A wall embedded part positioning quality evaluation method based on laser ranging

Abstract

The application discloses a wall embedded part positioning quality evaluation method based on laser ranging, and relates to the technical field of graphic processing, which comprises the following steps: based on a wall embedded part construction drawing, marking the construction mode of the wall embedded part, and evaluating the optimal reference vector of the wall embedded part; based on real-time wall embedded part construction process point cloud data and IMU data, utilizing a clustering algorithm to segment the wall embedded part point cloud data, and obtaining the embedded part point cloud cluster of the real-time wall embedded part construction task; marking the construction action in the construction process image data, obtaining the construction video stream of the real-time wall embedded part construction task and the positioning point cloud cluster of the real-time wall embedded part construction task, establishing a wall embedded part positioning multi-modal evaluation model, and generating the deviation vector of the wall embedded part; judging whether the comprehensive deviation vector of the wall embedded part is in the optimal reference vector interval of the wall embedded part, and if not, outputting that the deviation is too large. The application has the advantages of improving the embedded part positioning measurement accuracy, reducing the installation error and lowering the rework rate.

Description

Technical Field

[0001] This invention relates to the field of graphics processing technology, specifically to a method for evaluating the positioning quality of embedded wall components based on laser ranging. Background Technology

[0002] The quality assessment of embedded wall component positioning using laser ranging technology involves precisely measuring key parameters such as the installation position, verticality, and horizontality of the embedded components to ensure they meet design requirements. The assessment includes the surface flatness, dimensional accuracy, and connection strength of the embedded components to the main structure, ensuring the long-term safety and durability of building curtain walls and other structures.

[0003] Existing laser ranging methods for assessing the positioning quality of embedded wall components primarily rely on static measurement methods, which involve single data collection under fixed conditions. However, actual construction environments are subject to dynamic interference factors such as vibration, temperature changes, and human error, leading to potential deviations in measurement results. Traditional solutions do not consider dynamic compensation mechanisms. Furthermore, stress release or concrete shrinkage after the installation of embedded components can cause positional shifts, which static measurements cannot capture, ultimately affecting positioning accuracy and the reliability of project acceptance. Summary of the Invention

[0004] To address the aforementioned technical problems, this paper provides a method for assessing the positioning quality of embedded wall components based on laser ranging. This solution overcomes the limitations of existing laser ranging methods that primarily rely on static measurement, i.e., single data collection under fixed conditions. In actual construction environments, dynamic interference factors such as vibration, temperature changes, and human error can easily lead to measurement deviations. Traditional methods do not consider dynamic compensation mechanisms. Furthermore, the release of structural stress or concrete shrinkage after the embedded component is installed can cause positional shifts, which static measurements cannot capture, ultimately affecting positioning accuracy and the reliability of project acceptance.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for assessing the positioning quality of embedded wall components based on laser ranging, comprising:

[0007] Based on the construction drawings of wall embedded parts, the construction methods of wall embedded parts are marked, the construction preferences of construction methods are analyzed, and the optimal reference vector of wall embedded parts is evaluated.

[0008] Multiple laser rangefinders and image sensors are deployed around the real-time wall embedded part construction task to collect construction task parameters and construct real-time wall embedded part construction process time series data; the construction process time series data includes: point cloud data, IMU data, calibration target feature points, and image data.

[0009] Based on the point cloud data and IMU data of the construction process of wall embedded parts in real time, the pose transformation matrix of the laser ranging sensor for the construction task of wall embedded parts in real time is established, and the point cloud data of wall embedded parts is segmented by clustering algorithm to obtain the point cloud cluster of embedded parts for the construction task of wall embedded parts in real time.

[0010] Based on the construction process image data of real-time wall embedded parts, the construction actions in the construction process image data are marked to obtain the construction video stream of the real-time wall embedded parts construction task and the positioning point cloud cluster of the real-time wall embedded parts construction task. A multi-modal evaluation model for wall embedded parts positioning is established to generate the deviation vector of the wall embedded parts.

[0011] Determine whether the comprehensive deviation vector of the wall embedded part is within the optimal reference vector range of the wall embedded part. If yes, output to continue execution; otherwise, output that the deviation is too large.

[0012] Preferably, based on the wall embedded part construction drawings, the geometric and attribute information of the wall embedded part construction drawings are extracted to obtain the application scenarios of the wall embedded parts;

[0013] Based on the expected service life of the application scenarios of wall embedded parts, determine the performance requirements of the application scenarios of wall embedded parts, screen the embedded parts construction methods that meet the performance requirements, and establish a data array of optional embedded parts construction methods for the application scenarios of wall embedded parts.

[0014] Multi-source factors affecting the performance degradation of embedded parts in the application scenarios of wall embedded parts;

[0015] Based on the data array of optional embedded part construction methods for wall embedded parts application scenarios and the multi-source factor parameters that affect the performance degradation of embedded part construction methods in wall embedded parts application scenarios, an influencing factor matrix of optional embedded part construction methods for wall embedded parts application scenarios is established.

[0016] Preferably, the matrix of factors influencing the optional construction methods of wall embedded parts in the application scenarios is normalized, and the weights of the factors influencing the optional construction methods of wall embedded parts in the application scenarios are assigned according to the entropy weight method.

[0017] Based on the weights of the factors influencing the optional embedding construction methods in the application scenarios of wall embedded parts and the parameters of the multi-source factors that affect the performance degradation of the embedding construction methods in the application scenarios of wall embedded parts, the performance influence coefficient of the embedding construction methods in the application scenarios of wall embedded parts is calculated.

[0018] Based on the ideal performance index of each optional embedded construction method in the data array of optional embedded construction methods for the application scenario of wall embedded parts, the performance influence coefficient of the embedded construction method for the application scenario of wall embedded parts is used for correction to obtain the actual performance value of the embedded construction method for the application scenario of wall embedded parts.

[0019] Based on the actual performance values ​​of the embedded parts construction methods in the application scenarios of wall embedded parts, and according to the performance requirements of the application scenarios of wall embedded parts, a second filtering is performed on the data array of optional embedded parts construction methods for the application scenarios of wall embedded parts to obtain the data array of candidate embedded parts construction methods for the application scenarios of wall embedded parts.

[0020] The construction cost and construction time of each candidate embedded part construction method in the data array of candidate embedded part construction methods for the application scenarios of wall embedded parts are estimated.

[0021] Based on linear programming, the objective function is the unique construction method of the wall embedded parts in the candidate embedded parts construction method data array that selects the application scenarios of wall embedded parts. The constraint is the minimization of construction cost and construction time for each candidate embedded parts construction method. A construction method decision model for wall embedded parts is constructed to generate the optimal reference vector for wall embedded parts.

[0022] Preferably, based on the real-time construction progress point cloud data and IMU data of the wall embedded parts, the data is divided according to the time sampling rate of the data to establish the real-time construction progress point cloud sequence and IMU pose sequence of the wall embedded parts.

[0023] Based on the construction process point cloud sequence and IMU pose sequence of real-time wall embedded parts, the minimum Euclidean distance between the continuous frame ICP registration of the point cloud and the IMU motion estimation is calculated using the least squares method, so as to obtain the difference optimization time offset between the construction process point cloud sequence and the IMU pose sequence of real-time wall embedded parts.

[0024] Based on linear interpolation, the IMU pose sequence of the construction process of the wall embedded parts is completed. The time error of the IMU pose sequence is compensated by the difference optimization time offset to obtain the point cloud-time synchronized IMU pose sequence.

[0025] The motion distortion of the point cloud sequence of the construction process of the wall embedded parts is corrected by using the point cloud-time synchronized IMU pose sequence, and the motion distortion compensated point cloud sequence is obtained.

[0026] Preferably, based on SIFT3D scale-invariant feature transformation, the motion distortion compensation point cloud sequence and calibration target feature points are matched to extract the matching feature point pairs of the construction process of the real-time wall embedded parts, and the rigid transformation volume of the matching feature points is solved by the singular value decomposition algorithm to obtain the initial transformation matrix of the construction process of the real-time wall embedded parts.

[0027] A world coordinate system transformation matrix is ​​established between the synchronous point cloud-time synchronous IMU pose sequence and the motion distortion compensation point cloud sequence. The initial transformation matrix of the construction process of the wall embedded parts is dynamically updated to obtain the recursive real-time transformation matrix of the construction process of the wall embedded parts.

[0028] Preferably, based on the global point cloud data in the recursive real-time transformation matrix of the construction process of the wall embedded parts, the average distance and standard deviation of several nearest neighbors of each point cloud are calculated, and outlier point clouds are removed.

[0029] Using DBSCAN density clustering, the median Euclidean distance between each pair of points in the global point cloud data in the real-time transformation matrix of the real-time wall embedded parts construction progress is used as the point cloud segmentation distance threshold. The global point cloud data is then segmented to obtain the embedded part point cloud clusters for the real-time wall embedded parts construction task.

[0030] Preferably, based on the construction video stream of the real-time wall embedded part construction task, the RGB-D stacked data of the construction video stream is extracted after preprocessing for image distortion and temporal alignment.

[0031] Based on the TCN temporal convolutional network, RGB-D stacked data are continuously input according to the sampling frame rate of the construction video stream of the real-time wall embedded part construction task to generate the frame rate action category probability of the construction video stream of the real-time wall embedded part construction task.

[0032] Based on the frame rate action category probability of the construction video stream for real-time wall embedded part construction task, calculate the inter-frame average optical flow change in the frame rate action category probability of each construction video stream, and filter out local peak frames that are greater than the average optical flow change and standard deviation of the global sampling frames to obtain the key frames of the frame rate action category probability of the construction video stream for real-time wall embedded part construction task.

[0033] Based on the I3D dilated dual-stream convolutional network, the keyframes and interval frames of the construction video stream of the real-time wall embedded part construction task are used as input. The appearance features and optical flow direction features of the construction video stream frames are extracted according to the RGB stream architecture layer and the optical flow architecture layer. Global average pooling is performed using the classification head layer to output the frame rate and action classification probability of the construction video stream of the real-time wall embedded part construction task.

[0034] Preferably, based on the PointFusion architecture, an image coding branch is established according to ResNet-50 and a point cloud coding branch is established according to PointNet. The frame rate and action classification probability of the construction video stream of the real-time wall embedded part construction task and the embedded part point cloud cluster of the real-time wall embedded part construction task are used as inputs to encode the corresponding codes, and the construction action context features and construction embedded part geometric features of the real-time wall embedded part construction task are extracted.

[0035] Based on Transformer cross-modal attention, the construction action context features of the real-time wall embedded part construction task are used as the key, and the geometric features of the construction embedded part are used as the value for feature fusion to generate the embedded part pose deviation vector and the embedded part construction process compliance deviation probability of the real-time wall embedded part construction task.

[0036] Based on the embedding position deviation vector of the real-time wall embedding construction task, the embedding construction process deviation probability of the real-time wall embedding construction task is used as an adjustment factor to calculate the confidence level of the embedding position deviation vector of the real-time wall embedding construction task, and generate the comprehensive deviation vector of the wall embedding.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0038] This invention proposes a laser ranging-based method for assessing the positioning quality of embedded wall components. It constructs a high-precision point cloud cluster of embedded components using laser ranging point clouds and IMU pose data. This is combined with temporal analysis of construction actions based on image recognition (TCN+I3D) and a multimodal fusion model (PointFusion+Transformer) to correlate geometric deviations with process compliance. Finally, the optimal reference vector is used as the benchmark to determine the construction quality of the embedded wall components. The beneficial effects are: improved positioning measurement accuracy; cross-modal analysis of construction actions and geometric deviations enables joint optimization of process and pose, reducing installation errors and rework rates. Attached Figure Description

[0039] Figure 1 This is a flowchart of a method for assessing the positioning quality of embedded wall components based on laser ranging. Detailed Implementation

[0040] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0041] Reference Figure 1 As shown, a method for assessing the positioning quality of embedded wall components based on laser ranging includes:

[0042] Step 1: Based on the wall embedded part construction drawings, mark the construction methods of the wall embedded parts, analyze the construction preferences of the construction methods, and evaluate the optimal reference vector of the wall embedded parts;

[0043] Step one includes the following:

[0044] Step 101: Based on the wall embedded part construction drawing, extract the geometric and attribute information from the wall embedded part construction drawing to obtain the application scenario of the wall embedded part;

[0045] Based on the expected service life of the application scenarios of wall embedded parts, determine the performance requirements of the application scenarios of wall embedded parts, screen the embedded parts construction methods that meet the performance requirements, and establish a data array of optional embedded parts construction methods for the application scenarios of wall embedded parts.

[0046] Multi-source factors affecting the performance degradation of embedded parts in the application scenarios of wall embedded parts;

[0047] Based on the data array of optional embedded part construction methods for wall embedded parts application scenarios and the multi-source factor parameters that affect the performance degradation of embedded part construction methods in wall embedded parts application scenarios, an influencing factor matrix of optional embedded part construction methods for wall embedded parts application scenarios is established.

[0048]

[0049] Among them, a ij For the application scenario of wall embedded parts, the j-th influencing factor of the i-th optional embedded part construction method, m is the total number of optional embedded part construction methods, and n is the total number of influencing factors;

[0050] Step 102: Normalize the matrix of factors influencing the optional construction methods of wall embedded parts for the application scenarios, and assign weights to the factors influencing the optional construction methods of wall embedded parts for the application scenarios according to the entropy weight method.

[0051] Based on the weights of the factors influencing the optional embedding construction methods in the application scenarios of wall embedded parts and the parameters of the multi-source factors that affect the performance degradation of the embedding construction methods in the application scenarios of wall embedded parts, the performance influence coefficient of the embedding construction methods in the application scenarios of wall embedded parts is calculated.

[0052] Based on the ideal performance index of each optional embedded construction method in the data array of optional embedded construction methods for the application scenario of wall embedded parts, the performance influence coefficient of the embedded construction method for the application scenario of wall embedded parts is used for correction to obtain the actual performance value of the embedded construction method for the application scenario of wall embedded parts.

[0053] Based on the actual performance values ​​of the embedded parts construction methods for wall embedded parts application scenarios, and according to the performance requirements of the wall embedded parts application scenarios, a secondary filtering is performed on the data array of optional embedded parts construction methods for the wall embedded parts application scenarios to obtain the data array of candidate embedded parts construction methods for the wall embedded parts application scenarios, as follows:

[0054]

[0055] Where Array is a data array of candidate embedded part construction methods for wall embedded parts application scenarios, w ij Let α be the weight of the j-th influencing factor for the i-th optional embedding construction method in the application scenario of wall embedded parts. j Let represent the j-th influencing factor parameter value that affects the performance degradation of the embedded component construction method in the application scenario of wall embedded components. The normalized performance value of the j-th influencing factor for the i-th optional embedding construction method in the application scenario of wall embedded parts. Let T be the actual performance value of the i-th optional embedded part construction method in the application scenario of the wall embedded part, and let T be the performance requirement threshold of the application scenario of the wall embedded part.

[0056] Step 103: Estimate the construction cost and construction time of each candidate embedded part construction method in the candidate embedded part construction method data array for the application scenario of wall embedded parts;

[0057] Based on linear programming, the objective function is the unique construction method of the wall embedded parts in the data array of candidate embedded parts construction methods for selecting application scenarios. The constraint is the minimization of construction cost and construction time for each candidate embedded part construction method. A construction method decision model for wall embedded parts is constructed to generate the optimal reference vector for wall embedded parts.

[0058] When using it, refer to the content in steps 101 to 103.

[0059] As a further point: Since the current construction methods for wall embedded parts mainly rely on the personal experience of design engineers, the usage scenarios of wall embedded parts are easily overlooked, which makes it impossible for the design service life of wall embedded parts to meet the expected standards, making later maintenance difficult and reducing the overall construction quality.

[0060] Therefore, by extracting the application scenarios of embedded parts and screening initial optional construction methods, the entropy weight method is used to quantify the impact of multiple factors (such as corrosion and vibration) on the performance of the construction methods, and the ideal performance indicators of the construction methods are corrected to obtain the actual performance values. Subsequently, based on linear programming, a unique construction method is selected under cost and time constraints, and finally the optimal reference vector is generated. The beneficial effects are: 1. By dynamically correcting the performance of the construction methods, the environmental adaptability of the construction methods is improved; 2. Linear programming optimization reduces the overall implementation cost and shortens the construction period; 3. The standardized output of the reference vector reduces the bias of human judgment.

[0061] Step 2: Deploy multiple laser rangefinders and image sensors around the real-time wall embedded part construction task to collect the construction task parameters of the real-time wall embedded part and construct the construction process time series data of the real-time wall embedded part; the construction process time series data includes: point cloud data, IMU data, calibration target feature points, and image data.

[0062] Step 3: Based on the real-time wall embedded parts construction progress point cloud data and IMU data, establish the pose transformation matrix of the laser ranging sensor for the real-time wall embedded parts construction task, and use clustering algorithm to segment the wall embedded parts point cloud data to obtain the embedded parts point cloud cluster for the real-time wall embedded parts construction task.

[0063] Step three includes the following:

[0064] Step 301: Based on the real-time wall embedded parts construction progress point cloud data and IMU data, divide the data according to the time sampling rate and establish the real-time wall embedded parts construction progress point cloud sequence and IMU pose sequence.

[0065] Based on the construction process point cloud sequence and IMU pose sequence of real-time wall embedded parts, the minimum Euclidean distance between the continuous frame ICP registration of the point cloud and the IMU motion estimation is calculated using the least squares method, so as to obtain the difference optimization time offset between the construction process point cloud sequence and the IMU pose sequence of real-time wall embedded parts.

[0066] Based on linear interpolation, the IMU pose sequence of the construction process of the wall embedded parts is completed. The time error of the IMU pose sequence is compensated by the difference optimization time offset to obtain the point cloud-time synchronized IMU pose sequence.

[0067] The motion distortion of the point cloud sequence of the construction process of the wall embedded parts in real time is corrected by using the point cloud-time synchronized IMU pose sequence, and the motion distortion compensated point cloud sequence is obtained.

[0068] Step 302: Based on SIFT3D scale-invariant feature transformation, match the motion distortion compensation point cloud sequence and calibration target feature points, extract the matching feature point pairs of the construction process of the real-time wall embedded parts, and use the singular value decomposition algorithm to solve the rigid transformation volume of the matching feature points to obtain the initial transformation matrix of the construction process of the real-time wall embedded parts.

[0069] Establish the world coordinate system transformation matrix of the synchronous point cloud-time synchronous IMU pose sequence and the motion distortion compensation point cloud sequence, and dynamically update the initial transformation matrix for the construction process of the real-time wall embedded parts to obtain the recursive real-time transformation matrix of the construction process of the real-time wall embedded parts.

[0070] Step 303: Based on the global point cloud data in the recursive real-time transformation matrix of the construction process of the wall embedded parts, calculate the average distance and standard deviation of several nearest neighbors of each point cloud, and remove outlier point clouds.

[0071] Using DBSCAN density clustering, the median Euclidean distance between each pair of points in the global point cloud data in the real-time transformation matrix of the real-time wall embedded parts construction progress is used as the point cloud partitioning distance threshold. The global point cloud data is then partitioned to obtain the embedded part point cloud clusters for the real-time wall embedded parts construction task.

[0072] When using it, refer to the content in steps 301 to 303.

[0073] As a further point, the existing static single-point measurement mode for wall embedded parts positioning is difficult to capture dynamic deformation during construction (such as ±5mm displacement deviation caused by concrete pouring). Secondly, there are timing asynchrony errors when fusioning multi-sensor data, which often leads to the final embedded part installation position error exceeding the allowable range of the project, seriously affecting the construction accuracy and acceptance rate.

[0074] This solution achieves precise alignment of point cloud and IMU data through time synchronization and motion distortion compensation. It utilizes SIFT3D feature matching and singular value decomposition to solve the pose transformation matrix, and then combines this with DBSCAN clustering to segment the embedded part point cloud clusters. The beneficial effects are: effectively overcoming point cloud distortion caused by construction vibration through dynamic pose correction, providing reliable data for automated construction quality control.

[0075] Step 4: Based on the construction process image data of real-time wall embedded parts, mark the construction actions in the construction process image data, obtain the construction video stream of the real-time wall embedded parts construction task and the positioning point cloud cluster of the real-time wall embedded parts construction task, establish a multi-modal evaluation model for wall embedded parts positioning, and generate the deviation vector of the wall embedded parts.

[0076] Step 401: Based on the construction video stream of the real-time wall embedded part construction task, perform image distortion and time sequence alignment preprocessing, and extract the RGB-D stacked data of the construction video stream.

[0077] Based on the TCN temporal convolutional network, RGB-D stacked data are continuously input according to the sampling frame rate of the construction video stream of the real-time wall embedded part construction task to generate the frame rate action category probability of the construction video stream of the real-time wall embedded part construction task.

[0078] As a further development, the internal structure of the TCN temporal convolutional network includes: convolutional layers that preserve temporal causality, dilated convolutional layers, and residual connection layers that avoid gradient vanishing. In order to avoid imbalance in the final action class classification, the loss function needs to introduce weighted cross-entropy.

[0079] Based on the frame rate action category probability of the construction video stream for real-time wall embedded part construction task, calculate the inter-frame average optical flow change in the frame rate action category probability of each construction video stream, and filter out local peak frames that are greater than the average optical flow change and standard deviation of the global sampling frames to obtain the key frames of the frame rate action category probability of the construction video stream for real-time wall embedded part construction task.

[0080] Based on the I3D dilated dual-stream convolutional network, the key frames and interval frames of the construction video stream of the real-time wall embedded part construction task are used as input. According to the RGB stream architecture layer and the optical flow architecture layer, the appearance features and optical flow direction features of the construction video stream frame are extracted. Global average pooling is performed using the classification head layer to output the frame rate and action classification probability of the construction video stream of the real-time wall embedded part construction task.

[0081] Step 402: Based on the PointFusion architecture, establish an image coding branch according to ResNet-50 and a point cloud coding branch according to PointNet. Take the frame rate of the construction video stream of the real-time wall embedded part construction task and the embedded part point cloud cluster of the real-time wall embedded part construction task as inputs and extract the construction action context features and construction embedded part geometric features of the real-time wall embedded part construction task.

[0082] Based on Transformer cross-modal attention, the construction action context features of the real-time wall embedded part construction task are used as the key, and the geometric features of the construction embedded part are used as the value for feature fusion to generate the embedded part pose deviation vector and the embedded part construction process compliance deviation probability of the real-time wall embedded part construction task.

[0083] Based on the embedded part pose deviation vector of the real-time wall embedded part construction task, the embedded part construction process deviation probability of the real-time wall embedded part construction task is used as an adjustment factor to calculate the confidence level of the embedded part pose deviation vector of the real-time wall embedded part construction task, and generate the comprehensive deviation vector of the wall embedded part, as follows:

[0084]

[0085] Among them, V enhanced Let be the comprehensive deviation vector of the wall embedded parts, where Δx, Δy, Δz, and Δθ are the embedding part pose deviation components of the real-time wall embedded part construction task, φ and β are adjustment factors, and p is the probability of compliance deviation in the embedding part construction process of the real-time wall embedded part construction task. This is a transpose.

[0086] When using it, refer to the content in steps 401 to 402.

[0087] As a further development: By fusing construction video streams (TCN temporal segmentation + I3D action classification) and point cloud data (PointNet geometric features), and combining the Transformer cross-modal attention mechanism, the semantics of construction actions are dynamically associated with the geometric pose of embedded parts to generate a comprehensive deviation vector. The beneficial effects are: Temporal action features are extracted using the Temporal Convolutional Network (TCN) and dilated I3D convolution; image-point cloud feature alignment is achieved through the PointFusion architecture; attention weighting is then performed using the construction action context as the key and geometric features as the value; finally, pose deviations are corrected using process compliance probability. This enables real-time multimodal monitoring of the construction process, simultaneously capturing action compliance and pose accuracy; and through optical flow keyframe filtering and attention fusion, computational redundancy is significantly reduced, improving the quality and efficiency of embedded part installation.

[0088] Step 6: Determine whether the comprehensive deviation vector of the wall embedded part is within the optimal reference vector range of the wall embedded part. If yes, continue execution; otherwise, output that the deviation is too large.

[0089] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A wall embedded part positioning quality evaluation method based on laser ranging, characterized in that, include: S1. Based on the construction drawings of wall embedded parts, mark the construction methods of wall embedded parts, analyze the construction preferences of construction methods, and evaluate the optimal reference vector of wall embedded parts. S2. Deploy multiple laser ranging sensors and image sensors around the real-time wall embedded part construction task to collect the construction task parameters of the real-time wall embedded part and construct the construction process time series data of the real-time wall embedded part; the construction process time series data includes: point cloud data, IMU data, calibration target feature points, and image data. S3. Based on the point cloud data of the construction process of wall embedded parts and IMU data, establish the pose transformation matrix of the laser ranging sensor for the construction task of wall embedded parts in real time, and use the clustering algorithm to segment the point cloud data of wall embedded parts to obtain the point cloud cluster of embedded parts for the construction task of wall embedded parts in real time. S4. Based on the real-time construction progress image data of wall embedded parts, mark the construction actions in the construction progress image data to obtain the construction video stream of the real-time wall embedded part construction task, establish a multi-modal evaluation model for wall embedded part positioning, and generate the deviation vector of the wall embedded part, including: Based on the construction video stream of the real-time wall embedded parts construction task, image distortion and temporal alignment preprocessing are performed to extract the RGB-D stacked data of the construction video stream. Based on the TCN temporal convolutional network, RGB-D stacked data are continuously input according to the sampling frame rate of the construction video stream of the real-time wall embedded part construction task to generate the frame rate action category probability of the construction video stream of the real-time wall embedded part construction task. Based on the frame rate action category probability of the construction video stream for real-time wall embedded part construction task, calculate the inter-frame average optical flow change in the frame rate action category probability of each construction video stream, and filter out local peak frames that are greater than the average optical flow change and standard deviation of the global sampling frames to obtain the key frames of the frame rate action category probability of the construction video stream for real-time wall embedded part construction task. Based on the I3D dilated dual-stream convolutional network, the key frames and interval frames of the construction video stream of the real-time wall embedded part construction task are used as input. According to the RGB stream architecture layer and the optical flow architecture layer, the appearance features and optical flow direction features of the construction video stream frame are extracted. Global average pooling is performed using the classification head layer to output the frame rate and action classification probability of the construction video stream of the real-time wall embedded part construction task. Based on the PointFusion architecture, an image coding branch is established using ResNet-50 and a point cloud coding branch is established using PointNet. The frame rate and action classification probability of the construction video stream of the real-time wall embedded part construction task and the embedded part point cloud cluster of the real-time wall embedded part construction task are used as inputs to encode the corresponding codes, and the construction action context features and construction embedded part geometric features of the real-time wall embedded part construction task are extracted. Based on Transformer cross-modal attention, the construction action context features of the real-time wall embedded part construction task are used as the key, and the geometric features of the construction embedded part are used as the value for feature fusion to generate the embedded part pose deviation vector and the embedded part construction process compliance deviation probability of the real-time wall embedded part construction task. Based on the embedding position deviation vector of the real-time wall embedding construction task, the embedding construction process deviation probability of the real-time wall embedding construction task is used as an adjustment factor to calculate the confidence of the embedding position deviation vector of the real-time wall embedding construction task, and generate the deviation vector of the wall embedding. S5. Determine whether the deviation vector of the wall embedded part is within the optimal reference vector range of the wall embedded part. If yes, output to continue execution; otherwise, output that the deviation is too large.

2. The method for evaluating the positioning quality of embedded wall components based on laser ranging according to claim 1, characterized in that, S1 includes: Based on the construction drawings of wall embedded parts, extract the geometric and attribute information from the construction drawings of wall embedded parts to obtain the application scenarios of wall embedded parts; Based on the expected service life of the application scenarios of wall embedded parts, determine the performance requirements of the application scenarios of wall embedded parts, screen the embedded parts construction methods that meet the performance requirements, and establish a data array of optional embedded parts construction methods for the application scenarios of wall embedded parts. Multi-source factors affecting the performance degradation of embedded parts in the application scenarios of wall embedded parts; Based on the data array of optional embedded part construction methods for wall embedded parts application scenarios and the multi-source factor parameters that affect the performance degradation of embedded part construction methods in wall embedded parts application scenarios, an influencing factor matrix of optional embedded part construction methods for wall embedded parts application scenarios is established.

3. The method for evaluating the positioning quality of embedded wall components based on laser ranging according to claim 2, characterized in that, S1 further includes: The matrix of factors influencing the optional construction methods of wall embedded parts in the application scenarios is normalized, and the weights of the factors influencing the optional construction methods of wall embedded parts in the application scenarios are assigned according to the entropy weight method. Based on the weights of the factors influencing the optional embedding construction methods in the application scenarios of wall embedded parts and the parameters of the multi-source factors that affect the performance degradation of the embedding construction methods in the application scenarios of wall embedded parts, the performance influence coefficient of the embedding construction methods in the application scenarios of wall embedded parts is calculated. Based on the ideal performance index of each optional embedded construction method in the data array of optional embedded construction methods for the application scenario of wall embedded parts, the performance influence coefficient of the embedded construction method for the application scenario of wall embedded parts is used for correction to obtain the actual performance value of the embedded construction method for the application scenario of wall embedded parts. Based on the actual performance values ​​of the embedded parts construction methods in the application scenarios of wall embedded parts, and according to the performance requirements of the application scenarios of wall embedded parts, a second filtering is performed on the data array of optional embedded parts construction methods for the application scenarios of wall embedded parts to obtain the data array of candidate embedded parts construction methods for the application scenarios of wall embedded parts. The construction cost and construction time of each candidate embedded part construction method in the data array of candidate embedded part construction methods for the application scenarios of wall embedded parts are estimated. Based on linear programming, the objective function is the unique construction method of the wall embedded parts in the candidate embedded parts construction method data array that selects the application scenarios of wall embedded parts. The constraint is the minimization of construction cost and construction time for each candidate embedded parts construction method. A construction method decision model for wall embedded parts is constructed to generate the optimal reference vector for wall embedded parts.

4. The method for evaluating the positioning quality of embedded wall components based on laser ranging according to claim 1, characterized in that, S3 includes: Based on the real-time construction progress point cloud data and IMU data of wall embedded parts, the data is divided according to the time sampling rate of the data, and the real-time construction progress point cloud sequence and IMU pose sequence of wall embedded parts are established. Based on the construction process point cloud sequence and IMU pose sequence of real-time wall embedded parts, the minimum Euclidean distance between the continuous frame ICP registration of the point cloud and the IMU motion estimation is calculated using the least squares method, so as to obtain the difference optimization time offset between the construction process point cloud sequence and the IMU pose sequence of real-time wall embedded parts. Based on linear interpolation, the IMU pose sequence of the construction process of the wall embedded parts is completed. The time error of the IMU pose sequence is compensated by the difference optimization time offset to obtain the point cloud-time synchronized IMU pose sequence. The motion distortion of the point cloud sequence of the construction process of the wall embedded parts is corrected by using the point cloud-time synchronized IMU pose sequence, and the motion distortion compensated point cloud sequence is obtained.

5. The method for evaluating the positioning quality of embedded wall components based on laser ranging according to claim 4, characterized in that, S3 further includes: Based on SIFT3D scale-invariant feature transformation, the motion distortion compensation point cloud sequence and calibration target feature points are matched to extract the matching feature point pairs of the construction process of the real-time wall embedded parts. The rigid transformation volume of the matching feature points is solved by the singular value decomposition algorithm to obtain the initial transformation matrix of the construction process of the real-time wall embedded parts. Establish the world coordinate system transformation matrix of the synchronous point cloud-time synchronous IMU pose sequence and the motion distortion compensation point cloud sequence, and dynamically update the initial transformation matrix for the construction process of the real-time wall embedded parts to obtain the recursive real-time transformation matrix of the construction process of the real-time wall embedded parts. Based on the global point cloud data in the recursive real-time transformation matrix of the construction process of wall embedded parts, calculate the average distance and standard deviation of several nearest neighbors of each point cloud, and remove outlier point clouds. Using DBSCAN density clustering, the median Euclidean distance between each pair of points in the global point cloud data in the real-time transformation matrix of the real-time wall embedded parts construction progress is used as the point cloud segmentation distance threshold. The global point cloud data is then segmented to obtain the embedded part point cloud clusters for the real-time wall embedded parts construction task.

Images