260 results about "Point set" patented technology

The invention discloses a PINN-based high-precision hydrodynamic numerical simulation method and system, and the method comprises the steps: firstly building a computational domain, setting reasonable geometric parameters and boundary conditions, and constructing a dimensionless Navier-Stokes control equation set; then designing a deep neural network architecture with space-time coordinate input and flow field variable output, and adopting a loss function combining physical constraint and data driving; the core innovation lies in providing a timing sequence sensing RAR-D adaptive sampling strategy, dividing a time domain into a plurality of time frames, performing residual error evaluation in each frame, constructing a probability density function related to residual errors, and balancing priority sampling and overall coverage of a high residual error region; adam and L-BFGS optimizers are adopted to carry out network training, the weight of a loss function is dynamically adjusted, and a sampling point set is periodically updated; and finally, the solution precision is verified through multi-dimensional flow field visualization analysis. Therefore, the prediction precision of the complex flow field is effectively improved, and the calculation efficiency is remarkably improved.

The invention discloses a dragging positioning spraying track planning method for a local area of the surface of special equipment and a storage medium, and belongs to the technical field of industrial robot automation. The method comprises the steps of obtaining point set data of a to-be-sprayed area; calculating a convex hull based on the point set, and solving a minimum enclosing rectangle by using a rotary caliper method to determine an accurate rectangle spraying boundary; constructing a rectangular amplitude limiting sedimentary model through spraying testing and parameter identification; generating a grid track with a buffer area based on the model and the boundary, and optimizing the spraying speed by taking the minimization time as a target; and for the curved surface, performing B-spline curved surface reconstruction and extracting a normal vector to control the attitude of the spray gun. According to the method, the complex multi-parameter trajectory optimization problem is simplified into single-speed optimization through the rectangular amplitude limiting deposition model, the problems that in local spraying, trajectory planning is complex, edge control is not precise, a coating is not uniform and the like are effectively solved, and the spraying efficiency and quality are remarkably improved.

The invention provides a motion video key clip extraction method based on behavior analysis. The method comprises the following steps: firstly, performing decoding and frame standardization on a match video stream, detecting and positioning a coach target, and obtaining and expanding a bounding box; extracting a candidate skeleton key point set in the extended region, selecting the skeleton with the most key points as the skeleton of the coach, and performing cross-frame tracking; analyzing the skeleton in real time, triggering hand fine analysis and extracting hand key points when a scoring trend appears, comprehensively judging based on geometry, kinematics and time sequence rules, and generating a trigger signal when a specific scoring gesture is detected; and the background thread extracts fragments before and after the triggering moment from the video stream as key fragments, and stores the key fragments in association with metadata such as event types, coach identities and competition states.

The invention discloses a video key frame extraction method fused with self-supervised deep learning, and the method comprises the following steps: carrying out the standardized sampling of an input video according to a fixed interval, extracting a SuperPoint local key point and a Video MAE global semantic feature, and generating a dense descriptor and a semantic vector; constructing multi-dimensional change indexes such as local matching degree and global similarity; constructing a soft distribution matrix and a matching point set based on the fusion features; dynamically judging the key frame through a self-adaptive multi-threshold rule; and outputting the key frame set. The method fuses local and global spatio-temporal information, has robust feature extraction and key frame discrimination capabilities under a weak supervision condition, and can effectively improve the efficiency and precision of video compression, abstract and event detection.

The invention discloses a mechanical arm tail end posture constraint path optimization method based on constraint manifold. A discrete constraint manifold point set which is high in posture precision, robust in singular point, uniform in space distribution and constrained in kinematics is generated based on a Monte Carlo method, a weighted damping pseudo-inverse method, an attenuation type learning rate gradient descent iteration method and voxel density optimization; based on measurement of a laser tracker, the relation between static environment information and a target point relative to a mechanical arm base coordinate system is constructed; a coarse path is obtained through a sampling method, and a feasible path on a constraint manifold meeting attitude constraint and having no collision is generated based on a search strategy of Euler distance difference + maximum joint angle variation + collision detection + index reconstruction criterion; and in combination with a multi-target weighted CHOMP algorithm, the feasible path is optimized into a collision-free and smooth path which meets the requirements of attitude constraint and kinematics constraint. According to the method, the problems of insufficient consideration of attitude constraint, low efficiency, local convergence and the like of traditional path planning are solved.

The invention, which relates to the technical field of mine geology and urban safety, discloses a refined collaborative prediction method and system for subsidence of a global goaf, comprising the steps of establishing a hierarchical storage system, and correcting a working face calculation boundary; extracting the maximum influence radius of all the working faces and four-dimensional coordinates of the mining boundary of each working face, and calculating to obtain a global prediction range to generate a global surface prediction grid; point set insertion and Delaunay triangulation are adopted to obtain an effective triangular unit, a local influence domain range of the effective triangular unit is calculated, and an influenced sub-grid is screened from the global surface prediction grid; and calculating a predicted point movement deformation value based on a parallel computing architecture, accumulating the predicted point movement deformation value to a global result array through a coordinate index mechanism, synthesizing a deformation component in a specific direction, generating a visual result, and performing statistical analysis. According to the method, the problems of poor adaptability and low efficiency of a traditional scheme are effectively solved, and the prediction precision and efficiency are remarkably improved.

Disclosed in the present invention is a zero-knowledge-proof-oriented CPU-GPU data processing and transmission optimization system, which is used for executing multi-scalar multiplication operations on the basis of elliptic curve cryptography, so as to generate zero-knowledge proofs. The system comprises a CPU and a GPU, wherein a data transmission channel is provided between the CPU and the GPU; the CPU is used for acquiring and storing point sets and scalar sets that are involved in multi-scalar multiplication operations, and using a set parallelized data transmission mechanism to communicate with the GPU; and the GPU executes multi-scalar multiplication computation on the basis of the point sets and the scalar sets, and returns a computation result to the CPU. By means of the coordinated effect of a plurality of technical features, the present invention significantly improves the speed and efficiency of zero-knowledge proof generation and optimizes resource utilization efficiency.

The invention discloses a landslide modeling method and system based on unmanned aerial vehicle image and multi-modal feature fusion, and belongs to the technical field of landslide monitoring. The landslide modeling method comprises the following steps: acquiring an original image; detecting a bounding box of a landslide in the image, and extracting a feature vector of a landslide area in the bounding box and a central point of the bounding box; a sliding window is used for sliding on the image sequence, and center points contained in the window at each position form a point pool; collinear points in the point pool are detected, and center points corresponding to straight lines containing the most collinear points are determined as a point set; forming a candidate class by the center points with the similarity meeting a first preset condition; combining the candidate classes of which the similarity meets a second preset condition to form a final class; and drawing a mask for each final class and performing three-dimensional modeling. The problem that in the prior art, the landslide identification process needs to depend on manual intervention to define the specific landslide object of the geographic space corresponding to the landslide body in the image is solved.

An unsupervised process monitoring method and apparatus for a repetitive production system, and a device. The method comprises: collecting a plurality of videos of a target production process, and obtaining an image sequence of each video (210); using a CVAE model to perform feature extraction on the image sequences, so as to obtain latent variable sequences (220); performing adaptive change-point detection on the latent variable sequence of each video, so as to obtain an initial change-point set (230); using an IDTW algorithm to process the initial change-point sets of the plurality of videos, so as to obtain a universal change-point set (240); on the basis of the universal change-point set, updating the CVAE model until the CVAE model converges (250); using the converged CVAE model to process an image sequence of the target production process that is collected in real time, so as to predict a production stage (260); and on the basis of the predicted production stage, detecting a progress deviation (270). Thus, the present disclosure significantly reduces reliance on manually labeled data, lowers implementation costs, can adapt to different production scenarios, and realizes high-precision unsupervised process monitoring, thereby improving production efficiency.

The invention discloses an automatic chip packaging defect identification method based on computer vision, which comprises the following steps of: generating multi-scale features and candidate regions, and establishing a detection head containing array parameter estimation and RepPoints point set regression and classification; the pitch, the rotation angle, the original point and the relaxation threshold value are regressed, and a pitch locking grid model is constructed; outputting a point set containing coordinates, scales, kernel weights and gating probabilities, and screening effective points; projecting according to the grid model and applying bounded offset to obtain a pitch locking point; constructing an implicit distance field based on the locking point and extracting a defect contour; calculating a minimum enclosing rectangle, a length, a width, an area and a minimum gap; fusing the classification score, the gating retention rate and the curvature stability to generate an instance confidence coefficient, and performing non-maximum suppression; and outputting defect types, position frames, contours and measurement results. According to the invention, integrated processing of array prior, contour reconstruction and metering is realized.

The invention relates to the technical field of three-dimensional point cloud measurement and intelligent path planning, solves the technical problems that a traditional method is strong in shielding, large in normal change, limited in reachability and difficult in path execution in point cloud measurement, and particularly relates to a double-layer optimization measurement planning method for a complex model measurement task. Calculating and caching a visible point set of each viewpoint under the conditions of angle constraint and shielding elimination based on the adjacency graph of the candidate viewpoints and a visibility evaluation mechanism; in the inner layer optimization, an initial measurement route and a viewpoint set are generated from an initial viewpoint, and a continuous executable measurement route is reconstructed after full coverage constraint is met; in the outer layer optimization, a genetic algorithm is adopted to carry out global search on a starting viewpoint, and the coverage rate and viewpoint scale cost are used as fitness to output an optimal measurement viewpoint set and a measurement path. According to the method, high-coverage-rate measurement planning can be realized under complex shielding and strict view angle constraint conditions, the number of viewpoints and path redundancy are reduced, and the planning efficiency and robustness are improved.

The invention discloses a novel symmetric iteration nearest point cloud registration calculation method for quality detection, and the calculation method comprises the steps: setting a point set and a point set in a three-dimensional space, carrying out the registration of a point set P and a point set Q, so as to solve a six-degree-of-freedom rigid body transformation matrix, and carrying out the registration of the point set P and the point set Q; the six-degree-of-freedom rigid body transformation matrix comprises a three-degree-of-freedom rotation matrix R and a three-degree-of-freedom translation vector t; a weighted point-surface model is constructed, and a symmetric iteration nearest point objective function based on weighted point-surface measurement and an adaptive robust loss function is constructed based on the weighted point-surface model; the calculation of the symmetric iteration nearest point objective function based on the weighted point-surface measurement and the adaptive robust loss function comprises the step of alternately executing a corresponding point updating step and a registration step until a convergence condition is met.

The invention discloses a feature recognition and path planning method for point cloud three-dimensional-two-dimensional-three-dimensional conversion of a curved-surface workpiece, and the method comprises the steps: obtaining three-dimensional point cloud data of the curved-surface workpiece, and carrying out the preprocessing of the three-dimensional point cloud data; projecting and converting the preprocessed three-dimensional point cloud data into two-dimensional point cloud data by adopting a slice projection method, and forming a fitting curve based on the two-dimensional point cloud data; identifying and obtaining a two-dimensional inflection point set meeting the requirement by a curve inflection point detection method based on an angle integral window; converting the two-dimensional inflection point set back to a three-dimensional coordinate space; adopting a two-stage fitting strategy to identify and obtain an optimal fitting plane from the three-dimensional inflection point set; and a plane cutting method is adopted to obtain a planned path for actual machining. According to the method, a complicated point cloud feature extraction problem is converted into a two-dimensional analysis problem with higher calculation efficiency, so that the algorithm complexity is reduced; the problem of low feature extraction accuracy in a noise environment is effectively solved; the robustness under the condition that the outliers exist is enhanced; an intermediate link of CAD modeling in a traditional method is avoided, and accumulative errors are reduced.

The invention relates to a self-supervised multi-modal fusion and collaborative optimization method suitable for a curve and ramp scene. The method comprises the following steps: acquiring an original perception image; generating four paths of geometrically consistent recovery images; constructing a multi-modal fusion model, and generating a depth confidence map aligned with the restored image; uniform ground plane parameters are obtained; collecting all coordinate points to construct an initial 3D lane candidate point set; generating a high-density locally enhanced BEV lane representation; and outputting the fused global consistency 3D lane map. And outputting the structured 3D lane line marking data. Non-planar structures such as curve superelevation and longitudinal ramps can be accurately depicted, and geometric consistency in a complex road scene is greatly improved; the problems of single vehicle shielding, sensor noise and the like are effectively relieved, the precision, the integrity and the system-level reliability of 3D lane reconstruction are remarkably improved, meanwhile, dependence on a high-precision map or 3D true value marking is avoided, and the method has high engineering landing value.

The invention relates to the technical field of point cloud processing and deep learning, and discloses a point cloud semantic segmentation method based on multiple sparseness fusion sampling and local neighborhood space geometric color feature enhancement coding, and the method comprises the following steps: fusing two sampling results according to a preset proportion, and obtaining a sampling point set giving consideration to global and local distribution; the geometric and color features are uniformly input into the multilayer perceptron sharing the weight for feature mapping, an enhanced feature vector is generated, the enhanced feature vector is further fused with the center point features, a final code is output, and end-to-end training is achieved. The method has the beneficial effects that through multi-sparseness fusion sampling, the representativeness of dense and sparse point cloud regions can be dynamically balanced, and the segmentation performance of the network in a complex structure or non-uniform distribution scene is remarkably improved; local neighborhood space geometry and color features are fused, the perception ability of the network to fine structures and texture differences is enhanced, and the category confusion phenomenon is effectively reduced.

The invention discloses a target tracking method and device based on machine vision, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence or other related fields, and the method comprises the steps: obtaining a target video sequence containing at least two video frames, performing feature collection in the current video frame according to a predetermined to-be-tracked target to obtain a feature point set; performing matching analysis according to the feature point set and a previous feature point set corresponding to a previous video frame to obtain a feature point pair set; calculating a scale change value and a displacement value corresponding to the target according to the feature point pair set, and obtaining position information of a target frame in the previous video frame; and updating the position of the target frame in the current video frame according to the scale change value, the displacement value and the position information of the target frame in the previous video frame to obtain a target tracking result. Through the target tracking method and device, the technical problem that the tracking precision and continuity of a target tracking algorithm in a complex changing environment are reduced in the related technology is solved.

The invention discloses a grid diagram and boundary optimization combined three-dimensional incremental model updating method and device, and the method comprises the steps: setting a plane as a grid diagram, and carrying out the fine registration of an incremental model and a stock model based on the registration relation between an incremental model layering line cluster and a stock model layering line cluster on the grid diagram; obtaining a to-be-updated overlapping region through the overlapping part of the incremental model and the stock model; projecting the point cloud in the to-be-updated overlapping region to a two-dimensional plane to obtain a two-dimensional point set, constructing a triangulation network for the two-dimensional point set through triangulation, and forming an initial contour along the boundary of the triangulation network; optimizing the initial contour to obtain an optimized mosaic line; and respectively cutting the triangulation network of the incremental model and the triangulation network of the stock model by using the optimized mosaic line, and merging the triangulation network parts after cutting to complete updating of the stock model. By the adoption of the technical scheme, fine registration is achieved, and the accuracy and smoothness of the complex scene boundary are improved.

The invention relates to a method for grid reconstruction based on a skeleton-driven pipeline net-shaped structure, and the method comprises the steps: extracting a skeleton from a point cloud of the pipeline net-shaped structure based on an improved Laplace shrinkage algorithm, and obtaining a skeleton point set and a skeleton curve; calculating the two-dimensional radius of a skeleton point on an image plane by using a segmentation mask obtained by fusing the multi-view image and the point cloud, and then mapping the two-dimensional radius to a real three-dimensional radius by using camera parameters in combination with the depth information of the skeleton point; generating a surface model of the pipeline net-shaped structure according to the skeleton of the pipeline net-shaped structure and the real three-dimensional radius information; the improved Laplacian contraction algorithm specifically comprises the following steps: sensing local density distribution characteristics of point cloud data in real time, so that the Laplacian contraction weight is dynamically inversely proportional to the local point cloud density. Compared with the prior art, the method has the advantages of improving the integrity and accuracy of the three-dimensional reconstruction model of the pipeline network structure and the like.

The invention belongs to the technical field of three-dimensional geometric measurement, and particularly relates to a three-coordinate detection data processing method and system for automobile parts, and the method comprises the steps: obtaining an actual point cloud and a standard point cloud; by calculating the maximum angle gap of the data points, screening to obtain actual and standard feature point sets; anti-noise geometric descriptors based on tangential weights are constructed for the feature points in the two sets of feature point sets respectively; matching the two groups of feature points based on the descriptors and generating an initial matching set; solving global optimal transformation from the initial matching set by adopting a random sampling consistency algorithm; and the transformation is applied to the actual point cloud, fine registration is carried out by using an iterative nearest point algorithm, and finally deviation analysis is completed. The technical problem that traditional registration depends on initial alignment and is prone to falling into local optimum is solved, and the robustness and accuracy of registration are improved.

The invention relates to the technical field of remote sensing surveying and mapping, and particularly discloses an intelligent surveying and mapping system and method based on a remote sensing technology, and the method comprises the steps: obtaining a multi-time-sequence remote sensing image data set of a target region through multiple platforms carrying intelligent sensing elements; performing three-dimensional reconstruction and cross-time-phase accurate alignment on the time-phase data to generate a three-dimensional space coordinate sequence under a unified coordinate system; carrying out conjoint analysis on the multi-time-sequence attribute of each spatial point in the sequence, and generating a fused spatio-temporal feature by distinguishing a persistent structure and instantaneous interference; constructing a three-dimensional graph structure according to the features, performing hierarchical aggregation, and identifying a point set with similar features and continuous space as an entity unit with a single semantic identifier; based on the semantic and geometric attributes of the entity units, automatically establishing a spatial topology and time evolution relationship, and generating a structured information set containing complete space-time dimension information; according to the invention, high-precision intelligent surveying and mapping from static modeling to dynamic spatio-temporal knowledge generation is realized.

The invention discloses a multi-robot path planning method in a complex environment based on MQAHA, and belongs to the technical field of multi-robot path planning. According to the method, firstly, an optimal point set initialization strategy based on the number theory is adopted, an initial population which is evenly distributed is constructed, and diversity and coverage of a search starting point are remarkably improved; secondly, proposing an elite-guided variation migration foraging strategy, fusing direction guidance of a current optimal solution and a disturbance mechanism of a random individual, and effectively enhancing local development capability and global escape performance; furthermore, a learning-driven strategy self-adaptive selection mechanism is introduced, the foraging behavior probability is dynamically adjusted according to the population state, efficient balance of exploration and development is achieved, and therefore the premature convergence problem of the algorithm is systematically relieved. According to the method, the multi-robot cooperative motion path can be quickly generated in a complex obstacle environment, static and dynamic obstacles are effectively avoided while the total path length is reduced, and the motion efficiency and operation safety of a multi-robot system are remarkably improved.

The invention provides an out-of-picture object information detection method, system and device and a medium, and relates to the technical field of audio and video processing, and the method comprises the steps: obtaining two continuous frames of images of a picture as a first image and a second image; respectively extracting first key point information corresponding to the first image and second key point information of the second image; performing feature matching according to the first key point information and the second key point information, and screening to obtain reliable matching points; converting the reliable matching points into a two-dimensional point set, and fitting a similarity transformation model corresponding to the two-dimensional point set by applying a set robust estimation algorithm; the similarity transformation model comprises a scaling factor, a rotation angle and a translation vector; setting that the change from the first image to the second image is realized by similar transformation, and modeling a similar transformation model; and obtaining the position of the predicted object based on the first image and the second image by using a modeling result. According to the invention, by introducing a continuous inter-frame similarity transformation modeling mechanism, the prediction robustness and precision of the position of the object outside the picture are remarkably improved.

The invention relates to a gravity background field construction method based on iterative optimization Kriging. The method comprises the following steps: S1, obtaining in-situ gravity measurement data as a known point set; s2, based on the known point set, performing preliminary interpolation on grid points of the gridding background image by adopting a Kriging method to obtain a Kriging estimated value of each grid point; s3, by introducing a local gravity anomaly covariance and a Kriging variation function, evaluating the random uncertainty of a Kriging estimated value in an interpolation process, and dividing each grid point into a reference point and a point to be corrected based on the random uncertainty; and S4, combining the reference point and the known point set to construct a continuous distribution constraint curved surface, carrying out local continuity correction on the continuous distribution constraint curved surface based on the obtained reference point, and carrying out iterative expansion on the basis of the corrected local constraint curved surface until the continuous correction of the whole continuous distribution constraint curved surface is completed. And the construction of the gravity background field is realized.

The invention relates to the technical field of geometric error evaluation of hole and shaft parts in the field of machinery, and discloses a hole and shaft part action boundary discrimination method, which comprises the following steps of: deriving a motion coefficient vector for describing radius change of each measuring point based on a tiny rigid body motion model of a surface measuring point set of a measured part; and the motion coefficients are combined into a motion coefficient matrix. Furthermore, the method establishes a discriminant inequality group based on a mutual exclusion proposition. The judgment process is realized by analyzing the rank of the motion coefficient matrix and iteratively solving an equation set formed by the maximum linear independent matrix of the motion coefficient matrix, and finally, whether the fitting cylinder is the action boundary or not is determined by judging whether the inequality set has a feasible solution or not. According to the method, the problems of complicated geometric discrimination conditions, lack of universality and the like in the existing evaluation method can be solved, and a reliable basis which is easy to realize in a stylization manner is provided for determining the action boundary of the hole-shaft part.

To provide a game program in which various courses are set on a field, a race can be performed for each course, and courses with variations can be set.SOLUTION: An example of the game system according to the exemplary embodiment is configured to present, after the end of a first race on a course having a goal point set in a first base area, a plurality of candidates including a first type of course candidate including an inter-base route from the first base area to another second base area and a second type of course candidate including an in-base route in a third base area different from the first base area to a player as course candidates for a next second race, One of the plurality of candidates is set as a second course on the basis of the player's selection.SELECTED DRAWING: Figure 7

The invention discloses a convex hull algorithm optimization and applicability analysis method based on rotation contraction. The method comprises the following steps: step 1, processing a point set by a rotation contraction preprocessing strategy; and step 2, convex hull calculation. According to the method, the filtering operation is executed, a large number of non-convex hull points in the point set are deleted, the convex hull is calculated based on the classical convex hull algorithm, the convex hull algorithm optimization and applicability analysis method based on rotation contraction is constructed, the computer memory can be saved when the convex hull is calculated based on the method, meanwhile, the convex hull calculation time can be shortened, and the calculation efficiency is improved. And technical support is provided for the fields of computational geometry, computer graphics, computer vision and the like.

The present disclosure provides a capital construction graphic calculation method, system, electronic device and storage medium, which belongs to the technical field of capital construction engineering and engineering cost. The method determines the overlapping area between the steel bars and the concrete by obtaining the point cloud data of the steel bars and the concrete and the steel bar spacing parameter, extracts the boundary point set of the overlapping area to generate a first grid unit, generates a second grid unit according to the steel bar spacing parameter, corrects the first grid unit through the node coordinate offset between the first grid unit and the second grid unit to generate a third grid unit, and determines the gap filling ratio of the concrete according to the third grid unit to form a continuous boundary model. In this way, the discontinuous boundary error caused by the curved surface overlapping area between the components in the traditional graphic calculation method is effectively eliminated, so that the real geometric shape of the components can be accurately reflected, the precision of the component volume and material consumption calculation is improved, the component volume calculation precision can be improved to ±0.3%, and the material consumption budget accuracy rate reaches 98%.

The invention provides a pipeline defect detection method, electronic equipment and a storage medium, and relates to the technical field of computer vision. The method comprises the following steps: performing coordinate conversion on an initial fisheye video stream to obtain a multi-frame plane image; for any frame of plane image, determining a binarization mask of the frame of plane image based on a semantic segmentation network, and extracting feature points of a pipe wall region in the frame of plane image by taking the binarization mask as a constraint to form a feature point set; determining an optimal suture line between any two adjacent frames of feature point sets by adopting a graph cut algorithm based on energy minimization, and carrying out splicing to obtain a pipeline panorama; and identifying the pipeline panorama by using a deep neural network model to perform defect identification to obtain a target defect. According to the method, the binarization mask is used as a constraint, and non-pipe wall area interference is eliminated; an optimal suture line is determined and splicing is completed based on an energy minimization graph cut algorithm, so that inter-frame splicing gaps and artifacts are effectively eliminated, and rapid and accurate detection of target defects can be realized.

The application discloses a curtain wall-based closed polyline generation method and system, obtains an initial point set from point cloud data, adopts a voxel segmentation method to perform grid processing on the initial point set, calculates the point density of each voxel, if the point density is lower than a preset point density threshold value, marks the point as a noise point and removes the noise point, and obtains a denoised point cloud data set; for the denoised point cloud data set, adopts a principal component analysis method to extract the local geometric feature of each point, calculates the normal vector and curvature of each point, if the curvature is greater than a preset curvature threshold value, marks the point as a candidate boundary point, and obtains a candidate boundary point set; according to the candidate boundary point set, adopts a moving least square method to locally fit the candidate boundary points, generates a smooth boundary curve segment, if the included angle between adjacent curve segments is smaller than a preset included angle threshold value, merges the adjacent curve segments into a continuous boundary polyline, and obtains a preliminary boundary polyline. The application improves the accuracy and smoothness of point cloud boundary extraction.

The invention discloses a to-be-welded weld center track real-time labeling method based on bidirectional edge enhancement and geometric constraint fitting, and relates to the technical field of automatic auxiliary welding. The method comprises the following steps: performing directional gradient edge enhancement on a weld image, fusing with an original image, and inputting into a deep learning network to extract an edge; candidate line segments are obtained through Hough transform, and effective weld boundary pairs are screened out based on groove width and parallelism constraint; calculating midpoints of the boundary pairs to form a central point set, and performing cubic B-spline curve fitting to obtain a smooth trajectory; and finally, the fitting track and the real-time deviation between the fitting track and the welding gun are displayed in an augmented reality mode in an overlapping mode. According to the method, the robustness and accuracy of welding seam edge extraction under complex interference are remarkably improved through directional enhancement and geometric constraint, and accurate extraction and visual interaction of a welding seam center track are achieved through high-precision curve fitting and AR visualization.