A method and system for measuring the concrete volume of a construction project based on artificial intelligence and unmanned aerial vehicle mapping technology

Abstract

The present invention belongs to the technical field of intelligent construction of building engineering, and discloses a method and system for surveying and mapping the concrete volume of building engineering based on artificial intelligence and unmanned aerial vehicle (UAV) surveying and mapping technology. The method for surveying and mapping the concrete volume of building engineering includes: obtaining point cloud information data at a target terrain; constructing a real-time three-dimensional state model of the target terrain according to the obtained point cloud information data; obtaining real-time data information on the dimensions to be poured at the building location according to the comparison result between the real-time three-dimensional state model and a preset three-dimensional target model; and obtaining concrete volume requirement information according to the obtained real-time data information on the dimensions to be poured at the building location. In the present invention, by obtaining information data at the target terrain in real time and comparing it with the building pouring target information in real time, the remaining concrete volume requirement is reflected and displayed, guiding engineering operations to ensure the construction efficiency and quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent construction of building engineering. Specifically, it relates to a method and system for surveying and mapping the concrete volume of building engineering based on artificial intelligence and UAV mapping technology. Background Art

[0002] The concrete volume refers to the volume of concrete, with the unit of cubic meters. In building engineering, the volume of concrete poured is usually calculated by a special department based on a model. Due to the certain difference between the theoretical model and the actual situation, there will inevitably be problems of overproduction or shortage of precast concrete during the on-site pouring process. During the on-site pouring process, when the precast concrete is insufficient, it is necessary to supplement the concrete. Due to the time-delay effect of delivery, there is an uncertain time difference from issuing the delivery instruction to the concrete being transported to the site. If the waiting time is too long, it may lead to cold joints in the pouring. The real-time calculation and feedback of the concrete volume demand (remaining concrete pouring volume) are related to the timeliness of the concrete volume finishing and have a direct impact on the quality and efficiency of the project construction.

[0003] Therefore, there is an urgent need to provide a method and system for surveying and mapping the concrete volume of building engineering based on artificial intelligence and UAV mapping technology that can effectively reflect the concrete volume demand to solve the above problems.

[0004] In view of this, this application is specifically proposed. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiency that the prior art cannot provide real-time feedback on the concrete volume demand, and provide a method for surveying and mapping the concrete volume of building engineering based on artificial intelligence and UAV mapping technology.

[0006] Another purpose of the present invention is to provide a system for surveying and mapping the concrete volume of building engineering that adopts the above method for surveying and mapping the concrete volume of building engineering.

[0007] To solve the above technical problems, the basic concept of the technical solution adopted by the present invention is: A method for surveying and mapping the concrete volume of building engineering based on artificial intelligence and UAV mapping technology, including the steps of:

[0008] S1. A UAV equipped with a three-dimensional laser scanner flies along a predetermined trajectory at the target terrain to obtain the point cloud information data at the target terrain;

[0009] S2. According to the obtained point cloud information data, construct a real-time three-dimensional state model of the target terrain;

[0010] S3. According to the comparison result between the real-time three-dimensional state model and the preset three-dimensional target model, obtain the real-time data information of the dimensions to be poured at the building location;

[0011] S4. Obtain the concrete volume requirement information based on the obtained real-time data information of the dimensions to be poured at the building location.

[0012] According to an embodiment of the present invention, the method for surveying the concrete volume of a construction project further includes the steps:

[0013] S5. Reconstruct the real-time three-dimensional state model at the target terrain with the point cloud information data obtained at a predetermined time interval;

[0014] S6. Obtain the corrected data information of the dimensions to be poured at the building location according to the comparison result between the reconstructed real-time three-dimensional state model at the target terrain and the preset three-dimensional target model;

[0015] S7. Obtain the real-time concrete volume requirement information based on the obtained corrected data information of the dimensions to be poured at the building location.

[0016] According to an embodiment of the present invention, the step S1 includes:

[0017] S1.1. Determine the distance information between the unmanned aerial vehicle (UAV) and the target object according to the time difference between the emission and return reception of each pulse of the laser scanner;

[0018] S1.2. Convert the determined distance information between the UAV and the target object into three-dimensional coordinate point information according to the positioning and attitude data of the UAV, so as to obtain the point cloud information data at the target terrain.

[0019] According to an embodiment of the present invention, the step S2 includes:

[0020] S2.1. Perform data denoising processing and point cloud registration processing on the obtained point cloud information data at the target terrain;

[0021] S2.2. Construct the real-time three-dimensional state model at the target terrain according to the point cloud information data at the target terrain after data processing.

[0022] According to an embodiment of the present invention, the step S3 includes:

[0023] S3.1. Identify the image information captured during the flight of the UAV along a predetermined trajectory and the preset three-dimensional target model by applying multi-view image recognition technology and computer vision recognition technology, and determine the volume, shape and position distribution information of the target concrete building;

[0024] S3.2. Generate a three-dimensional volume model of the remaining concrete volume requirement according to the determined volume, shape and position distribution information of the target concrete building and the comparison result between the constructed real-time three-dimensional state model and the preset three-dimensional target model;

[0025] S3.3. Obtain real-time data information on the dimensions to be poured at the building location based on the generated three-dimensional model of the remaining required concrete volume.

[0026] According to an embodiment of the present invention, wherein the step S3.1 includes:

[0027] S3.1.1. Preprocess the captured multi-view images using multi-view image recognition technology;

[0028] S3.1.2. Extract feature points from the preprocessed multi-view images, and perform alignment and merging operations on the repeatedly extracted feature points;

[0029] S3.1.3. Locate and extract the volume, shape, and position distribution information of the target concrete building in the preset three-dimensional target model.

[0030] According to an embodiment of the present invention, wherein the step S3.2 includes:

[0031] S3.2.1. Construct and train an artificial intelligence deep learning model;

[0032] S3.2.2. The artificial intelligence deep learning model generates a three-dimensional volume model of the remaining required concrete volume according to the recognized volume, shape, and position distribution information of the target concrete building and the comparison result between the constructed real-time three-dimensional state model and the preset three-dimensional target model.

[0033] According to an embodiment of the present invention, wherein the step S3.2.2 includes:

[0034] A volume solving system for estimating the volume of a geometric model is generated within the artificial intelligence deep learning model;

[0035] The volume solving formula obtains real-time data information on the dimensions to be poured at the building location according to the received data information, and / or the volume solving system obtains corrected data information on the dimensions to be poured at the building location according to the data information obtained within a predetermined time interval.

[0036] The present invention also provides a building engineering concrete volume surveying and mapping system based on artificial intelligence and unmanned aerial vehicle surveying and mapping technology. Using the above-mentioned building engineering concrete volume surveying and mapping method, the building engineering concrete volume surveying and mapping system includes:

[0037] A data acquisition component, which is used to acquire image information and distance information at the target terrain;

[0038] A data processing component, which is used to process the acquired image information and distance information and construct a 3D model;

[0039] A model display component, which is used to display a preset model, a historical model, and a newly generated model;

[0040] An information reminder component, which provides corresponding reminders of model change information and concrete volume requirement information.

[0041] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art:

[0042] 1) In the present invention, by acquiring information data at the target terrain in real time and comparing it with the building pouring target information in real time, the remaining concrete volume requirement is reflected and displayed to guide engineering operations, so as to ensure the construction efficiency and quality;

[0043] 2) In the present invention, by reconstructing the real-time 3D state model at a predetermined time interval, the accuracy of the reflected remaining concrete volume requirement is ensured.

[0044] The following further describes the specific implementation manners of the present invention in detail with reference to the accompanying drawings. Description of the Drawings

[0045] The accompanying drawings, as a part of the present invention, are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention, but do not constitute an improper limitation to the present invention. Obviously, the accompanying drawings in the following description are only some embodiments. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts. In the drawings:

[0046] Figure 1 It is a flowchart of the steps of the method for surveying and mapping the concrete volume of a building project in an embodiment of the present invention.

[0047] It should be noted that these drawings and text descriptions are not intended to limit the scope of the concept of the present invention in any way, but to illustrate the concept of the present invention to those skilled in the art by referring to specific embodiments. Specific Embodiments

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0049] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0050] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] As Figure 1 shown, a method for surveying the concrete volume of a construction project based on artificial intelligence and unmanned aerial vehicle (UAV) mapping technology according to the present invention includes the following steps:

[0052] S1. A UAV equipped with a three-dimensional laser scanner flies at a target terrain according to a predetermined trajectory to obtain point cloud information data of the target terrain.

[0053] S2. According to the obtained point cloud information data, a real-time three-dimensional state model of the target terrain is constructed.

[0054] S3. According to the comparison result between the real-time three-dimensional state model and a preset three-dimensional target model, real-time data information on the dimensions to be poured at the construction location is obtained.

[0055] S4. According to the obtained real-time data information on the dimensions to be poured at the construction location, the concrete volume requirement information is obtained.

[0056] In the present invention, by obtaining the information data of the target terrain in real time and comparing it with the construction target in real time, the remaining concrete volume requirement is reflected and displayed, guiding the engineering operation and ensuring the construction efficiency and quality.

[0057] In a specific implementation manner of this embodiment, before the UAV runs, a predetermined trajectory delimited according to the area size and height difference of the target terrain is imported into the control system of the UAV, and the UAV flies according to the predetermined trajectory after taking off.

[0058] In a specific implementation manner of this embodiment, the predetermined trajectory is reflected in controlling the drone carrying a three-dimensional laser scanner (LiDAR sensor) to obtain data information (image information or distance information) of a specific part at the target terrain at different heights, different angles, or different speeds.

[0059] In a specific implementation manner of this embodiment, the preset three-dimensional target model is pre-constructed and set in advance according to the construction requirements.

[0060] Please refer to the appendix Figure 1 , in a specific implementation manner of this embodiment, the method for surveying and mapping the concrete volume of a building project further includes the steps:

[0061] S5. Reconstruct the real-time three-dimensional state model of the target terrain with the point cloud information data obtained at a predetermined time interval;

[0062] S6. Obtain the data information of the dimensions to be poured at the building position after correction according to the comparison result between the reconstructed real-time three-dimensional state model of the target terrain and the preset three-dimensional target model;

[0063] S7. Obtain the real-time concrete volume demand information according to the obtained data information of the dimensions to be poured at the building position after correction.

[0064] In the present invention, by reconstructing the real-time three-dimensional state model at a predetermined time interval, the accuracy of the remaining concrete volume demand is ensured.

[0065] In a specific implementation manner of this embodiment, the predetermined time interval is 30 min.

[0066] In a specific implementation manner of this embodiment, the predetermined time interval is 1 h. For example, use the point cloud information data obtained at 12 o'clock to reconstruct the real-time three-dimensional state model of the target terrain to replace the real-time three-dimensional state model of the target terrain constructed based on the point cloud information data obtained at 11 o'clock. Among them, the comparison result between the real-time three-dimensional state model of the target terrain reconstructed with the point cloud information data obtained at 12 o'clock and the real-time three-dimensional state model of the target terrain constructed with the point cloud information data obtained at 11 o'clock reflects the information of the concrete pouring volume within the predetermined interval period; the comparison result between the real-time three-dimensional state model of the target terrain reconstructed with the point cloud information data obtained at 12 o'clock and the preset three-dimensional target model reflects the information of the real-time concrete volume demand (remaining concrete pouring volume).

[0067] Of course, the predetermined time interval can be other time, and the specific length of the predetermined time interval is determined according to the on-site construction requirements. For example, it can be 10 min or 15 min. It can be understood that the shorter the predetermined time interval is, the faster the updated volume of concrete demand is, but the higher the requirements for the system will be.

[0068] In a specific implementation manner of this embodiment, the length of the predetermined time interval is different in different time periods.

[0069] Specifically, the predetermined time interval is t1 during the working period of the workers and t2 during the rest period of the workers; numerically, t2 is greater than t1.

[0070] In a specific implementation manner of this embodiment, step S1 includes:

[0071] S1.1: Determine the distance information between the UAV and the target object according to the time difference between the emission and return reception of each pulse of the laser scanner.

[0072] S1.2: According to the positioning and attitude data of the UAV (provided by GPS and IMU), convert the determined distance information between the UAV and the target object into three-dimensional coordinate point information, so as to obtain the point cloud information data at the target terrain; the point cloud information data refers to the set of a large number of three-dimensional coordinate points on the surface of the target object.

[0073] In the present invention, by converting the three-dimensional information of the UAV into the three-dimensional coordinate information between the target objects, the conversion is more convenient without changing the reference system, the system calculation logic is unified, and the efficiency of information processing can be effectively improved.

[0074] In a specific implementation manner of this embodiment, step S2 includes:

[0075] S2.1: Perform denoising processing and point cloud registration processing on the obtained point cloud information data at the target terrain.

[0076] S2.2: Construct a real-time three-dimensional state model of the target terrain according to the point cloud information data at the target terrain after data processing.

[0077] In the present invention, by applying the data processing solution, a large number of noise points and redundant data included in the collected point cloud information data can be effectively removed, which not only improves the efficiency of subsequent calculations, but also improves the accuracy of three-dimensional model construction.

[0078] In a specific implementation manner of this embodiment, the denoising processing refers to removing the noise points in the point cloud information data, such as isolated points and floating points.

[0079] In another specific implementation manner of this embodiment, before the point cloud information data obtained at the target terrain is subjected to registration processing after denoising processing, data downsampling processing and ground filtering processing are also performed; the downsampling processing refers to reducing the coordinate points in the point cloud information data that significantly indicate the same object and the same plane, and reducing the point density in the point cloud information data; the ground filtering processing refers to distinguishing the ground points and non-ground points in the point cloud information data, excluding the ground points, so as to extract the surface points of the target object.

[0080] In a specific implementation manner of this embodiment, the point cloud registration processing adopts the ICP algorithm (Iterative Closest Point) to align the overlapping parts of multiple point cloud data through iterative optimization, or, through global registration: using GPS and IMU data for preliminary registration and then performing fine alignment.

[0081] In a specific implementation manner of this embodiment, the processed and registered point cloud information data is used to construct a three-dimensional model, and a real-time three-dimensional state model of the target terrain is constructed.

[0082] In a specific implementation manner of this embodiment, the construction method used is as follows:

[0083] Mesh reconstruction to convert the point cloud information data into a polygon mesh and generate a surface model of the target object;

[0084] Surface fitting, through a fitting algorithm, to construct a smoother surface model for the generated surface model of the target object.

[0085] In a specific implementation manner of this embodiment, the parameters of the mesh reconstruction include: mesh density, smoothing parameter, and hole filling parameter. The parameters of the mesh reconstruction are determined by the obtained point cloud information data.

[0086] In a specific implementation manner of this embodiment, the step S3 includes:

[0087] S3.1. By applying multi-view image recognition technology and computer vision recognition technology, identify the image information captured during the flight of the drone along a predetermined trajectory and the preset three-dimensional target model, and determine the volume, shape, and position distribution information of the target concrete building;

[0088] S3.2. According to the determined volume, shape, and position distribution information of the target concrete building and the comparison result between the constructed real-time three-dimensional state model and the preset three-dimensional target model, generate a three-dimensional volume model of the remaining required volume of concrete.

[0089] S3.3. Obtain real-time data information on the dimensions to be poured at the construction location based on the generated 3D model of the remaining concrete demand volume.

[0090] In a specific implementation manner of this embodiment, a camera device for taking images is also carried on the drone. Through the image information and distance information obtained by the drone, the two data information are compared and coordinated with each other to determine the target volume, shape and position, ensuring the accuracy of information extraction.

[0091] In a specific implementation manner of this embodiment, the constructed real-time 3D state model includes generating sparse and dense point clouds through SfM (structure from motion) and MVS (multi-view stereo); using the RANSAC algorithm and ICP algorithm for point cloud denoising and registration; generating a 3D model through Poisson Surface Reconstruction or Marching Cubes; calculating the volume using the Voxelization or ConvexHull algorithm; using training and application models such as CNN / U-Net / ResNet for image recognition and volume analysis; and improving the model performance through cross-validation and hyperparameter optimization.

[0092] In a specific implementation manner of this embodiment, step S3.1 includes:

[0093] S3.1.1. Preprocess the captured multi-view images using multi-view image recognition technology. The preprocessing refers to correcting and aligning the images.

[0094] S3.1.2. Extract feature points from the preprocessed multi-view images (through SIFT / SURF / ORB), and perform alignment and merging operations on the repeatedly extracted feature points for matching.

[0095] S3.1.3. Locate and extract the volume, shape, and position distribution information of the target concrete building according to the feature points in the preset 3D target model.

[0096] In a specific implementation manner of this embodiment, step S3.2 includes:

[0097] S3.2.1. Construct and train an artificial intelligence deep learning model.

[0098] S3.2.2. The artificial intelligence deep learning model generates a 3D volume model of the remaining concrete demand volume according to the recognized volume, shape, and position distribution information of the target concrete building and the comparison result between the constructed real-time 3D state model and the preset 3D target model.

[0099] In a specific implementation manner of this embodiment, the step S3.2.2 includes:

[0100] Inside the artificial intelligence deep learning model, a volume solving system for estimating the volume of a geometric model is generated according to data mining, machine learning, and deep learning;

[0101] Based on the received data information, the volume solving formula obtains real-time data information on the dimensions to be poured at the building location, and / or, based on the data information obtained within a predetermined time interval, the volume solving system obtains corrected data information on the dimensions to be poured at the building location.

[0102] In the present invention, the artificial intelligence deep learning model feeds back the volume of concrete poured within a predetermined time interval to the volume solving system to correct and modify the model.

[0103] The present invention also provides a building engineering concrete volume surveying system based on artificial intelligence and unmanned aerial vehicle (UAV) mapping three-dimensional laser scanning technology. Using the above-mentioned building engineering concrete volume surveying method based on artificial intelligence and UAV mapping technology, the building engineering concrete volume surveying system includes:

[0104] A data acquisition component, which is used to acquire image information and distance information at the target terrain;

[0105] A data processing component, which is used to process the acquired image information and distance information and construct a three-dimensional model;

[0106] A model display component, which is used to display a preset model, a historical model, and a newly generated model;

[0107] An information reminder component, which provides corresponding reminders of model changes and reminders of concrete volume requirements.

[0108] In a specific implementation manner of this embodiment, the data acquisition component is a UAV equipped with a three-dimensional laser scanner.

[0109] According to the received information reminders, the operator can grasp the concrete pouring progress and concrete volume requirements in real time, and plan in advance the prefabrication and transfer of concrete in subsequent construction work.

[0110] In the present invention, by combining artificial intelligence and UAV mapping technology, a Longmap digital twin cloud visualization application is constructed to realize real-time observation of data such as the remaining concrete volume to be poured and the concrete volume that has been poured.

[0111] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art of this patent, without departing from the scope of the technical solution of the present invention, can make some changes or modifications using the technical content prompted above as equivalent embodiments of equivalent changes. The implementation schemes in the above embodiments can also be further combined or replaced. However, as long as it does not depart from the content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the scope of the present invention's solution.

Claims

1. A method for surveying the concrete volume of a construction project based on artificial intelligence and unmanned aerial vehicle surveying and mapping technology, characterized in that, Including the steps: S1. A drone equipped with a three-dimensional laser scanner flies over the target terrain along a predetermined trajectory to obtain the point cloud information data of the target terrain; S1.

1. Determine the distance information between the drone and the target object according to the time difference between the emission and return reception of each pulse of the laser scanner; S1.

2. According to the positioning and attitude data of the drone, convert the determined distance information between the drone and the target object into three-dimensional coordinate point information, thereby obtaining the point cloud information data of the target terrain; S2. Construct a real-time three-dimensional state model of the target terrain based on the obtained point cloud information data; S3. Obtain the real-time building position to-be-poured dimension data information according to the comparison result between the real-time three-dimensional state model and the preset three-dimensional target model; S3.

1. By applying multi-view image recognition technology and computer vision recognition technology, identify the image information captured during the flight of the drone along the predetermined trajectory and the preset three-dimensional target model, and determine the volume, shape, and position distribution information of the target concrete building; S3.1.

1. Preprocess the captured multi-view images using multi-view image recognition technology; S3.1.

2. Extract feature points from the preprocessed multi-view images, and perform alignment and merging operations on the repeatedly extracted feature points; S3.1.

3. Locate and extract the volume, shape, and position distribution information of the target concrete building in the preset three-dimensional target model according to the feature points; S3.

2. Generate a three-dimensional volume model of the remaining concrete demand volume according to the determined volume, shape, and position distribution information of the target concrete building and the comparison result between the constructed real-time three-dimensional state model and the preset three-dimensional target model; S3.2.

1. Construct and train an artificial intelligence deep learning model; S3.2.

2. The artificial intelligence deep learning model generates a three-dimensional volume model of the remaining concrete demand volume according to the identified volume, shape, and position distribution information of the target concrete building and the comparison result between the constructed real-time three-dimensional state model and the preset three-dimensional target model; A volume solving system for estimating the volume of a geometric model is generated in the artificial intelligence deep learning model; The volume solving formula obtains the real-time building position to-be-poured dimension data information according to the received data information, and / or the volume solving system obtains the corrected building position to-be-poured dimension data information according to the data information obtained within a predetermined time interval; S4. Obtain the concrete volume demand information according to the obtained real-time building position to-be-poured dimension data information; S5. Reconstruct the real-time three-dimensional state model of the target terrain with the point cloud information data obtained within a predetermined time interval; S6. Obtain the corrected building position to-be-poured dimension data information according to the comparison result between the reconstructed real-time three-dimensional state model of the target terrain and the preset three-dimensional target model; S7. Obtain the real-time concrete volume demand information according to the obtained corrected building position to-be-poured dimension data information.

2. The method for surveying the concrete quantity of a construction project based on artificial intelligence and unmanned aerial vehicle surveying and mapping technology according to claim 1, characterized in that, The step S2 includes: S2.

1. Denoise the point cloud information data obtained at the target terrain and perform point cloud registration processing on the data; S2.

2. Construct a real-time three-dimensional state model at the target terrain based on the point cloud information data that has undergone data processing.

3. A building engineering concrete volume surveying and mapping system based on artificial intelligence and unmanned aerial vehicle surveying and mapping technology, characterized in that, Adopt a method for surveying the concrete volume of a construction project based on artificial intelligence and unmanned aerial vehicle surveying and mapping technology according to any one of claims 1-2. The construction project concrete volume surveying system includes: A data acquisition component, which is used to acquire image information and distance information at the target terrain; A data processing component, which is used to process the acquired image information and distance information and construct a three-dimensional model; A model display component, which is used to display a preset model, a historical model, and a newly generated model; An information reminder component, which provides corresponding reminders of model changes and reminders of concrete volume requirements.

Images