Building indoor fire risk early warning method and system based on 3D scanning
Through the 3D scanning-based building indoor fire risk warning method, the fire risks in the building indoors are identified and evaluated, and the shortcomings of traditional assessment methods are solved, and efficient and accurate fire risk monitoring and early warning are achieved.
Patent Information
- Application Number
- CN202411695687.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-25
- Publication Date
- 2025-03-07
AI Technical Summary
Traditional fire risk assessment methods have problems such as long assessment cycles, insufficient results, and the inability to achieve active fire monitoring throughout the entire period.
The indoor fire risk warning method of building based on 3D scanning is adopted to build a 3D model by obtaining 3D scanning results, identifying the target components to obtain their size and material information, calculate the fire risk index, and conduct full-time monitoring and early warning.
It realizes a more accurate and reliable fire risk assessment, and can conduct active fire monitoring throughout the whole period, save time and cost, and quickly obtain fire risk assessment results.
Smart Images
Figure CN119580469A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of fire warning technology, and in particular to a method and system for warning indoor fire risks in buildings based on 3D scanning. Background Art
[0002] The frequent occurrence of building fire accidents has always been an important safety issue worldwide. With the acceleration of urbanization and the increase in high-rise buildings and large commercial complexes, once a fire occurs, its harm is often more serious, not only causing huge economic losses, but also causing irreparable casualties. Therefore, how to quickly and accurately assess indoor fire risks and achieve effective early warning has become a key issue in improving building safety.
[0003] Traditional fire risk assessment methods are mostly focused on collecting various types of building information and firefighting facility layouts, such as building usage, building area data, fire alarm data, fire extinguishing system data, fire equipment status data, etc., and analyzing this information to derive the building's fire risk level. Traditional methods do not have real-time monitoring capabilities and cannot achieve continuous and active fire risk monitoring of the building environment. Moreover, traditional methods are based on building information for risk assessment, but fires mainly occur when combustibles in the building's interior catch fire, so risk assessment based on building information cannot accurately assess and warn of fire risks in the building in advance. In summary, current fire risk assessment methods have problems such as long assessment cycles, inaccurate results, and inability to achieve full-time active fire monitoring. Summary of the invention
[0004] Based on this, in response to the above technical problems, a building indoor fire risk warning method and system based on 3D scanning is provided to solve the problems of traditional fire risk assessment methods in the existing technology, such as long assessment cycle, inaccurate results, and inability to achieve full-time active fire monitoring.
[0005] In a first aspect, a method for early warning of indoor fire risk in a building based on 3D scanning is provided, the method comprising:
[0006] Acquire a 3D scanning result of the interior of a target building sent by a scanning device installed in the interior of the building; and construct a 3D model according to the 3D scanning result;
[0007] Performing target detection according to the 3D model, identifying target components and obtaining size and material information of the target components; the target components are components in the target building that can cause fire;
[0008] Acquire combustion property data of the target component according to the material information of the target component, and calculate the product of the combustion property data and the size of the target component to obtain the fire risk index of the target component;
[0009] Adding the fire risk indexes of all target components in the building to obtain a final fire risk index in the building;
[0010] The final fire risk index in the building is analyzed, and when the final fire risk index is greater than a certain threshold, an early warning is output.
[0011] In the above solution, optionally, after constructing the 3D model according to the 3D scanning result, the method further includes: preprocessing the 3D model and performing noise reduction processing.
[0012] In the above solution, further optionally, the 3D model is preprocessed based on convolutional neural network technology.
[0013] In the above solution, optionally, the 3D model performs target detection, identifies the target component and obtains the size and material information of the target component, including:
[0014] According to the 3D scanning results, the deep learning-based object detection method identifies the target parts and obtains the size and material information of the target parts.
[0015] In the above solution, optionally, the early warning includes issuing an early warning prompt to the fire department and the building manager or issuing an early warning prompt to the building manager.
[0016] In a second aspect, a building indoor fire risk early warning system based on 3D scanning, the system comprising:
[0017] 3D model building module: used to obtain the 3D scanning result of the target building interior sent by the scanning device installed in the building interior; and build a 3D model according to the 3D scanning result;
[0018] Target detection module: used to perform target detection based on the 3D model, identify target components and obtain the size and material information of the target components; the target components are components in the target building that can cause fire;
[0019] Combustion property acquisition module: used to obtain the combustion property data of the target component according to the material information of the target component, and calculate the product of the combustion property data and the size of the target component to obtain the fire risk index of the target component;
[0020] A final fire risk index acquisition module: used for adding the fire risk indexes of all target components in the building to obtain a final fire risk index in the building;
[0021] Warning result output module: analyzes the final fire risk index in the building, and outputs a warning when the final fire risk index is greater than a certain threshold.
[0022] In the above solution, optionally, the system further includes a preprocessing module for preprocessing the 3D model and performing noise reduction.
[0023] In the above solution, optionally, the early warning includes issuing an early warning prompt to the fire department and the building manager or issuing an early warning prompt to the building manager.
[0024] In a third aspect, a computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the building indoor fire risk warning method based on 3D scanning described in the first aspect are implemented.
[0025] In a fourth aspect, a computer program product includes a computer program / instruction, which, when executed by a processor, implements the steps of the building indoor fire risk warning method based on 3D scanning as described in the first aspect.
[0026] This application has at least the following beneficial effects:
[0027] This application constructs a 3D model of the interior of a building through 3D scanning, identifies the target components in the building, obtains the material information and size of the target components, obtains the combustion property data of the target components based on the material information of the target components, calculates the product of the combustion property data and the size of the target components to obtain the fire risk index of the target components; adds the fire risk indexes of all target components in the building to obtain the final fire risk index of the building; analyzes the final fire risk index of the building, and outputs an early warning when the final fire risk index is greater than a certain threshold. This application establishes an assessment method that comprehensively considers building information and fire risk factors of internal components. The assessment results are more accurate and reliable. Fire risk assessment based on fire risk factors of internal components can achieve full-time active fire monitoring. Moreover, with 3D scanning technology, there is no need for manual investigation, which saves time and cost, and quickly obtains fire risk assessment results. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 A flowchart of a method for early warning of indoor fire risk in a building based on 3D scanning is provided for one embodiment of the present application;
[0029] Figure 2 A structural diagram of a scanning device provided in one embodiment of the present application;
[0030] Description of reference numerals:
[0031] 1. Outer shell; 2. Mounting base; 3. Base; 4. Left camera; 5. Right camera; 6. LiDAR; 7. Depth camera. DETAILED DESCRIPTION
[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0033] In one embodiment, Figure 1 As shown, a method for early warning of indoor fire risk in a building based on 3D scanning is provided, the method comprising:
[0034] Step S1: obtaining a 3D scanning result of the interior of a target building sent by a scanning device installed in the interior of the building; and constructing a 3D model according to the 3D scanning result.
[0035] In step S1, Figure 2 The figure shows a schematic diagram of the structure of the scanning device. The camera and radar of the scanning device are used to perform a 3D scan of the fire activity scene, and a 3D model of the room is constructed by transmitting the data to the host.
[0036] Step S2: Target detection is performed based on the 3D model to identify target components and obtain size and material information of the target components; the target components are components in the target building that can cause fire.
[0037] In step S2, the object detection method based on deep learning (FasterR-CNN) identifies the target component and obtains the size and material information of the target component. In the target detection process, this embodiment improves the recognition accuracy of the target component by constructing a sample library of indoor components and performing machine learning based on a large sample database. FasterR-CNN extracts image features through a convolutional neural network and uses a region proposal network to generate candidate target frames on the feature map through a sliding window. The region proposal network calculates the probability that each candidate region is a target and the corresponding bounding box coordinates, selects the target region according to the probability, and then performs target classification and bounding box regression to obtain the target detection result. Compared with other recognition methods, it reduces the computational complexity and increases the detection speed.
[0038] Step S3: Obtain the combustion property data of the target component according to the material information of the target component, and calculate the product of the combustion property data and the size of the target component to obtain the fire risk index of the target component.
[0039] In step S3, risk factors are screened based on indoor component information. Corresponding combustion property data is obtained according to the target component type, and the fire risk index of the target component is obtained according to the product of the component size data and the component combustion property data. Target components such as sofas, tables and chairs, cartons, wardrobes, etc. are remotely monitored.
[0040] Step S4: Adding the fire risk indexes of all target components in the building interior to obtain a final fire risk index for the building interior.
[0041] Step S5: Analyze the final fire risk index inside the building, and output a warning when the final fire risk index is greater than a certain threshold.
[0042] In step S5, multiple threshold points can be set, and different warnings can be issued when the final fire risk index is in different intervals. For example, when the fire risk level is level three (greater than the minimum threshold), the alarm module will issue a safety reminder to the building manager; if the fire risk level is level two (greater than the middle threshold), the alarm module will issue a warning to the building manager; if the fire risk level is level three (greater than the maximum threshold), the alarm module will issue a warning to the fire department and the building manager.
[0043] In the above-mentioned 3D scanning-based indoor fire risk warning method for a building, a 3D model of the interior of the building is constructed through 3D scanning, the target components in the interior of the building are identified, and the material information and size of the target components are obtained. The combustion property data of the target components are obtained according to the material information of the target components, and the product of the combustion property data and the size of the target components is calculated to obtain the fire risk index of the target components; the fire risk indexes of all target components in the building are added to obtain the final fire risk index of the building; the final fire risk index of the building is analyzed, and when the final fire risk index is greater than a certain threshold, an early warning is output. The present application establishes an assessment method that comprehensively considers building information and fire risk factors of internal components. The assessment results are more accurate and reliable. Fire risk assessment is performed based on the fire risk factors of internal components, and active fire monitoring can be achieved throughout the entire period. Moreover, the use of 3D scanning technology eliminates the need for manual investigation, saves time and cost, and quickly obtains fire risk assessment results.
[0044] In one embodiment, after constructing the 3D model according to the 3D scanning result, the method further includes: preprocessing the 3D model and performing noise reduction processing.
[0045] In this embodiment, since the accuracy of 3D scanning may be affected by factors such as light intensity, component material, and environmental occlusion, this embodiment preprocesses the obtained fire activity image based on convolutional neural network technology to obtain a preprocessed image.
[0046] Among them, convolutional neural networks learn features and patterns in images by training a large number of noisy image samples, and are suitable for image denoising tasks. Convolutional neural network models usually use an autoencoder architecture to compress input images into low-dimensional feature representations and reconstruct clean images from them. Data augmentation technology helps increase the diversity of training data and improve the robustness of the model. After training, convolutional neural networks can accurately remove noise from images, resulting in clearer and more realistic image results.
[0047] In one embodiment, the 3D model performs target detection, identifies target components, and obtains size and material information of the target components, including:
[0048] According to the 3D scanning results, the deep learning-based object detection method identifies the target parts and obtains the size and material information of the target parts.
[0049] In this embodiment, a deep learning-based object detection method (FasterR-CNN) identifies target components and obtains the size and material information of the target components. In the target detection process, this embodiment improves the recognition accuracy of target components by constructing a sample library of indoor components and performing machine learning based on a large sample database. FasterR-CNN extracts image features through a convolutional neural network and uses a region proposal network to generate candidate target frames on a feature map through a sliding window. The region proposal network calculates the probability that each candidate region is a target and the corresponding bounding box coordinates, selects the target region according to the probability, and then performs target classification and bounding box regression to obtain the target detection result. Compared with other recognition methods, it reduces the computational complexity and increases the detection speed.
[0050] This application realizes full-time fire monitoring while taking into account the changes in indoor building components. This application obtains indoor environmental information, identifies indoor components and predicts fire risks by building a 3D scanning model, and issues timely warnings to relevant personnel based on the prediction results, greatly reducing the probability of indoor fires; compared with traditional building indoor fire risk assessment methods, the following improvements are achieved:
[0051] 1) Fast and efficient: Using 3D scanning technology, there is no need for manual survey, which saves time and cost and allows fire risk assessment results to be obtained quickly.
[0052] 2) Accurate and reliable: An assessment method has been established that comprehensively considers building information and fire risk factors of internal components, and the assessment results are more accurate and reliable.
[0053] 3) Real-time warning: Once the assessment result exceeds the warning threshold, a warning signal will be issued immediately, which will help to take timely fire response measures and reduce fire losses.
[0054] In one embodiment, a building indoor fire risk early warning system based on 3D scanning is provided, the system comprising:
[0055] 3D model building module: used to obtain the 3D scanning result of the target building interior sent by the scanning device installed in the building interior; and build a 3D model according to the 3D scanning result;
[0056] Target detection module: used to perform target detection based on the 3D model, identify target components and obtain the size and material information of the target components; the target components are components in the target building that can cause fire;
[0057] Combustion property acquisition module: used to obtain the combustion property data of the target component according to the material information of the target component, and calculate the product of the combustion property data and the size of the target component to obtain the fire risk index of the target component;
[0058] A final fire risk index acquisition module: used for adding the fire risk indexes of all target components in the building to obtain a final fire risk index in the building;
[0059] Warning result output module: analyzes the final fire risk index in the building, and outputs a warning when the final fire risk index is greater than a certain threshold.
[0060] In one embodiment, the system further includes a preprocessing module for preprocessing the 3D model and performing noise reduction.
[0061] In one embodiment, the early warning includes sending an early warning prompt to the fire department and the building manager or sending an early warning prompt to the building manager.
[0062] For the specific definition of a building indoor fire risk warning system based on 3D scanning, please refer to the definition of a building indoor fire risk warning method based on 3D scanning above, which will not be repeated here. Each module in the above-mentioned building indoor fire risk warning system based on 3D scanning can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0063] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, a memory, and a network interface 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above-mentioned indoor fire risk warning method for a building based on 3D scanning is implemented.
[0064] In one embodiment, a computer program product is also provided, including a computer program / instruction, which, when executed by a processor, involves all or part of the process in the above-mentioned embodiment method.
[0065] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0066] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0067] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A building indoor fire risk early warning method based on 3D scanning, characterized in that: The method comprises: Acquire a 3D scanning result of the interior of a target building sent by a scanning device installed in the interior of the building; and construct a 3D model according to the 3D scanning result; Performing target detection according to the 3D model, identifying target components and obtaining size and material information of the target components; the target components are components in the target building that can cause fire; Acquire combustion property data of the target component according to the material information of the target component, and calculate the product of the combustion property data and the size of the target component to obtain the fire risk index of the target component; Adding the fire risk indexes of all target components in the building to obtain a final fire risk index in the building; The final fire risk index in the building is analyzed, and when the final fire risk index is greater than a certain threshold, an early warning is output.
2. The method for early warning of indoor fire risk in a building based on 3D scanning according to claim 1 is characterized in that: After constructing the 3D model according to the 3D scanning result, the method further includes: preprocessing the 3D model and performing noise reduction processing.
3. The method for early warning of indoor fire risk in a building based on 3D scanning according to claim 2 is characterized in that: The 3D model is preprocessed based on convolutional neural network technology.
4. The method for early warning of indoor fire risk in a building based on 3D scanning according to claim 1, characterized in that: The 3D model performs target detection, identifies target components, and obtains size and material information of the target components, including: According to the 3D scanning results, the deep learning-based object detection method identifies the target parts and obtains the size and material information of the target parts.
5. The method for early warning of indoor fire risk in a building based on 3D scanning according to claim 1, characterized in that: The early warning includes sending an early warning prompt to the fire department and the building manager or sending an early warning prompt to the building manager.
6. A building indoor fire risk early warning system based on 3D scanning, characterized in that: The system comprises: 3D model building module: used to obtain the 3D scanning result of the target building interior sent by the scanning device installed in the building interior; and build a 3D model according to the 3D scanning result; Target detection module: used to perform target detection based on the 3D model, identify target components and obtain the size and material information of the target components; the target components are components in the target building that can cause fire; Combustion property acquisition module: used to obtain the combustion property data of the target component according to the material information of the target component, and calculate the product of the combustion property data and the size of the target component to obtain the fire risk index of the target component; A final fire risk index acquisition module: used for adding the fire risk indexes of all target components in the building to obtain a final fire risk index in the building; Warning result output module: analyzes the final fire risk index in the building, and outputs a warning when the final fire risk index is greater than a certain threshold.
7. The building indoor fire risk early warning system based on 3D scanning according to claim 6 is characterized in that: The system also includes a preprocessing module for preprocessing the 3D model and performing noise reduction.
8. The building indoor fire risk early warning system based on 3D scanning according to claim 6 is characterized in that: The early warning includes sending an early warning prompt to the fire department and the building manager or sending an early warning prompt to the building manager.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of implementing the method according to any one of claims 1 to 5 are implemented.