An ai-based construction site inspection management system and method

Abstract

The application discloses an AI-based building construction site inspection management system and method, and relates to the technical field of construction inspection.The application plans an inspection equipment operation path according to an inspection task; detection data is collected by the inspection equipment during the inspection process; a three-dimensional point cloud model is established based on the detection data after data cleaning; a space coordinate system is constructed in the three-dimensional point cloud model, and space position information of an inspection target is analyzed; the best detection section of the inspection equipment is analyzed according to the space position information of the inspection equipment and the inspection target; the real-time inspection angle of the inspection equipment is found and adjusted based on an inspection parameter sequence, the real-time inspection angle corresponding to the real-time detection data that does not meet the condition is further adjusted, and the real-time inspection angle is updated.The quality of the detection data is improved, and the overall analysis efficiency of the inspection system is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of construction inspection, and particularly relates to an AI-based building construction site inspection management system and method. BACKGROUND

[0002] In modern urban construction, building construction site safety has always been a focus of attention. In order to ensure the safety of workers and improve construction efficiency, more and more building construction sites use intelligent building construction site safety inspection systems. The intelligent building construction site safety inspection system can comprehensively monitor the safety status of the building construction site, and timely find and solve potential safety hazards.

[0003] The data acquisition equipment of the existing safety inspection system is often in the data acquisition stage from the start to the end of the inspection, and part of the collected data is of low quality, thereby reducing the analysis value and easily causing data stacking of the database, and reducing the overall analysis efficiency of the inspection system.

[0004] Therefore, the application discloses an AI-based building construction site inspection management system and method to solve the above problems. SUMMARY

[0005] The application aims to provide an AI-based building construction site inspection management system and method to solve the problems in the prior art.

[0006] To achieve the above-mentioned purpose, the application provides the following technical scheme: an AI-based building construction site inspection management method, which comprises the following steps:

[0007] S1: planning a running path of an inspection device according to an inspection task; controlling the inspection device to perform safety inspection and keeping the detection height of a data collector of the inspection device consistent, and collecting detection data through the inspection device in the inspection process;

[0008] S2: performing data cleaning on the detection data in the running process of the inspection device, establishing a three-dimensional point cloud model based on the detection data after data cleaning; constructing a space coordinate system in the three-dimensional point cloud model, and analyzing space position information of an inspection target;

[0009] S3: analyzing the best detection section of the inspection device according to the space position information of the inspection device and the inspection target;

[0010] S4: establishing an inspection parameter group according to the space position information of the best detection section and corresponding inspection parameters; finding and adjusting the real-time inspection angle of the inspection device based on the inspection parameter sequence, further adjusting the real-time inspection angle corresponding to the real-time detection data that does not meet the condition, and updating.

[0011] According to the scheme, in S1, the data collector of the inspection device comprises a scanning instrument and a camera; the detection height comprises a scanning instrument detection height and a camera detection height; the scanning instrument detection height represents the vertical distance between the scanning instrument and the ground where the inspection device is located; the camera detection height represents the vertical distance between the camera and the ground where the inspection device is located; and the detection data comprises three-dimensional point cloud data and image data.

[0012] According to the scheme, in S2, the following is included:

[0013] S201: Extract three-dimensional point cloud data in the detection data, and remove three-dimensional point cloud data corresponding to moving objects in the scanning process;

[0014] S202: Establish a three-dimensional point cloud model by using the three-dimensional point cloud data after data cleaning; in construction of any plane of the three-dimensional point cloud model, adopt an RANSA algorithm to analyze a plane that meets a preset requirement and has the most points, mark the plane as an optimal plane; mark point clouds in the optimal plane as optimal point clouds, and for any optimal point cloud, count the number of point clouds within a radius threshold, if the number of point clouds within the radius threshold is greater than or equal to a quantity threshold, save the optimal point cloud; if the number of point clouds within the radius threshold is less than the quantity threshold, remove the optimal point cloud.

[0015] The scanning instrument of the inspection device can quickly obtain three-dimensional space information and a surface model on a running path of the inspection device, and construct a three-dimensional point cloud model; point cloud quantity analysis on the optimal point cloud can further improve the accuracy of the three-dimensional point cloud model; and under the support of a digital ground model and high-resolution images, high-efficiency and high-precision line inspection applications are realized.

[0016] S203: Construct a space coordinate system in the three-dimensional point cloud model, extract the spatial coordinates of the boundary of the inspection target in the three-dimensional point cloud model, and analyze the spatial coordinates of the gravity center point of the inspection target, marked as (a, b, c); wherein a, b and c respectively represent the numerical values of the gravity center point of the inspection target on the spatial coordinate axes in the three-dimensional point cloud model.

[0017] According to the scheme, in S3, the following is included:

[0018] S301: Mark the spatial coordinates of the camera in the inspection device as (x, y, z); wherein x, y and z represent spatial coordinate variables in the three-dimensional point cloud model; extract the spatial coordinates corresponding to the camera when the inspection device is on the running path, and analyze the actual maximum observation area of the inspection target corresponding to the camera at different spatial coordinates, marked as S(x, y, z); the actual maximum observation area represents the maximum surface area size that can be projected and displayed in the image data under the volume of the corresponding inspection target; and the spatial coordinates of one camera correspond to one actual maximum observation area.

[0019] S302: Obtain the focal length f of the camera of the inspection device and the actual size P of a single pixel, analyze the distance between the camera of the inspection device and the center of gravity of the inspection target, denoted as L(x, y, z); according to each actual maximum observation area, calculate the pixel area PI(x, y, z) of the inspection target displayed in the image data under different spatial coordinates of the camera; the specific calculation formula is:

[0020] L(x, y, z) = [(x-a) 2 +(y-b) 2 +(z-c) 2 ] 1 / 2 ;

[0021] PI(x, y, z) = S(x, y, z) x f 2 ÷ [L(x, y, z) x P] 2 ;

[0022] S303: Extract the pixel area of the actual maximum observation area of the camera under different spatial coordinates of the inspection device on the running path, and assemble the pixel area set; analyze the analysis reference value of each pixel area in the pixel area set:

[0023] ARV i = [1 ÷ (2πα 2 ) 1 / 2 ] x exp[- (PI i - β) 2 ÷ (2 x α 2 )];

[0024] Where ARV i represents the i-th pixel area in the pixel area set, β represents the mean value of the pixel area set, and α represents the standard deviation of the pixel area set;

[0025] S304: Set the analysis reference value threshold to the analysis reference value, extract the spatial coordinates of the camera corresponding to the pixel area whose analysis reference value is equal to the analysis reference value threshold, mark the spatial boundary, and record the running path of the inspection device between the two spatial boundaries as the best detection section. When the spatial coordinates of the camera of the inspection device belong to the best detection section, the camera is turned on to perform the detection task; the pixel area corresponding to the spatial coordinates in the best detection section is greater than the pixel area threshold.

[0026] By analyzing the maximum observation area of the inspection target under different position information and the distance between the inspection target and the inspection device, the pixel area in the image data is analyzed, the analysis reference value is calculated according to the pixel area, the best detection section is obtained, the amount of detection data is reduced, the quality of the detection data is improved, the data stacking of the database is avoided, and the overall analysis efficiency of the inspection system is improved;

[0027] According to the above scheme, in S4, the following is included:

[0028] S401: Extract the spatial coordinates of the optimal detection section and the spatial coordinates of the optimal detection section in the actual maximum observation area corresponding to the inspection angle θ of the inspection target, and assemble the inspection parameter group (x, y, z, θ); the inspection angle is the angle between the horizontal plane of the camera and the shooting direction of the camera;

[0029] S402: Group all inspection parameter groups according to the running direction of the inspection equipment to form an inspection parameter sequence, and store the inspection parameter sequence in the database; after starting the camera, use the spatial coordinates of the camera to find the corresponding inspection parameter group in the database, and adjust the real-time inspection angle of the camera of the inspection equipment according to the inspection parameter group;

[0030] S403: Extract real-time image data collected based on the inspection parameter group, analyze the real-time pixel area of the inspection target in the image data, and the real-time pixel area is equal to the actual size of a single pixel multiplied by the number of pixels of the inspection target; if the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient, no processing is performed; if the real-time pixel area is less than the pixel area multiplied by the preset proportion coefficient, adjust the real-time inspection angle until the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient; update the adjusted real-time inspection angle to the inspection parameter group.

[0031] The application can effectively improve the real-time inspection angle acquisition speed and further improve the work efficiency by assembling the inspection parameter group and the inspection parameter sequence, using the spatial coordinates of the camera to find the corresponding inspection parameter group in the database, and adjusting the real-time inspection angle of the camera of the inspection equipment according to the inspection parameter group. Further analysis of real-time image data and adjustment of real-time inspection angle can timely discover low-quality data and further improve the quality of subsequent data collection.

[0032] Another aspect of the application provides an AI-based building construction site inspection management system, which is applied to the AI-based building construction site inspection management method described above, and the system includes an inspection data acquisition module, a spatial model construction module, an optimal section analysis model, and a parameter adjustment and update module.

[0033] The inspection data acquisition module is used to plan the inspection equipment running path according to the inspection task, control the inspection equipment to perform safe inspection and keep the detection height of the data collector of the inspection equipment consistent, and collect detection data through the inspection equipment during the inspection process.

[0034] The space model construction module is configured to clean data of the detection data during the operation of the inspection device, and establish a three-dimensional point cloud model based on the cleaned detection data; a space coordinate system is constructed in the three-dimensional point cloud model, and the spatial position information of the inspection target is analyzed;

[0035] The optimal route analysis model is configured to analyze the optimal detection route of the inspection device according to the spatial position information of the inspection device and the inspection target;

[0036] The parameter adjustment and update module is configured to establish an inspection parameter group according to the spatial position information of the optimal detection route and the corresponding inspection parameters; the real-time inspection angle of the inspection device is searched and adjusted based on the inspection parameter sequence, the real-time inspection angle corresponding to the real-time detection data that does not meet the condition is further adjusted, and the real-time inspection angle is updated.

[0037] According to the above scheme, the inspection data acquisition module includes an operation path planning unit and an acquisition control unit;

[0038] The operation path planning unit is configured to plan an operation path of the inspection device according to an inspection task;

[0039] The acquisition control unit is configured to control the inspection device to perform safe inspection and keep the detection height of a data collector of the inspection device consistent, and to acquire detection data through the inspection device during the inspection; the data collector of the inspection device includes a scanning instrument and a camera; the detection height includes a scanning instrument detection height and a camera detection height; the scanning instrument detection height represents the vertical distance between the scanning instrument and the ground where the inspection device is located; the camera detection height represents the vertical distance between the camera and the ground where the inspection device is located; and the detection data includes three-dimensional point cloud data and image data.

[0040] According to the above scheme, the space model construction module includes a three-dimensional point cloud model construction unit and an inspection target space analysis unit;

[0041] The three-dimensional point cloud model construction unit is configured to extract three-dimensional point cloud data from the detection data, and remove the three-dimensional point cloud data corresponding to moving objects in the scanning process; and a three-dimensional point cloud model is established using the cleaned three-dimensional point cloud data;

[0042] The inspection target space analysis unit is configured to construct a space coordinate system in the three-dimensional point cloud model, extract the spatial coordinates of the boundary of the inspection target in the three-dimensional point cloud model, and analyze the spatial coordinates of the center of gravity of the inspection target.

[0043] According to the above scheme, the optimal route analysis model includes an inspection target image analysis unit and an optimal detection route judgment unit;

[0044] The inspection target image analysis unit is configured to analyze actual maximum observation areas of the inspection target corresponding to different spatial coordinates of the camera; and calculate pixel areas of the inspection target displayed in the image data under different spatial coordinates of the camera according to the actual maximum observation areas.

[0045] The optimal detection path judgment unit is configured to analyze the analysis reference values of the pixel areas in the pixel area set; and mark the spatial coordinates of the camera corresponding to the pixel area with the analysis reference value equal to the analysis reference value threshold as spatial boundaries, and record the running path of the inspection equipment between the two spatial boundaries as the optimal detection path.

[0046] According to the above scheme, the parameter adjustment and update module comprises a real-time control unit and a parameter update unit.

[0047] The real-time control unit is configured to group all the inspection parameter groups according to the running direction of the inspection equipment to form an inspection parameter sequence, and store the inspection parameter sequence in a database; after the camera is started, the spatial coordinates of the camera are used to search for the corresponding inspection parameter group in the database, and the real-time inspection angle of the camera of the inspection equipment is adjusted according to the inspection parameter group.

[0048] The parameter update unit is configured to analyze a real-time pixel area of the inspection target in the image data in the real-time image data, wherein the real-time pixel area is equal to the actual size of a single pixel multiplied by the pixel number of the inspection target; if the real-time pixel area is greater than or equal to the pixel area multiplied by a preset proportion coefficient, no processing is performed; if the real-time pixel area is less than the pixel area multiplied by the preset proportion coefficient, the real-time inspection angle is adjusted until the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient; and the adjusted real-time inspection angle is updated to the inspection parameter group.

[0049] Compared with the prior art, the beneficial effects of the present application are that: through the scanning instrument of the inspection equipment, the three-dimensional space information and the surface model on the running path of the inspection equipment can be quickly obtained, and a three-dimensional point cloud model is constructed; the point cloud quantity analysis on the optimal point cloud can further improve the accuracy of the three-dimensional point cloud model; under the support of the digital ground model and high-resolution images, efficient and high-precision line inspection applications are realized; by analyzing the maximum observation area of the inspection target under different position information and the distance between the inspection target and the inspection equipment, the pixel area in the image data is analyzed, the reference value is calculated and analyzed according to the pixel area, the best detection section is obtained, the amount of detection data is reduced, the quality of detection data is improved, the data stacking of the database is avoided, and the overall analysis efficiency of the inspection system is improved; the application forms an inspection parameter group and an inspection parameter sequence, uses the spatial coordinates of the camera to find the corresponding inspection parameter group in the database, adjusts the real-time inspection angle of the camera of the inspection equipment according to the inspection parameter group; the real-time inspection angle acquisition speed can be effectively improved, and the work efficiency is further improved; further analyzing the real-time image data and adjusting the real-time inspection angle can timely find the case of low data quality, and further improve the quality of subsequent data collection. BRIEF DESCRIPTION OF DRAWINGS

[0050] The accompanying drawings are included to provide a further understanding of the application, and constitute a part of the specification, illustrate the application, and are used to explain the application together with the embodiments of the application, and do not constitute a limitation on the application. In the drawings:

[0051] Figure 1 A flowchart of a building construction site inspection management method based on AI according to the present application;

[0052] Figure 2 A structural schematic diagram of a building construction site inspection management system based on AI according to the present application. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0054] Please refer to Figure 1 The present application provides a technical solution: a building construction site inspection management method based on AI, which comprises the following steps:

[0055] S1: planning a path of the inspection device according to the inspection task; controlling the inspection device to perform a safety inspection and keep the detection height of a data collector of the inspection device consistent, and collecting detection data by the inspection device during the inspection process;

[0056] In S1, the data collector of the inspection device includes a scanning instrument and a camera; the detection height includes a scanning instrument detection height and a camera detection height; the scanning instrument detection height represents a vertical distance between the scanning instrument and the ground where the inspection device is located; the camera detection height represents a vertical distance between the camera and the ground where the inspection device is located; and the detection data includes three-dimensional point cloud data and image data.

[0057] S2: performing data cleaning on the detection data during the operation of the inspection device, establishing a three-dimensional point cloud model based on the detection data after data cleaning, constructing a space coordinate system in the three-dimensional point cloud model, and analyzing the spatial position information of the inspection target;

[0058] In S2, the following contents are included:

[0059] S201: extracting the three-dimensional point cloud data in the detection data, and removing the three-dimensional point cloud data corresponding to the moving objects in the scanning process;

[0060] S202: establishing a three-dimensional point cloud model by using the three-dimensional point cloud data after data cleaning; in the construction of any plane of the three-dimensional point cloud model, using the RANSA algorithm to analyze the plane that meets the preset requirements and has the most points as the optimal plane; recording the point cloud in the optimal plane as the optimal point cloud, and for any optimal point cloud, counting the number of point clouds within the radius threshold, if the number of point clouds within the radius threshold is greater than or equal to the number threshold, saving the optimal point cloud; if the number of point clouds within the radius threshold is less than the number threshold, removing the optimal point cloud;

[0061] S203: constructing a space coordinate system in the three-dimensional point cloud model, extracting the spatial coordinates of the boundary of the inspection target in the three-dimensional point cloud model, and analyzing the spatial coordinates of the center of gravity point of the inspection target, recorded as (a, b, c); wherein a, b and c respectively represent the numerical values of the center of gravity point of the inspection target on the spatial coordinate axes in the three-dimensional point cloud model.

[0062] S3: analyzing the best detection section of the inspection device according to the spatial position information of the inspection device and the inspection target;

[0063] In S3, the following contents are included:

[0064] S301: record the spatial coordinates of the camera in the inspection equipment as (x, y, z); wherein x, y and z represent spatial coordinate variables in a three-dimensional point cloud model; extract the spatial coordinates of the camera corresponding to the inspection equipment when running on a path, analyze the actual maximum observation area of the inspection target corresponding to the camera at different spatial coordinates, denoted as S(x, y, z); the actual maximum observation area represents the maximum surface area size that can be projected and displayed in the image data under the corresponding inspection target volume; the spatial coordinates of one camera correspond to one actual maximum observation area;

[0065] S302: obtain the focal length f of the camera of the inspection equipment and the actual size P of a single pixel, analyze the distance between the camera of the inspection equipment and the center of gravity of the inspection target, denoted as L(x, y, z); according to each actual maximum observation area, calculate the pixel area PI(x, y, z) of the inspection target displayed in the image data under different spatial coordinates of the camera; the specific calculation formula is:

[0066] L(x, y, z) = [(x-a) 2 +(y-b) 2 +(z-c) 2 ] 1 / 2 ;

[0067] PI(x, y, z) = S(x, y, z) × f 2 ÷ [L(x, y, z) × P] 2 ;

[0068] Embodiment 1: In this embodiment, the focal length f of the camera is 0.05 m; the physical size of the camera sensor is 6.4 mm × 4.8 mm; the resolution is 640 × 480 pixels; the distance L(x, y, z) between the camera of the inspection equipment and the center of gravity of the inspection target is 5 m; the actual maximum observation area S(x, y, z) is 40 cm 2 ;

[0069] Then P = sensor width ÷ resolution width = 6.4 mm ÷ 640 = 0.01 mm = 10 -5 m;

[0070] P 2 = 10 -10 m 2 ; L(x, y, z) 2 = 25 m 2 ; f 2 = 0.0025 m 2 ; S(x, y, z) = 0.0004 m 2 ;

[0071] PI(x, y, z) = 0.0004 × 0.0025 ÷ [10-10 x25] = 400 pixels 2

[0072] S303: Extract the pixel area corresponding to the actual maximum observation area of the camera at different spatial coordinates when the inspection device is on the running path, and form a pixel area set; analyze the analysis reference value of each pixel area in the pixel area set:

[0073] ARV i = [1 ÷ (2πα 2 ) 1 / 2 ] × exp[-(PI i - β) 2 ÷ (2 × α 2 )];

[0074] where ARV i represents the i-th pixel area in the pixel area set, β represents the mean value of the pixel area set, and α represents the standard deviation of the pixel area set;

[0075] S304: Set an analysis reference value threshold for the analysis reference value, and extract the spatial coordinates of the camera corresponding to the pixel area with the analysis reference value equal to the analysis reference value threshold as the spatial boundary. The running path of the inspection device between the two spatial boundaries is recorded as the best detection section. When the spatial coordinates of the camera of the inspection device belong to the best detection section, the camera is turned on for detection tasks. The pixel area corresponding to the spatial coordinates in the best detection section is greater than the pixel area threshold.

[0076] S4: Form an inspection parameter group according to the spatial position information of the best detection section and the corresponding inspection parameters; based on the inspection parameter sequence, adjust the real-time inspection angle of the inspection device, further adjust the real-time inspection angle corresponding to the real-time detection data that does not meet the condition, and update.

[0077] In S4, the following contents are included:

[0078] S401: Extract the spatial coordinates of the best detection section and the spatial coordinates of the best detection section in the inspection target actual maximum observation area corresponding to the inspection angle θ, and form an inspection parameter group (x, y, z, θ); the inspection angle is the angle between the horizontal plane where the camera is located and the shooting direction of the camera;

[0079] S402: Group all inspection parameter groups according to the running direction of the inspection device to form an inspection parameter sequence, and store the inspection parameter sequence in a database; after turning on the camera, use the spatial coordinates of the camera to search for the corresponding inspection parameter group in the database, and adjust the real-time inspection angle of the camera of the inspection device according to the inspection parameter group;

[0080] ​S403: Extract real-time image data collected based on the inspection parameter group, analyze the real-time pixel area of ​​the inspection target in the image data, the real-time pixel area is equal to the actual size of a single pixel multiplied by the number of pixels of the inspection target; if the real-time pixel area is greater than or equal to the pixel area multiplied by the preset scaling factor, no processing is performed; if the real-time pixel area is less than the pixel area multiplied by the preset scaling factor, adjust the real-time inspection angle until the real-time pixel area is greater than or equal to the pixel area multiplied by the preset scaling factor; update the adjusted real-time inspection angle to the inspection parameter group.

[0081] Please see Figure 2 The present invention provides a technical solution: an AI-based construction site inspection and management system, which includes an inspection data acquisition module, a spatial model construction module, an optimal road segment analysis model, and a parameter adjustment and update module;

[0082] The inspection data acquisition module is used to plan the operation path of the inspection equipment according to the inspection task, control the inspection equipment to carry out safety inspections and maintain the consistency of the detection height of the data acquisition device of the inspection equipment; and collect detection data through the inspection equipment during the inspection process.

[0083] The spatial model building module is used to clean the detection data during the operation of the inspection equipment, and to build a three-dimensional point cloud model based on the cleaned detection data; a spatial coordinate system is built in the three-dimensional point cloud model to analyze the spatial location information of the inspection target;

[0084] The optimal road segment analysis model is used to analyze the optimal inspection road segment for the inspection equipment based on the spatial location information of the inspection equipment and the inspection target.

[0085] The parameter adjustment and update module is used to form an inspection parameter group based on the spatial location information of the best detection section and the corresponding inspection parameters; it searches and adjusts the real-time inspection angle of the inspection equipment based on the inspection parameter sequence, further adjusts the real-time inspection angle corresponding to the real-time detection data that does not meet the conditions, and updates it.

[0086] The inspection data acquisition module includes a path planning unit and an acquisition control unit;

[0087] The operation path planning unit is used to plan the operation path of the inspection equipment according to the inspection task.

[0088] The collection control unit is configured to control the inspection device to perform safety inspection and keep the detection heights of the data collectors of the inspection device consistent, and collect detection data by the inspection device during the inspection; the data collector of the inspection device comprises a scanning instrument and a camera; the detection height comprises a scanning instrument detection height and a camera detection height; the scanning instrument detection height represents the vertical distance between the scanning instrument and the ground where the inspection device is located; the camera detection height represents the vertical distance between the camera and the ground where the inspection device is located; and the detection data comprises three-dimensional point cloud data and image data.

[0089] The space model construction module comprises a three-dimensional point cloud model construction unit and an inspection target space analysis unit.

[0090] The three-dimensional point cloud model construction unit is configured to extract the three-dimensional point cloud data in the detection data, remove the three-dimensional point cloud data corresponding to the moving objects in the scanning process, and establish a three-dimensional point cloud model by using the three-dimensional point cloud data after data cleaning.

[0091] The inspection target space analysis unit is configured to construct a space coordinate system in the three-dimensional point cloud model, extract the space coordinates of the boundary of the inspection target in the three-dimensional point cloud model, and analyze the space coordinates of the center of gravity of the inspection target.

[0092] The optimal route analysis model comprises an inspection target image analysis unit and an optimal detection route judgment unit.

[0093] The inspection target image analysis unit is configured to analyze the actual maximum observation areas of the inspection target corresponding to different space coordinates of the camera, and calculate the pixel areas of the inspection target displayed in the image data under different space coordinates of the camera according to the actual maximum observation areas.

[0094] The optimal detection route judgment unit is configured to analyze the analysis reference values of the pixel areas in a pixel area set, mark the space coordinates of the camera corresponding to the pixel area whose analysis reference value is equal to an analysis reference value threshold as a space boundary, and record the running path of the inspection device between the two space boundaries as an optimal detection route.

[0095] The parameter adjustment and update module comprises a real-time control unit and a parameter update unit.

[0096] The real-time control unit is configured to group all the inspection parameter groups into an inspection parameter sequence according to the running direction of the inspection device, store the inspection parameter sequence in a database, and find the corresponding inspection parameter group in the database by using the space coordinates of the camera after the camera is turned on, and adjust the real-time inspection angle of the camera of the inspection device according to the inspection parameter group.

[0097] The parameter updating unit is used for analyzing a real-time pixel area of the inspection target in the real-time image data in the image data, and the real-time pixel area is equal to the actual size of a single pixel multiplied by the pixel number of the inspection target; if the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient, no processing is performed; if the real-time pixel area is less than the pixel area multiplied by the preset proportion coefficient, the real-time inspection angle is adjusted until the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient; and the adjusted real-time inspection angle is updated to the inspection parameter group.

[0098] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0099] It will be apparent to those skilled in the art that the application is not limited to the details of the above-exemplified embodiments and that the application can be implemented in other particular forms without departing from the spirit or essential characteristics of the application. The embodiments should therefore be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the above description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference signs in the claims should be considered as limiting the scope of the claims.

Claims

1. An AI-based construction site inspection management method, characterized by, The method comprises the following steps: S1: planning a device operation path according to a patrol task; controlling the device to perform a safety patrol and keeping the detection height of a data collector of the device consistent, and collecting detection data by the device during the patrol; S2: performing data cleaning on the detection data during the operation of the device, and establishing a three-dimensional point cloud model based on the detection data after data cleaning; constructing a space coordinate system in the three-dimensional point cloud model, and analyzing the spatial position information of the patrol target; S3: analyzing the best detection section of the device according to the spatial position information of the device and the patrol target; In S3, the following contents are included: S301: the space coordinates of a camera in the device are denoted as (x, y, z); wherein x, y and z represent space coordinate variables in the three-dimensional point cloud model; the space coordinates corresponding to the camera of the device on the operation path are extracted, the actual maximum observation area of the camera corresponding to different space coordinates is analyzed, and is denoted as S(x, y, z); the actual maximum observation area represents the maximum surface area size that can be projected and displayed in the image data under the volume of the corresponding patrol target; the space coordinates of one camera correspond to one actual maximum observation area; S302: the focal length f of the camera of the device and the actual size P of a single pixel are obtained, the distance between the camera of the device and the center of gravity of the patrol target is analyzed, and is denoted as L(x, y, z); according to each actual maximum observation area, the pixel area PI(x, y, z) of the patrol target displayed in the image data by the camera under different space coordinates is calculated; the specific calculation formula is: L(x, y, z) = [(x - a) 2 +(y - b) 2 +(z - c) 2 ] 1 / 2 ; PI(x, y, z) = S(x, y, z) x f 2 ÷ [L(x, y, z) x P] 2 ; S303: the pixel area of the actual maximum observation area corresponding to the camera under different space coordinates of the device on the operation path is extracted, and a pixel area set is established; the analysis reference value of each pixel area in the pixel area set is analyzed: ARV i = [1 ÷ (2πα 2 ) 1 / 2 ] × exp[-(PI i -β) 2 ÷ (2×α 2 )] where ARV i represents the i-th pixel area in the set of pixel areas, β represents the mean of the set of pixel areas, and a represents the standard deviation of the set of pixel areas; S304: an analysis reference value threshold is set for the analysis reference value, the space coordinates of the camera corresponding to the pixel area with the analysis reference value equal to the analysis reference value threshold are extracted and denoted as space boundaries, the operation path of the device between the two space boundaries is denoted as the best detection section, and the camera is turned on to perform the detection task when the space coordinates of the camera of the device belong to the best detection section; the pixel area corresponding to the space coordinates in the best detection section is greater than the pixel area threshold; S4: a patrol parameter group is established according to the spatial position information of the best detection section and the corresponding patrol parameters; the real-time patrol angle of the device is found and adjusted based on the patrol parameter sequence, the real-time detection data corresponding to the real-time patrol angle that does not meet the condition is further adjusted, and is updated.

2. The AI-based construction site inspection management method of claim 1, wherein: In S1, the data collector of the device comprises a scanning instrument and a camera; the detection height comprises a scanning instrument detection height and a camera detection height; the scanning instrument detection height represents the vertical distance between the scanning instrument and the ground where the device is located; the camera detection height represents the vertical distance between the camera and the ground where the device is located; and the detection data comprises three-dimensional point cloud data and image data. 3.The AI-based construction site inspection management method of claim 2, wherein: In S2, the following contents are included: S201: Extract three-dimensional point cloud data in the detection data, and remove three-dimensional point cloud data corresponding to a moving object in a scanning process; S202: Establish a three-dimensional point cloud model by using the three-dimensional point cloud data after data cleaning; in construction of any plane of the three-dimensional point cloud model, adopt an RANSA algorithm to analyze a plane meeting a preset requirement and having the most points, mark the plane as an optimal plane; mark point cloud in the optimal plane as optimal point cloud, and for any optimal point cloud, count a number of point clouds within a radius threshold, if the number of point clouds within the radius threshold is greater than or equal to a number threshold, save the optimal point cloud; if the number of point clouds within the radius threshold is less than the number threshold, remove the optimal point cloud; S203: Construct a space coordinate system in the three-dimensional point cloud model, extract a space coordinate of a boundary of the inspection target in the three-dimensional point cloud model, and analyze a space coordinate of a gravity center point of the inspection target, mark the space coordinate as (a, b, c); a, b, and c respectively represent numerical values of the gravity center point of the inspection target on space coordinate axes in the three-dimensional point cloud model.

4. The AI-based construction site inspection management method of claim 3, wherein: In S4, the following content is included: S401: Extract a space coordinate of a best detection section and a space coordinate of the best detection section at an inspection angle θ corresponding to an actual maximum observation area of the inspection target, and establish an inspection parameter group (x, y, z, θ); the inspection angle is an angle between a horizontal plane where a camera is located and a shooting direction of the camera; S402: Group all inspection parameter groups according to a running direction of the inspection equipment to form an inspection parameter sequence, and store the inspection parameter sequence in a database; after the camera is started, use a space coordinate of the camera to search for a corresponding inspection parameter group in the database, and adjust a real-time inspection angle of the camera of the inspection equipment according to the inspection parameter group; S403: Extract real-time image data collected based on the inspection parameter group, analyze a real-time pixel area of the inspection target in the image data, and the real-time pixel area is equal to an actual size of a single pixel multiplied by a pixel number of the inspection target; if the real-time pixel area is greater than or equal to a pixel area multiplied by a preset proportion coefficient, no processing is performed; if the real-time pixel area is less than the pixel area multiplied by the preset proportion coefficient, adjust the real-time inspection angle until the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient; and update the adjusted real-time inspection angle to the inspection parameter group.

5. An AI-based construction site inspection management system, the system being applied to implement the AI-based construction site inspection management method of any one of claims 1-4, characterized in that, The system includes an inspection data acquisition module, a space model construction module, a best section analysis model, and a parameter adjustment and update module; The inspection data acquisition module is configured to plan a running path of the inspection equipment according to an inspection task, control the inspection equipment to perform safe inspection, and keep detection heights of data collectors of the inspection equipment consistent; Detection data is collected by the inspection equipment in an inspection process; The space model construction module is configured to perform data cleaning on the detection data in a running process of the inspection equipment, establish a three-dimensional point cloud model based on the detection data after data cleaning, construct a space coordinate system in the three-dimensional point cloud model, and analyze space position information of the inspection target; The best section analysis model is configured to analyze a best detection section of the inspection equipment according to the space position information of the inspection equipment and the inspection target; The parameter adjustment updating module is configured to establish a patrol parameter group according to the spatial position information of the optimal detection path and the corresponding patrol parameter group. The real-time patrol angle of the patrol device is searched and adjusted based on the patrol parameter sequence, and the real-time patrol angle corresponding to the real-time detection data that does not meet the condition is further adjusted and updated.

6. The AI-based construction site inspection management system according to claim 5, characterized in that: The patrol data acquisition module comprises a running path planning unit and an acquisition control unit. The running path planning unit is configured to plan a running path of the patrol device according to a patrol task. The acquisition control unit is configured to control the patrol device to perform safe patrol and keep the detection height of the data collector of the patrol device consistent, and to acquire detection data by the patrol device during the patrol.

7. The AI-based construction site inspection management system of claim 5, wherein: The data collector of the patrol device comprises a scanning instrument and a camera. The detection height comprises a scanning instrument detection height and a camera detection height. The scanning instrument detection height represents the vertical distance between the scanning instrument and the ground where the patrol device is located.

8. The AI-based construction site inspection management system of claim 5, wherein: The camera detection height represents the vertical distance between the camera and the ground where the patrol device is located. The detection data comprises three-dimensional point cloud data and image data. The spatial model construction module comprises a three-dimensional point cloud model construction unit and a patrol target space analysis unit. The three-dimensional point cloud model construction unit is configured to extract the three-dimensional point cloud data in the detection data, remove the three-dimensional point cloud data corresponding to the moving objects in the scanning process, and establish a three-dimensional point cloud model by using the three-dimensional point cloud data after data cleaning. The patrol target space analysis unit is configured to construct a spatial coordinate system in the three-dimensional point cloud model, extract the spatial coordinates of the boundary of the patrol target in the three-dimensional point cloud model, and analyze the spatial coordinates of the center of gravity of the patrol target.

9. The AI-based construction site inspection management system of claim 5, wherein: The optimal path analysis model comprises a patrol target image analysis unit and an optimal detection path judgment unit. The patrol target image analysis unit is configured to analyze the actual maximum observation area of the patrol target corresponding to different spatial coordinates of the camera. According to each actual maximum observation area, the pixel area of the patrol target displayed in the image data under different spatial coordinates of the camera is calculated. The optimal detection path judgment unit is configured to analyze each pixel area in the analysis reference value of the pixel area set. The spatial coordinates of the camera corresponding to the pixel area with the analysis reference value equal to the analysis reference value threshold are marked as spatial boundaries, and the running path of the patrol device between the two spatial boundaries is marked as the optimal detection path. The parameter adjustment updating module comprises a real-time control unit and a parameter updating unit. The real-time control unit is configured to group all the patrol parameter groups according to the running direction of the patrol device to form a patrol parameter sequence, store the patrol parameter sequence in a database, and search for the corresponding patrol parameter group in the database by using the spatial coordinates of the camera after the camera is turned on, and adjust the real-time patrol angle of the camera of the patrol device according to the patrol parameter group. The parameter updating unit is configured to analyze the real-time pixel area of the patrol target in the image data, which is equal to the actual size of a single pixel multiplied by the number of pixels of the patrol target. If the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient, no processing is performed. If the real-time pixel area is less than the pixel area multiplied by the preset proportion coefficient, the real-time inspection angle is adjusted until the real-time pixel area is greater than or equal to the pixel area multiplied by the preset proportion coefficient; and the adjusted real-time inspection angle is updated to the inspection parameter group.

Images