area. Combining the data of these two sensors, the robot can dynamically perceive the changes in the fire scene, automatically plan the path and avoid obstacles, avoid collisions and continue to move forward. By fusing the data of the laser radar and infrared thermal imager through Kalman filtering, the noise can be effectively eliminated and the accuracy of the environmental model can be optimized. This technology not only improves the accuracy of sensor measurement, but also enables the robot to more clearly identify and understand the distribution of obstacles and fire sources in the surrounding environment. The application of the DWA algorithm enables the robot to respond quickly to changes in the surrounding environment, and ensures the real-time obstacle avoidance function during the movement process through flexible path adjustment. This is crucial for uncertain environmental changes in the fire scene. For example, if there is a sudden obstacle or change in the location of the fire source, the robot can respond immediately to avoid being trapped or damaged. After the obstacle avoidance path is confirmed, the robot will perform path adjustment to avoid obstacles and optimize the motion trajectory by adjusting the speed and steering angle. This process ensures that the robot can flexibly avoid complex obstacles at the fire scene (such as collapsed walls, leaked materials, etc.) and ensure the smooth execution of its tasks. By monitoring the distribution of fire sources with infrared thermal imagers and combining laser radar data for three-dimensional spatial modeling, the robot can accurately calibrate the location of the fire source and predict the speed and path of fire spread by analyzing heat source data. Through continuous monitoring of ambient temperature and smoke diffusion, the robot can provide real-time fire data to the fire command system to help formulate more accurate fire extinguishing and evacuation strategies.

[0057] S2, after reaching the target point, perform three-dimensional laser scanning and collect data, process the collected data and perform three-dimensional modeling;

[0058] Specifically, performing three-dimensional laser scanning and collecting data after reaching the target point means starting the laser radar scanner after the robot reaches the target point, collecting three-dimensional point cloud data of the fire scene, generating a spatial model, detecting the thermal radiation image of the target point through an infrared thermal imager, calibrating the high-temperature area of ​​the fire source in real time and generating a thermal map.

[0059] By combining 3D laser scanning technology with infrared thermal imaging monitoring systems, the spatial information and heat source distribution of the fire scene can be accurately captured, providing real-time fire source monitoring and spread prediction. This method has significant application prospects in fire safety monitoring, especially for monitoring and emergency response of fire scenes in complex buildings, underground facilities, etc. It can effectively improve the accuracy of fire monitoring, the speed of response and the safety of the scene.

[0060] Furthermore, processing the collected data and performing three-dimensional modeling means pre-processing the point cloud data and transforming the coordinate system of the lidar point cloud data and the robot coordinate system through a translation transformation algorithm, splicing multiple point cloud data after the coordinate system conversion using an ICP algorithm, converting the point cloud into a three-dimensional model based on the merged point cloud data using a Delaunay triangulation algorithm, superimposing a heat source distribution map and temperature data on the three-dimensional model, mapping the temperature information to the surface of the three-dimensional model, and forming a three-dimensional thermal map of the heat source area.

[0061] Preprocessing of point cloud data can remove errors and noise in the data, ensuring the accuracy and reliability of subsequent steps. The introduction of translation transformation algorithms, especially the conversion between robot and lidar coordinate systems, can effectively solve the coordinate errors caused by different sensor positions. Through this algorithm, data from different sensors can be accurately registered in a unified coordinate system. This process not only improves the accuracy of the data, but also lays the foundation for subsequent point cloud splicing and three-dimensional modeling. The use of the CP algorithm greatly improves the accuracy of point cloud data splicing. Multiple point cloud data usually come from different times or locations, and there is a certain spatial deviation. The ICP algorithm can accurately align these point clouds through repeated comparison and optimization, thus forming a more complete and detailed three-dimensional space model. The Delaunay triangulation algorithm can convert the spliced ​​point cloud data into a three-dimensional model, making the model boundary smoother, more stable and without overlap. This algorithm is crucial for generating accurate spatial geometric structures, especially in the modeling of buildings or complex scenes. At the fire scene, the heat source distribution map can effectively help identify the heat intensity, thereby providing a basis for the prediction of fire spread. By combining 3D modeling, heat source distribution maps and temperature data, a 3D heat map of the fire scene can be generated in real time, providing a scientific basis for smoke diffusion analysis and fire spread prediction. Based on the dynamic update of the 3D model, the changes of the fire can be continuously tracked, and the path, speed and direction of fire spread can be predicted, thereby providing accurate emergency response data for on-site commanders.

[0062] S3, based on 3D modeling, calibrate the heat source distribution and analyze the smoke diffusion trajectory and speed, predict the fire spread path, and generate a 3D fire scene map based on the analysis results;

[0063] Specifically, based on 3D modeling, heat source distribution is calibrated and smoke diffusion trajectory and speed are analyzed. Predicting the fire spread path means extracting temperature data of each point from the 3D model and confirming the heat source distribution of the target point based on the 3D thermal map data. The heat source data is classified using the SVM model, and the heat source data of the target point is classified into fire source points and non-fire source points. The fire source position in the 3D space is identified through SVM classification.

[0064] Collect wind speed and direction data at the fire scene and build a CFD model based on the fire source location and temperature distribution. Enter this data into CFD software such as OpenFOAM and set initial boundary conditions and physical parameters (such as fluid density, viscosity, temperature, etc.);

[0065] Solve the fluid dynamics equations through numerical methods, output the concentration distribution and diffusion speed of smoke at different time points according to the CFD simulation results, simulate its spreading path, speed and staying area, and generate the smoke diffusion map through the CFD simulation results;

[0066] The smoke diffusion map includes the change of smoke concentration at each moment, and indicates the area with the thickest smoke and the direction of spread;

[0067] Combined with the building structure diagram, analyze the flow path of smoke between different rooms and floors to assess the risk of fire spread;

[0068] During a fire, as the fire source changes and smoke spreads dynamically, new environmental data is continuously input for simulation updates.

[0069] Through accurate three-dimensional modeling and heat source distribution calibration, the present invention can clearly present the spatial layout and fire source location of the fire scene. This not only helps in real-time monitoring of the fire scene, but also provides basic data for fire spread prediction. The application of the SVM model improves the accuracy and efficiency of fire source identification. By classifying the heat source data, the present invention can automatically distinguish between the fire source and the non-fire source area, avoiding manual labeling and inefficient detection methods. The introduction of SVM classification technology not only enhances the automation and intelligence of fire source detection, but also effectively reduces false alarms and improves the reliability of the fire monitoring system. CFD simulation can accurately simulate the diffusion path and speed of smoke during the fire process, and generate a smoke diffusion map based on the simulation results. This process not only helps to predict the trajectory of fire spread, but also provides information on the area with the thickest smoke, guiding the fire brigade to formulate more scientific emergency response measures. By combining the building structure diagram with the smoke diffusion map and analyzing the flow path of smoke between different rooms and floors, the risk of fire spread can be assessed, helping firefighters to judge the spread trend of the fire and take precautions in advance.

[0070] Further, generating a three-dimensional fire scene map based on the analysis result means using Kalman filtering to fuse the fire source location data, temperature data, smoke concentration distribution and diffusion path, and generating a three-dimensional fire scene map by using a graphical tool to fuse the fused fire source location, smoke diffusion path and temperature data;

[0071] The three-dimensional fire scene map includes the location of the fire source, the distribution of smoke concentration and the building structure;

[0072] The fire intelligence map is output to the on-site commanders to formulate real-time fire rescue plans.

[0073] By fusing multiple sensor data through Kalman filtering technology, a three-dimensional fire scene map is generated in real time, which not only effectively improves the accuracy and real-time nature of fire scene information, but also provides fire commanders with a more intuitive and scientific basis for decision-making. It can effectively improve the efficiency of fire emergency response, optimize resource allocation, and ensure the safety of personnel during fire rescue. It is widely applicable to intelligent monitoring and management of various fire scenes.

[0074] This embodiment also provides a fire scene fire monitoring system based on three-dimensional laser scanning technology, including:

[0075] Path planning module, used to collect fire scene structure diagrams for path planning;

[0076] Navigation and obstacle avoidance module, which is used to deploy sensors on the robot for real-time path navigation and obstacle avoidance;

[0077] A 3D modeling module is used to perform 3D laser scanning and collect data after reaching the target point, process the collected data and perform 3D modeling;

[0078] The simulation and prediction module is used to build a CFD model to simulate smoke diffusion and predict the path and risk area of ​​fire spread;

[0079] The real-time monitoring module is used to generate a three-dimensional fire scene map based on the analysis results, and output the fire intelligence map to the on-site commanders for the formulation of real-time fire rescue plans.

[0080] This embodiment also provides a computer device, which is suitable for the fire scene fire monitoring method based on three-dimensional laser scanning technology, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the fire scene fire monitoring method based on three-dimensional laser scanning technology proposed in the above embodiment.

[0081] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0082] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the fire scene fire monitoring method based on three-dimensional laser scanning technology proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination of them, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

Claims

1. A fire scene fire monitoring method based on three-dimensional laser scanning technology, characterized in that: include, Collect structural diagrams of the fire scene for path planning, and deploy sensors on the robot for real-time path navigation and obstacle avoidance; After reaching the target point, three-dimensional laser scanning is performed and data is collected, and the collected data is processed and three-dimensional modeling is performed; Based on 3D modeling, the heat source distribution is calibrated and the smoke diffusion trajectory and speed are analyzed to predict the fire spread path. Based on the analysis results, a 3D fire scene map is generated.

2. The method for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology according to claim 1, characterized in that: The collecting of the fire scene structure diagram for path planning refers to collecting the building structure diagram at the fire scene, and the user imports the floor plan and elevation of the building through the operation interface; The fire scene area is abstracted into a network, where each node represents a location, the lines between nodes represent feasible paths, and the cost of each node consists of the actual cost and the estimated cost; The actual cost refers to the actual path cost from the starting point to the current node, which represents the time and resources required for the robot to move from the starting point to the current position; The estimated cost refers to the estimated cost from the current node to the target node, which is calculated using a heuristic function; All feasible paths are evaluated through the A* algorithm, and the path with the smallest total cost is selected as the best route for the robot and the target point is determined.

3. The method for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology according to claim 2, characterized in that: The deployment of sensors on the robot for real-time path navigation and obstacle avoidance refers to the deployment of a laser radar and an infrared thermal imager on the robot, wherein the robot scans the surrounding environment through the laser radar to obtain real-time environmental point cloud data, measures the distance to obstacles in all directions through the laser radar, and monitors the heat source distribution at the fire scene in real time through the infrared thermal imager to generate thermal map data, marks high temperature areas according to the thermal map data, and fuses the measurement data of the laser radar and the infrared thermal imager through Kalman filtering to form a comprehensive environmental model; Define the dynamic window according to the robot's speed, direction and environmental data in the environment model during driving, calculate the obstacle position of the robot at different speeds and steering angles, and calculate the safe distance between the robot and the obstacle and the length of the obstacle-free free path; The optimal obstacle avoidance path is calculated using the DWA formula based on the robot's forward speed, steering angle, safety distance, and free path length; After the obstacle avoidance path is confirmed, the robot performs path adjustment to avoid obstacles and adjust the motion trajectory in real time.

4. The method for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology as claimed in claim 3, characterized in that: The three-dimensional laser scanning and data collection after reaching the target point refers to starting the laser radar scanner after the robot reaches the target point, collecting three-dimensional point cloud data of the fire scene, generating a spatial model, detecting the thermal radiation image of the target point through an infrared thermal imager, calibrating the high-temperature area of ​​the fire source in real time and generating a thermal map.

5. The method for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology as claimed in claim 4, characterized in that: The processing of the collected data and three-dimensional modeling refers to pre-processing the point cloud data and using a translation transformation algorithm to unify the coordinate system of the lidar point cloud data and the robot coordinate system, using an ICP algorithm to splice multiple point cloud data after the coordinate system conversion, and based on the merged point cloud data, using a Delaunay triangulation algorithm to convert the point cloud into a three-dimensional model, superimposing a heat source distribution map and temperature data on the three-dimensional model, mapping the temperature information to the surface of the three-dimensional model, and forming a three-dimensional thermal map of the heat source area.

6. The method for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology according to claim 5, characterized in that: The heat source distribution is calibrated based on the three-dimensional modeling and the smoke diffusion trajectory and speed are analyzed to predict the fire spread path, which means extracting the temperature data of each point from the three-dimensional model and confirming the heat source distribution of the target point based on the three-dimensional heat map data, using the SVM model to classify the heat source data, classifying the heat source data of the target point into fire source points and non-fire source points, and identifying the fire source position in the three-dimensional space through SVM classification; Collect wind speed and direction data at the fire scene and build a CFD model based on the fire source location and temperature distribution. Enter this data into the CFD software and set initial boundary conditions and physical parameters. Solve the fluid dynamics equations through numerical methods, output the concentration distribution and diffusion speed of smoke at different time points according to the CFD simulation results, simulate its spreading path, speed and staying area, and generate the smoke diffusion map through the CFD simulation results; The smoke diffusion map includes the change of smoke concentration at each moment, and indicates the area with the thickest smoke and the direction of spread; Combined with the building structure diagram, analyze the flow path of smoke between different rooms and floors to assess the risk of fire spread; During a fire, as the fire source changes and smoke spreads dynamically, new environmental data is continuously input for simulation updates.

7. The method for monitoring fire conditions at a fire scene based on three-dimensional laser scanning technology according to claim 6, characterized in that: Generating a three-dimensional fire scene map based on the analysis results refers to using Kalman filtering to fuse the fire source location data, temperature data, smoke concentration distribution and diffusion path, and generating a three-dimensional fire scene map with the fused fire source location, smoke diffusion path and temperature data through a graphical tool; The three-dimensional fire scene map includes the location of the fire source, the distribution of smoke concentration and the building structure; The fire intelligence map is output to the on-site commanders to formulate real-time fire rescue plans.

8. A fire scene fire monitoring system based on three-dimensional laser scanning technology based on the fire scene fire monitoring method based on three-dimensional laser scanning technology according to any one of claims 1 to 7, characterized in that: include, Path planning module, used to collect fire scene structure diagrams for path planning; Navigation and obstacle avoidance module, which is used to deploy sensors on the robot for real-time path navigation and obstacle avoidance; A 3D modeling module is used to perform 3D laser scanning and collect data after reaching the target point, process the collected data and perform 3D modeling; The simulation and prediction module is used to build a CFD model to simulate smoke diffusion and predict the path and risk area of ​​fire spread; The real-time monitoring module is used to generate a three-dimensional fire scene map based on the analysis results, and output the fire intelligence map to the on-site commanders for the formulation of real-time fire rescue plans.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the fire scene fire monitoring method based on three-dimensional laser scanning technology described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fire scene fire monitoring method based on three-dimensional laser scanning technology described in any one of claims 1 to 7 are implemented.

Images