43 results about "Surface point" patented technology

The application provides a nail contour extraction method and system. The extraction method based on the system comprises the following steps: a data acquisition step: 3D scanning to obtain finger 3D data of a target finger, the finger 3D data containing complete nail 3D data; a data point cloud step: converting the finger 3D data into 3D point cloud data to obtain finger point cloud, the finger point cloud containing nail curved surface point cloud; a nail point cloud acquisition step: segmenting the finger point cloud to obtain the nail curved surface point cloud; a nail point cloud flattening step: flattening the nail curved surface point cloud with equal surface area to obtain nail plane point cloud in a plane state; and a nail contour drawing step: drawing a nail contour according to the contour of the nail plane point cloud. The nail contour extraction method and system of the application obtain nail plane point cloud formed by flattening nail curved surface point cloud of a nail with an arc, and the shape of the peripheral contour point cloud of the flattened nail plane point cloud is more consistent with the peripheral contour of the nail with the arc.

This invention discloses a method, system, and storage medium for interactive welding of the three-dimensional surface of a rudder workpiece, belonging to the field of automated welding technology. The welding method includes: acquiring complete raw point cloud data of the rudder workpiece through point cloud scanning; performing semantic segmentation on the three-dimensional surface structure in the raw point cloud data to obtain the rudder top surface point cloud; extracting the skeleton contour structure of the rudder workpiece based on the rudder top surface point cloud as welding guide lines; sorting the welding guide lines according to a pre-set arrangement; and adjusting the sorting of the welding guide lines interactively according to actual processing requirements to complete the interactive welding of the three-dimensional surface of the rudder workpiece. The welding system of this invention includes a structured light camera, a robotic arm, and an information processing computer. This invention automates the welding process of rudder workpieces, eliminating the problem of inconsistent results from manual welding, and also features interactive weld line selection functionality, adapting to different welding processes with high flexibility.

This invention provides a method, apparatus, electronic device, and storage medium for detecting tank deformation. The method includes: scanning the contour of the tank to be tested and its base surface to obtain contour point cloud data and base surface point cloud data; constructing a tank model and base surface in a coordinate system based on the contour point cloud data and base surface point cloud data; using a plane perpendicular to the Z-axis as a slicing plane, cutting the tank model at equal intervals to obtain multiple slices, and acquiring the slice feature points of each slice; cutting the base surface to obtain a base circle; fitting characteristic curves based on the slice feature points of each slice; determining the fitting circle based on the characteristic curves; and determining the deformation detection result of the tank to be tested based on the fitting circle and the base circle. This method achieves integrated, online detection and evaluation of tank body and base deformation, featuring high detection and evaluation accuracy, short time consumption, simplicity and speed, strong operability, and ease of engineering application.

The present application relates to image simulation, data enhancement technical field, especially to a kind of involute surface image subpixel level rotation simulation method, comprising: S1, establish multidimensional conversion relationship, establish the mapping rule of image pixel and three-dimensional space point in world coordinate system;S2, determine the continuous space-time motion trajectory of surface point, and establish the dynamic corresponding relationship between the trajectory and image pixel;S3, solve the instantaneous surface point corresponding to target pixel in world coordinate system at t time and its involute angle;Original pixel and its original pixel value corresponding to the instantaneous surface point at initial time are deduced reversely;S4, original pixel value is corrected, and instantaneous gray value is obtained;S5, double integration operation is carried out on the motion trajectory corresponding to target pixel in space and time dimension;Synthesis has physical consistency motion blur image.The present application can efficiently generate dynamic blur image with space-time consistency and geometric reality.

The present application relates to the technical field of seepage mechanics, and particularly relates to a conical sealing surface leakage rate calculation method based on Darcy's law, comprising the following steps: a W-M function is used to simulate the random topography of the workpiece surface at a microscale, and a normalization method is used to generate surface point cloud data meeting roughness requirements; according to the surface point cloud data, a contact mechanics model is used to solve the change law between the contact state and the external load, and according to the Hertz contact theory, the contact between the rough surfaces is reconstructed as the contact between a rigid plane and a flexible rough surface; the surface is discretized into a three-dimensional grid model, the effective porosity is screened and calculated by using the connected domain discrimination method; a micro-leakage rate calculation method for the conical sealing surface in the flared pipe joint is obtained based on the effective porosity and the seepage mechanics theory algorithm; the leakage rate of the conical sealing interface is calculated, and the sealing performance of the interface is quantitatively evaluated. The present application improves the comprehensiveness and accuracy of the sealing performance evaluation.

This invention discloses a 3D defect detection method, system, and device based on typical geometric alignment and multi-view adaptive rendering, comprising the following steps: S1, acquiring the initial 3D point cloud of the object to be detected, and performing unsupervised feature analysis on the initial 3D point cloud through typical geometric alignment to obtain a standardized aligned point cloud of the object to be detected; S2, converting the standardized aligned point cloud of the object to be detected into a set of geometric feature maps from multiple camera views; S3, inputting the geometric feature maps of the object to be detected from the camera views into a general 2D image anomaly detection network, outputting point-level anomaly scores, and then back-projecting them onto the corresponding surface points of the standardized aligned point cloud to obtain object-level anomaly indicators for 3D defects. This invention does not rely on the geometric structure and observation posture of the object to be detected, and can achieve robust anomaly defect detection on unaligned object 3D point clouds, achieving high-precision point-level anomaly localization.

The application relates to the technical field of visual detection, and discloses a visual detection device and a detection method suitable for appearance detection of special-shaped workpieces. The device comprises a pre-compensation weight module, a shape-dependent parameter module, a pose solution module, a driving instruction module, a uniform light imaging module and a defect analysis module. Three-dimensional numerical models are subjected to grid division, normal vectors and curvature values are calculated, and a pre-compensation light weight atlas is constructed. A shape-dependent lighting parameter table is established. Surface point cloud data is acquired, the surface point cloud data is matched with the three-dimensional numerical models, and a spatial pose offset is obtained. Index coordinates in the shape-dependent lighting parameter table are subjected to spatial transformation, and light source driving instructions are generated. Uniform light projection is carried out on the surface of the special-shaped workpiece to be detected, and a shape-dependent uniform light image is obtained. The shape-dependent uniform light image is enhanced and defect features are extracted. Difference analysis is carried out on the defect features and preset defect criteria, and appearance defects are determined. The application can improve the visual detection efficiency of appearance detection of special-shaped workpieces.

A method of image rendering quality prediction and path planning for large-scale scenes is provided. In the method, multiple surface points of a proxy model within a viewpoint range of a virtual viewpoint are obtained. For each surface point, a photometric error among multiple photometric information corresponding to the surface point is determined. The multiple photometric information refers to the photometric information of the surface point at multiple visible acquisition viewpoints respectively. The visible collection viewpoint are those acquisition viewpoints where the surface point is visible among the multiple acquisition viewpoints. Based on the photometric error, a viewing angle similarity and a resolution similarity between the virtual viewpoint and the visible acquisition viewpoints with respect to the surface point are determined. A rendering quality information of the proxy model at the virtual viewpoint is determined based on the viewing angle similarities and the resolution similarities.

The application relates to a grouting and filling mining surface subsidence dynamic prediction method, which comprises the following steps of: dividing a rectangular working face into a plurality of mining units; calculating the subsidence influence of each mining unit on any surface point by using a probability integral method; calculating a Weibull model time function value of each mining unit at a preset time; and multiplying the subsidence amount of each mining unit at any surface point and the Weibull model time function value, so as to obtain the dynamic subsidence value of any surface point affected by mining and grouting of each mining unit at the preset time. n T T The application improves the subsidence coefficient in the probability integral method according to the technical features of the mining and grouting technology of the bed separation grouting and filling mining, and simultaneously considers the influences of the mining and grouting on the surface deformation; the Weibull model with the improved subsidence coefficient is used as a theoretical model of the grouting and filling mining surface subsidence dynamic prediction, the model basis is more reasonable, and the surface subsidence dynamic prediction precision is higher.​​

This invention provides a machine vision-based quality inspection method and apparatus for injection molding processes. The method includes: identifying regions where the light intensity gradient direction undergoes discontinuous transitions within a preset time window after demolding of the injection molded part, based on the spatial distribution of light intensity on the surface of the injection molded part, thus obtaining gradient anomaly regions; determining the three-dimensional position evolution trajectory based on the three-dimensional positions of the surface points of the injection molded part corresponding to the gradient anomaly regions within consecutive time frames within the preset time window; performing displacement evolution analysis based on the relative spatial relationship between the three-dimensional position evolution trajectory and the geometric center of the injection molded part to obtain a displacement evolution pattern; if the displacement evolution pattern is a continuous unidirectional displacement pattern, it is determined that the injection molded part is in an unstable deformation state due to the release of internal stress during the injection molding process. This invention enables forward-looking judgment of the long-term dimensional reliability of injection molded parts, improving the consistency between quality inspection results and the actual performance of the product.

This invention provides a digital measurement method and system for aircraft skin depression areas based on point cloud scanning, relating to the field of parts inspection technology. The method includes: acquiring point clouds of the skin surface; locating feature regions based on local curvature; extracting and fitting feature contour lines using projection and envelope methods; selecting measurement points on the contour lines; determining the search range on the opposite side; searching and calculating the shortest geodesic length between the two contour lines; establishing a cross-section at the geodesic endpoint and projecting the local point cloud; fitting a linear segment and determining the theoretical contour points based on a deviation threshold; calculating the projection compensation distance; and obtaining the final size of the depression area by combining the geodesic length. The advantages are: acquiring point clouds through 3D scanning eliminates the need for dedicated molds, reducing costs and improving inspection accuracy and efficiency; the feature extraction method based on local curvature perception accurately extracts the required feature contour lines; and the use of the shortest geodesic and projection distance compensation effectively reduces contour recognition errors, achieving accurate measurement of the depression area.

This invention provides a method for evaluating wall flatness based on three-dimensional laser scanning technology. The method first uses a three-dimensional laser scanner to acquire raw three-dimensional point cloud data of the wall surface. Then, the raw data is preprocessed to improve its quality. Based on the processed point cloud data, a reference plane representing the overall trend of the wall surface is extracted using plane fitting technology. Next, the effective area of ​​the wall surface to be evaluated is determined from the point cloud data, and at least one evaluation reference line is planned within this area. Then, the actual surface point data corresponding to the reference line is extracted, and the deviation value of each point from the reference plane is calculated. Finally, these deviation values ​​are statistically analyzed to calculate evaluation indicators such as standard deviation and range, thereby achieving an objective, comprehensive, and quantitative evaluation of wall flatness. This invention has the advantages of high detection efficiency, accurate and intuitive results, and strong repeatability, and is applicable to fields such as building quality acceptance and decoration project evaluation.

The application relates to a corner point recognition method and system based on a point cloud, which comprises the following steps: acquiring a surface point cloud; acquiring a boundary point set based on the surface point cloud; for each boundary point in the boundary point set, extracting a three-dimensional neighborhood point set of the boundary point in the surface point cloud, and obtaining a two-dimensional neighborhood point set of the boundary point through dimension reduction processing; constructing a first feature line according to the farthest point pairs in the two-dimensional neighborhood point set; identifying a corner region point set through the distribution characteristics of the points located on both sides of the first feature line; identifying a candidate corner point based on the farthest point pairs in the corner region point set and the farthest points of a second feature line constructed from the farthest point pairs; constructing a third feature line based on the two non-candidate corner points in the farthest point pairs and the farthest points of the corner region point set corresponding to each candidate corner point, and determining the density index and the cutoff distance of the candidate corner point; and determining the final corner point according to the density index and the cutoff distance of all candidate corner points. The application can accurately and quickly recognize corner points.

This invention discloses a multimodal grading method for seedless watermelons that integrates appearance texture and single-fruit weight. The method includes: simultaneously capturing images of the watermelon placed on a weighing device using a circular camera array and a top-view camera to obtain multi-view image sequences and single-fruit weight data; reconstructing a three-dimensional surface point cloud of the watermelon based on the image sequence and fitting it as a hyperellipsoidal model; mapping the three-dimensional surface texture to a two-dimensional texture map and simultaneously generating a distortion-corrected weight map; using this weight map to weight the two-dimensional texture map and extracting appearance features with real physical meaning, such as defect area and texture statistics; inputting these distortion-corrected appearance features and single-fruit weight data into a deep fusion network based on a cross-modal attention mechanism; and determining the final quality grade of the watermelon by mining deep correlations between modalities. This invention improves the objectivity of grading standards and the accuracy of predicting internal quality.

This invention relates to marking and automated path planning for oil drilling tools, and discloses a method for locating laser-marked working surfaces and planning identification code trajectories on oil drill pipes. The method acquires 3D point cloud data including the curved working surface at the drill pipe end, and obtains a fine-tuned cross-section set through cross-section fitting, axis extraction, and attitude calibration. Based on changes in cross-sectional geometric features, it automatically locates and extracts a subset of the point cloud of the target working surface to determine its spatial position and boundaries. It acquires and parses the user-provided identification code bitmap, and extracts a set of strokes through skeletal modeling. It constructs a family of planes passing through the center of a circle in the working surface point cloud subset, projects the stroke set, and intersects it with the curved surface to obtain a 3D stroke point set conforming to the curved surface. The point set is discretized into TCP coordinates and attitude sequences, and an executable path file is output, along with a process parameter package. This method reduces manual teaching and offline correction, and improves adaptability and forming consistency under different specifications and clamping attitudes.

The application discloses a workpiece off-machine reference detection and machining allowance confirmation method based on point cloud data, comprising the following steps: dividing the workpiece surface into several independent detection areas according to single photographing points; obtaining a workpiece theoretical model and converting it into a theoretical point cloud; collecting a golden workpiece actual point cloud, combining the theoretical point cloud with each detection area, and generating each area template point cloud; collecting a jig area actual point cloud, comparing it with a jig standard template, and determining whether the jig assembly is qualified; collecting a workpiece and jig contact point area actual point cloud, and determining whether the contact point is in place; collecting a machined workpiece actual surface point cloud, combining the corresponding template point cloud to calculate the workpiece surface allowance and overcut proportion, outputting the area detection result according to a preset rule, and completing the quantitative detection of the workpiece global machining allowance and overcut state. The application has high overall detection efficiency and reliable precision, and is suitable for the off-machine reference detection and allowance confirmation scene of various curved surface workpieces such as cylindrical shells, blades and mold surfaces.

This invention proposes a method for detecting the bonding quality of complex curved surfaces, comprising: defining a turntable coordinate system and a robot base coordinate system and calibrating their poses; acquiring multi-view point cloud data of the inner workpiece, the outer workpiece, and the assembled assembly; using a TrICP algorithm based on curvature similarity to perform point cloud registration, generating three-dimensional surface models of the inner layer, outer layer, and assembled assembly respectively; combining the inner and outer layer point clouds into the same coordinate system and ensuring their axes are collinear to form a combined point cloud; based on the principle of non-contact measurement, solving for the normal direction of the surface point cloud of the bonding area, calculating the distances from the component surface, inner layer surface, and outer layer surface to the axis along the normal direction, and calculating the adhesive layer thickness through projection difference; and using the adhesive layer thickness to reflect the bonding quality of the curved surface. This invention overcomes the accuracy limitations of traditional contact measurement, achieving high-precision, non-contact, and automated adhesive layer thickness detection, and has significant engineering application value and broad promotion potential.

This invention relates to the field of measurement technology, specifically to a composite laser precision measurement method based on a unified spatial reference, comprising the following steps: S1, constructing a unified spatial reference and installing bolts; S2, using a laser sensor to perform a three-dimensional scan of the bolt ball head to obtain its surface features, with a scan line spacing of 0.1 mm and a point spacing of 0.02 mm on each line; S3, performing multi-point measurements on the bearing plane and fitting a plane equation; S4, calculating the distance from all points on the sphere to the plane using point cloud data, with the minimum value being the minimum gap; S5, if the measured value does not meet 0.3 mm, guiding the bolt rotation adjustment according to the gap distribution, repeating the steps until qualified, thus solving the problem that the gap formed by the sphere and the plane has a three-dimensional spatial distribution, resulting in the unknown location of the minimum gap point, and that when the bolt is rotated and adjusted, the surface points rotate around the axis, and the fixed position sensor measures different physical points, making it impossible to distinguish between axial displacement and tangential displacement.

The application relates to the technical field of three-dimensional scanning, and particularly discloses an automatic scanning method and system based on a scanner, which comprises the following steps: configuring a scanning parameter set containing a turntable, a scanner and a turnover control parameter; scanning a front surface of a workpiece based on the set and intelligently removing a turntable interference point cloud to obtain pure front surface data; automatically turning over based on front surface point cloud features, verifying a pose, compensating for deviation, finally scanning a bottom surface and fusing the bottom surface with the front surface data to form a complete three-dimensional model; and the system comprises a central processing module, a scanner, a turntable and a turnover module. The application realizes full-process automation from front surface scanning, automatic turning over to bottom surface scanning, significantly reduces manual intervention through parameter setting and automatic interference point cloud removal, and improves scanning efficiency and data consistency.

A registration method includes a storage of two three-dimensional representations of an object and locations of at least three reference points of the object in these two three-dimensional representations; an angular registration of the first three-dimensional representation on the object from a recording of locations of the reference points of the object in a reference frame linked to a reference ancillary fixed on the object; a surface registration of the first three-dimensional representation on the object, including a recording of locations of surface points other than the reference points on the surface of the object in the three-dimensional reference frame linked to the referencing ancillary; and a registration of the second three-dimensional representation of the object on the object itself including a surface registration of this second three-dimensional representation on the basis of the recording of the surface point locations made for the surface registration of the first three-dimensional representation.

The present application relates to the technical field of mechanical arm trajectory planning, and specifically discloses a spraying mechanical arm trajectory collaborative planning method considering process and safety constraints, comprising: obtaining a work object surface point cloud and spraying process parameters, and establishing a spraying area boundary model and an environmental obstacle geometric model; based on the spraying process parameters, generating a reciprocating scanning center line set on the surface point cloud corresponding curved surface, and locally adaptively correcting the scanning line spacing according to the curved surface geometric characteristics and the spray gun incident angle. The present application constructs an iterative planning mechanism of deep collaboration of process, motion and safety, effectively resolving the conflict between high-standard process requirements and mechanical arm physical execution capabilities. In actual operation, the scheme first adaptively adjusts the scanning line spacing according to the curved surface geometric characteristics to offset the projection error caused by the attitude change, ensuring the uniformity of the lap joint.

The application provides a surgery data dynamic registration method and system based on physical simulation and multi-modal constraint, and the method comprises the following steps: reconstructing a three-dimensional model of a target organ based on preoperative images and labeling feature points; predicting intraoperative deformation through physical simulation to obtain a prediction model; collecting surface point clouds at the beginning of surgery for rigid registration; constructing multi-modal constraint by fusing electromagnetic positioning and visual data in real time during surgery; driving model non-rigid deformation by using position dynamics method to realize dynamic registration. The application can compensate soft tissue deformation with high precision and physical reasonableness, has real-time response capability, does not need to implant markers, is suitable for various soft tissue surgery scenes, and improves the accuracy and safety of surgery navigation.

The application discloses a transparent material internal precision machining method and device based on surface-point double-beam threshold superposition and belongs to the technical field of laser precision machining. Two independently controllable low-power lasers are arranged, a first path forms a two-dimensional plane light field through a beam shaping element, and a second path is a focused light beam, and neither of the two lasers can damage the material. Only in the spatial intersection area of the focused light beam and the two-dimensional plane light field, energy is superposed and breaks through the material modification threshold, and three-dimensional structure construction in the transparent material is completed. Through the surface-to-point configuration of the function separation, the application solves the high dependence problem of the traditional double-beam scheme on the precision alignment of the point-to-point configuration, and has the advantages of high fault tolerance, good machining quality and low equipment cost.

This application relates to the fields of robot calibration and computer vision, and discloses a robust calibration method for a line laser robot vision system based on model reconstruction. The method includes: fixing a line laser sensor and initializing a hand-eye matrix; installing a freeform surface calibration object on the robot's end effector to acquire surface point clouds and end effector pose data in multiple poses; transforming the point cloud to the robot's end effector coordinate system based on the initial hand-eye matrix to obtain a reconstructed point cloud; searching for the nearest point from the reconstructed point cloud to the calibration object surface and calculating the point-to-surface distance residual; deriving the Jacobian matrix of the residual with respect to the current hand-eye matrix using a Lie algebra right-multiplication perturbation model; establishing an optimization function with residual minimization as the objective and introducing adaptive weights; solving for the hand-eye matrix error vector; and performing manifold updates on the hand-eye matrix until convergence. This application eliminates the dependence on standard parts, removes intermediate fitting errors, and suppresses measurement posture interference through a robust weighting mechanism, thereby improving calibration accuracy and robustness.

The application discloses a lunar surface point cloud obstacle semantic segmentation method, system, electronic equipment and program product, and belongs to the cross field of computer vision, deep learning and planetary exploration environment perception technology. The application introduces a boundary enhancement mechanism based on local geometric change in the point cloud feature coding stage, strengthens the feature expression of the obstacle boundary area points, and effectively alleviates the boundary information loss problem caused by random sampling. And by introducing a global context perception mechanism on the feature transmission path between the feature coding unit and the semantic decoding unit, the long-distance semantic dependence information is compensated, so that the segmentation result of the large-scale lunar surface scene is more coherent and stable. The application effectively solves the precision decline problem caused by boundary blur and global context loss in lunar surface point cloud segmentation, significantly improves the segmentation precision of obstacles such as impact craters and rocks, maintains the high efficiency of the algorithm, and is suitable for a star-borne computing platform.

The application discloses a digital positioning system door and window installation precision detection method and system, relates to the technical field of door and window installation, and comprises the following steps: extracting first contact component design parameters from system door and window design parameters; positioning in a preset coordinate system, obtaining first mode contact surface point cloud coordinates, analyzing first demand point cloud coordinates of an installation area contact surface, and analyzing Nth demand point cloud coordinates of the installation area contact surface; obtaining installation area contact surface detection point cloud coordinates, obtaining first intersection and union ratio until Nth intersection and union ratio; when the first intersection and union ratio until the Nth intersection and union ratio are all greater than or equal to a first intersection and union ratio threshold, a local installation precision qualified mark is generated; and when all contact components have the local installation precision qualified mark, a system door and window installable instruction is generated. The technical problem that the existing system door and window installation measurement method has large error, low efficiency, single detection dimension and is difficult to meet installation precision requirements is solved.