Building fire prevention inspection method and device based on handheld laser radar and storage medium

Abstract

The present application relates to the technical field of building fire safety detection, and particularly relates to a building fire safety inspection method and device based on a handheld laser radar and a storage medium. The method comprises: collecting point cloud data of a building area; performing component recognition and semantic segmentation on the point cloud data of the building area to identify building components; extracting fireproof feature parameters based on the building components identified from the point cloud data; and establishing a fireproof specification quantization database based on the fireproof feature parameters to determine whether the fireproof requirements are met and to perform three-dimensional visual labeling. The present application collects high-precision three-dimensional point cloud data of a building by using a handheld laser radar device, and automatically and quickly determines whether various fireproof measures of the building conform to national specifications by using subsequent data processing and analysis algorithms.

Description

Technical Field

[0001] This invention relates to the field of building fire safety inspection technology, and in particular to a building fire inspection method, device and storage medium based on handheld lidar. Background Technology

[0002] With the acceleration of urbanization, buildings are becoming increasingly complex in scale and function, posing serious challenges to fire safety management. Traditional fire inspections rely on manual on-site measurement and recording, which is inefficient, results in scattered data, and is difficult to systematize. In recent years, 3D laser scanning technology has developed rapidly in the field of building information technology, providing new data acquisition and spatial analysis methods for building fire inspections and promoting the evolution of fire inspections towards digitalization and refinement.

[0003] Current building fire safety inspections mainly rely on manual on-site measurements and records using tools such as measuring tapes and rangefinders. This approach has the following problems: First, it is inefficient and cannot cover large areas or complex building structures, especially in high-ceilinged spaces or areas with dense pipelines, where blind spots exist. Second, the measurement results are highly subjective, with poor consistency among different personnel and weak data traceability. Third, the spatial relationships between fire-resistant components are difficult to quantify, making it impossible to systematically determine whether they meet the requirements of the standards. Fourth, the inspection results are mostly presented in two-dimensional drawings or text records, lacking intuitive spatial positioning and visual representation, which is not conducive to subsequent rectification and acceptance management. Summary of the Invention

[0004] The purpose of this invention is to provide a building fire inspection method, device, and storage medium based on handheld lidar, so as to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A method for inspecting building fire safety based on handheld lidar includes:

[0007] Collect point cloud data of the building area;

[0008] Component identification and semantic segmentation are performed on the point cloud data of the building area to identify building components;

[0009] Fire protection feature parameters are extracted from building components identified based on point cloud data;

[0010] A quantitative database of fire protection standards is established based on fire protection characteristic parameters to determine whether fire protection requirements are met and to perform three-dimensional visualization annotation.

[0011] Furthermore, a pre-defined building component feature database is provided, which contains geometric feature parameters of various building components. The point cloud data is then semantically segmented based on the building component feature database to label the building components.

[0012] Furthermore, when determining the net evacuation width, for the evacuation corridor, a section perpendicular to the centerline is generated every 0.5 meters along its centerline, and the minimum Euclidean distance between the point cloud of the left wall and the point cloud of the right wall of each section is calculated as the net evacuation width.

[0013] For fire doors, the minimum horizontal distance between the point cloud of the door leaf and the point cloud of the door frame is extracted as the net evacuation width.

[0014] Furthermore, after identifying the fire damper, the centerline of the duct to which it is attached is traced to identify the firewall closest to the fire damper. The vertical projection distance from the center point of the end face of the fire damper on the side closest to the firewall to the duct penetration opening of the firewall is taken as the installation distance of the fire damper.

[0015] Furthermore, after identifying the pipe penetration opening, the point cloud of the fireproof sealing material around the pipe penetration opening is extracted. The point cloud with the reflection intensity within the preset range of fireproof sealing material reflection intensity is taken as the fireproof sealing material. The two end faces of the fireproof sealing material in the penetration direction are fitted, and the average distance between the two end faces is taken as the fireproof sealing thickness.

[0016] Furthermore, the point clouds of the load-bearing steel structure are extracted separately, and the mean μg and standard deviation σg of the reflection intensity of the point cloud are determined to calculate the apparent parameters of the fireproof coating. The apparent parameters of the fireproof coating are μg - k × σg, where k represents the adjustment coefficient.

[0017] Furthermore, the value ranges of fire protection characteristic parameters in the building design fire protection code are extracted to generate thresholds for evacuation width, fire damper installation distance, fire sealing thickness, and fire-resistant coating appearance parameters. A quantitative database of fire protection codes is then established based on the generated thresholds.

[0018] Furthermore, the fire protection characteristic parameters are compared with the thresholds in the fire protection code quantitative database to determine whether the fire protection requirements are met:

[0019] When the net evacuation width of the evacuation corridor / fire door is greater than or equal to the evacuation width threshold, the evacuation corridor / fire door is deemed to meet the fire protection requirements; otherwise, the evacuation corridor / fire door is deemed not to meet the fire protection requirements.

[0020] When the installation distance of a fire damper is less than or equal to the fire damper installation distance threshold, the fire damper is deemed to meet the fire protection requirements; otherwise, the fire damper is deemed not to meet the fire protection requirements.

[0021] When the fire-stopping thickness is greater than or equal to the fire-stopping thickness threshold, the fire-stopping of the pipe penetration opening is deemed to meet the fire protection requirements; otherwise, the fire-stopping of the pipe penetration opening is deemed not to meet the fire protection requirements.

[0022] When the apparent parameters of the fire-retardant coating are greater than the threshold of the apparent parameters of the fire-retardant coating, the steel structure is deemed to meet the fire protection requirements; otherwise, the steel structure is deemed not to meet the fire protection requirements.

[0023] In the point cloud data of the building area, the points corresponding to building components that do not meet the fire protection requirements are highlighted in red, and an inspection report is generated.

[0024] On the other hand, the present invention also provides a building fire inspection device based on handheld lidar, comprising:

[0025] The point cloud acquisition module is used to collect point cloud data of the building area;

[0026] The component recognition module is used to perform component recognition and semantic segmentation on the point cloud data of the building area in order to identify building components;

[0027] The feature extraction module is used to extract fire protection feature parameters from building components identified based on point cloud data;

[0028] The report generation module is used to establish a quantitative database of fire protection standards based on fire protection characteristic parameters, in order to determine whether fire protection requirements are met and to perform three-dimensional visualization annotation.

[0029] On the other hand, the present invention also provides a storage medium storing instructions that, when run on a computer, cause the computer to execute the building fire inspection method based on handheld lidar as described above.

[0030] The beneficial effects of this invention are as follows: By collecting high-precision point cloud data of building areas using handheld lidar, and combining this with automatic component identification, quantitative extraction of fire protection feature parameters, and quantitative comparison with standards, a complete digital inspection technology solution for building fire protection is constructed. This method achieves fully automated processing from data collection to compliance judgment, significantly improving the efficiency and accuracy of fire protection inspections and reducing the arbitrariness and omission risks of manual operation. Simultaneously, through 3D visualization annotation and structured report output, the intuitiveness and traceability of inspection results are enhanced, providing scientific and efficient technical support for building fire protection design, construction acceptance, and operation and maintenance management, and possessing significant value for engineering application and promotion. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used 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 those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1This is a flowchart of the building fire inspection method based on handheld lidar in this embodiment.

[0033] Figure 2 This is a flowchart of the method for extracting fire protection characteristic parameters in this embodiment.

[0034] Figure 3 This is a flowchart of the fire inspection report generation method in this embodiment.

[0035] Figure 4 This is a schematic diagram of the building fire inspection device based on handheld lidar in this embodiment. Detailed Implementation

[0036] The following detailed description, in conjunction with the accompanying drawings and specific embodiments, provides a further detailed account of the building fire inspection method, apparatus, and storage medium based on handheld lidar disclosed in this invention. It should be noted that the technical features or combinations of technical features described in the following embodiments should not be considered isolated; they can be combined to achieve better technical effects. In the accompanying drawings of the following embodiments, the same reference numerals in each drawing represent the same features or components, which can be applied to different embodiments. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0037] It should be noted that the structures, proportions, sizes, etc., illustrated in the accompanying drawings are merely for illustrative purposes and to aid those skilled in the art in understanding and reading the invention. They are not intended to limit the conditions under which the invention can be implemented. Any modifications to the structure, changes in proportions, or adjustments to size, provided they do not affect the effectiveness or purpose of the invention, should fall within the scope of the technical content disclosed in the invention. The scope of the preferred embodiments of the present invention includes other implementations, wherein functions may be performed not in the order stated or discussed, including substantially simultaneously or in reverse order, depending on the functions involved. This should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0038] Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and apparatus should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0039] In the description of the embodiments of this application, " / " means "or", and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" means: A and B exist alone, B exists alone, and A and B exist simultaneously. In the description of the embodiments of this application, "multiple" refers to two or more embodiments.

[0040] Please see Figure 1 As shown, this embodiment illustrates a building fire inspection method based on handheld lidar, comprising:

[0041] Step S1: Collect point cloud data of the building area. The point cloud data of the building area is obtained by a person carrying a handheld LiDAR scanning device to scan the target building area in all directions along a preset path. The preset path includes the building's internal corridors, evacuation stairwells, fire compartment boundaries, equipment rooms, and the perimeter of the building's exterior walls. The handheld LiDAR scanning device has a scanning frequency of 300,000 points / second and a ranging accuracy of ±1-3 cm. After scanning, the original data is processed using the SLAM algorithm to eliminate motion distortion, and the data is stitched and fused. The result is output as a building information point cloud model in LAS format. After processing, the average point cloud density of the point cloud model reaches 5,000 points per square meter, and the coordinate accuracy is better than ±2 cm.

[0042] Specifically, in step S1 of this embodiment, the inspection personnel, carrying a handheld LiDAR, perform a full-range scan of the building area along a preset path, which can efficiently acquire high-density, high-precision three-dimensional point cloud data. This method breaks through the spatial limitations of traditional manual measurement and is particularly suitable for collecting building information on complex structures, hidden areas, and large-span spaces. It provides a reliable data foundation for subsequent component identification and fire protection feature extraction, significantly improving the comprehensiveness and data quality of on-site inspection.

[0043] Please continue reading. Figure 1 As shown, the building fire inspection method based on handheld lidar also includes:

[0044] Step S2 involves performing component identification and semantic segmentation on the point cloud data of the building area to identify building components.

[0045] Specifically, in step S2 of this embodiment, a building construction feature database is preset. The building construction feature database contains geometric feature parameters of various building components, such as the horizontal normal vector and thickness of the wall (150-500mm), the vertical normal vector and thickness of the floor slab (100-300mm), the width of the rectangular air duct (200-2000mm), the diameter of the circular air duct (100-1500mm), the fire damper (rectangular with a side length of 300-1200mm), and the fire door (rectangular with a width of 800-2000mm and a height of 1800-2400mm).

[0046] Specifically, in step S2 of this embodiment, semantic segmentation is performed on the point cloud data based on the building construction feature database:

[0047] For walls, point clouds with a normal vector angle of less than 10 degrees to the horizontal plane are selected by calculating the local point cloud normal vectors and then performing plane fitting. The fitted plane thickness is identified as a wall if it is between 150mm and 500mm. Walls whose thickness meets the preset firewall thickness range are marked as firewalls.

[0048] For floor slabs, point clouds with a normal vector angle greater than 80 degrees to the horizontal plane are selected and plane fitting is performed. The fitted plane with a thickness between 100mm and 300mm is identified as a floor slab.

[0049] For air ducts, cylindrical / rectangular cylinder fitting is performed on the remaining point cloud. Cylinders with a diameter between 100mm and 1500mm, or rectangular cylinders with a width between 200mm and 2000mm, and with a length greater than 500mm are identified as air ducts.

[0050] For fire dampers, on the identified duct section, search for abrupt changes in the outward expansion size of the local point cloud. If the projection length of the point cloud in a certain area in the direction perpendicular to the duct axis is more than 50mm larger than the diameter / width of the duct, but the shape is a regular rectangle, it is marked as a candidate fire damper. Combined with the reflection intensity of the point cloud, candidate fire dampers with a reflection intensity greater than that of the duct are identified as fire dampers.

[0051] For fire doors, search for rectangular areas with missing points in the wall point cloud. Rectangular areas with a width of 800-2000mm and a height of 1800-2400mm are identified as fire doors.

[0052] For evacuation corridors, under the constraint of wall point cloud, continuously extending strip-shaped areas are searched. Areas with a width between 1200-3000mm and a length greater than 5000mm are identified as evacuation corridors.

[0053] For pipe penetration openings, search for missing circular or rectangular holes in the point cloud of the wall or floor slab. Holes with a diameter or side length greater than 100mm are identified as pipe penetration openings.

[0054] For steel structures, point cloud clusters with cross-sectional shapes such as I-shaped, H-shaped, and box-shaped, and a length greater than 1000mm, are identified as steel structures. The identified steel structures are then marked as load-bearing steel structures using a user-defined calibration method. In this embodiment, the preset firewall thickness range is set to 200-240mm.

[0055] Specifically, in step S2 of this embodiment, based on a preset building component feature database, and combining multiple discrimination mechanisms such as normal vector calculation, plane fitting, shape recognition, and reflection intensity analysis, automatic identification and semantic segmentation of building components such as walls, floors, air ducts, fire dampers, fire doors, evacuation corridors, pipe penetrations, and steel structures are achieved. This method fully utilizes the spatial geometric information and physical attributes of point clouds, achieving a high degree of automation and accurate classification in the identification process. It effectively solves the problems of low efficiency and inconsistent standards in manual identification, laying a solid foundation for the accurate extraction of fire protection feature parameters.

[0056] Please continue reading. Figure 1 As shown, the building fire inspection method based on handheld lidar also includes:

[0057] Step S3: Extract fire protection feature parameters from the building components identified based on point cloud data. The fire protection feature parameters include net evacuation width, fire damper installation distance, fire sealing thickness, and fire-resistant coating appearance parameters.

[0058] Please see Figure 2 As shown, this is a method for extracting fire protection characteristic parameters, including:

[0059] Step S31: Determine the net evacuation width based on the evacuation corridor and fire doors.

[0060] Specifically, in step S31 of this embodiment, when determining the net evacuation width, for the evacuation corridor, a cross section perpendicular to the center line is generated every 0.5 meters along its center line, and the minimum Euclidean distance between the point cloud of the left wall and the point cloud of the right wall of each cross section is calculated as the net evacuation width.

[0061] For fire doors, the minimum horizontal distance between the point cloud of the door leaf and the point cloud of the door frame is extracted as the net evacuation width.

[0062] Specifically, in step S31 of this embodiment, taking a certain evacuation corridor on the 5th floor as an example, a cross-section perpendicular to the centerline is generated every 0.5 meters along its centerline, for a total of 15 cross-sections. The distance values ​​of the 15 cross-sections are: 1.85m, 1.87m, 1.90m, 1.88m, 1.82m, 1.80m, 1.78m, 1.75m, 1.76m, 1.79m, 1.81m, 1.84m, 1.86m, 1.89m, and 1.91m. The minimum value of 1.75m is taken as the net evacuation width.

[0063] Specifically, in step S31 of this embodiment, the net width of the evacuation route is accurately quantified by generating equidistant cross-sections along the centerline of the evacuation corridor, calculating the minimum Euclidean distance between walls, and extracting the minimum horizontal distance between door panels and door frames. This method fully considers the actual usable space of corridors and doorways, avoids errors caused by limitations in perspective and tools during manual measurement, objectively reflects the actual passage capacity of evacuation routes, and provides reliable data support for determining whether the requirements for safe evacuation of personnel are met.

[0064] Please continue reading. Figure 2 As shown, the method for extracting the fire-resistant characteristic parameters further includes:

[0065] Step S32: Determine the installation distance of the fire damper based on the air duct, fire damper and pipe penetration opening.

[0066] Specifically, in step S32 of this embodiment, after identifying the fire damper, the center line of the duct to which it is attached is traced, the firewall closest to the fire damper is identified, and the vertical projection distance from the center point of the end face of the fire damper on the side closest to the firewall to the pipe penetration opening of the firewall is taken as the installation distance of the fire damper.

[0067] Specifically, in step S32 of this embodiment, by tracing the centerline of the duct and identifying the firewall closest to the fire damper, the vertical projection distance from the center point of the fire damper's end face to the duct penetration opening in the firewall is used as the installation distance, thus achieving precise quantification of the spatial relationship between the fire damper and the firewall. This method fully reflects the regulatory intent that fire dampers "should be installed close to fire compartments," effectively solving the problem of accurately locating the relative position of fire dampers in traditional inspections, and improving the scientific nature of judging the compliance of fire compartmentation measures.

[0068] Please continue reading. Figure 2 As shown, the method for extracting the fire-resistant characteristic parameters further includes:

[0069] Step S33: Determine the fireproof sealing thickness based on the pipe penetration opening.

[0070] Specifically, in step S33 of this embodiment, after identifying the pipe penetration opening, the point cloud of the fireproof sealing material around the pipe penetration opening is extracted. Point clouds with reflection intensity within the preset fireproof sealing material reflection intensity range are used as the fireproof sealing material. The two end faces of the fireproof sealing material in the penetration direction are fitted, and the average distance between the two end faces is used as the fireproof sealing thickness. In this embodiment, the preset fireproof sealing material reflection intensity range is set to 80-120 W / m. 2 .

[0071] Specifically, in step S33 of this embodiment, the point cloud of the fireproof sealing material around the pipe penetration opening is extracted, and the effective sealing area is screened based on the reflection intensity. The two end faces of the sealing material in the penetration direction are fitted to calculate the sealing thickness. This method achieves high-precision non-contact detection of the fireproof sealing quality of concealed parts, avoids damage to the building structure caused by destructive testing, and can objectively reflect the continuity and thickness uniformity of the sealing, providing a quantitative basis for determining whether the fireproof sealing meets the fire resistance limit requirements.

[0072] Please continue reading. Figure 2 As shown, the method for extracting the fire-resistant characteristic parameters further includes:

[0073] Step S34: Determine the apparent parameters of the fireproof coating based on the steel structure.

[0074] Specifically, in step S34 of this embodiment, the point cloud of the load-bearing steel structure is extracted, and the mean μg and standard deviation σg of the reflection intensity of the point cloud are determined to calculate the apparent parameters of the fireproof coating. The apparent parameters of the fireproof coating are μg - k × σg, where k represents an adjustment coefficient. In this embodiment, the adjustment coefficient is set to 1.5.

[0075] Specifically, in step S34 of this embodiment, it is necessary to collect sample data of the building area and the load-bearing steel structure using the same spraying process and with intact coatings in advance, and calculate the mean value μg0 and standard deviation σg0 of the reflection intensity of the sample data in order to set the fireproof coating appearance benchmark, wherein the fireproof coating appearance benchmark = μg0 - k × σg0.

[0076] Specifically, in step S34 of this embodiment, the mean and standard deviation of the reflection intensity of the point cloud of the load-bearing steel structure are extracted to construct the apparent parameters of the fireproof coating. A benchmark value is then established by combining this with samples of intact coatings, thus achieving a quantitative assessment of the construction quality of the fireproof coating. This method fully utilizes the sensitivity of point cloud reflection intensity to the surface condition of the material, objectively reflecting the coating uniformity, adhesion status, and potential deterioration, providing an efficient and reproducible technical means for reliable assessment of fire protection for steel structures.

[0077] Please continue reading. Figure 1As shown, the building fire inspection method based on handheld lidar also includes:

[0078] Step S4: Establish a quantitative database of fire protection standards based on fire protection characteristic parameters to determine whether fire protection requirements are met and perform three-dimensional visualization annotation.

[0079] Please see Figure 3 As shown, this is a method for generating a fire inspection report, including:

[0080] Step S41: Establish a quantitative database of fire protection standards based on building fire protection design codes.

[0081] Specifically, in step S41 of this embodiment, the value range of fire protection characteristic parameters in the building design fire protection code is extracted to generate evacuation width threshold, fire damper installation distance threshold, fire sealing thickness threshold and fire-resistant coating appearance parameter threshold, and a fire protection code quantitative database is established based on the generated thresholds.

[0082] Specifically, in step S41 of this embodiment, when establishing the quantitative database of fire protection specifications, the evacuation width threshold can be set to 1.4m for evacuation corridors and 0.9m for fire doors when the corridors are flanked by rooms, as recorded in the building design fire protection code.

[0083] Regarding the installation distance threshold for fire dampers, it can be determined according to the building fire protection design code that the air ducts and their insulation materials within 2.0m on both sides of the fire damper should be made of non-combustible materials, and the fire damper should be installed close to the fire separation. In actual engineering, it is usually required that the distance from the wall is no more than 200mm. Therefore, the installation distance threshold for fire dampers is set at 200mm.

[0084] Regarding the fire-stopping thickness threshold, the fire-stopping thickness threshold is set at 250mm, based on the requirement in the building design fire protection code that the fire-stopping must meet a 3-hour fire resistance limit. The fire-stopping is achieved by using a combination of fireproof bags and fireproof putty, with a minimum thickness requirement of 250mm.

[0085] For the fire-retardant coating appearance parameter threshold, the fire-retardant coating appearance benchmark calculated in step S34 above is used as the fire-retardant coating appearance parameter threshold.

[0086] Specifically, in step S41 of this embodiment, the system extracts quantitative requirements for key indicators such as evacuation width, fire damper installation distance, fire sealing thickness, and fire-resistant coating appearance parameters from the building fire protection design code, constructing a structured quantitative database of fire protection codes. This database transforms the written specifications into calculable and comparable numerical thresholds, providing a standardized reference for subsequent automated compliance assessments and effectively solving the problem of difficulty in directly comparing code provisions with on-site measured data.

[0087] Please continue reading. Figure 3 As shown, the method for generating the fire inspection report also includes:

[0088] Step S42: Determine whether the fire protection requirements are met based on fire protection characteristic parameters and a quantitative database of fire protection standards.

[0089] Specifically, in step S42 of this embodiment, the fire protection characteristic parameters are compared with each threshold in the fire protection code quantitative database to determine whether the fire protection requirements are met.

[0090] When the net evacuation width of the evacuation corridor / fire door is greater than or equal to the evacuation width threshold, the evacuation corridor / fire door is deemed to meet the fire protection requirements; otherwise, the evacuation corridor / fire door is deemed not to meet the fire protection requirements.

[0091] When the installation distance of a fire damper is less than or equal to the fire damper installation distance threshold, the fire damper is deemed to meet the fire protection requirements; otherwise, the fire damper is deemed not to meet the fire protection requirements.

[0092] When the fire-stopping thickness is greater than or equal to the fire-stopping thickness threshold, the fire-stopping of the pipe penetration opening is deemed to meet the fire protection requirements; otherwise, the fire-stopping of the pipe penetration opening is deemed not to meet the fire protection requirements.

[0093] When the apparent parameters of the fire-retardant coating are greater than the threshold of the apparent parameters of the fire-retardant coating, the steel structure is deemed to meet the fire protection requirements; otherwise, the steel structure is deemed not to meet the fire protection requirements.

[0094] Specifically, in step S42 of this embodiment, the extracted fire protection feature parameters are compared item by item with the thresholds in the fire protection code quantitative database to achieve automatic compliance judgment of key fire protection elements such as evacuation corridors, fire doors, fire dampers, fireproof sealing, and steel structures. This method transforms complex code provisions into clear right-or-wrong judgment logic, reduces the subjectivity of human judgment, improves the objectivity and consistency of inspection results, and facilitates the rapid location of fire hazards.

[0095] Please continue reading. Figure 3 As shown, the method for generating the fire inspection report also includes:

[0096] Step S43: Based on the determination of fire protection requirements, perform three-dimensional visualization annotation and generate an inspection report.

[0097] Specifically, in step S43 of this embodiment, the points corresponding to building components that do not meet fire protection requirements are highlighted in red in the point cloud data of the building area, and an inspection report is generated. The inspection report includes the project name, inspection date, inspection personnel, and a list of items that do not meet fire protection requirements. Each item that does not meet fire protection requirements includes the building component, location coordinates, measured value, standard value, deviation value, and is accompanied by a red highlighting of the point cloud data.

[0098] Specifically, in step S43 of this embodiment, by highlighting the corresponding points of building components that do not meet fire protection requirements in red within the point cloud data of the building area, and combining this with project information, measured values, standard values, deviation values, etc., a structured inspection report is generated, achieving spatial visualization and data traceability of the inspection results. This method significantly improves the intuitive expression of fire hazards, facilitating rapid problem identification and rectification by inspection personnel, design units, and acceptance units, effectively supporting building fire protection acceptance and operation and maintenance management.

[0099] Please see Figure 4 As shown, this is a building fire inspection device based on handheld lidar in this embodiment, including:

[0100] The point cloud acquisition module is used to collect point cloud data of the building area;

[0101] The component recognition module is used to perform component recognition and semantic segmentation on the point cloud data of the building area in order to identify building components;

[0102] The feature extraction module is used to extract fire protection feature parameters from building components identified based on point cloud data;

[0103] The report generation module is used to establish a quantitative database of fire protection standards based on fire protection characteristic parameters, in order to determine whether fire protection requirements are met and to perform three-dimensional visualization annotation.

[0104] This application also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the building fire inspection method based on handheld lidar as described in the above method embodiments.

[0105] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable programs, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable programs, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0106] In the above description, the disclosure of this invention is not intended to limit itself to these aspects. Rather, within the scope of the objectives of this disclosure, components can be selectively and operationally combined in any number. Furthermore, terms such as “comprising,” “encompassing,” and “having” should be interpreted by default as inclusive or open-ended, rather than exclusive or closed, unless explicitly defined as such. All technical, scientific, or other terms are to be understood by those skilled in the art, unless defined as such. Public terms found in dictionaries should not be interpreted in the context of the relevant technical documents in an overly idealistic or impractical manner, unless explicitly defined as such in this disclosure. Any modifications or alterations made by those skilled in the art based on the foregoing disclosure are within the scope of the claims.

Claims

1. A method for inspecting building fire safety based on handheld lidar, characterized in that, include: Collect point cloud data of the building area; Component identification and semantic segmentation are performed on the point cloud data of the building area to identify building components; Fire protection feature parameters are extracted from building components identified based on point cloud data; A quantitative database of fire protection standards is established based on fire protection characteristic parameters to determine whether fire protection requirements are met and to perform three-dimensional visualization annotation.

2. The building fire inspection method based on handheld lidar according to claim 1, characterized in that, A pre-defined building construction feature database is provided, which contains geometric feature parameters of various building components. The point cloud data is semantically segmented based on the building construction feature database to label the building components.

3. The building fire inspection method based on handheld lidar according to claim 2, characterized in that, When determining the net evacuation width, for evacuation corridors, a section perpendicular to the centerline is generated every 0.5 meters along the centerline, and the minimum Euclidean distance between the point cloud of the left wall and the point cloud of the right wall of each section is calculated as the net evacuation width. For fire doors, the minimum horizontal distance between the point cloud of the door leaf and the point cloud of the door frame is extracted as the net evacuation width.

4. The building fire inspection method based on handheld lidar according to claim 3, characterized in that, After identifying the fire damper, trace the centerline of the duct it is attached to, identify the firewall closest to the fire damper, and take the vertical projection distance from the center point of the end face of the fire damper on the side closest to the firewall to the pipe penetration opening of the firewall as the installation distance of the fire damper.

5. The building fire inspection method based on handheld lidar according to claim 4, characterized in that, After identifying the pipe penetration opening, the point cloud of the fireproof sealing material around the pipe penetration opening is extracted. The point cloud with the reflection intensity within the preset range of fireproof sealing material reflection intensity is taken as the fireproof sealing material. The two end faces of the fireproof sealing material in the penetration direction are fitted, and the average distance between the two end faces is taken as the fireproof sealing thickness.

6. The building fire inspection method based on handheld lidar according to claim 5, characterized in that, Point clouds of the load-bearing steel structure are extracted separately, and the mean μg and standard deviation σg of the reflection intensity of the point cloud are determined to calculate the apparent parameters of the fireproof coating. The apparent parameters of the fireproof coating are μg - k × σg, where k represents the adjustment coefficient.

7. The building fire inspection method based on handheld lidar according to claim 6, characterized in that, The value ranges of fire protection characteristic parameters in the building design fire protection code are extracted to generate thresholds for evacuation width, fire damper installation distance, fire sealing thickness, and fire-resistant coating appearance parameters. A quantitative database of fire protection codes is then established based on the generated thresholds.

8. The building fire inspection method based on handheld lidar according to claim 7, characterized in that, The fire protection characteristic parameters are compared with the thresholds in the fire protection code quantitative database to determine whether the fire protection requirements are met. When the net evacuation width of the evacuation corridor / fire door is greater than or equal to the evacuation width threshold, the evacuation corridor / fire door is deemed to meet the fire protection requirements; otherwise, the evacuation corridor / fire door is deemed not to meet the fire protection requirements. When the installation distance of a fire damper is less than or equal to the fire damper installation distance threshold, the fire damper is deemed to meet the fire protection requirements; otherwise, the fire damper is deemed not to meet the fire protection requirements. When the fire-stopping thickness is greater than or equal to the fire-stopping thickness threshold, the fire-stopping of the pipe penetration opening is deemed to meet the fire protection requirements; otherwise, the fire-stopping of the pipe penetration opening is deemed not to meet the fire protection requirements. When the apparent parameters of the fire-retardant coating are greater than the threshold of the apparent parameters of the fire-retardant coating, the steel structure is deemed to meet the fire protection requirements; otherwise, the steel structure is deemed not to meet the fire protection requirements. In the point cloud data of the building area, the points corresponding to building components that do not meet the fire protection requirements are highlighted in red, and an inspection report is generated.

9. A building fire inspection device based on a handheld lidar, applied to the building fire inspection method based on a handheld lidar as described in any one of claims 1-8, characterized in that, include: The point cloud acquisition module is used to collect point cloud data of the building area; The component recognition module is used to perform component recognition and semantic segmentation on the point cloud data of the building area in order to identify building components; The feature extraction module is used to extract fire protection feature parameters from building components identified based on point cloud data; The report generation module is used to establish a quantitative database of fire protection standards based on fire protection characteristic parameters, in order to determine whether fire protection requirements are met and to perform three-dimensional visualization annotation.

10. A storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the building fire inspection method based on a handheld lidar as described in any one of claims 1-8.

Images