Construction site three-dimensional reconstruction method, device and system and storage medium

Abstract

The invention discloses a construction site three-dimensional reconstruction method, device and system and a storage medium. The construction site three-dimensional reconstruction method comprises the steps that a laser radar and an IMU are arranged at a suspension arm based on a tower crane; data are collected in real time based on the IMU in the running state of the tower crane, and pose information is obtained; the method comprises the following steps: scanning a construction site based on a laser radar in a tower crane operation state to obtain site three-dimensional point cloud information; preprocessing the on-site three-dimensional point cloud information and the pose information; fusing the preprocessed field three-dimensional point cloud data and the pose information to obtain fused data; and performing three-dimensional reconstruction on the fused data. By adopting the technical scheme of the invention, three-dimensional reconstruction is performed on the construction site, the construction progress is automatically acquired, the subjective interference of workers is reduced, the cost is reduced, and the mapping efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of three-dimensional reconstruction, and in particular relates to a three-dimensional reconstruction method and system for a construction site, and a storage medium. Background Art

[0002] All construction projects require construction progress monitoring, and scientific monitoring methods are the prerequisite for ensuring the smooth implementation of construction projects. Traditional construction progress monitoring mainly involves manual on-site inspections and verifications according to the construction schedule. This method is inefficient, labor-intensive, and has large blind spots, and has long been unable to meet the needs of the fast-paced industry. At present, with the development of drone technology, there are also methods that use drone aerial images to reconstruct three-dimensional grids or point cloud models of actual scenes, and use related design models to compare with real-scene models to obtain basic construction conditions. This method still has disadvantages, is costly, and is labor-intensive. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a multi-sensor fusion construction site three-dimensional reconstruction method and system, and a storage medium, which adopts laser radar and IMU in combination with real-time data collection to perform three-dimensional reconstruction of the construction site and monitor the construction progress.

[0004] To achieve the above object, the present invention adopts the following technical solution:

[0005] A construction site three-dimensional reconstruction method, comprising:

[0006] Based on IMU, real-time data is collected when the tower crane is in operation to obtain position information;

[0007] Scan the construction site with the tower crane in operation using laser radar to obtain 3D point cloud information on site;

[0008] Preprocessing the on-site three-dimensional point cloud information and position information;

[0009] Fusing the pre-processed on-site 3D point cloud data and position information to obtain fused data;

[0010] The fused data is three-dimensionally reconstructed.

[0011] Preferably, the preprocessing includes denoising, filtering and registration.

[0012] Preferably, a laser radar and an IMU are arranged at the boom of a tower crane.

[0013] The present invention also provides a construction site three-dimensional reconstruction device, comprising:

[0014] The first acquisition module is used to collect data in real time based on the IMU when the tower crane is in operation, and obtain the posture information;

[0015] The second acquisition module is used to scan the construction site based on the laser radar when the tower crane is in operation to obtain the three-dimensional point cloud information of the site;

[0016] A preprocessing module, used for preprocessing the on-site three-dimensional point cloud information and position information;

[0017] A fusion module is used to fuse the pre-processed on-site 3D point cloud data and posture information to obtain fused data;

[0018] A reconstruction module is used to perform three-dimensional reconstruction on the fused data.

[0019] Preferably, the preprocessing includes denoising, filtering and registration.

[0020] Preferably, a laser radar and an IMU are arranged at the boom of a tower crane.

[0021] The present invention also provides a construction site three-dimensional reconstruction system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a construction site three-dimensional reconstruction method when executed by the processor.

[0022] The present invention also provides a storage medium, on which a computer program is stored, and the computer program executes the three-dimensional reconstruction method of the construction site when running.

[0023] The present invention can realize panoramic mapping of the construction site by rotating the tower arm one circle when the tower crane is idle or in working state; the tower crane is used to perform three-dimensional reconstruction of the construction site, and the construction progress is automatically obtained, reducing human subjective interference. Compared with the method of drone reconstruction, it reduces costs and improves the efficiency of mapping. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0025] Figure 1 The figure is a flow chart of a method for three-dimensional reconstruction of a construction site according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] Embodiment 1:

[0029] like Figure 1 As shown, an embodiment of the present invention provides a multi-sensor fusion construction site 3D reconstruction method, including:

[0030] Step 1: Deploy LiDAR and IMU

[0031] Based on the tower crane, the laser radar and IMU are installed on the boom of the tower crane, and the laser radar is placed vertically to ensure that the viewing angle can scan all areas under the boom. The IMU is placed relatively still and as close as possible to the laser radar without blocking the laser radar scanning angle.

[0032] Step 2: Collect IMU data

[0033] Based on the IMU being stationary, 120 minutes of IMU data was collected, and the IMU internal parameters were calibrated to obtain bias stability data and white noise data;

[0034] Step 3: Joint calibration of LiDAR and IMU

[0035] Based on the laser radar and IMU, when the laser radar and IMU remain relatively still, the laser point cloud data and IMU data are collected at the same time, and the laser radar and IMU are calibrated with external parameters to obtain the coordinate transformation matrix from IMU to laser radar;

[0036] Step 4: Build a 3D model

[0037] Based on the tower crane, LiDAR and IMU, point cloud information and position information of the surrounding construction site are collected during the tower crane's rotation.

[0038] Based on the posture information, the laser radar point cloud data is dedistorted as follows:

[0039] The acceleration and angular velocity provided by the IMU need to be converted into attitude. In the process of distortion removal, the attitude change is represented by a rotation matrix. The attitude change formula is as follows:

[0040] R(t)=R(t0)·exp(ω(t-t0))

[0041] Among them, R(t) represents the rotation matrix at time t, R(t0) is the rotation matrix at the start time of scanning, and ω is the angular velocity exp represents the exponential mapping of angular velocity (using Lie group Lie algebra).

[0042] The IMU is used to calculate the motion compensation from the start to the end of the laser radar scan, and the motion compensation of each laser point is corrected at the time of LIDAR acquisition. i The position is P i , and its corrected position in the initial reference coordinate system is:

[0043]

[0044] Among them, R(t i ) and T(t i ) represent the time t i The rotation matrix and displacement, are the coordinates of the point after dedistortion;

[0045] Based on the point cloud after distortion removal, line feature points and surface feature points are extracted from the point cloud, and the extracted feature point cloud is combined with the original point cloud and then released; the details are as follows:

[0046] Curvature is an important indicator for describing the local geometric changes of point clouds and is used to distinguish line features from surface features. i , by calculating the relative position change between it and the surrounding adjacent points, the curvature value is obtained. The curvature calculation formula is:

[0047]

[0048] Among them, C i It's point P i The curvature of N is P i The surrounding neighborhood point set, P j is with P i Adjacent points, ||P j -P i || is point P j and P i The Euclidean distance between them reflects the geometric changes between points.

[0049] If the curvature C of a point i If the curvature C of a point is higher than the set threshold and the geometric changes of its local environment are large, it is considered to be a line feature point. i If it is lower than the set threshold and the local geometric transformation is small, it is considered to be a surface feature point.

[0050] Downsample based on the feature point cloud, select several key frames before the current radar frame, build a local map, then match the current feature point cloud to the local map and perform graph optimization; the details are as follows:

[0051] Match the line feature points and surface feature points of the current frame with the feature points in the previous frame or the local map. i , find the two nearest line feature points P in the previous frame or map a and P b , these points should form a straight line. The goal is to project the line feature points of the current frame onto the line segments in the previous frame or map. For each face feature point P in the current frame i , find the three nearest surface feature points P in the previous frame or map a , P b , P c , these three points should form a plane. The goal is to project the face feature points of the current frame onto the plane in the previous frame or map.

[0052] Based on the absolute coordinate system optimized by the graph and the relatively accurate IMU posture estimated from the original IMU data, the highest frequency and more accurate posture is obtained;

[0053] Based on the above steps, a 3D model of the construction site is constructed, and target detection is performed with the 3D model of the project to determine the current major project progress information and project status;

[0054] Perform target detection based on the reconstructed 3D model and the project 3D model to determine the current project progress information and project status;

[0055] Based on the latest project progress, through objective data comparison, we can find out the lagging project points and possible problem points, help project managers to better formulate solutions and complete the project construction with quality and quantity.

[0056] In the embodiment of the present invention, a laser radar and an IMU are fused based on a tower crane to perform three-dimensional reconstruction of the construction site and monitor the construction progress; the advantages of the tower crane's own height and the long detection distance of the laser radar are utilized to achieve large-scale scanning, improve the efficiency of three-dimensional reconstruction, and reduce the cost of monitoring; and the high-frequency IMU data posture information is fused with the laser radar point cloud data to remove point cloud motion distortion.

[0057] Embodiment 2:

[0058] The embodiment of the present invention further provides a construction site three-dimensional reconstruction device, comprising:

[0059] The first acquisition module is used to collect data in real time based on the IMU when the tower crane is in operation, and obtain the posture information;

[0060] The second acquisition module is used to scan the construction site based on the laser radar when the tower crane is in operation to obtain the three-dimensional point cloud information of the site;

[0061] A preprocessing module, used for preprocessing the on-site three-dimensional point cloud information and position information;

[0062] A fusion module is used to fuse the pre-processed on-site 3D point cloud data and posture information to obtain fused data;

[0063] A reconstruction module is used to perform three-dimensional reconstruction on the fused data.

[0064] As an implementation manner of the embodiment of the present invention, the preprocessing includes denoising, filtering, and registration.

[0065] As an implementation method of the embodiment of the present invention, a laser radar and an IMU are arranged at the boom of a tower crane.

[0066] Embodiment 3:

[0067] An embodiment of the present invention further provides a construction site three-dimensional reconstruction system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a construction site three-dimensional reconstruction method when executed by the processor.

[0068] Embodiment 4:

[0069] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and the computer program executes a method for three-dimensional reconstruction of a construction site when running.

[0070] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for three-dimensional reconstruction of a construction site, characterized in that: include: Based on IMU, real-time data is collected when the tower crane is in operation to obtain position information; Scan the construction site with the tower crane in operation using laser radar to obtain 3D point cloud information on site; Preprocessing the on-site three-dimensional point cloud information and position information; Fusing the pre-processed on-site 3D point cloud data and position information to obtain fused data; The fused data is three-dimensionally reconstructed.

2. The method for three-dimensional reconstruction of a construction site according to claim 1, characterized in that: The preprocessing includes denoising, filtering and registration.

3. The method for three-dimensional reconstruction of a construction site according to claim 2, characterized in that: Based on the tower crane, lidar and IMU are deployed on the boom.

4. A construction site three-dimensional reconstruction device, characterized in that: include: The first acquisition module is used to collect data in real time based on the IMU when the tower crane is in operation, and obtain the posture information; The second acquisition module is used to scan the construction site based on the laser radar when the tower crane is in operation to obtain the three-dimensional point cloud information of the site; A preprocessing module, used for preprocessing the on-site three-dimensional point cloud information and position information; A fusion module is used to fuse the pre-processed on-site 3D point cloud data and posture information to obtain fused data; A reconstruction module is used to perform three-dimensional reconstruction on the fused data.

5. The construction site three-dimensional reconstruction device according to claim 4, characterized in that: The preprocessing includes denoising, filtering and registration.

6. The construction site three-dimensional reconstruction device according to claim 5, characterized in that: Based on the tower crane, lidar and IMU are deployed on the boom.

7. A construction site 3D reconstruction system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the method for three-dimensional reconstruction of a construction site as described in any one of claims 1 to 3 is executed.

8. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the three-dimensional reconstruction method for a construction site as described in any one of claims 1 to 3.

Images