230 results about "Surface point" patented technology

The invention provides a pipe thread positioning and measuring method and system based on three-dimensional vision, and belongs to the technical field of industrial automation and three-dimensional vision. According to the method, a measuring system composed of a robot measuring system and a three-dimensional visual locating system is built, and hand-eye calibration is completed; the method comprises the following steps: acquiring a three-dimensional point cloud model of the end part of a pipe thread workpiece, and extracting an end surface normal vector, a tangent vector and a circle center coordinate through preprocessing, cylinder fitting, near-end surface point cloud extraction and end surface circle fitting so as to establish a measurement reference coordinate system; and converting the reference coordinate system to a robot base coordinate system based on a hand-eye calibration result and the tail end pose of the robot, generating a robot moving trajectory, guiding the robot to be positioned to a measurement position, and completing preparation before measurement. According to the invention, automatic high-precision extraction of the pipe thread measurement reference is realized, the problems of non-uniform reference, large error and low efficiency in traditional measurement are solved, the method is suitable for various pipe thread workpieces, and a reliable basis is provided for subsequent high-precision measurement.

The invention discloses a robot variable stiffness surface path planning method based on three-dimensional perception and application. The method comprises the following steps: processing workpiece surface point cloud data; a surface defect detection model is established, and deformation deviation generated by workpiece surface defects in the point cloud data is compensated; and performing path planning analysis on the point cloud model to generate a self-adaptive tool path. In the process that the robot executes the planned path, passive analysis is conducted through a variable stiffness impedance control law under energy constraint, force control surface treatment is achieved by collecting a force feedback track as a reference and combining a quadratic programming optimization controller, and task execution of the robot planned path is completed. According to the method, a planned path model is combined, an AI auxiliary programming framework is designed, and a user parameterization task and tool are guided through a natural language interface and a knowledge representation engine. According to the method, the adaptive capacity of the robot to the complex variable stiffness surface is improved, the machining consistency and efficiency can be remarkably improved, and the wide application prospect is achieved.

The invention provides a 6D attitude rapid estimation method and device for a target object, and relates to the field of electrical digital data processing in the technical field of machine vision and perception, and the method comprises the steps: obtaining an RGB image and a depth image of the target object, inputting the RGB image into a segmentation model, and obtaining a binary mask of the target object; acquiring a camera internal reference matrix, and constructing a curved surface point cloud matrix of the target object according to the depth image, the binary mask and the camera internal reference matrix; constructing a cubic package of the target object, and constructing a fitting penalty function according to the curved surface point cloud matrix and the cubic package; according to the curved surface point cloud matrix, the cubic package and the fitting penalty function, gradient vectors of the center point and the Euler angle of the target object are obtained through calculation; and performing iterative solution on the gradient vectors of the central point and the Euler angle through a gradient descent algorithm to obtain optimal solutions of the central point and the Euler angle, and taking the optimal solutions of the central point and the Euler angle as the 6D attitude of the target object.

A method and system for eliminating 2D features from planar surfaces in 2D images. Three digital images are taken, from a single camera at a fixed position, of a subject such as a pallet of boxes. One image (IA) is taken with ambient lighting, one image (I1) has ambient lighting plus a first added light source, and one image (I2) has ambient lighting plus a second added light source. An output image Q is then computed by Q=(I1−IA) / (I2−IA). Subtracting the ambient image removes ambient diffuse and specular reflections. Division eliminates all variations in the output image caused by color. The only variations that remain are those due to the angle between each surface point's normal direction and the direction from the light to that point. The output image Q, devoid of all colors and 2D features, is well suited for computing a robot grasp of an object in the image.

The invention discloses a reinforcing steel bar surface binding point identification and positioning method based on point cloud and pixel mapping. The method comprises the following steps: obtaining original three-dimensional point cloud data to carry out outlier noise point elimination; performing plane fitting on the denoised point clouds, identifying template surface point clouds and removing the template surface point clouds; mapping the spatial physical coordinate attribute of the steel bar surface point cloud into a three-channel coding image; separating the three-channel coded image into three single-channel images: a length image, a width image and a depth image; processing the depth image to extract an initial reinforcing steel bar straight line set; screening out a parallel steel bar straight line set from the initial steel bar straight line set according to a set reference direction and a parallel angle tolerance threshold value; and calculating straight line intersection points in the parallel steel bar straight line set to obtain candidate binding point pixel coordinates, determining representative binding point pixel positions through clustering, querying coordinate information of the three single-channel images, and outputting three-dimensional space coordinates of the steel bar binding points. According to the invention, robust and accurate steel bar binding point identification and positioning are realized.

The application relates to the technical field of image processing, in particular to a camera-based progressive feature distribution sampling 6D pose estimation method and system, which comprises the following steps: obtaining dense pixel points by using a multilayer progressive feature sampling network of Unet++; analyzing three-dimensional model surface point features by using graph convolution to form a corresponding distribution relationship between image pixel points and surface points; calculating the probability distribution of the corresponding key of the image pixel coordinate point set features by querying the model to obtain the mask probability of the corresponding three-dimensional surface of the image pixel coordinates; calculating the best probability distribution value; scoring and voting each generated hypothesis; refining the obtained best voting score attitude hypothesis according to the surface distribution to obtain the target final attitude estimation pose. The application solves the problems that the stability and accuracy of pose estimation of a target object are not high when only RGB data is used, and the accuracy is not high when irregular features exist in three-dimensional model surface feature sampling.

The invention discloses a virtual pre-assembly method for a bridge closure section. The method comprises the following steps: acquiring three-dimensional point cloud data of the closure section and a closure gap; carrying out closure section connection section area data extraction and closure gap connection section area data extraction based on a bisection method, and obtaining connection end face area data; extracting connection end face point cloud data from the connection end face region; extracting outer boundaries of the connecting end faces and fitting feature angular points to obtain all key angular points on each connecting end face, and finally obtaining a feature angular point data set of the closure section and the closure gap; and feature point three-dimensional model construction and virtual pre-assembly: establishing a feature point three-dimensional model based on the feature angular points of the closure section and the closure gap, simulating the final state of hoisting butt joint by using a virtual pre-assembly method, and calculating the matching and cutting amount of the closure section. According to the method, the cutting amount of each feature point position can be automatically calculated, and the precision and efficiency of closure construction are greatly improved.

The invention discloses a method and system for processing a circular weld joint based on point cloud data, and belongs to the technical field of machine identification of weld joints, and the method comprises the following steps: collecting the point cloud data of the surface of a workpiece through a visual sensor; preprocessing the collected point cloud data; calculating a normal vector of each point in the point cloud data; segmenting the workpiece surface point cloud and the reflective interference points based on a normal vector, and filtering the interference points deviating from a preset range in the normal direction to obtain a target point cloud and a reference point cloud; projecting the target point cloud to a reference plane obtained by fitting the reference point cloud, generating a target projection point cloud, detecting boundary points of the target projection point cloud, screening candidate weld joints based on distance distribution from the boundary points to the center of mass, and extracting weld information. According to the method, the workpiece made of the material with high light reflection is treated, the finally obtained result can still keep good precision, and the quality of the workpiece is improved.

A method and a registration device for sampling relevant surface points of a subject for a medical navigation system is presented. From a plurality of surface points of the subject, relevant surface points are accepted and non-relevant surface points are discarded. The method allows the surface geometry acquisition of a subject to be improved. For this purpose, additional information of the surface points is acquired and assigned to the respective surface point for validating each surface point.

The invention relates to the technical field of robot automatic polishing, in particular to a vision-guided robot polishing path planning method and system, and the method comprises the steps: obtaining a workpiece surface point cloud in real time through a three-dimensional vision sensor, generating a trajectory seed point with adaptive density in combination with curvature, a normal vector and a defect semantic tag, and carrying out the positioning of a workpiece surface point; and a polishing quality evaluation function is constructed based on force sense feedback and a visual reconstruction result, so that path online correction is realized. According to the method, the polishing path and the tool posture can be dynamically adjusted, high-precision differentiation processing is achieved on the free-form surface, the edge and the defect area, and the polishing consistency and efficiency are improved.

Disclosed in the present invention is a three-dimensional circle detection method for a freeform surface, comprising: acquiring freeform surface point cloud data, and using a normal vector-guided rolling ball method to extract a freeform surface circular-hole point cloud boundary contour from the point cloud data; performing Euclidean clustering-based boundary segmentation on the point cloud boundary contour to obtain a clustering result of all boundary point clouds, the clustering result consisting of a plurality of circular-hole contours; performing a density-based weighted iterative algorithm on each circular-hole contour to obtain a freeform surface circular-hole normal vector; and projecting a freeform surface circular hole along the freeform surface circular-hole normal vector onto a plane, and then performing circular-hole iterative fitting based on solving an overdetermined equation on the projected circular-hole point cloud to obtain final positioning information. The present invention is applicable to circular-hole positioning on freeform surfaces of different curvatures, has strong robustness, and effectively improves the accuracy of circular-hole positioning on the freeform surfaces.

The application relates to the technical field of ultra-precision machining, and discloses a free curved surface envelope machining track planning method and system based on an arbitrary curved section tool, which comprises the following steps: step 1, judging the concave-convex property of discrete points of a tool section curve, retaining convex envelope points, discarding concave envelope points, obtaining a set of all convex envelope points of the tool section curve, and defining the set as a full-convex envelope contour matrix of the tool section curve; step 2, calculating a new tool section curve convex envelope interpolation contour, and calculating a new tool section curve according to the new tool section curve convex envelope interpolation contour; and step 3, obtaining a tool curved surface point cloud according to the new tool section curve in step 2, and planning a free curved surface workpiece envelope machining track based on the tool curved surface point cloud.

The invention discloses a horizontal rotary coating control method and system based on a neural network, and relates to the technical field of data processing, and the method comprises the following steps: obtaining surface point cloud data of a part at a spraying station inlet; obtaining the current curvature of the part according to the surface point cloud data; paint viscosity and environment temperature are obtained; inputting the current curvature, the coating viscosity and the environment temperature into a rotating speed prediction model, and outputting a predicted rotating speed; acquiring the current curvature, the coating viscosity and the environment temperature at a preset time interval, and updating the predicted rotating speed; and controlling the rotation speed of the part according to the predicted rotation speed. According to the method, the part data and the environment data on the horizontal rotary coating line are obtained in real time, the rotating speed of the part is dynamically adjusted through the rotating speed prediction model, paint film forming of the part at the proper rotating speed is facilitated, and the quality of the paint film is improved.

To provide a method, a device and a system capable of measuring the displacement of the inner space of a tunnel at high speed.SOLUTION: 1) In the initial measurement step, the unevenness feature of the target 100a to 100e is acquired. In addition, the point cloud of the inner surface of the tunnel including the target 100a to 100e is obtained as the first point cloud, and the unevenness feature is extracted from the first point cloud to obtain the first position information of the target 100a to 100e. In the displacement measurement step (2) performed after a predetermined time elapses, a search region including a position specified based on the first positional information and having a larger area than the targets 100a to 100e is set, point cloud of the search region is acquired, and the targets 100a to 100e are extracted from the point cloud of the search region based on the unevenness feature information to acquire the second positional information. Then, the displacement of the inner space of the tunnel is measured based on the difference between the first position information and the second position information.SELECTED DRAWING: Figure 17

The invention discloses a method for measuring the thickness based on laser profile scanning of a 3D wheel of a conveying belt, particularly relates to the field of laser scanning thickness measurement, and is used for solving the problems that shutdown is needed and the measurement range is limited in existing conveying belt thickness detection. According to the method, three-dimensional point cloud data of the upper surface and three-dimensional point cloud data of the lower surface are collected at the same time, initial segmentation of the upper surface and the lower surface is completed through double criteria based on curvature and normal, a dynamic stability threshold value is constructed in combination with the running speed and transverse swing of the conveying belt, and a stable surface point set is formed through screening; then, a thin-plate spline algorithm of dynamic tensor weight is adopted to respectively fit continuous upper surface and lower surface reference curved surface models; and finally, the sampling points on the upper surface are projected to the lower surface along the normal direction and the Euclidean distance is calculated, so that the real thickness distribution of the conveying belt in the full width and full length range is obtained. Non-stop, non-contact and high-coverage online thickness measurement is realized, and the operation safety and maintenance management efficiency of the conveyor belt are improved.

The invention relates to a welding seam information extraction method and device, equipment, a storage medium and a program product. The method comprises the steps that workpiece point cloud of a target workpiece is obtained, a fitting weld joint is obtained based on fitting of the workpiece point cloud, and the workpiece point cloud comprises a bottom plate plane point cloud and a rib plate upper surface point cloud; constructing a first bounding box based on the fitting welding seam, and determining a welding edge application type of the fitting welding seam according to a first point cloud of the bottom plate plane point cloud in the first bounding box; a second bounding box is constructed based on the fitting weld joint, and the height of the rib plate is determined according to the height difference of the point cloud of the upper surface of the rib plate in the second point cloud of the second bounding box; and determining the fitting welding seam, the welding edge application type and the rib plate height as welding seam information. By adopting the method, the welding seam information extraction efficiency can be improved.

The invention discloses an industrial complex curved surface point cloud reconstruction method based on adaptive projection, and aims to solve the problem of surface reconstruction of high-noise, non-uniformly-distributed and complex geometric point clouds. The method comprises the following steps of firstly performing down-sampling based on spatial distribution on an original three-dimensional point cloud, and then denoising and homogenizing the point cloud through an adaptive weighted local optimal projection algorithm; fitting a local plane by adopting a local least square method, projecting the point cloud to two dimensions, and then carrying out Delaunay triangularization; mapping the two-dimensional triangulation network topological relation to three dimensions to generate a three-dimensional triangulation network; and finally, abnormal triangles are eliminated through side length constraint, and the grid quality is optimized. According to the method, through whole-process cooperative processing, the point cloud data quality and complex curved surface adaptability are remarkably improved, it is ensured that reconstructed grids are smooth, regular and consistent in precision, and the high-precision requirement of complex curved surface reverse engineering in the fields of aviation, molds and the like can be met.

The invention discloses a small hybrid spraying robot trajectory planning method and system for a local area of the surface of special equipment, and the method comprises the steps: S1, task shunting: determining a scene of visual shunting when a target area does not meet a repetitive or standardized repair condition, S2, point cloud acquisition and segmentation: segmenting a plane point cloud and a curved surface point cloud, and storing the segmented points; s3, deposition modeling: mapping the plane coating deposition model to a curved surface point cloud corresponding area according to a geometrical relationship to obtain a deposition model suitable for a free-form surface; s4, parameter joint optimization: establishing a deposition superposition model of a single track and an adjacent track, and solving the distance between the adjacent tracks and the running speed of the spray gun in a joint manner by taking the minimum coating thickness variance as a target; and S5, track generation: in a visual shunting scene, applying the optimal parameter pair output in the step S4 to set a path spacing and a speed, and generating an execution track. According to the method, in-situ repairing of the special equipment is achieved, adaptability is high, and precision is high.

The invention discloses an anchor rod corrosion morphology three-dimensional reconstruction method and system based on three-dimensional laser scanning. The method comprises the following steps: acquiring anchor rod surface point cloud data through three-dimensional laser scanning and preprocessing the anchor rod surface point cloud data; performing serialized slicing processing on the point cloud, and establishing a local coordinate system axially aligned with the anchor rod; adopting an improved RANSAC (Random Sample Consensus) algorithm with adjacent slice continuity constraint, fitting the contour of the non-rusted reference circle piece by piece, and reconstructing a reference geometric shape; the corrosion degree is quantified by calculating the corrosion deviation value of the actual contour point and the reference circle, and is converted into polar coordinates to analyze circumferential distribution; and on the basis of the corrosion deviation value, a three-dimensional morphology cloud picture and a polar coordinate expansion picture are generated through bidirectional dynamic color mapping, and multi-dimensional visualization of the corrosion morphology is achieved. According to the method, the limitation that original contour data cannot be obtained through a traditional method is overcome, accurate quantification and reconstruction of anchor rod corrosion under the standard-free condition are achieved, and high robustness and engineering applicability are achieved.

An example method collects first data comprising first surface points within an environment by a sensor associated with a processing system. The method further determines an estimated position of the processing system by analyzing the first data using a simultaneous localization and mapping algorithm and identifies a first set of surface features from the first data. The method further collects second data comprising second surface points within the environment by a three-dimensional (3D) coordinate measuring device associated with the processing system and identifies a second set of surface features from the second data. The method further matches the first set of surface features to the second set of surface features and refines the estimated position of the processing system to generate a refined position of the processing system. The method further displays an augmented reality representation of the second data based at least in part on the refined position.

The invention relates to the technical field of industrial vision, in particular to a building structure crack recognition method and system based on image analysis, and the method comprises the following steps: projecting a preset coding pattern sequence to the surface of a building structure, and collecting and obtaining a distortion pattern image set, and coding information in the distortion pattern image set is decoded pixel by pixel and triangulation positioning calculation is carried out. According to the method, the coding pattern is projected on the surface of the building structure, the distorted image is synchronously acquired, triangulation positioning calculation is performed after pixel-by-pixel decoding, three-dimensional surface point cloud data with complete details can be generated, a two-dimensional crack grayscale image with uniform illumination is acquired, crack feature missing caused by single-dimensional information is avoided, and the accuracy of crack feature detection is improved. A normal vector and a maximum principal curvature value are calculated based on the three-dimensional surface point cloud data, a threshold value is set to screen a high-change area, and crack points and background points are effectively distinguished, so that the three-dimensional geometrical morphology of the crack can be accurately separated and reserved.

The invention discloses an IC board warping degree and curved surface groove detection method based on a three-dimensional point cloud, and the method comprises the following steps: S1, collecting the point cloud data of the surface of an IC board through a three-dimensional imaging device, and carrying out the noise filtering, resampling and attitude normalization preprocessing; s2, nine key points distributed on the surface of the IC board are automatically extracted, a reference surface is generated through a curved surface fitting algorithm based on coordinates of the key points, and the height deviation value of each key point relative to the reference surface is calculated; according to the method, nine key points are selected on the surface of the IC Board, the global reference curved surface is generated by combining the curved surface fitting technology of the three-dimensional point cloud, and errors caused by local height anomaly or measurement noise are effectively avoided. Through the multi-dimensional analysis of the height difference between the central point and the edge point, the quantification of the warping degree is more comprehensive, the measurement result is more stable and reliable, and compared with a traditional single-point or linear measurement method, the method has higher precision and robustness.

The invention relates to the technical field of computer graphics and reverse engineering, in particular to a ship workpiece point cloud reverse modeling method based on OpenCasCad, which comprises the following steps: collecting ship workpiece point cloud data through laser 3D scanning; preprocessing the point cloud by adopting uniform sampling and radius filtering; segmenting the point cloud into a bottom surface point cloud and a top surface point cloud through slicing processing and region growth, and extracting contour data containing vertex data and normal vectors; constructing a unique bottom plane based on bottom surface contour data fitting; projecting the top surface and the bottom surface to the bottom plane, carrying out gap splicing on the top surface, and fitting a minimum external contour on the bottom surface; and stretching the top surface along the reverse direction of the normal of the bottom plane, cutting the stretched entity by using the original top surface, and splicing with the bottom surface to form a complete model. According to the method, the problems of non-coplanar contours, inclined plane deviation, gap defects and the like in the prior art are solved, the modeling precision and efficiency are improved in combination with OpenCasCad, and the method is suitable for reverse modeling of complex workpieces of ships.

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.

The invention discloses a dynamic projection interaction calibration method and system for an annular science magic space, and belongs to the technical field of projection interaction. The method comprises the steps of obtaining three-dimensional point cloud data of an annular wall surface and spatial pose information of each projector, constructing a wall surface point cloud model, completing projector calibration according to the wall surface point cloud model, and obtaining a pose parameter data set; and based on the data set, mapping each frame of pixel of a preset picture sequence to a corresponding position of the wall surface in real time. And if user interaction is detected, determining an interaction area and executing corresponding logic. In the process, projection feedback images are continuously collected, dynamic calibration and tiny compensation are carried out in combination with pose parameters, calibration projection coordinates and real-time interaction response data are generated, and accordingly, all projectors are controlled to complete real-time and stable projection display on the annular wall surface. According to the scheme, the projection picture is highly consistent with the annular wall surface and user operation, dynamic calibration and real-time interaction are realized, the display precision and stability of projection are improved, and the immersion experience of a user is enhanced.

The present application provides a method and system for extracting nail contours. The method is based on the system and comprises: the step of data acquisition: carrying out 3D scanning to obtain finger 3D data of a target finger, wherein the finger 3D data include complete nail 3D data: the step of point cloud processing of data: converting the finger 3D data converted into 3D point cloud data to obtain a finger point cloud, wherein the finger point cloud includes a nail curved-surface point cloud; the step of nail point cloud acquisition: segmenting the finger point cloud to obtain the nail curved-surface point cloud; the step of nail point cloud flattening: flattening the nail curved-surface point cloud in an equal surface area manner to obtain a nail plane point cloud in a planar state; and the step of nail contour drawing: drawing a nail contour according to the contour of the nail plane point cloud. According to the method and system for extracting nail contours, the nail plane point cloud formed after the nail curved-surface point cloud of the curved nail is flattened is obtained, and the shape of an outer contour point cloud of the flattened nail plane point cloud better fits the outer contour of the curved nail.

The invention discloses a spiral groove milling curved surface point cloud simulation calculation method based on intersection points, and the method specifically comprises the steps: firstly, constructing a tool general parameterized model; then, a cutter milling kinematics model is constructed and used for guiding the milling process, and the milling mode of the spiral groove is achieved; secondly, solving a spiral groove milling curved surface point cloud model based on an envelope principle; and finally, carrying out reconstruction calculation on the point cloud model through point cloud intersection point calculation and a point cloud selection principle, and carrying out comparison verification on the calculated spiral groove milling curved surface point cloud simulation model and a model after importing a cutter milling track and a geometric shape into Veicut to carry out spiral groove curved surface simulation. According to the method, high-precision visual display is carried out on spiral groove milling curved surface point cloud simulation, and correctness and effectiveness of related theories of the method are proved.

The invention discloses an intelligent wearable watch case precision detection method based on visual inspection, and relates to the technical field of machine vision, and the method comprises the steps: collecting a watch surface point cloud and a watch case image, carrying out the point cloud denoising and image distortion correction, and obtaining registration multi-modal data; performing multi-layer pyramid convolution on the registered multi-modal data, and outputting geometric-texture features of the watchcase; curvature gradient calculation and spatial relation modeling are carried out on the geometric-texture features of the watchcase, and curvature distribution parameters and a spatial relation adjacency matrix are obtained; the curvature distribution parameters are used as nodes of the topological structure, the spatial relation adjacent matrix is used as edges of the topological structure, and a case geometrical relation graph is constructed. According to the method, the watch surface point cloud and the watchcase image are fused and subjected to multi-layer pyramid convolution, the comprehensiveness and positioning precision of watchcase defect recognition are improved, and meanwhile, the engineering practicability of the detection process is effectively improved by utilizing a graph attention defect prediction model and an SPC statistical process control algorithm.

The invention discloses a mulberry leaf picking and positioning method and device based on machine vision, and relates to the technical field of machine vision. The method comprises the following steps: acquiring calibrated and synchronized multi-modal image data of a mulberry target area, wherein the data can be a binocular sequence or a depth camera color-depth pair; performing preprocessing including brightness color normalization and image degradation compensation on the data to obtain an enhanced frame; inputting the enhanced frame into a target detection and maturity evaluation joint network, identifying each mulberry leaf instance, and outputting an instance segmentation mask defining the contour of the mulberry leaf instance and a probability vector representing the maturity; based on the instance segmentation mask and depth information, pixels in the mask are converted into a three-dimensional leaf surface point cloud; according to the point cloud, the six-degree-of-freedom pose of each mulberry leaf target is obtained, and at least one candidate picking site is determined; and finally, performing priority ranking on the candidate picking sites according to a preset comprehensive scoring function, and generating a scheduling queue containing timestamps, six-degree-of-freedom poses and priorities.

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.